1
linux/tools/perf/util/stat-display.c

1634 lines
41 KiB
C
Raw Normal View History

#include <stdlib.h>
#include <stdio.h>
#include <inttypes.h>
#include <linux/string.h>
#include <linux/time64.h>
#include <math.h>
#include <perf/cpumap.h>
#include "color.h"
#include "counts.h"
#include "evlist.h"
#include "evsel.h"
#include "stat.h"
#include "top.h"
#include "thread_map.h"
#include "cpumap.h"
#include "string2.h"
#include <linux/ctype.h>
#include "cgroup.h"
#include <api/fs/fs.h>
#include "util.h"
#include "iostat.h"
perf stat: Avoid hybrid PMU list perf_pmu__is_hybrid implicitly uses the hybrid PMU list. Instead return false if hybrid isn't present, if it is then see if any evsel's PMUs are core. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-23-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:58 -07:00
#include "pmu.h"
perf pmu: Separate pmu and pmus Separate and hide the pmus list in pmus.[ch]. Move pmus functionality out of pmu.[ch] into pmus.[ch] renaming pmus functions which were prefixed perf_pmu__ to perf_pmus__. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-28-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:22:03 -07:00
#include "pmus.h"
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
#define MGROUP_LEN 50
#define METRIC_LEN 38
#define EVNAME_LEN 32
#define COUNTS_LEN 18
#define INTERVAL_LEN 16
#define CGROUP_LEN 16
#define COMM_LEN 16
#define PID_LEN 7
#define CPUS_LEN 4
static int aggr_header_lens[] = {
[AGGR_CORE] = 18,
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
[AGGR_CACHE] = 22,
[AGGR_CLUSTER] = 20,
[AGGR_DIE] = 12,
[AGGR_SOCKET] = 6,
[AGGR_NODE] = 6,
[AGGR_NONE] = 6,
[AGGR_THREAD] = 16,
[AGGR_GLOBAL] = 0,
};
static const char *aggr_header_csv[] = {
[AGGR_CORE] = "core,cpus,",
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
[AGGR_CACHE] = "cache,cpus,",
[AGGR_CLUSTER] = "cluster,cpus,",
[AGGR_DIE] = "die,cpus,",
[AGGR_SOCKET] = "socket,cpus,",
[AGGR_NONE] = "cpu,",
[AGGR_THREAD] = "comm-pid,",
[AGGR_NODE] = "node,",
[AGGR_GLOBAL] = ""
};
static const char *aggr_header_std[] = {
[AGGR_CORE] = "core",
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
[AGGR_CACHE] = "cache",
[AGGR_CLUSTER] = "cluster",
[AGGR_DIE] = "die",
[AGGR_SOCKET] = "socket",
[AGGR_NONE] = "cpu",
[AGGR_THREAD] = "comm-pid",
[AGGR_NODE] = "node",
[AGGR_GLOBAL] = ""
};
static void print_running_std(struct perf_stat_config *config, u64 run, u64 ena)
{
if (run != ena)
fprintf(config->output, " (%.2f%%)", 100.0 * run / ena);
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_running_csv(struct perf_stat_config *config, u64 run, u64 ena)
{
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
double enabled_percent = 100;
if (run != ena)
enabled_percent = 100 * run / ena;
fprintf(config->output, "%s%" PRIu64 "%s%.2f",
config->csv_sep, run, config->csv_sep, enabled_percent);
}
static void print_running_json(struct perf_stat_config *config, u64 run, u64 ena)
{
double enabled_percent = 100;
if (run != ena)
enabled_percent = 100 * run / ena;
fprintf(config->output, "\"event-runtime\" : %" PRIu64 ", \"pcnt-running\" : %.2f, ",
run, enabled_percent);
}
static void print_running(struct perf_stat_config *config,
u64 run, u64 ena, bool before_metric)
{
if (config->json_output) {
if (before_metric)
print_running_json(config, run, ena);
} else if (config->csv_output) {
if (before_metric)
print_running_csv(config, run, ena);
} else {
if (!before_metric)
print_running_std(config, run, ena);
}
}
static void print_noise_pct_std(struct perf_stat_config *config,
double pct)
{
if (pct)
fprintf(config->output, " ( +-%6.2f%% )", pct);
}
static void print_noise_pct_csv(struct perf_stat_config *config,
double pct)
{
fprintf(config->output, "%s%.2f%%", config->csv_sep, pct);
}
static void print_noise_pct_json(struct perf_stat_config *config,
double pct)
{
fprintf(config->output, "\"variance\" : %.2f, ", pct);
}
static void print_noise_pct(struct perf_stat_config *config,
double total, double avg, bool before_metric)
{
double pct = rel_stddev_stats(total, avg);
if (config->json_output) {
if (before_metric)
print_noise_pct_json(config, pct);
} else if (config->csv_output) {
if (before_metric)
print_noise_pct_csv(config, pct);
} else {
if (!before_metric)
print_noise_pct_std(config, pct);
}
}
static void print_noise(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool before_metric)
{
struct perf_stat_evsel *ps;
if (config->run_count == 1)
return;
ps = evsel->stats;
print_noise_pct(config, stddev_stats(&ps->res_stats), avg, before_metric);
}
static void print_cgroup_std(struct perf_stat_config *config, const char *cgrp_name)
{
fprintf(config->output, " %-*s", CGROUP_LEN, cgrp_name);
}
static void print_cgroup_csv(struct perf_stat_config *config, const char *cgrp_name)
{
fprintf(config->output, "%s%s", config->csv_sep, cgrp_name);
}
static void print_cgroup_json(struct perf_stat_config *config, const char *cgrp_name)
{
fprintf(config->output, "\"cgroup\" : \"%s\", ", cgrp_name);
}
static void print_cgroup(struct perf_stat_config *config, struct cgroup *cgrp)
{
if (nr_cgroups || config->cgroup_list) {
const char *cgrp_name = cgrp ? cgrp->name : "";
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->json_output)
print_cgroup_json(config, cgrp_name);
else if (config->csv_output)
print_cgroup_csv(config, cgrp_name);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
else
print_cgroup_std(config, cgrp_name);
}
}
static void print_aggr_id_std(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
FILE *output = config->output;
int idx = config->aggr_mode;
char buf[128];
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
switch (config->aggr_mode) {
case AGGR_CORE:
snprintf(buf, sizeof(buf), "S%d-D%d-C%d", id.socket, id.die, id.core);
break;
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
case AGGR_CACHE:
snprintf(buf, sizeof(buf), "S%d-D%d-L%d-ID%d",
id.socket, id.die, id.cache_lvl, id.cache);
break;
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-07 19:40:26 -07:00
case AGGR_CLUSTER:
snprintf(buf, sizeof(buf), "S%d-D%d-CLS%d", id.socket, id.die, id.cluster);
break;
case AGGR_DIE:
snprintf(buf, sizeof(buf), "S%d-D%d", id.socket, id.die);
break;
case AGGR_SOCKET:
snprintf(buf, sizeof(buf), "S%d", id.socket);
break;
case AGGR_NODE:
snprintf(buf, sizeof(buf), "N%d", id.node);
break;
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
snprintf(buf, sizeof(buf), "S%d-D%d-C%d ",
id.socket, id.die, id.core);
fprintf(output, "%-*s ",
aggr_header_lens[AGGR_CORE], buf);
} else if (id.cpu.cpu > -1) {
fprintf(output, "CPU%-*d ",
aggr_header_lens[AGGR_NONE] - 3, id.cpu.cpu);
}
return;
case AGGR_THREAD:
fprintf(output, "%*s-%-*d ",
COMM_LEN, perf_thread_map__comm(evsel->core.threads, id.thread_idx),
PID_LEN, perf_thread_map__pid(evsel->core.threads, id.thread_idx));
return;
case AGGR_GLOBAL:
case AGGR_UNSET:
case AGGR_MAX:
default:
return;
}
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
fprintf(output, "%-*s %*d ", aggr_header_lens[idx], buf, 4, aggr_nr);
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_aggr_id_csv(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
FILE *output = config->output;
const char *sep = config->csv_sep;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
switch (config->aggr_mode) {
case AGGR_CORE:
fprintf(output, "S%d-D%d-C%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.socket, id.die, id.core, sep, aggr_nr, sep);
break;
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
case AGGR_CACHE:
fprintf(config->output, "S%d-D%d-L%d-ID%d%s%d%s",
id.socket, id.die, id.cache_lvl, id.cache, sep, aggr_nr, sep);
break;
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-07 19:40:26 -07:00
case AGGR_CLUSTER:
fprintf(config->output, "S%d-D%d-CLS%d%s%d%s",
id.socket, id.die, id.cluster, sep, aggr_nr, sep);
break;
case AGGR_DIE:
fprintf(output, "S%d-D%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.socket, id.die, sep, aggr_nr, sep);
break;
case AGGR_SOCKET:
fprintf(output, "S%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.socket, sep, aggr_nr, sep);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
break;
perf stat: Add --per-node agregation support Adding new --per-node option to aggregate counts per NUMA nodes for system-wide mode measurements. You can specify --per-node in live mode: # perf stat -a -I 1000 -e cycles --per-node # time node cpus counts unit events 1.000542550 N0 20 6,202,097 cycles 1.000542550 N1 20 639,559 cycles 2.002040063 N0 20 7,412,495 cycles 2.002040063 N1 20 2,185,577 cycles 3.003451699 N0 20 6,508,917 cycles 3.003451699 N1 20 765,607 cycles ... Or in the record/report stat session: # perf stat record -a -I 1000 -e cycles # time counts unit events 1.000536937 10,008,468 cycles 2.002090152 9,578,539 cycles 3.003625233 7,647,869 cycles 4.005135036 7,032,086 cycles ^C 4.340902364 3,923,893 cycles # perf stat report --per-node # time node cpus counts unit events 1.000536937 N0 20 9,355,086 cycles 1.000536937 N1 20 653,382 cycles 2.002090152 N0 20 7,712,838 cycles 2.002090152 N1 20 1,865,701 cycles 3.003625233 N0 20 6,604,441 cycles 3.003625233 N1 20 1,043,428 cycles 4.005135036 N0 20 6,350,522 cycles 4.005135036 N1 20 681,564 cycles 4.340902364 N0 20 3,403,188 cycles 4.340902364 N1 20 520,705 cycles Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20190904073415.723-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 01:17:43 -07:00
case AGGR_NODE:
fprintf(output, "N%d%s%d%s",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.node, sep, aggr_nr, sep);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
break;
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
fprintf(output, "S%d-D%d-C%d%s",
id.socket, id.die, id.core, sep);
} else if (id.cpu.cpu > -1) {
fprintf(output, "CPU%d%s",
id.cpu.cpu, sep);
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
}
break;
case AGGR_THREAD:
fprintf(output, "%s-%d%s",
perf_thread_map__comm(evsel->core.threads, id.thread_idx),
perf_thread_map__pid(evsel->core.threads, id.thread_idx),
sep);
break;
case AGGR_GLOBAL:
case AGGR_UNSET:
case AGGR_MAX:
default:
break;
}
}
static void print_aggr_id_json(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
FILE *output = config->output;
switch (config->aggr_mode) {
case AGGR_CORE:
fprintf(output, "\"core\" : \"S%d-D%d-C%d\", \"aggregate-number\" : %d, ",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.socket, id.die, id.core, aggr_nr);
break;
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
case AGGR_CACHE:
fprintf(output, "\"cache\" : \"S%d-D%d-L%d-ID%d\", \"aggregate-number\" : %d, ",
id.socket, id.die, id.cache_lvl, id.cache, aggr_nr);
break;
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-07 19:40:26 -07:00
case AGGR_CLUSTER:
fprintf(output, "\"cluster\" : \"S%d-D%d-CLS%d\", \"aggregate-number\" : %d, ",
id.socket, id.die, id.cluster, aggr_nr);
break;
case AGGR_DIE:
fprintf(output, "\"die\" : \"S%d-D%d\", \"aggregate-number\" : %d, ",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.socket, id.die, aggr_nr);
break;
case AGGR_SOCKET:
fprintf(output, "\"socket\" : \"S%d\", \"aggregate-number\" : %d, ",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.socket, aggr_nr);
break;
case AGGR_NODE:
fprintf(output, "\"node\" : \"N%d\", \"aggregate-number\" : %d, ",
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
id.node, aggr_nr);
break;
case AGGR_NONE:
if (evsel->percore && !config->percore_show_thread) {
fprintf(output, "\"core\" : \"S%d-D%d-C%d\"",
id.socket, id.die, id.core);
} else if (id.cpu.cpu > -1) {
fprintf(output, "\"cpu\" : \"%d\", ",
id.cpu.cpu);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
}
break;
case AGGR_THREAD:
fprintf(output, "\"thread\" : \"%s-%d\", ",
perf_thread_map__comm(evsel->core.threads, id.thread_idx),
perf_thread_map__pid(evsel->core.threads, id.thread_idx));
break;
case AGGR_GLOBAL:
case AGGR_UNSET:
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
case AGGR_MAX:
default:
break;
}
}
static void aggr_printout(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct evsel *evsel, struct aggr_cpu_id id, int aggr_nr)
{
if (config->json_output)
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_aggr_id_json(config, evsel, id, aggr_nr);
else if (config->csv_output)
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_aggr_id_csv(config, evsel, id, aggr_nr);
else
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_aggr_id_std(config, evsel, id, aggr_nr);
}
struct outstate {
FILE *fh;
bool newline;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
bool first;
const char *prefix;
int nfields;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
int aggr_nr;
struct aggr_cpu_id id;
struct evsel *evsel;
struct cgroup *cgrp;
};
static void new_line_std(struct perf_stat_config *config __maybe_unused,
void *ctx)
{
struct outstate *os = ctx;
os->newline = true;
}
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
static inline void __new_line_std_csv(struct perf_stat_config *config,
struct outstate *os)
{
fputc('\n', os->fh);
perf stat: Check existence of os->prefix, fixing a segfault We need to check if we have a OS prefix, otherwise we stumble on a metric segv that I'm now seeing in Arnaldo's tree: $ gdb --args perf stat -M Backend true ... Performance counter stats for 'true': 4,712,355 TOPDOWN.SLOTS # 17.3 % tma_core_bound Program received signal SIGSEGV, Segmentation fault. __strlen_evex () at ../sysdeps/x86_64/multiarch/strlen-evex.S:77 77 ../sysdeps/x86_64/multiarch/strlen-evex.S: No such file or directory. (gdb) bt #0 __strlen_evex () at ../sysdeps/x86_64/multiarch/strlen-evex.S:77 #1 0x00007ffff74749a5 in __GI__IO_fputs (str=0x0, fp=0x7ffff75f5680 <_IO_2_1_stderr_>) #2 0x0000555555779f28 in do_new_line_std (config=0x555555e077c0 <stat_config>, os=0x7fffffffbf10) at util/stat-display.c:356 #3 0x000055555577a081 in print_metric_std (config=0x555555e077c0 <stat_config>, ctx=0x7fffffffbf10, color=0x0, fmt=0x5555558b77b5 "%8.1f", unit=0x7fffffffbb10 "% tma_memory_bound", val=13.165355724442199) at util/stat-display.c:380 #4 0x00005555557768b6 in generic_metric (config=0x555555e077c0 <stat_config>, metric_expr=0x55555593d5b7 "((CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES))"..., metric_events=0x555555f334e0, metric_refs=0x555555ec81d0, name=0x555555f32e80 "TOPDOWN.SLOTS", metric_name=0x555555f26c80 "tma_memory_bound", metric_unit=0x55555593d5b1 "100%", runtime=0, map_idx=0, out=0x7fffffffbd90, st=0x555555e9e620 <rt_stat>) at util/stat-shadow.c:934 #5 0x0000555555778cac in perf_stat__print_shadow_stats (config=0x555555e077c0 <stat_config>, evsel=0x555555f289d0, avg=4712355, map_idx=0, out=0x7fffffffbd90, metric_events=0x555555e078e8 <stat_config+296>, st=0x555555e9e620 <rt_stat>) at util/stat-shadow.c:1329 #6 0x000055555577b6a0 in printout (config=0x555555e077c0 <stat_config>, os=0x7fffffffbf10, uval=4712355, run=325322, ena=325322, noise=4712355, map_idx=0) at util/stat-display.c:741 #7 0x000055555577bc74 in print_counter_aggrdata (config=0x555555e077c0 <stat_config>, counter=0x555555f289d0, s=0, os=0x7fffffffbf10) at util/stat-display.c:838 #8 0x000055555577c1d8 in print_counter (config=0x555555e077c0 <stat_config>, counter=0x555555f289d0, os=0x7fffffffbf10) at util/stat-display.c:957 #9 0x000055555577dba0 in evlist__print_counters (evlist=0x555555ec3610, config=0x555555e077c0 <stat_config>, _target=0x555555e01c80 <target>, ts=0x0, argc=1, argv=0x7fffffffe450) at util/stat-display.c:1413 #10 0x00005555555fc821 in print_counters (ts=0x0, argc=1, argv=0x7fffffffe450) at builtin-stat.c:1040 #11 0x000055555560091a in cmd_stat (argc=1, argv=0x7fffffffe450) at builtin-stat.c:2665 #12 0x00005555556b1eea in run_builtin (p=0x555555e11f70 <commands+336>, argc=4, argv=0x7fffffffe450) at perf.c:322 #13 0x00005555556b2181 in handle_internal_command (argc=4, argv=0x7fffffffe450) at perf.c:376 #14 0x00005555556b22d7 in run_argv (argcp=0x7fffffffe27c, argv=0x7fffffffe270) at perf.c:420 #15 0x00005555556b26ef in main (argc=4, argv=0x7fffffffe450) at perf.c:550 (gdb) Fixes: f123b2d84ecec9a3 ("perf stat: Remove prefix argument in print_metric_headers()") Signed-off-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: http://lore.kernel.org/lkml/CAP-5=fUOjSM5HajU9TCD6prY39LbX4OQbkEbtKPPGRBPBN=_VQ@mail.gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-12-05 05:34:04 -07:00
if (os->prefix)
fputs(os->prefix, os->fh);
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
aggr_printout(config, os->evsel, os->id, os->aggr_nr);
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
}
static inline void __new_line_std(struct outstate *os)
{
fprintf(os->fh, " ");
}
static void do_new_line_std(struct perf_stat_config *config,
struct outstate *os)
{
__new_line_std_csv(config, os);
if (config->aggr_mode == AGGR_NONE)
fprintf(os->fh, " ");
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
__new_line_std(os);
}
static void print_metric_std(struct perf_stat_config *config,
void *ctx, const char *color, const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
int n;
bool newline = os->newline;
os->newline = false;
if (unit == NULL || fmt == NULL) {
fprintf(out, "%-*s", METRIC_LEN, "");
return;
}
if (newline)
do_new_line_std(config, os);
n = fprintf(out, " # ");
if (color)
n += color_fprintf(out, color, fmt, val);
else
n += fprintf(out, fmt, val);
fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
}
static void new_line_csv(struct perf_stat_config *config, void *ctx)
{
struct outstate *os = ctx;
int i;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
__new_line_std_csv(config, os);
for (i = 0; i < os->nfields; i++)
fputs(config->csv_sep, os->fh);
}
static void print_metric_csv(struct perf_stat_config *config __maybe_unused,
void *ctx,
const char *color __maybe_unused,
const char *fmt, const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[64], *vals, *ends;
if (unit == NULL || fmt == NULL) {
fprintf(out, "%s%s", config->csv_sep, config->csv_sep);
return;
}
snprintf(buf, sizeof(buf), fmt, val);
ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
fprintf(out, "%s%s%s%s", config->csv_sep, vals, config->csv_sep, skip_spaces(unit));
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_metric_json(struct perf_stat_config *config __maybe_unused,
void *ctx,
const char *color __maybe_unused,
const char *fmt __maybe_unused,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
perf metric: Change divide by zero and !support events behavior Division by zero causes expression parsing to fail and no metric to be generated. This can mean for short running benchmarks metrics are not shown. Change the behavior to make the value nan, which gets shown like: ''' $ perf stat -M TopdownL2 true Performance counter stats for 'true': 1,031,492 INST_RETIRED.ANY # nan % tma_fetch_bandwidth # nan % tma_heavy_operations # nan % tma_light_operations 29,304 CPU_CLK_UNHALTED.REF_XCLK # nan % tma_fetch_latency # nan % tma_branch_mispredicts # nan % tma_machine_clears # nan % tma_core_bound # nan % tma_memory_bound 2,658,319 IDQ_UOPS_NOT_DELIVERED.CORE 11,167 EXE_ACTIVITY.BOUND_ON_STORES 262,058 EXE_ACTIVITY.1_PORTS_UTIL <not counted> BR_MISP_RETIRED.ALL_BRANCHES (0.00%) <not counted> INT_MISC.RECOVERY_CYCLES_ANY (0.00%) <not counted> CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE (0.00%) <not counted> CPU_CLK_UNHALTED.THREAD (0.00%) <not counted> UOPS_RETIRED.RETIRE_SLOTS (0.00%) <not counted> CYCLE_ACTIVITY.STALLS_MEM_ANY (0.00%) <not counted> UOPS_RETIRED.MACRO_FUSED (0.00%) <not counted> IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE (0.00%) <not counted> EXE_ACTIVITY.2_PORTS_UTIL (0.00%) <not counted> CYCLE_ACTIVITY.STALLS_TOTAL (0.00%) <not counted> MACHINE_CLEARS.COUNT (0.00%) <not counted> UOPS_ISSUED.ANY (0.00%) 0.002864879 seconds time elapsed 0.003012000 seconds user 0.000000000 seconds sys ''' When events aren't supported a count of 0 can be confusing and make metrics look meaningful. Change these to be nan also which, with the next change, gets shown like: ''' $ perf stat true Performance counter stats for 'true': 1.25 msec task-clock:u # 0.387 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 46 page-faults:u # 36.702 K/sec 255,942 cycles:u # 0.204 GHz (88.66%) 123,046 instructions:u # 0.48 insn per cycle 28,301 branches:u # 22.580 M/sec 2,489 branch-misses:u # 8.79% of all branches 4,719 CPU_CLK_UNHALTED.REF_XCLK:u # 3.765 M/sec # nan % tma_frontend_bound # nan % tma_retiring # nan % tma_backend_bound # nan % tma_bad_speculation 344,855 IDQ_UOPS_NOT_DELIVERED.CORE:u # 275.147 M/sec <not supported> INT_MISC.RECOVERY_CYCLES_ANY:u <not counted> CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE:u (0.00%) <not counted> CPU_CLK_UNHALTED.THREAD:u (0.00%) <not counted> UOPS_RETIRED.RETIRE_SLOTS:u (0.00%) <not counted> UOPS_ISSUED.ANY:u (0.00%) 0.003238142 seconds time elapsed 0.000000000 seconds user 0.003434000 seconds sys ''' Ensure that nan metric values are quoted as nan isn't a valid number in JSON. Signed-off-by: Ian Rogers <irogers@google.com> Tested-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Edward Baker <edward.baker@intel.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Samantha Alt <samantha.alt@intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: Yang Jihong <yangjihong1@huawei.com> Link: https://lore.kernel.org/r/20230502223851.2234828-2-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-02 15:38:08 -07:00
fprintf(out, "\"metric-value\" : \"%f\", ", val);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
fprintf(out, "\"metric-unit\" : \"%s\"", unit);
if (!config->metric_only)
fprintf(out, "}");
}
static void new_line_json(struct perf_stat_config *config, void *ctx)
{
struct outstate *os = ctx;
fputs("\n{", os->fh);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (os->prefix)
fprintf(os->fh, "%s", os->prefix);
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
aggr_printout(config, os->evsel, os->id, os->aggr_nr);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
}
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
static void print_metricgroup_header_json(struct perf_stat_config *config,
void *ctx,
const char *metricgroup_name)
{
if (!metricgroup_name)
return;
fprintf(config->output, "\"metricgroup\" : \"%s\"}", metricgroup_name);
new_line_json(config, ctx);
}
static void print_metricgroup_header_csv(struct perf_stat_config *config,
void *ctx,
const char *metricgroup_name)
{
struct outstate *os = ctx;
int i;
if (!metricgroup_name) {
/* Leave space for running and enabling */
for (i = 0; i < os->nfields - 2; i++)
fputs(config->csv_sep, os->fh);
return;
}
for (i = 0; i < os->nfields; i++)
fputs(config->csv_sep, os->fh);
fprintf(config->output, "%s", metricgroup_name);
new_line_csv(config, ctx);
}
static void print_metricgroup_header_std(struct perf_stat_config *config,
void *ctx,
const char *metricgroup_name)
{
struct outstate *os = ctx;
int n;
if (!metricgroup_name) {
__new_line_std(os);
return;
}
n = fprintf(config->output, " %*s", EVNAME_LEN, metricgroup_name);
fprintf(config->output, "%*s", MGROUP_LEN - n - 1, "");
}
/* Filter out some columns that don't work well in metrics only mode */
static bool valid_only_metric(const char *unit)
{
if (!unit)
return false;
if (strstr(unit, "/sec") ||
strstr(unit, "CPUs utilized"))
return false;
return true;
}
static const char *fixunit(char *buf, struct evsel *evsel,
const char *unit)
{
if (!strncmp(unit, "of all", 6)) {
snprintf(buf, 1024, "%s %s", evsel__name(evsel),
unit);
return buf;
}
return unit;
}
static void print_metric_only(struct perf_stat_config *config,
void *ctx, const char *color, const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[1024], str[1024];
unsigned mlen = config->metric_only_len;
if (!valid_only_metric(unit))
return;
unit = fixunit(buf, os->evsel, unit);
if (mlen < strlen(unit))
mlen = strlen(unit) + 1;
if (color)
mlen += strlen(color) + sizeof(PERF_COLOR_RESET) - 1;
color_snprintf(str, sizeof(str), color ?: "", fmt ?: "", val);
fprintf(out, "%*s ", mlen, str);
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
os->first = false;
}
static void print_metric_only_csv(struct perf_stat_config *config __maybe_unused,
void *ctx, const char *color __maybe_unused,
const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[64], *vals, *ends;
char tbuf[1024];
if (!valid_only_metric(unit))
return;
unit = fixunit(tbuf, os->evsel, unit);
snprintf(buf, sizeof(buf), fmt ?: "", val);
ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
fprintf(out, "%s%s", vals, config->csv_sep);
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
os->first = false;
}
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
static void print_metric_only_json(struct perf_stat_config *config __maybe_unused,
void *ctx, const char *color __maybe_unused,
const char *fmt,
const char *unit, double val)
{
struct outstate *os = ctx;
FILE *out = os->fh;
char buf[64], *vals, *ends;
char tbuf[1024];
if (!valid_only_metric(unit))
return;
unit = fixunit(tbuf, os->evsel, unit);
snprintf(buf, sizeof(buf), fmt ?: "", val);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
ends = vals = skip_spaces(buf);
while (isdigit(*ends) || *ends == '.')
ends++;
*ends = 0;
if (!unit[0] || !vals[0])
return;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
fprintf(out, "%s\"%s\" : \"%s\"", os->first ? "" : ", ", unit, vals);
os->first = false;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
}
static void new_line_metric(struct perf_stat_config *config __maybe_unused,
void *ctx __maybe_unused)
{
}
static void print_metric_header(struct perf_stat_config *config,
void *ctx, const char *color __maybe_unused,
const char *fmt __maybe_unused,
const char *unit, double val __maybe_unused)
{
struct outstate *os = ctx;
char tbuf[1024];
/* In case of iostat, print metric header for first root port only */
if (config->iostat_run &&
os->evsel->priv != os->evsel->evlist->selected->priv)
return;
if (os->evsel->cgrp != os->cgrp)
return;
perf stat: Fix --metric-only --json output Currently it prints all metric headers for JSON output. But actually it skips some metrics with valid_only_metric(). So the output looks like: $ perf stat --metric-only --json true {"unit" : "CPUs utilized", "unit" : "/sec", "unit" : "/sec", "unit" : "/sec", "unit" : "GHz", "unit" : "insn per cycle", "unit" : "/sec", "unit" : "branch-misses of all branches"} {"metric-value" : "3.861"}{"metric-value" : "0.79"}{"metric-value" : "3.04"} As you can see there are 8 units in the header but only 3 metric-values are there. It should skip the unused headers as well. Also each unit should be printed as a separate object like metric values. With this patch: $ perf stat --metric-only --json true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"metric-value" : "4.166"}{"metric-value" : "0.73"}{"metric-value" : "2.96"} Fixes: df936cadfb58ba93 ("perf stat: Add JSON output option") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Claire Jensen <cjense@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221107213314.3239159-6-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-07 14:33:10 -07:00
if (!valid_only_metric(unit))
return;
unit = fixunit(tbuf, os->evsel, unit);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->json_output)
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
return;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
else if (config->csv_output)
fprintf(os->fh, "%s%s", unit, config->csv_sep);
else
fprintf(os->fh, "%*s ", config->metric_only_len, unit);
}
static void print_counter_value_std(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool ok)
{
FILE *output = config->output;
double sc = evsel->scale;
const char *fmt;
const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED;
if (config->big_num)
fmt = floor(sc) != sc ? "%'*.2f " : "%'*.0f ";
else
fmt = floor(sc) != sc ? "%*.2f " : "%*.0f ";
if (ok)
fprintf(output, fmt, COUNTS_LEN, avg);
else
fprintf(output, "%*s ", COUNTS_LEN, bad_count);
if (evsel->unit)
fprintf(output, "%-*s ", config->unit_width, evsel->unit);
fprintf(output, "%-*s", EVNAME_LEN, evsel__name(evsel));
}
static void print_counter_value_csv(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool ok)
{
FILE *output = config->output;
double sc = evsel->scale;
const char *sep = config->csv_sep;
const char *fmt = floor(sc) != sc ? "%.2f%s" : "%.0f%s";
const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED;
if (ok)
fprintf(output, fmt, avg, sep);
else
fprintf(output, "%s%s", bad_count, sep);
if (evsel->unit)
fprintf(output, "%s%s", evsel->unit, sep);
fprintf(output, "%s", evsel__name(evsel));
}
static void print_counter_value_json(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool ok)
{
FILE *output = config->output;
const char *bad_count = evsel->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED;
if (ok)
fprintf(output, "\"counter-value\" : \"%f\", ", avg);
else
fprintf(output, "\"counter-value\" : \"%s\", ", bad_count);
if (evsel->unit)
fprintf(output, "\"unit\" : \"%s\", ", evsel->unit);
fprintf(output, "\"event\" : \"%s\", ", evsel__name(evsel));
}
static void print_counter_value(struct perf_stat_config *config,
struct evsel *evsel, double avg, bool ok)
{
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->json_output)
print_counter_value_json(config, evsel, avg, ok);
else if (config->csv_output)
print_counter_value_csv(config, evsel, avg, ok);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
else
print_counter_value_std(config, evsel, avg, ok);
}
static void abs_printout(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct aggr_cpu_id id, int aggr_nr,
struct evsel *evsel, double avg, bool ok)
{
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
aggr_printout(config, evsel, id, aggr_nr);
print_counter_value(config, evsel, avg, ok);
print_cgroup(config, evsel->cgrp);
}
static bool is_mixed_hw_group(struct evsel *counter)
{
struct evlist *evlist = counter->evlist;
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 04:24:29 -07:00
u32 pmu_type = counter->core.attr.type;
struct evsel *pos;
if (counter->core.nr_members < 2)
return false;
evlist__for_each_entry(evlist, pos) {
/* software events can be part of any hardware group */
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 04:24:29 -07:00
if (pos->core.attr.type == PERF_TYPE_SOFTWARE)
continue;
if (pmu_type == PERF_TYPE_SOFTWARE) {
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 04:24:29 -07:00
pmu_type = pos->core.attr.type;
continue;
}
libperf: Move perf_event_attr field from perf's evsel to libperf's perf_evsel Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'. Committer notes: Fixed up these: tools/perf/arch/arm/util/auxtrace.c tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/arm-spe.c tools/perf/arch/s390/util/auxtrace.c tools/perf/util/cs-etm.c Also cc1: warnings being treated as errors tests/sample-parsing.c: In function 'do_test': tests/sample-parsing.c:162: error: missing initializer tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus') struct evsel evsel = { .needs_swap = false, - .core.attr = { - .sample_type = sample_type, - .read_format = read_format, + .core = { + . attr = { + .sample_type = sample_type, + .read_format = read_format, + }, [perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1 gcc (GCC) 4.4.7 Also we don't need to include perf_event.h in tools/perf/lib/include/perf/evsel.h, forward declaring 'struct perf_event_attr' is enough. And this even fixes the build in some systems where things are used somewhere down the include path from perf_event.h without defining __always_inline. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-07-21 04:24:29 -07:00
if (pmu_type != pos->core.attr.type)
return true;
}
return false;
}
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
static bool evlist__has_hybrid(struct evlist *evlist)
{
struct evsel *evsel;
perf pmus: Remove perf_pmus__has_hybrid perf_pmus__has_hybrid was used to detect when there was >1 core PMU, this can be achieved with perf_pmus__num_core_pmus that doesn't depend upon is_pmu_hybrid and PMU name comparisons. When modifying the function calls take the opportunity to improve comments, enable/simplify tests that were previously failing for hybrid but now pass and to simplify generic code. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-34-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:22:09 -07:00
if (perf_pmus__num_core_pmus() == 1)
perf stat: Avoid hybrid PMU list perf_pmu__is_hybrid implicitly uses the hybrid PMU list. Instead return false if hybrid isn't present, if it is then see if any evsel's PMUs are core. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-23-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:58 -07:00
return false;
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
evlist__for_each_entry(evlist, evsel) {
perf stat: Avoid hybrid PMU list perf_pmu__is_hybrid implicitly uses the hybrid PMU list. Instead return false if hybrid isn't present, if it is then see if any evsel's PMUs are core. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-23-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:58 -07:00
if (evsel->core.is_pmu_core)
perf evlist: Reduce scope of evlist__has_hybrid Function is only used in printout, reduce scope to stat-display.c. Remove the now empty evlist-hybrid.c and evlist-hybrid.h. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ali Saidi <alisaidi@amazon.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Dmitrii Dolgov <9erthalion6@gmail.com> Cc: Huacai Chen <chenhuacai@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mike Leach <mike.leach@linaro.org> Cc: Ming Wang <wangming01@loongson.cn> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Link: https://lore.kernel.org/r/20230527072210.2900565-15-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-27 00:21:50 -07:00
return true;
}
return false;
}
static void printout(struct perf_stat_config *config, struct outstate *os,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
double uval, u64 run, u64 ena, double noise, int aggr_idx)
{
struct perf_stat_output_ctx out;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
print_metric_t pm;
new_line_t nl;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
print_metricgroup_header_t pmh;
bool ok = true;
struct evsel *counter = os->evsel;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
if (config->csv_output) {
pm = config->metric_only ? print_metric_only_csv : print_metric_csv;
nl = config->metric_only ? new_line_metric : new_line_csv;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
pmh = print_metricgroup_header_csv;
perf stat: Fix printing field separator in CSV metrics output In 'perf stat' with CSV output option, number of fields in metrics output is not matching with number of fields in other event output lines. Sample output below after applying patch to fix printing os->prefix. # ./perf stat -x, --per-socket -a -C 1 ls S0,1,82.11,msec,cpu-clock,82111626,100.00,1.000,CPUs utilized S0,1,2,,context-switches,82109314,100.00,24.358,/sec ------ ====> S0,1,,,,,,,1.71,stalled cycles per insn The above command line uses field separator as "," via "-x," option and per-socket option displays socket value as first field. But here the last line for "stalled cycles per insn" has more separators. Each csv output line is expected to have 8 field separators (for the 9 fields), where as last line has 9 "," in the result. Patch fixes this issue. The counter stats are displayed by function "perf_stat__print_shadow_stats" in code "util/stat-shadow.c". While printing the stats info for "stalled cycles per insn", function "new_line_csv" is used as new_line callback. The fields printed in each line contains: "Socket_id,aggr nr,Avg,unit,event_name,run,enable_percent,ratio,unit" The metric output prints Socket_id, aggr nr, ratio and unit. It has to skip through remaining five fields ie, Avg,unit,event_name,run,enable_percent. The csv line callback uses "os->nfields" to know the number of fields to skip to match with other lines. Currently it is set as: os.nfields = 3 + aggr_fields[config->aggr_mode] + (counter->cgrp ? 1 : 0); But in case of aggregation modes, csv_sep already gets printed along with each field (Function "aggr_printout" in util/stat-display.c). So aggr_fields can be removed from nfields. And fixed number of fields to skip has to be "4". This is to skip fields for: "avg, unit, event name, run, enable_percent" This needs 4 csv separators. Patch removes aggr_fields and uses 4 as fixed number of os->nfields to skip. After the patch: # ./perf stat -x, --per-socket -a -C 1 ls S0,1,79.08,msec,cpu-clock,79085956,100.00,1.000,CPUs utilized S0,1,7,,context-switches,79084176,100.00,88.514,/sec ------ ====> S0,1,,,,,,0.81,stalled cycles per insn Fixes: 92a61f6412d3a09d ("perf stat: Implement CSV metrics output") Reported-by: Disha Goel <disgoel@linux.vnet.ibm.com> Reviewed-by: Kajol Jain <kjain@linux.ibm.com> Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Disha Goel <disgoel@linux.vnet.ibm.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ian Rogers <irogers@google.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Nageswara R Sastry <rnsastry@linux.ibm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: linuxppc-dev@lists.ozlabs.org Link: https://lore.kernel.org/r/20221205042852.83382-1-atrajeev@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-12-04 21:28:52 -07:00
os->nfields = 4 + (counter->cgrp ? 1 : 0);
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
} else if (config->json_output) {
pm = config->metric_only ? print_metric_only_json : print_metric_json;
nl = config->metric_only ? new_line_metric : new_line_json;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
pmh = print_metricgroup_header_json;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
} else {
pm = config->metric_only ? print_metric_only : print_metric_std;
nl = config->metric_only ? new_line_metric : new_line_std;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
pmh = print_metricgroup_header_std;
}
perf stat: Align CSV output for summary mode The 'perf stat' subcommand supports the request for a summary of the interval counter readings. But the summary lines break the CSV output so it's hard for scripts to parse the result. Before: # perf stat -x, -I1000 --interval-count 1 --summary 1.001323097,8013.48,msec,cpu-clock,8013483384,100.00,8.013,CPUs utilized 1.001323097,270,,context-switches,8013513297,100.00,0.034,K/sec 1.001323097,13,,cpu-migrations,8013530032,100.00,0.002,K/sec 1.001323097,184,,page-faults,8013546992,100.00,0.023,K/sec 1.001323097,20574191,,cycles,8013551506,100.00,0.003,GHz 1.001323097,10562267,,instructions,8013564958,100.00,0.51,insn per cycle 1.001323097,2019244,,branches,8013575673,100.00,0.252,M/sec 1.001323097,106152,,branch-misses,8013585776,100.00,5.26,of all branches 8013.48,msec,cpu-clock,8013483384,100.00,7.984,CPUs utilized 270,,context-switches,8013513297,100.00,0.034,K/sec 13,,cpu-migrations,8013530032,100.00,0.002,K/sec 184,,page-faults,8013546992,100.00,0.023,K/sec 20574191,,cycles,8013551506,100.00,0.003,GHz 10562267,,instructions,8013564958,100.00,0.51,insn per cycle 2019244,,branches,8013575673,100.00,0.252,M/sec 106152,,branch-misses,8013585776,100.00,5.26,of all branches The summary line loses the timestamp column, which breaks the CSV output. We add a column at the original 'timestamp' position and it just says 'summary' for the summary line. After: # perf stat -x, -I1000 --interval-count 1 --summary 1.001196053,8012.72,msec,cpu-clock,8012722903,100.00,8.013,CPUs utilized 1.001196053,218,,context-switches,8012753271,100.00,0.027,K/sec 1.001196053,9,,cpu-migrations,8012769767,100.00,0.001,K/sec 1.001196053,0,,page-faults,8012786257,100.00,0.000,K/sec 1.001196053,15004518,,cycles,8012790637,100.00,0.002,GHz 1.001196053,7954691,,instructions,8012804027,100.00,0.53,insn per cycle 1.001196053,1590259,,branches,8012814766,100.00,0.198,M/sec 1.001196053,82601,,branch-misses,8012824365,100.00,5.19,of all branches summary,8012.72,msec,cpu-clock,8012722903,100.00,7.986,CPUs utilized summary,218,,context-switches,8012753271,100.00,0.027,K/sec summary,9,,cpu-migrations,8012769767,100.00,0.001,K/sec summary,0,,page-faults,8012786257,100.00,0.000,K/sec summary,15004518,,cycles,8012790637,100.00,0.002,GHz summary,7954691,,instructions,8012804027,100.00,0.53,insn per cycle summary,1590259,,branches,8012814766,100.00,0.198,M/sec summary,82601,,branch-misses,8012824365,100.00,5.19,of all branches Now it's easy for script to analyse the summary lines. Of course, we also consider not to break possible existing scripts which can continue to use the broken CSV format by using a new '--no-csv-summary.' option. # perf stat -x, -I1000 --interval-count 1 --summary --no-csv-summary 1.001213261,8012.67,msec,cpu-clock,8012672327,100.00,8.013,CPUs utilized 1.001213261,197,,context-switches,8012703742,100.00,24.586,/sec 1.001213261,9,,cpu-migrations,8012720902,100.00,1.123,/sec 1.001213261,644,,page-faults,8012738266,100.00,80.373,/sec 1.001213261,18350698,,cycles,8012744109,100.00,0.002,GHz 1.001213261,12745021,,instructions,8012759001,100.00,0.69,insn per cycle 1.001213261,2458033,,branches,8012770864,100.00,306.768,K/sec 1.001213261,102107,,branch-misses,8012781751,100.00,4.15,of all branches 8012.67,msec,cpu-clock,8012672327,100.00,7.985,CPUs utilized 197,,context-switches,8012703742,100.00,24.586,/sec 9,,cpu-migrations,8012720902,100.00,1.123,/sec 644,,page-faults,8012738266,100.00,80.373,/sec 18350698,,cycles,8012744109,100.00,0.002,GHz 12745021,,instructions,8012759001,100.00,0.69,insn per cycle 2458033,,branches,8012770864,100.00,306.768,K/sec 102107,,branch-misses,8012781751,100.00,4.15,of all branches This option can be enabled in perf config by setting the variable 'stat.no-csv-summary'. # perf config stat.no-csv-summary=true # perf config -l stat.no-csv-summary=true # perf stat -x, -I1000 --interval-count 1 --summary 1.001330198,8013.28,msec,cpu-clock,8013279201,100.00,8.013,CPUs utilized 1.001330198,205,,context-switches,8013308394,100.00,25.583,/sec 1.001330198,10,,cpu-migrations,8013324681,100.00,1.248,/sec 1.001330198,0,,page-faults,8013340926,100.00,0.000,/sec 1.001330198,8027742,,cycles,8013344503,100.00,0.001,GHz 1.001330198,2871717,,instructions,8013356501,100.00,0.36,insn per cycle 1.001330198,553564,,branches,8013366204,100.00,69.081,K/sec 1.001330198,54021,,branch-misses,8013375952,100.00,9.76,of all branches 8013.28,msec,cpu-clock,8013279201,100.00,7.985,CPUs utilized 205,,context-switches,8013308394,100.00,25.583,/sec 10,,cpu-migrations,8013324681,100.00,1.248,/sec 0,,page-faults,8013340926,100.00,0.000,/sec 8027742,,cycles,8013344503,100.00,0.001,GHz 2871717,,instructions,8013356501,100.00,0.36,insn per cycle 553564,,branches,8013366204,100.00,69.081,K/sec 54021,,branch-misses,8013375952,100.00,9.76,of all branches Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210319070156.20394-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-03-19 00:01:55 -07:00
if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
if (config->metric_only) {
pm(config, os, NULL, "", "", 0);
return;
}
ok = false;
if (counter->supported) {
perf stat: Disable the NMI watchdog message on hybrid If we run a single workload that only runs on big core, there is always a ugly message about disabling the NMI watchdog because the atom is not counted. Before: # ./perf stat true Performance counter stats for 'true': 0.43 msec task-clock # 0.396 CPUs utilized 0 context-switches # 0.000 /sec 0 cpu-migrations # 0.000 /sec 45 page-faults # 103.918 K/sec 639,634 cpu_core/cycles/ # 1.477 G/sec <not counted> cpu_atom/cycles/ (0.00%) 643,498 cpu_core/instructions/ # 1.486 G/sec <not counted> cpu_atom/instructions/ (0.00%) 123,715 cpu_core/branches/ # 285.694 M/sec <not counted> cpu_atom/branches/ (0.00%) 4,094 cpu_core/branch-misses/ # 9.454 M/sec <not counted> cpu_atom/branch-misses/ (0.00%) 0.001092407 seconds time elapsed 0.001144000 seconds user 0.000000000 seconds sys Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog # ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' true Performance counter stats for 'true': <not counted> cpu_atom/cycles/ (0.00%) <not counted> msr/tsc/ (0.00%) 0.001904106 seconds time elapsed 0.001947000 seconds user 0.000000000 seconds sys Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The events in group usually have to be from the same PMU. Try reorganizing the group. Now we disable the NMI watchdog message on hybrid, otherwise there are too many false positives. After: # ./perf stat true Performance counter stats for 'true': 0.79 msec task-clock # 0.419 CPUs utilized 0 context-switches # 0.000 /sec 0 cpu-migrations # 0.000 /sec 48 page-faults # 60.889 K/sec 777,692 cpu_core/cycles/ # 986.519 M/sec <not counted> cpu_atom/cycles/ (0.00%) 669,147 cpu_core/instructions/ # 848.828 M/sec <not counted> cpu_atom/instructions/ (0.00%) 128,635 cpu_core/branches/ # 163.176 M/sec <not counted> cpu_atom/branches/ (0.00%) 4,089 cpu_core/branch-misses/ # 5.187 M/sec <not counted> cpu_atom/branch-misses/ (0.00%) 0.001880649 seconds time elapsed 0.001935000 seconds user 0.000000000 seconds sys # ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' true Performance counter stats for 'true': <not counted> cpu_atom/cycles/ (0.00%) <not counted> msr/tsc/ (0.00%) 0.000963319 seconds time elapsed 0.000999000 seconds user 0.000000000 seconds sys Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210610034557.29766-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-06-09 20:45:57 -07:00
if (!evlist__has_hybrid(counter->evlist)) {
config->print_free_counters_hint = 1;
if (is_mixed_hw_group(counter))
config->print_mixed_hw_group_error = 1;
}
}
}
out.print_metric = pm;
out.new_line = nl;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
out.print_metricgroup_header = pmh;
out.ctx = os;
out.force_header = false;
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
if (!config->metric_only && !counter->default_metricgroup) {
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
abs_printout(config, os->id, os->aggr_nr, counter, uval, ok);
print_noise(config, counter, noise, /*before_metric=*/true);
print_running(config, run, ena, /*before_metric=*/true);
}
if (ok) {
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
if (!config->metric_only && counter->default_metricgroup) {
void *from = NULL;
aggr_printout(config, os->evsel, os->id, os->aggr_nr);
/* Print out all the metricgroup with the same metric event. */
do {
int num = 0;
/* Print out the new line for the next new metricgroup. */
if (from) {
if (config->json_output)
new_line_json(config, (void *)os);
else
__new_line_std_csv(config, os);
}
print_noise(config, counter, noise, /*before_metric=*/true);
print_running(config, run, ena, /*before_metric=*/true);
from = perf_stat__print_shadow_stats_metricgroup(config, counter, aggr_idx,
&num, from, &out,
&config->metric_events);
} while (from != NULL);
} else
perf_stat__print_shadow_stats(config, counter, uval, aggr_idx,
&out, &config->metric_events);
} else {
pm(config, os, /*color=*/NULL, /*format=*/NULL, /*unit=*/"", /*val=*/0);
}
if (!config->metric_only) {
print_noise(config, counter, noise, /*before_metric=*/false);
print_running(config, run, ena, /*before_metric=*/false);
}
}
static void uniquify_event_name(struct evsel *counter)
{
char *new_name;
char *config;
int ret = 0;
if (counter->uniquified_name || counter->use_config_name ||
perf stat: Avoid SEGV on counter->name Switch to use evsel__name() that doesn't return NULL for hardware and similar events. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Edward Baker <edward.baker@intel.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kang Minchul <tegongkang@gmail.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Rob Herring <robh@kernel.org> Cc: Samantha Alt <samantha.alt@intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Sumanth Korikkar <sumanthk@linux.ibm.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Tiezhu Yang <yangtiezhu@loongson.cn> Cc: Weilin Wang <weilin.wang@intel.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: Yang Jihong <yangjihong1@huawei.com> Link: https://lore.kernel.org/r/20230426070050.1315519-8-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-04-26 00:00:17 -07:00
!counter->pmu_name || !strncmp(evsel__name(counter), counter->pmu_name,
strlen(counter->pmu_name)))
return;
config = strchr(counter->name, '/');
if (config) {
if (asprintf(&new_name,
"%s%s", counter->pmu_name, config) > 0) {
free(counter->name);
counter->name = new_name;
}
} else {
if (evsel__is_hybrid(counter)) {
ret = asprintf(&new_name, "%s/%s/",
counter->pmu_name, counter->name);
} else {
ret = asprintf(&new_name, "%s [%s]",
counter->name, counter->pmu_name);
}
if (ret) {
free(counter->name);
counter->name = new_name;
}
}
counter->uniquified_name = true;
}
static bool hybrid_uniquify(struct evsel *evsel, struct perf_stat_config *config)
{
return evsel__is_hybrid(evsel) && !config->hybrid_merge;
}
static void uniquify_counter(struct perf_stat_config *config, struct evsel *counter)
{
perf stat: Combine the -A/--no-aggr and --no-merge options The -A or --no-aggr option disables aggregation of core events: $ perf stat -A -e cycles,data_total -a true Performance counter stats for 'system wide': CPU0 1,287,665 cycles CPU1 1,831,681 cycles CPU2 27,345,998 cycles CPU3 1,964,799 cycles CPU4 236,174 cycles CPU5 3,302,825 cycles CPU6 9,201,446 cycles CPU7 1,403,043 cycles CPU0 110.90 MiB data_total 0.008961761 seconds time elapsed The --no-merge option disables the aggregation of uncore events: $ perf stat --no-merge -e cycles,data_total -a true Performance counter stats for 'system wide': 38,482,778 cycles 15.04 MiB data_total [uncore_imc_free_running_1] 15.00 MiB data_total [uncore_imc_free_running_0] 0.005915155 seconds time elapsed Having two options confuses users who generally don't appreciate the difference in PMUs. Keep all the options but make it so they all disable aggregation both of core and uncore events: $ perf stat -A -e cycles,data_total -a true Performance counter stats for 'system wide': CPU0 85,878 cycles CPU1 88,179 cycles CPU2 60,872 cycles CPU3 3,265,567 cycles CPU4 82,357 cycles CPU5 83,383 cycles CPU6 84,156 cycles CPU7 220,803 cycles CPU0 2.38 MiB data_total [uncore_imc_free_running_0] CPU0 2.38 MiB data_total [uncore_imc_free_running_1] 0.001397205 seconds time elapsed Update the relevant 'perf stat' man page information. Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Changbin Du <changbin.du@huawei.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Kaige Ye <ye@kaige.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20231214060256.2094017-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-12-13 23:02:56 -07:00
if (config->aggr_mode == AGGR_NONE || hybrid_uniquify(counter, config))
uniquify_event_name(counter);
}
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 12:24:31 -07:00
/**
* should_skip_zero_count() - Check if the event should print 0 values.
* @config: The perf stat configuration (including aggregation mode).
* @counter: The evsel with its associated cpumap.
* @id: The aggregation id that is being queried.
*
* Due to mismatch between the event cpumap or thread-map and the
* aggregation mode, sometimes it'd iterate the counter with the map
* which does not contain any values.
*
* For example, uncore events have dedicated CPUs to manage them,
* result for other CPUs should be zero and skipped.
*
* Return: %true if the value should NOT be printed, %false if the value
* needs to be printed like "<not counted>" or "<not supported>".
*/
static bool should_skip_zero_counter(struct perf_stat_config *config,
struct evsel *counter,
const struct aggr_cpu_id *id)
{
struct perf_cpu cpu;
int idx;
/*
* Skip value 0 when enabling --per-thread globally,
* otherwise it will have too many 0 output.
*/
if (config->aggr_mode == AGGR_THREAD && config->system_wide)
return true;
/* Tool events have the software PMU but are only gathered on 1. */
if (evsel__is_tool(counter))
return true;
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 12:24:31 -07:00
/*
* Skip value 0 when it's an uncore event and the given aggr id
* does not belong to the PMU cpumask.
*/
if (!counter->pmu || !counter->pmu->is_uncore)
return false;
perf_cpu_map__for_each_cpu(cpu, idx, counter->pmu->cpus) {
struct aggr_cpu_id own_id = config->aggr_get_id(config, cpu);
if (aggr_cpu_id__equal(id, &own_id))
return false;
}
return true;
}
static void print_counter_aggrdata(struct perf_stat_config *config,
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct evsel *counter, int aggr_idx,
struct outstate *os)
{
FILE *output = config->output;
u64 ena, run, val;
double uval;
struct perf_stat_evsel *ps = counter->stats;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
struct perf_stat_aggr *aggr = &ps->aggr[aggr_idx];
struct aggr_cpu_id id = config->aggr_map->map[aggr_idx];
double avg = aggr->counts.val;
bool metric_only = config->metric_only;
os->id = id;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
os->aggr_nr = aggr->nr;
os->evsel = counter;
/* Skip already merged uncore/hybrid events */
if (counter->merged_stat)
return;
uniquify_counter(config, counter);
val = aggr->counts.val;
ena = aggr->counts.ena;
run = aggr->counts.run;
perf stat: Filter out unmatched aggregation for hybrid event perf-stat has supported some aggregation modes, such as --per-core, --per-socket and etc. While for hybrid event, it may only available on part of cpus. So for --per-core, we need to filter out the unavailable cores, for --per-socket, filter out the unavailable sockets, and so on. Before: # perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 2 479,530 cpu_core/cycles/ S0-D0-C4 2 175,007 cpu_core/cycles/ S0-D0-C8 2 166,240 cpu_core/cycles/ S0-D0-C12 2 704,673 cpu_core/cycles/ S0-D0-C16 2 865,835 cpu_core/cycles/ S0-D0-C20 2 2,958,461 cpu_core/cycles/ S0-D0-C24 2 163,988 cpu_core/cycles/ S0-D0-C28 2 164,729 cpu_core/cycles/ S0-D0-C32 0 <not counted> cpu_core/cycles/ S0-D0-C33 0 <not counted> cpu_core/cycles/ S0-D0-C34 0 <not counted> cpu_core/cycles/ S0-D0-C35 0 <not counted> cpu_core/cycles/ S0-D0-C36 0 <not counted> cpu_core/cycles/ S0-D0-C37 0 <not counted> cpu_core/cycles/ S0-D0-C38 0 <not counted> cpu_core/cycles/ S0-D0-C39 0 <not counted> cpu_core/cycles/ 1.003597211 seconds time elapsed After: # perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 2 210,428 cpu_core/cycles/ S0-D0-C4 2 444,830 cpu_core/cycles/ S0-D0-C8 2 435,241 cpu_core/cycles/ S0-D0-C12 2 423,976 cpu_core/cycles/ S0-D0-C16 2 859,350 cpu_core/cycles/ S0-D0-C20 2 1,559,589 cpu_core/cycles/ S0-D0-C24 2 163,924 cpu_core/cycles/ S0-D0-C28 2 376,610 cpu_core/cycles/ 1.003621290 seconds time elapsed Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Co-developed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20210427070139.25256-16-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-04-27 00:01:28 -07:00
perf stat: New metricgroup output for the default mode In the default mode, the current output of the metricgroup include both events and metrics, which is not necessary and just makes the output hard to read. Since different ARCHs (even different generations in the same ARCH) may use different events. The output also vary on different platforms. For a metricgroup, only outputting the value of each metric is good enough. Add a new field default_metricgroup in evsel to indicate an event of the default metricgroup. For those events, printout() should print the metricgroup name rather than each event. Add perf_stat__skip_metric_event() to skip the evsel in the Default metricgroup, if it's not running or not the metric event. Add print_metricgroup_header_t to pass the functions which print the display name of each metricgroup in the Default metricgroup. Support all three output methods. Factor out perf_stat__print_shadow_stats_metricgroup() to print out each metrics. On SPR: Before: ./perf_old stat sleep 1 Performance counter stats for 'sleep 1': 0.54 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 125.445 K/sec 540,970 cycles:u # 0.998 GHz 556,325 instructions:u # 1.03 insn per cycle 123,602 branches:u # 228.018 M/sec 6,889 branch-misses:u # 5.57% of all branches 3,245,820 TOPDOWN.SLOTS:u # 18.4 % tma_backend_bound # 17.2 % tma_retiring # 23.1 % tma_bad_speculation # 41.4 % tma_frontend_bound 564,859 topdown-retiring:u 1,370,999 topdown-fe-bound:u 603,271 topdown-be-bound:u 744,874 topdown-bad-spec:u 12,661 INT_MISC.UOP_DROPPING:u # 23.357 M/sec 1.001798215 seconds time elapsed 0.000193000 seconds user 0.001700000 seconds sys After: $ ./perf stat sleep 1 Performance counter stats for 'sleep 1': 0.51 msec task-clock:u # 0.001 CPUs utilized 0 context-switches:u # 0.000 /sec 0 cpu-migrations:u # 0.000 /sec 68 page-faults:u # 132.683 K/sec 545,228 cycles:u # 1.064 GHz 555,509 instructions:u # 1.02 insn per cycle 123,574 branches:u # 241.120 M/sec 6,957 branch-misses:u # 5.63% of all branches TopdownL1 # 17.5 % tma_backend_bound # 22.6 % tma_bad_speculation # 42.7 % tma_frontend_bound # 17.1 % tma_retiring TopdownL2 # 21.8 % tma_branch_mispredicts # 11.5 % tma_core_bound # 13.4 % tma_fetch_bandwidth # 29.3 % tma_fetch_latency # 2.7 % tma_heavy_operations # 14.5 % tma_light_operations # 0.8 % tma_machine_clears # 6.1 % tma_memory_bound 1.001712086 seconds time elapsed 0.000151000 seconds user 0.001618000 seconds sys Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ahmad Yasin <ahmad.yasin@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: https://lore.kernel.org/r/20230616031420.3751973-3-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-06-15 20:14:17 -07:00
if (perf_stat__skip_metric_event(counter, &config->metric_events, ena, run))
return;
perf stat: Hide invalid uncore event output for aggr mode The current display code for perf stat iterates given cpus and build the aggr map to collect the event data for the aggregation mode. But uncore events have their own cpu maps and it won't guarantee that it'd match to the aggr map. For example, per-package uncore events would generate a single value for each socket. When user asks per-core aggregation mode, the output would contain 0 values for other cores. Thus it needs to check the uncore PMU's cpumask and if it matches to the current aggregation id. Before: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 3.73 Joules power/energy-pkg/ S0-D0-C1 0 <not counted> Joules power/energy-pkg/ S0-D0-C2 0 <not counted> Joules power/energy-pkg/ S0-D0-C3 0 <not counted> Joules power/energy-pkg/ 1.001404046 seconds time elapsed Some events weren't counted. Try disabling the NMI watchdog: echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ... echo 1 > /proc/sys/kernel/nmi_watchdog The core 1, 2 and 3 should not be printed because the event is handled in a cpu in the core 0 only. With this change, the output becomes like below. After: $ sudo ./perf stat -a --per-core -e power/energy-pkg/ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2.09 Joules power/energy-pkg/ Fixes: b897613510890d6e ("perf stat: Update event skip condition for system-wide per-thread mode and merged uncore and hybrid events") Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Ian Rogers <irogers@google.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lore.kernel.org/r/20230125192431.2929677-1-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-01-25 12:24:31 -07:00
if (val == 0 && should_skip_zero_counter(config, counter, &id))
return;
if (!metric_only) {
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
if (config->json_output)
fputc('{', output);
if (os->prefix)
fprintf(output, "%s", os->prefix);
else if (config->summary && config->csv_output &&
!config->no_csv_summary && !config->interval)
perf stat: Do not align time prefix in CSV output We don't care about the alignment in the CSV output as it's intended for machine processing. Let's get rid of it to make the output more compact. Before: # perf stat -a --summary -I 1 -x, true 0.001149309,219.20,msec,cpu-clock,219322251,100.00,219.200,CPUs utilized 0.001149309,144,,context-switches,219241902,100.00,656.935,/sec 0.001149309,38,,cpu-migrations,219173705,100.00,173.358,/sec 0.001149309,61,,page-faults,219093635,100.00,278.285,/sec 0.001149309,10679310,,cycles,218746228,100.00,0.049,GHz 0.001149309,6288296,,instructions,218589869,100.00,0.59,insn per cycle 0.001149309,1386904,,branches,218428851,100.00,6.327,M/sec 0.001149309,56863,,branch-misses,218219951,100.00,4.10,of all branches summary,219.20,msec,cpu-clock,219322251,100.00,20.025,CPUs utilized summary,144,,context-switches,219241902,100.00,656.935,/sec summary,38,,cpu-migrations,219173705,100.00,173.358,/sec summary,61,,page-faults,219093635,100.00,278.285,/sec summary,10679310,,cycles,218746228,100.00,0.049,GHz summary,6288296,,instructions,218589869,100.00,0.59,insn per cycle summary,1386904,,branches,218428851,100.00,6.327,M/sec summary,56863,,branch-misses,218219951,100.00,4.10,of all branches After: 0.001148449,224.75,msec,cpu-clock,224870589,100.00,224.747,CPUs utilized 0.001148449,176,,context-switches,224775564,100.00,783.103,/sec 0.001148449,38,,cpu-migrations,224707428,100.00,169.079,/sec 0.001148449,61,,page-faults,224629326,100.00,271.416,/sec 0.001148449,12172071,,cycles,224266368,100.00,0.054,GHz 0.001148449,6901907,,instructions,224108764,100.00,0.57,insn per cycle 0.001148449,1515655,,branches,223946693,100.00,6.744,M/sec 0.001148449,70027,,branch-misses,223735385,100.00,4.62,of all branches summary,224.75,msec,cpu-clock,224870589,100.00,21.066,CPUs utilized summary,176,,context-switches,224775564,100.00,783.103,/sec summary,38,,cpu-migrations,224707428,100.00,169.079,/sec summary,61,,page-faults,224629326,100.00,271.416,/sec summary,12172071,,cycles,224266368,100.00,0.054,GHz summary,6901907,,instructions,224108764,100.00,0.57,insn per cycle summary,1515655,,branches,223946693,100.00,6.744,M/sec summary,70027,,branch-misses,223735385,100.00,4.62,of all branches Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:01:56 -07:00
fprintf(output, "%s%s", "summary", config->csv_sep);
}
uval = val * counter->scale;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
printout(config, os, uval, run, ena, avg, aggr_idx);
if (!metric_only)
fputc('\n', output);
}
static void print_metric_begin(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os, int aggr_idx)
{
struct perf_stat_aggr *aggr;
struct aggr_cpu_id id;
struct evsel *evsel;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
os->first = true;
if (!config->metric_only)
return;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
if (config->json_output)
fputc('{', config->output);
if (os->prefix)
fprintf(config->output, "%s", os->prefix);
evsel = evlist__first(evlist);
id = config->aggr_map->map[aggr_idx];
aggr = &evsel->stats->aggr[aggr_idx];
aggr_printout(config, evsel, id, aggr->nr);
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
print_cgroup(config, os->cgrp ? : evsel->cgrp);
}
static void print_metric_end(struct perf_stat_config *config, struct outstate *os)
{
FILE *output = config->output;
if (!config->metric_only)
return;
if (config->json_output) {
if (os->first)
fputs("\"metric-value\" : \"none\"", output);
fputc('}', output);
}
fputc('\n', output);
}
static void print_aggr(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os)
{
struct evsel *counter;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
int aggr_idx;
if (!config->aggr_map || !config->aggr_get_id)
return;
/*
* With metric_only everything is on a single line.
* Without each counter has its own line.
*/
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
print_metric_begin(config, evlist, os, aggr_idx);
evlist__for_each_entry(evlist, counter) {
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_counter_aggrdata(config, counter, aggr_idx, os);
}
print_metric_end(config, os);
}
}
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
static void print_aggr_cgroup(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os)
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
{
struct evsel *counter, *evsel;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
int aggr_idx;
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
if (!config->aggr_map || !config->aggr_get_id)
return;
evlist__for_each_entry(evlist, evsel) {
if (os->cgrp == evsel->cgrp)
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
continue;
os->cgrp = evsel->cgrp;
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
print_metric_begin(config, evlist, os, aggr_idx);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
evlist__for_each_entry(evlist, counter) {
if (counter->cgrp != os->cgrp)
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
continue;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_counter_aggrdata(config, counter, aggr_idx, os);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
}
print_metric_end(config, os);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
}
}
}
static void print_counter(struct perf_stat_config *config,
struct evsel *counter, struct outstate *os)
{
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
int aggr_idx;
/* AGGR_THREAD doesn't have config->aggr_get_id */
if (!config->aggr_map)
return;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
print_counter_aggrdata(config, counter, aggr_idx, os);
}
}
static void print_no_aggr_metric(struct perf_stat_config *config,
struct evlist *evlist,
struct outstate *os)
{
perf cpumap: Give CPUs their own type A common problem is confusing CPU map indices with the CPU, by wrapping the CPU with a struct then this is avoided. This approach is similar to atomic_t. Committer notes: To make it build with BUILD_BPF_SKEL=1 these files needed the conversions to 'struct perf_cpu' usage: tools/perf/util/bpf_counter.c tools/perf/util/bpf_counter_cgroup.c tools/perf/util/bpf_ftrace.c Also perf_env__get_cpu() was removed back in "perf cpumap: Switch cpu_map__build_map to cpu function". Additionally these needed to be fixed for the ARM builds to complete: tools/perf/arch/arm/util/cs-etm.c tools/perf/arch/arm64/util/pmu.c Suggested-by: John Garry <john.garry@huawei.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Clarke <pc@us.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Vineet Singh <vineet.singh@intel.com> Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: zhengjun.xing@intel.com Link: https://lore.kernel.org/r/20220105061351.120843-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-01-04 23:13:51 -07:00
int all_idx;
struct perf_cpu cpu;
perf evlist: Rename cpus to user_requested_cpus evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps of all evsels. For non-task targets, cpus is set to be cpus requested from the command line, defaulting to all online cpus if no cpus are specified. For an uncore event, all_cpus may be just CPU 0 or every online CPU. This causes all_cpus to have fewer values than the cpus variable which is confusing given the 'all' in the name. To try to make the behavior clearer, rename cpus to user_requested_cpus and add comments on the two struct variables. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20220328232648.2127340-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-03-28 16:26:44 -07:00
perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.user_requested_cpus) {
struct evsel *counter;
bool first = true;
evlist__for_each_entry(evlist, counter) {
u64 ena, run, val;
double uval;
struct perf_stat_evsel *ps = counter->stats;
int aggr_idx = 0;
if (!perf_cpu_map__has(evsel__cpus(counter), cpu))
continue;
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
if (config->aggr_map->map[aggr_idx].cpu.cpu == cpu.cpu)
break;
}
os->evsel = counter;
os->id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
if (first) {
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_metric_begin(config, evlist, os, aggr_idx);
first = false;
}
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
val = ps->aggr[aggr_idx].counts.val;
ena = ps->aggr[aggr_idx].counts.ena;
run = ps->aggr[aggr_idx].counts.run;
uval = val * counter->scale;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
printout(config, os, uval, run, ena, 1.0, aggr_idx);
}
perf stat: Avoid printing cpus with no counters perf_evlist's user_requested_cpus can contain CPUs not present in any evsel's cpus, for example uncore counters. Avoid printing the prefix and trailing \n until the first valid counter is encountered. Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Ian Rogers <irogers@google.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yonghong Song <yhs@fb.com> Link: http://lore.kernel.org/lkml/20220503041757.2365696-4-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-05-02 21:17:54 -07:00
if (!first)
print_metric_end(config, os);
}
}
static void print_metric_headers_std(struct perf_stat_config *config,
bool no_indent)
{
fputc(' ', config->output);
if (!no_indent) {
int len = aggr_header_lens[config->aggr_mode];
if (nr_cgroups || config->cgroup_list)
len += CGROUP_LEN + 1;
fprintf(config->output, "%*s", len, "");
}
}
static void print_metric_headers_csv(struct perf_stat_config *config,
bool no_indent __maybe_unused)
{
const char *p;
if (config->interval)
fprintf(config->output, "time%s", config->csv_sep);
if (config->iostat_run)
return;
p = aggr_header_csv[config->aggr_mode];
while (*p) {
if (*p == ',')
fputs(config->csv_sep, config->output);
else
fputc(*p, config->output);
p++;
}
}
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
static void print_metric_headers_json(struct perf_stat_config *config __maybe_unused,
bool no_indent __maybe_unused)
{
}
static void print_metric_headers(struct perf_stat_config *config,
struct evlist *evlist, bool no_indent)
{
struct evsel *counter;
struct outstate os = {
.fh = config->output
};
struct perf_stat_output_ctx out = {
.ctx = &os,
.print_metric = print_metric_header,
.new_line = new_line_metric,
.force_header = true,
};
if (config->json_output)
print_metric_headers_json(config, no_indent);
else if (config->csv_output)
print_metric_headers_csv(config, no_indent);
else
print_metric_headers_std(config, no_indent);
if (config->iostat_run)
iostat_print_header_prefix(config);
if (config->cgroup_list)
os.cgrp = evlist__first(evlist)->cgrp;
/* Print metrics headers only */
evlist__for_each_entry(evlist, counter) {
if (!config->iostat_run &&
config->aggr_mode != AGGR_NONE && counter->metric_leader != counter)
perf stat: Don't display metric header for non-leader uncore events On an Intel tigerlake laptop a metric like: { "BriefDescription": "Test", "MetricExpr": "imc_free_running@data_read@ + imc_free_running@data_write@", "MetricGroup": "Test", "MetricName": "Test", "ScaleUnit": "6.103515625e-5MiB" }, Will have 4 events: uncore_imc_free_running_0/data_read/ uncore_imc_free_running_0/data_write/ uncore_imc_free_running_1/data_read/ uncore_imc_free_running_1/data_write/ If aggregration is disabled with metric-only 2 column headers are needed: $ perf stat -M test --metric-only -A -a sleep 1 Performance counter stats for 'system wide': MiB Test MiB Test CPU0 1821.0 1820.5 But when not, the counts aggregated in the metric leader and only 1 column should be shown: $ perf stat -M test --metric-only -a sleep 1 Performance counter stats for 'system wide': MiB Test 5909.4 1.001258915 seconds time elapsed Achieve this by skipping events that aren't metric leaders when printing column headers and aggregation isn't disabled. The bug is long standing, the fixes tag is set to a refactor as that is as far back as is reasonable to backport. Fixes: 088519f318be3a41 ("perf stat: Move the display functions to stat-display.c") Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kaige Ye <ye@kaige.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: K Prateek Nayak <kprateek.nayak@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Yicong Yang <yangyicong@hisilicon.com> Link: https://lore.kernel.org/r/20240510051309.2452468-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2024-05-09 22:13:09 -07:00
continue;
os.evsel = counter;
perf_stat__print_shadow_stats(config, counter, 0,
0,
&out,
perf stat: Hide runtime_stat runtime_stat is only shared for the sake of tests that don't care about its value. Move the definition into stat-shadow.c and have the tests also use the global version. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-48-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:44 -07:00
&config->metric_events);
}
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
if (!config->json_output)
fputc('\n', config->output);
}
static void prepare_interval(struct perf_stat_config *config,
char *prefix, size_t len, struct timespec *ts)
{
if (config->iostat_run)
return;
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
if (config->json_output)
scnprintf(prefix, len, "\"interval\" : %lu.%09lu, ",
(unsigned long) ts->tv_sec, ts->tv_nsec);
else if (config->csv_output)
scnprintf(prefix, len, "%lu.%09lu%s",
(unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep);
else
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
scnprintf(prefix, len, "%6lu.%09lu ",
(unsigned long) ts->tv_sec, ts->tv_nsec);
}
static void print_header_interval_std(struct perf_stat_config *config,
struct target *_target __maybe_unused,
struct evlist *evlist,
int argc __maybe_unused,
const char **argv __maybe_unused)
{
FILE *output = config->output;
switch (config->aggr_mode) {
case AGGR_NODE:
case AGGR_SOCKET:
case AGGR_DIE:
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-07 19:40:26 -07:00
case AGGR_CLUSTER:
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
case AGGR_CACHE:
case AGGR_CORE:
fprintf(output, "#%*s %-*s cpus",
INTERVAL_LEN - 1, "time",
aggr_header_lens[config->aggr_mode],
aggr_header_std[config->aggr_mode]);
break;
case AGGR_NONE:
fprintf(output, "#%*s %-*s",
INTERVAL_LEN - 1, "time",
aggr_header_lens[config->aggr_mode],
aggr_header_std[config->aggr_mode]);
break;
case AGGR_THREAD:
fprintf(output, "#%*s %*s-%-*s",
INTERVAL_LEN - 1, "time",
COMM_LEN, "comm", PID_LEN, "pid");
break;
case AGGR_GLOBAL:
default:
if (!config->iostat_run)
fprintf(output, "#%*s",
INTERVAL_LEN - 1, "time");
case AGGR_UNSET:
case AGGR_MAX:
break;
}
if (config->metric_only)
print_metric_headers(config, evlist, true);
else
fprintf(output, " %*s %*s events\n",
COUNTS_LEN, "counts", config->unit_width, "unit");
}
static void print_header_std(struct perf_stat_config *config,
struct target *_target, struct evlist *evlist,
int argc, const char **argv)
{
FILE *output = config->output;
int i;
fprintf(output, "\n");
fprintf(output, " Performance counter stats for ");
if (_target->bpf_str)
fprintf(output, "\'BPF program(s) %s", _target->bpf_str);
else if (_target->system_wide)
fprintf(output, "\'system wide");
else if (_target->cpu_list)
fprintf(output, "\'CPU(s) %s", _target->cpu_list);
else if (!target__has_task(_target)) {
fprintf(output, "\'%s", argv ? argv[0] : "pipe");
for (i = 1; argv && (i < argc); i++)
fprintf(output, " %s", argv[i]);
} else if (_target->pid)
fprintf(output, "process id \'%s", _target->pid);
else
fprintf(output, "thread id \'%s", _target->tid);
fprintf(output, "\'");
if (config->run_count > 1)
fprintf(output, " (%d runs)", config->run_count);
fprintf(output, ":\n\n");
if (config->metric_only)
print_metric_headers(config, evlist, false);
}
static void print_header_csv(struct perf_stat_config *config,
struct target *_target __maybe_unused,
struct evlist *evlist,
int argc __maybe_unused,
const char **argv __maybe_unused)
{
if (config->metric_only)
print_metric_headers(config, evlist, true);
}
static void print_header_json(struct perf_stat_config *config,
struct target *_target __maybe_unused,
struct evlist *evlist,
int argc __maybe_unused,
const char **argv __maybe_unused)
{
if (config->metric_only)
print_metric_headers(config, evlist, true);
}
static void print_header(struct perf_stat_config *config,
struct target *_target,
struct evlist *evlist,
int argc, const char **argv)
{
static int num_print_iv;
fflush(stdout);
if (config->interval_clear)
puts(CONSOLE_CLEAR);
if (num_print_iv == 0 || config->interval_clear) {
if (config->json_output)
print_header_json(config, _target, evlist, argc, argv);
else if (config->csv_output)
print_header_csv(config, _target, evlist, argc, argv);
else if (config->interval)
print_header_interval_std(config, _target, evlist, argc, argv);
else
print_header_std(config, _target, evlist, argc, argv);
}
if (num_print_iv++ == 25)
num_print_iv = 0;
}
static int get_precision(double num)
{
if (num > 1)
return 0;
return lround(ceil(-log10(num)));
}
static void print_table(struct perf_stat_config *config,
FILE *output, int precision, double avg)
{
char tmp[64];
int idx, indent = 0;
scnprintf(tmp, 64, " %17.*f", precision, avg);
while (tmp[indent] == ' ')
indent++;
fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
for (idx = 0; idx < config->run_count; idx++) {
double run = (double) config->walltime_run[idx] / NSEC_PER_SEC;
int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
fprintf(output, " %17.*f (%+.*f) ",
precision, run, precision, run - avg);
for (h = 0; h < n; h++)
fprintf(output, "#");
fprintf(output, "\n");
}
fprintf(output, "\n%*s# Final result:\n", indent, "");
}
static double timeval2double(struct timeval *t)
{
return t->tv_sec + (double) t->tv_usec/USEC_PER_SEC;
}
static void print_footer(struct perf_stat_config *config)
{
double avg = avg_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
FILE *output = config->output;
if (config->interval || config->csv_output || config->json_output)
return;
if (!config->null_run)
fprintf(output, "\n");
if (config->run_count == 1) {
fprintf(output, " %17.9f seconds time elapsed", avg);
if (config->ru_display) {
double ru_utime = timeval2double(&config->ru_data.ru_utime);
double ru_stime = timeval2double(&config->ru_data.ru_stime);
fprintf(output, "\n\n");
fprintf(output, " %17.9f seconds user\n", ru_utime);
fprintf(output, " %17.9f seconds sys\n", ru_stime);
}
} else {
double sd = stddev_stats(config->walltime_nsecs_stats) / NSEC_PER_SEC;
/*
* Display at most 2 more significant
* digits than the stddev inaccuracy.
*/
int precision = get_precision(sd) + 2;
if (config->walltime_run_table)
print_table(config, output, precision, avg);
fprintf(output, " %17.*f +- %.*f seconds time elapsed",
precision, avg, precision, sd);
print_noise_pct(config, sd, avg, /*before_metric=*/false);
}
fprintf(output, "\n\n");
if (config->print_free_counters_hint && sysctl__nmi_watchdog_enabled())
fprintf(output,
"Some events weren't counted. Try disabling the NMI watchdog:\n"
" echo 0 > /proc/sys/kernel/nmi_watchdog\n"
" perf stat ...\n"
" echo 1 > /proc/sys/kernel/nmi_watchdog\n");
if (config->print_mixed_hw_group_error)
fprintf(output,
"The events in group usually have to be from "
"the same PMU. Try reorganizing the group.\n");
}
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
static void print_percore(struct perf_stat_config *config,
struct evsel *counter, struct outstate *os)
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
{
bool metric_only = config->metric_only;
FILE *output = config->output;
struct cpu_aggr_map *core_map;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
int aggr_idx, core_map_len = 0;
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
if (!config->aggr_map || !config->aggr_get_id)
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
return;
perf stat: Show percore counts in per CPU output We have supported the event modifier "percore" which sums up the event counts for all hardware threads in a core and show the counts per core. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 395,072 cpu/event=cpu-cycles,percore/ S0-D0-C1 851,248 cpu/event=cpu-cycles,percore/ S0-D0-C2 954,226 cpu/event=cpu-cycles,percore/ S0-D0-C3 1,233,659 cpu/event=cpu-cycles,percore/ This patch provides a new option "--percore-show-thread". It is used with event modifier "percore" together to sum up the event counts for all hardware threads in a core but show the counts per hardware thread. This is essentially a replacement for the any bit (which is gone in Icelake). Per core counts are useful for some formulas, e.g. CoreIPC. The original percore version was inconvenient to post process. This variant matches the output of the any bit. With this patch, for example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,453,061 cpu/event=cpu-cycles,percore/ CPU1 1,823,921 cpu/event=cpu-cycles,percore/ CPU2 1,383,166 cpu/event=cpu-cycles,percore/ CPU3 1,102,652 cpu/event=cpu-cycles,percore/ CPU4 2,453,061 cpu/event=cpu-cycles,percore/ CPU5 1,823,921 cpu/event=cpu-cycles,percore/ CPU6 1,383,166 cpu/event=cpu-cycles,percore/ CPU7 1,102,652 cpu/event=cpu-cycles,percore/ We can see counts are duplicated in CPU pairs (CPU0/CPU4, CPU1/CPU5, CPU2/CPU6, CPU3/CPU7). The interval mode also works. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -I 1000 # time CPU counts unit events 1.000425421 CPU0 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU1 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU2 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU3 1,192,504 cpu/event=cpu-cycles,percore/ 1.000425421 CPU4 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU5 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU6 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU7 1,192,504 cpu/event=cpu-cycles,percore/ If we offline CPU5, the result is: # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,752,148 cpu/event=cpu-cycles,percore/ CPU1 1,009,312 cpu/event=cpu-cycles,percore/ CPU2 2,784,072 cpu/event=cpu-cycles,percore/ CPU3 2,427,922 cpu/event=cpu-cycles,percore/ CPU4 2,752,148 cpu/event=cpu-cycles,percore/ CPU6 2,784,072 cpu/event=cpu-cycles,percore/ CPU7 2,427,922 cpu/event=cpu-cycles,percore/ 1.001416041 seconds time elapsed v4: --- Ravi Bangoria reports an issue in v3. Once we offline a CPU, the output is not correct. The issue is we should use the cpu idx in print_percore_thread rather than using the cpu value. v3: --- 1. Fix the interval mode output error 2. Use cpu value (not cpu index) in config->aggr_get_id(). 3. Refine the code according to Jiri's comments. v2: --- Add the explanation in change log. This is essentially a replacement for the any bit. No code change. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200214080452.26402-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-14 01:04:52 -07:00
if (config->percore_show_thread)
return print_counter(config, counter, os);
perf stat: Show percore counts in per CPU output We have supported the event modifier "percore" which sums up the event counts for all hardware threads in a core and show the counts per core. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A -- sleep 1 Performance counter stats for 'system wide': S0-D0-C0 395,072 cpu/event=cpu-cycles,percore/ S0-D0-C1 851,248 cpu/event=cpu-cycles,percore/ S0-D0-C2 954,226 cpu/event=cpu-cycles,percore/ S0-D0-C3 1,233,659 cpu/event=cpu-cycles,percore/ This patch provides a new option "--percore-show-thread". It is used with event modifier "percore" together to sum up the event counts for all hardware threads in a core but show the counts per hardware thread. This is essentially a replacement for the any bit (which is gone in Icelake). Per core counts are useful for some formulas, e.g. CoreIPC. The original percore version was inconvenient to post process. This variant matches the output of the any bit. With this patch, for example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,453,061 cpu/event=cpu-cycles,percore/ CPU1 1,823,921 cpu/event=cpu-cycles,percore/ CPU2 1,383,166 cpu/event=cpu-cycles,percore/ CPU3 1,102,652 cpu/event=cpu-cycles,percore/ CPU4 2,453,061 cpu/event=cpu-cycles,percore/ CPU5 1,823,921 cpu/event=cpu-cycles,percore/ CPU6 1,383,166 cpu/event=cpu-cycles,percore/ CPU7 1,102,652 cpu/event=cpu-cycles,percore/ We can see counts are duplicated in CPU pairs (CPU0/CPU4, CPU1/CPU5, CPU2/CPU6, CPU3/CPU7). The interval mode also works. For example, # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -I 1000 # time CPU counts unit events 1.000425421 CPU0 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU1 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU2 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU3 1,192,504 cpu/event=cpu-cycles,percore/ 1.000425421 CPU4 925,032 cpu/event=cpu-cycles,percore/ 1.000425421 CPU5 430,202 cpu/event=cpu-cycles,percore/ 1.000425421 CPU6 436,843 cpu/event=cpu-cycles,percore/ 1.000425421 CPU7 1,192,504 cpu/event=cpu-cycles,percore/ If we offline CPU5, the result is: # perf stat -e cpu/event=cpu-cycles,percore/ -a -A --percore-show-thread -- sleep 1 Performance counter stats for 'system wide': CPU0 2,752,148 cpu/event=cpu-cycles,percore/ CPU1 1,009,312 cpu/event=cpu-cycles,percore/ CPU2 2,784,072 cpu/event=cpu-cycles,percore/ CPU3 2,427,922 cpu/event=cpu-cycles,percore/ CPU4 2,752,148 cpu/event=cpu-cycles,percore/ CPU6 2,784,072 cpu/event=cpu-cycles,percore/ CPU7 2,427,922 cpu/event=cpu-cycles,percore/ 1.001416041 seconds time elapsed v4: --- Ravi Bangoria reports an issue in v3. Once we offline a CPU, the output is not correct. The issue is we should use the cpu idx in print_percore_thread rather than using the cpu value. v3: --- 1. Fix the interval mode output error 2. Use cpu value (not cpu index) in config->aggr_get_id(). 3. Refine the code according to Jiri's comments. v2: --- Add the explanation in change log. This is essentially a replacement for the any bit. No code change. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200214080452.26402-1-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-14 01:04:52 -07:00
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
/*
* core_map will hold the aggr_cpu_id for the cores that have been
* printed so that each core is printed just once.
*/
core_map = cpu_aggr_map__empty_new(config->aggr_map->nr);
if (core_map == NULL) {
fprintf(output, "Cannot allocate per-core aggr map for display\n");
return;
}
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
struct perf_cpu curr_cpu = config->aggr_map->map[aggr_idx].cpu;
struct aggr_cpu_id core_id = aggr_cpu_id__core(curr_cpu, NULL);
bool found = false;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
for (int i = 0; i < core_map_len; i++) {
if (aggr_cpu_id__equal(&core_map->map[i], &core_id)) {
found = true;
break;
}
}
if (found)
continue;
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
print_counter_aggrdata(config, counter, aggr_idx, os);
perf stat: Add cpu_aggr_map for loop Rename variables, add a comment and add a cpu_aggr_map__for_each_idx to aid the readability of the stat-display code. In particular, try to make sure aggr_idx is used consistently to differentiate from other kinds of index. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexandre Torgue <alexandre.torgue@foss.st.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com> Cc: Caleb Biggers <caleb.biggers@intel.com> Cc: Eduard Zingerman <eddyz87@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jing Zhang <renyu.zj@linux.alibaba.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Garry <john.g.garry@oracle.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Perry Taylor <perry.taylor@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Sean Christopherson <seanjc@google.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Cc: linux-arm-kernel@lists.infradead.org Cc: linux-stm32@st-md-mailman.stormreply.com Link: https://lore.kernel.org/r/20230219092848.639226-49-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-02-19 02:28:45 -07:00
core_map->map[core_map_len++] = core_id;
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
}
free(core_map);
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
if (metric_only)
fputc('\n', output);
}
static void print_cgroup_counter(struct perf_stat_config *config, struct evlist *evlist,
struct outstate *os)
{
struct evsel *counter;
evlist__for_each_entry(evlist, counter) {
if (os->cgrp != counter->cgrp) {
if (os->cgrp != NULL)
print_metric_end(config, os);
os->cgrp = counter->cgrp;
print_metric_begin(config, evlist, os, /*aggr_idx=*/0);
}
print_counter(config, counter, os);
}
if (os->cgrp)
print_metric_end(config, os);
}
void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
struct target *_target, struct timespec *ts,
int argc, const char **argv)
{
bool metric_only = config->metric_only;
int interval = config->interval;
struct evsel *counter;
char buf[64];
struct outstate os = {
.fh = config->output,
perf stat: Fix JSON output in metric-only mode It generated a broken JSON output when aggregation mode or cgroup is used with --metric-only option. Also get rid of the header line and make the output single line for each entry. It needs to know whether the current metric is the first one or not. So add 'first' field in the outstate and mark it false after printing. Before: # perf stat -a -j --metric-only true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {{"metric-value" : "0.797"}{"metric-value" : "1.65"}{"metric-value" : "0.89"} ^ # perf stat -a -j --metric-only --per-socket true {"unit" : "GHz"}{"unit" : "insn per cycle"}{"unit" : "branch-misses of all branches"} {"socket" : "S0", "aggregate-number" : 8, {"metric-value" : "0.295"}{"metric-value" : "1.88"}{"metric-value" : "0.64"} ^ After: # perf stat -a -j --metric-only true {"GHz" : "0.990", "insn per cycle" : "2.06", "branch-misses of all branches" : "0.59"} # perf stat -a -j --metric-only --per-socket true {"socket" : "S0", "aggregate-number" : 8, "GHz" : "0.439", "insn per cycle" : "2.14", "branch-misses of all branches" : "0.51"} Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221123180208.2068936-14-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-23 11:02:06 -07:00
.first = true,
};
if (config->iostat_run)
evlist->selected = evlist__first(evlist);
if (interval) {
os.prefix = buf;
prepare_interval(config, buf, sizeof(buf), ts);
}
print_header(config, _target, evlist, argc, argv);
switch (config->aggr_mode) {
case AGGR_CORE:
perf stat: Setup the foundation to allow aggregation based on cache topology Processors based on chiplet architecture, such as AMD EPYC and Hygon do not expose the chiplet details in the sysfs CPU topology information. However, this information can be derived from the per CPU cache level information from the sysfs. 'perf stat' has already supported aggregation based on topology information using core ID, socket ID, etc. It'll be useful to aggregate based on the cache topology to detect problems like imbalance and cache-to-cache sharing at various cache levels. This patch lays the foundation for aggregating data in 'perf stat' based on the processor's cache topology. The cmdline option to aggregate data based on the cache topology is added in Patch 4 of the series while this patch sets up all the necessary functions and variables required to support the new aggregation option. The patch also adds support to display per-cache aggregation, or save it as a JSON or CSV, as splitting it into a separate patch would break builds when compiling with "-Werror=switch-enum" where the compiler will complain about the lack of handling for the AGGR_CACHE case in the output functions. Committer notes: Don't use perf_stat_config in tools/perf/util/cpumap.c, this would make code that is in util/, thus not really specific to a single builtin, use a specific builtin config structure. Move the functions introduced in this patch from tools/perf/util/cpumap.c since it needs access to builtin specific and is not strictly needed to live in the util/ directory. With this 'perf test python' is back building. Suggested-by: Gautham Shenoy <gautham.shenoy@amd.com> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com> Acked-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Ananth Narayan <ananth.narayan@amd.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@amd.com> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Wen Pu <puwen@hygon.cn> Link: https://lore.kernel.org/r/20230517172745.5833-3-kprateek.nayak@amd.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-17 10:27:42 -07:00
case AGGR_CACHE:
perf stat: Support per-cluster aggregation Some platforms have 'cluster' topology and CPUs in the cluster will share resources like L3 Cache Tag (for HiSilicon Kunpeng SoC) or L2 cache (for Intel Jacobsville). Currently parsing and building cluster topology have been supported since [1]. perf stat has already supported aggregation for other topologies like die or socket, etc. It'll be useful to aggregate per-cluster to find problems like L3T bandwidth contention. This patch add support for "--per-cluster" option for per-cluster aggregation. Also update the docs and related test. The output will be like: [root@localhost tmp]# perf stat -a -e LLC-load --per-cluster -- sleep 5 Performance counter stats for 'system wide': S56-D0-CLS158 4 1,321,521,570 LLC-load S56-D0-CLS594 4 794,211,453 LLC-load S56-D0-CLS1030 4 41,623 LLC-load S56-D0-CLS1466 4 41,646 LLC-load S56-D0-CLS1902 4 16,863 LLC-load S56-D0-CLS2338 4 15,721 LLC-load S56-D0-CLS2774 4 22,671 LLC-load [...] On a legacy system without cluster or cluster support, the output will be look like: [root@localhost perf]# perf stat -a -e cycles --per-cluster -- sleep 1 Performance counter stats for 'system wide': S56-D0-CLS0 64 18,011,485 cycles S7182-D0-CLS0 64 16,548,835 cycles Note that this patch doesn't mix the cluster information in the outputs of --per-core to avoid breaking any tools/scripts using it. Note that perf recently supports "--per-cache" aggregation, but it's not the same with the cluster although cluster CPUs may share some cache resources. For example on my machine all clusters within a die share the same L3 cache: $ cat /sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_list 0-31 $ cat /sys/devices/system/cpu/cpu0/topology/cluster_cpus_list 0-3 [1] commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die") Tested-by: Jie Zhan <zhanjie9@hisilicon.com> Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com> Reviewed-by: Ian Rogers <irogers@google.com> Signed-off-by: Yicong Yang <yangyicong@hisilicon.com> Cc: james.clark@arm.com Cc: 21cnbao@gmail.com Cc: prime.zeng@hisilicon.com Cc: Jonathan.Cameron@huawei.com Cc: fanghao11@huawei.com Cc: linuxarm@huawei.com Cc: tim.c.chen@intel.com Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240208024026.2691-1-yangyicong@huawei.com
2024-02-07 19:40:26 -07:00
case AGGR_CLUSTER:
case AGGR_DIE:
case AGGR_SOCKET:
perf stat: Add --per-node agregation support Adding new --per-node option to aggregate counts per NUMA nodes for system-wide mode measurements. You can specify --per-node in live mode: # perf stat -a -I 1000 -e cycles --per-node # time node cpus counts unit events 1.000542550 N0 20 6,202,097 cycles 1.000542550 N1 20 639,559 cycles 2.002040063 N0 20 7,412,495 cycles 2.002040063 N1 20 2,185,577 cycles 3.003451699 N0 20 6,508,917 cycles 3.003451699 N1 20 765,607 cycles ... Or in the record/report stat session: # perf stat record -a -I 1000 -e cycles # time counts unit events 1.000536937 10,008,468 cycles 2.002090152 9,578,539 cycles 3.003625233 7,647,869 cycles 4.005135036 7,032,086 cycles ^C 4.340902364 3,923,893 cycles # perf stat report --per-node # time node cpus counts unit events 1.000536937 N0 20 9,355,086 cycles 1.000536937 N1 20 653,382 cycles 2.002090152 N0 20 7,712,838 cycles 2.002090152 N1 20 1,865,701 cycles 3.003625233 N0 20 6,604,441 cycles 3.003625233 N1 20 1,043,428 cycles 4.005135036 N0 20 6,350,522 cycles 4.005135036 N1 20 681,564 cycles 4.340902364 N0 20 3,403,188 cycles 4.340902364 N1 20 520,705 cycles Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Joe Mario <jmario@redhat.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20190904073415.723-4-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-08-28 01:17:43 -07:00
case AGGR_NODE:
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
if (config->cgroup_list)
print_aggr_cgroup(config, evlist, &os);
perf stat: Add print_aggr_cgroup() for --for-each-cgroup and --topdown Normally, --for-each-cgroup only works with AGGR_GLOBAL. However the --topdown on some cpu (e.g. Intel Skylake) converts it to the AGGR_CORE internally. To support those machines, add print_aggr_cgroup and handle the events like in print_cgroup_events(). $ perf stat -a --for-each-cgroup system.slice,user.slice --topdown sleep 1 nmi_watchdog enabled with topdown. May give wrong results. Disable with echo 0 > /proc/sys/kernel/nmi_watchdog Performance counter stats for 'system wide': retiring bad speculation frontend bound backend bound S0-D0-C0 2 system.slice 49.0% -46.6% 31.4% S0-D0-C1 2 system.slice 55.5% 8.0% 45.5% -9.0% S0-D0-C2 2 system.slice 87.8% 22.1% 30.3% -40.3% S0-D0-C3 2 system.slice 53.3% -11.9% 45.2% 13.4% S0-D0-C0 2 user.slice 123.5% 4.0% 48.5% -75.9% S0-D0-C1 2 user.slice 19.9% 6.5% 89.9% -16.3% S0-D0-C2 2 user.slice 29.9% 7.9% 71.3% -9.1 S0-D0-C3 2 user.slice 28.0% 7.2% 43.3% 21.5% 1.004136937 seconds time elapsed Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20221114230227.1255976-20-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-11-14 16:02:27 -07:00
else
print_aggr(config, evlist, &os);
break;
case AGGR_THREAD:
case AGGR_GLOBAL:
if (config->iostat_run) {
iostat_print_counters(evlist, config, ts, buf,
(iostat_print_counter_t)print_counter, &os);
} else if (config->cgroup_list) {
print_cgroup_counter(config, evlist, &os);
} else {
print_metric_begin(config, evlist, &os, /*aggr_idx=*/0);
evlist__for_each_entry(evlist, counter) {
print_counter(config, counter, &os);
}
print_metric_end(config, &os);
}
break;
case AGGR_NONE:
if (metric_only)
print_no_aggr_metric(config, evlist, &os);
else {
evlist__for_each_entry(evlist, counter) {
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
if (counter->percore)
print_percore(config, counter, &os);
perf stat: Support 'percore' event qualifier With this patch, we can use the 'percore' event qualifier in perf-stat. root@skl:/tmp# perf stat -e cpu/event=0,umask=0x3,percore=1/,cpu/event=0,umask=0x3/ -a -A -I1000 1.000773050 S0-C0 98,352,832 cpu/event=0,umask=0x3,percore=1/ (50.01%) 1.000773050 S0-C1 103,763,057 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C2 196,776,995 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 S0-C3 176,493,779 cpu/event=0,umask=0x3,percore=1/ (50.02%) 1.000773050 CPU0 47,699,641 cpu/event=0,umask=0x3/ (50.02%) 1.000773050 CPU1 49,052,451 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU2 102,771,422 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU3 100,784,662 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU4 43,171,342 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU5 54,152,158 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU6 93,618,410 cpu/event=0,umask=0x3/ (49.98%) 1.000773050 CPU7 74,477,589 cpu/event=0,umask=0x3/ (49.99%) In this example, we count the event 'ref-cycles' per-core and per-CPU in one perf stat command-line. From the output, we can see: S0-C0 = CPU0 + CPU4 S0-C1 = CPU1 + CPU5 S0-C2 = CPU2 + CPU6 S0-C3 = CPU3 + CPU7 So the result is expected (tiny difference is ignored). Note that, the 'percore' event qualifier needs to use with option '-A'. Signed-off-by: Jin Yao <yao.jin@linux.intel.com> Tested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jin Yao <yao.jin@intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1555077590-27664-4-git-send-email-yao.jin@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-04-12 06:59:49 -07:00
else
print_counter(config, counter, &os);
}
}
break;
perf stat: Add JSON output option CSV output is tricky to format and column layout changes are susceptible to breaking parsers. New JSON-formatted output has variable names to identify fields that are consistent and informative, making the output parseable. CSV output example: 1.20,msec,task-clock:u,1204272,100.00,0.697,CPUs utilized 0,,context-switches:u,1204272,100.00,0.000,/sec 0,,cpu-migrations:u,1204272,100.00,0.000,/sec 70,,page-faults:u,1204272,100.00,58.126,K/sec JSON output example: {"counter-value" : "3805.723968", "unit" : "msec", "event" : "cpu-clock", "event-runtime" : 3805731510100.00, "pcnt-running" : 100.00, "metric-value" : 4.007571, "metric-unit" : "CPUs utilized"} {"counter-value" : "6166.000000", "unit" : "", "event" : "context-switches", "event-runtime" : 3805723045100.00, "pcnt-running" : 100.00, "metric-value" : 1.620191, "metric-unit" : "K/sec"} {"counter-value" : "466.000000", "unit" : "", "event" : "cpu-migrations", "event-runtime" : 3805727613100.00, "pcnt-running" : 100.00, "metric-value" : 122.447136, "metric-unit" : "/sec"} {"counter-value" : "208.000000", "unit" : "", "event" : "page-faults", "event-runtime" : 3805726799100.00, "pcnt-running" : 100.00, "metric-value" : 54.654516, "metric-unit" : "/sec"} Also added documentation for JSON option. There is some tidy up of CSV code including a potential memory over run in the os.nfields set up. To facilitate this an AGGR_MAX value is added. Committer notes: Fixed up using PRIu64 to format u64 values, not %lu. Committer testing: ⬢[acme@toolbox perf]$ perf stat -j sleep 1 {"counter-value" : "0.731750", "unit" : "msec", "event" : "task-clock:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000731, "metric-unit" : "CPUs utilized"} {"counter-value" : "0.000000", "unit" : "", "event" : "context-switches:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "0.000000", "unit" : "", "event" : "cpu-migrations:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 0.000000, "metric-unit" : "/sec"} {"counter-value" : "75.000000", "unit" : "", "event" : "page-faults:u", "event-runtime" : 731750, "pcnt-running" : 100.00, "metric-value" : 102.494021, "metric-unit" : "K/sec"} {"counter-value" : "578765.000000", "unit" : "", "event" : "cycles:u", "event-runtime" : 379366, "pcnt-running" : 49.00, "metric-value" : 0.790933, "metric-unit" : "GHz"} {"counter-value" : "1298.000000", "unit" : "", "event" : "stalled-cycles-frontend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.224271, "metric-unit" : "frontend cycles idle"} {"counter-value" : "21984.000000", "unit" : "", "event" : "stalled-cycles-backend:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 3.798433, "metric-unit" : "backend cycles idle"} {"counter-value" : "468197.000000", "unit" : "", "event" : "instructions:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 0.808959, "metric-unit" : "insn per cycle"} {"metric-value" : 0.046955, "metric-unit" : "stalled cycles per insn"} {"counter-value" : "103335.000000", "unit" : "", "event" : "branches:u", "event-runtime" : 768020, "pcnt-running" : 100.00, "metric-value" : 141.216262, "metric-unit" : "M/sec"} {"counter-value" : "2381.000000", "unit" : "", "event" : "branch-misses:u", "event-runtime" : 388654, "pcnt-running" : 50.00, "metric-value" : 2.304156, "metric-unit" : "of all branches"} ⬢[acme@toolbox perf]$ Signed-off-by: Claire Jensen <cjense@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alyssa Ross <hi@alyssa.is> Cc: Claire Jensen <clairej735@gmail.com> Cc: Florian Fischer <florian.fischer@muhq.space> Cc: Ingo Molnar <mingo@redhat.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Like Xu <likexu@tencent.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sandipan Das <sandipan.das@amd.com> Cc: Stephane Eranian <eranian@google.com> Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com> Link: https://lore.kernel.org/r/20220805200105.2020995-2-irogers@google.com Signed-off-by: Ian Rogers <irogers@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-08-05 13:01:04 -07:00
case AGGR_MAX:
case AGGR_UNSET:
default:
break;
}
print_footer(config);
fflush(config->output);
}