Commit 2ce7135adc ("psi: cgroup support") adds documentation which refers
to CONFIG_CGROUP, but the correct name is CONFIG_CGROUPS.
Correct the reference to CONFIG_CGROUPS.
Co-developed-by: Sabina Trendota <sabinatrendota@gmail.com>
Signed-off-by: Sabina Trendota <sabinatrendota@gmail.com>
Signed-off-by: Ramazan Safiullin <ram.safiullin2001@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20230728115600.231068-1-ram.safiullin2001@gmail.com
- Allow unprivileged PSI poll()ing
- Fix performance regression introduced by mm_cid
- Improve livepatch stalls by adding livepatch task switching to cond_resched(),
this resolves livepatching busy-loop stalls with certain CPU-bound kthreads.
- Improve sched_move_task() performance on autogroup configs.
- On core-scheduling CPUs, avoid selecting throttled tasks to run
- Misc cleanups, fixes and improvements.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
-----BEGIN PGP SIGNATURE-----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=Hgci
-----END PGP SIGNATURE-----
Merge tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- Allow unprivileged PSI poll()ing
- Fix performance regression introduced by mm_cid
- Improve livepatch stalls by adding livepatch task switching to
cond_resched(). This resolves livepatching busy-loop stalls with
certain CPU-bound kthreads
- Improve sched_move_task() performance on autogroup configs
- On core-scheduling CPUs, avoid selecting throttled tasks to run
- Misc cleanups, fixes and improvements
* tag 'sched-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/clock: Fix local_clock() before sched_clock_init()
sched/rt: Fix bad task migration for rt tasks
sched: Fix performance regression introduced by mm_cid
sched/core: Make sched_dynamic_mutex static
sched/psi: Allow unprivileged polling of N*2s period
sched/psi: Extract update_triggers side effect
sched/psi: Rename existing poll members in preparation
sched/psi: Rearrange polling code in preparation
sched/fair: Fix inaccurate tally of ttwu_move_affine
vhost: Fix livepatch timeouts in vhost_worker()
livepatch,sched: Add livepatch task switching to cond_resched()
livepatch: Skip task_call_func() for current task
livepatch: Convert stack entries array to percpu
sched: Interleave cfs bandwidth timers for improved single thread performance at low utilization
sched/core: Reduce cost of sched_move_task when config autogroup
sched/core: Avoid selecting the task that is throttled to run when core-sched enable
sched/topology: Make sched_energy_mutex,update static
Delay accounting does not track the delay of IRQ/SOFTIRQ. While
IRQ/SOFTIRQ could have obvious impact on some workloads productivity, such
as when workloads are running on system which is busy handling network
IRQ/SOFTIRQ.
Get the delay of IRQ/SOFTIRQ could help users to reduce such delay. Such
as setting interrupt affinity or task affinity, using kernel thread for
NAPI etc. This is inspired by "sched/psi: Add PSI_IRQ to track
IRQ/SOFTIRQ pressure"[1]. Also fix some code indent problems of older
code.
And update tools/accounting/getdelays.c:
/ # ./getdelays -p 156 -di
print delayacct stats ON
printing IO accounting
PID 156
CPU count real total virtual total delay total delay average
15 15836008 16218149 275700790 18.380ms
IO count delay total delay average
0 0 0.000ms
SWAP count delay total delay average
0 0 0.000ms
RECLAIM count delay total delay average
0 0 0.000ms
THRASHING count delay total delay average
0 0 0.000ms
COMPACT count delay total delay average
0 0 0.000ms
WPCOPY count delay total delay average
36 7586118 0.211ms
IRQ count delay total delay average
42 929161 0.022ms
[1] commit 52b1364ba0b1("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure")
Link: https://lkml.kernel.org/r/202304081728353557233@zte.com.cn
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Cc: Jiang Xuexin <jiang.xuexin@zte.com.cn>
Cc: wangyong <wang.yong12@zte.com.cn>
Cc: junhua huang <huang.junhua@zte.com.cn>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Improve the average delay precision of getdelay tool to microsecond. When
using the getdelay tool, it is sometimes found that the average delay
except CPU is not 0, but display is 0, because the precison is too low.
For example, see delay average of SWAP below when using ZRAM.
print delayacct stats ON
PID 32915
CPU count real total virtual total delay total delay average
339202 2793871936 9233585504 7951112 0.000ms
IO count delay total delay average
41 419296904 10ms
SWAP count delay total delay average
242589 1045792384 0ms
This wrong display is misleading, so improve the millisecond precision of
the average delay to microsecond just like CPU. Then user would get more
accurate information of delay time.
Link: https://lkml.kernel.org/r/202302131408087983857@zte.com.cn
Signed-off-by: Wang Yong <wang.yong12@zte.com.cn>
Reviewed-by: Yang Yang <yang.yang29@zte.com.cn>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
PSI offers 2 mechanisms to get information about a specific resource
pressure. One is reading from /proc/pressure/<resource>, which gives
average pressures aggregated every 2s. The other is creating a pollable
fd for a specific resource and cgroup.
The trigger creation requires CAP_SYS_RESOURCE, and gives the
possibility to pick specific time window and threshold, spawing an RT
thread to aggregate the data.
Systemd would like to provide containers the option to monitor pressure
on their own cgroup and sub-cgroups. For example, if systemd launches a
container that itself then launches services, the container should have
the ability to poll() for pressure in individual services. But neither
the container nor the services are privileged.
This patch implements a mechanism to allow unprivileged users to create
pressure triggers. The difference with privileged triggers creation is
that unprivileged ones must have a time window that's a multiple of 2s.
This is so that we can avoid unrestricted spawning of rt threads, and
use instead the same aggregation mechanism done for the averages, which
runs independently of any triggers.
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20230330105418.77061-5-cerasuolodomenico@gmail.com
Once upon a time, we only support accounting thrashing of page cache.
Then Joonsoo introduced workingset detection for anonymous pages and we
gained the ability to account thrashing of them[1].
So let delayacct account both the thrashing of page cache and anonymous
pages, this could make the codes more consistent and simpler.
[1] commit aae466b005 ("mm/swap: implement workingset detection for anonymous LRU")
Link: https://lkml.kernel.org/r/20220805033838.1714674-1-yang.yang29@zte.com.cn
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Signed-off-by: CGEL ZTE <cgel.zte@gmail.com>
Acked-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Yang Yang <yang.yang29@zte.com.cn>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Delay accounting does not track the delay of write-protect copy. When
tasks trigger many write-protect copys(include COW and unsharing of
anonymous pages[1]), it may spend a amount of time waiting for them. To
get the delay of tasks in write-protect copy, could help users to evaluate
the impact of using KSM or fork() or GUP.
Also update tools/accounting/getdelays.c:
/ # ./getdelays -dl -p 231
print delayacct stats ON
listen forever
PID 231
CPU count real total virtual total delay total delay average
6247 1859000000 2154070021 1674255063 0.268ms
IO count delay total delay average
0 0 0ms
SWAP count delay total delay average
0 0 0ms
RECLAIM count delay total delay average
0 0 0ms
THRASHING count delay total delay average
0 0 0ms
COMPACT count delay total delay average
3 72758 0ms
WPCOPY count delay total delay average
3635 271567604 0ms
[1] commit 31cc5bc4af70("mm: support GUP-triggered unsharing of anonymous pages")
Link: https://lkml.kernel.org/r/20220409014342.2505532-1-yang.yang29@zte.com.cn
Signed-off-by: Yang Yang <yang.yang29@zte.com.cn>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jiang Xuexin <jiang.xuexin@zte.com.cn>
Reviewed-by: Ran Xiaokai <ran.xiaokai@zte.com.cn>
Reviewed-by: wangyong <wang.yong12@zte.com.cn>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Martin find it confusing when look at the /proc/pressure/cpu output,
and found no hint about that CPU "full" line in psi Documentation.
% cat /proc/pressure/cpu
some avg10=0.92 avg60=0.91 avg300=0.73 total=933490489
full avg10=0.22 avg60=0.23 avg300=0.16 total=358783277
The PSI_CPU_FULL state is introduced by commit e7fcd76228
("psi: Add PSI_CPU_FULL state"), which mainly for cgroup level,
but also counted at the system level as a side effect.
Naturally, the FULL state doesn't exist for the CPU resource at
the system level. These "full" numbers can come from CPU idle
schedule latency. For example, t1 is the time when task wakeup
on an idle CPU, t2 is the time when CPU pick and switch to it.
The delta of (t2 - t1) will be in CPU_FULL state.
Another case all processes can be stalled is when all cgroups
have been throttled at the same time, which unlikely to happen.
Anyway, CPU_FULL metric is meaningless and confusing at the
system level. So this patch will report zeroes for CPU full
at the system level, and update psi Documentation accordingly.
Fixes: e7fcd76228 ("psi: Add PSI_CPU_FULL state")
Reported-by: Martin Steigerwald <Martin.Steigerwald@proact.de>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20220408121914.82855-1-zhouchengming@bytedance.com
propagation in the sched hierarchies and other minor cleanups and
improvements
-----BEGIN PGP SIGNATURE-----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=4m7x
-----END PGP SIGNATURE-----
Merge tag 'sched_urgent_for_v5.17_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Borislav Petkov:
"A bunch of fixes: forced idle time accounting, utilization values
propagation in the sched hierarchies and other minor cleanups and
improvements"
* tag 'sched_urgent_for_v5.17_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
kernel/sched: Remove dl_boosted flag comment
sched: Avoid double preemption in __cond_resched_*lock*()
sched/fair: Fix all kernel-doc warnings
sched/core: Accounting forceidle time for all tasks except idle task
sched/pelt: Relax the sync of load_sum with load_avg
sched/pelt: Relax the sync of runnable_sum with runnable_avg
sched/pelt: Continue to relax the sync of util_sum with util_avg
sched/pelt: Relax the sync of util_sum with util_avg
psi: Fix uaf issue when psi trigger is destroyed while being polled
With write operation on psi files replacing old trigger with a new one,
the lifetime of its waitqueue is totally arbitrary. Overwriting an
existing trigger causes its waitqueue to be freed and pending poll()
will stumble on trigger->event_wait which was destroyed.
Fix this by disallowing to redefine an existing psi trigger. If a write
operation is used on a file descriptor with an already existing psi
trigger, the operation will fail with EBUSY error.
Also bypass a check for psi_disabled in the psi_trigger_destroy as the
flag can be flipped after the trigger is created, leading to a memory
leak.
Fixes: 0e94682b73 ("psi: introduce psi monitor")
Reported-by: syzbot+cdb5dd11c97cc532efad@syzkaller.appspotmail.com
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Analyzed-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20220111232309.1786347-1-surenb@google.com
Assuming this stuff isn't actually used much; disable it by default
and avoid allocating and tracking the task_delay_info structure.
taskstats is changed to still report the regular sched and sched_info
and only skip the missing task_delay_info fields instead of not
reporting anything.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20210505111525.308018373@infradead.org
Replace the lkml.org links with lore to better use a single source
that's more likely to stay available long-term.
Done by bash script:
cvt_lkml_to_lore ()
{
tmpfile=$(mktemp ./.cvt_links.XXXXXXX)
header=$(echo $1 | sed 's@/lkml/@/lkml/headers/@')
wget -qO - $header > $tmpfile
if [[ $? == 0 ]] ; then
link=$(grep -i '^Message-Id:' $tmpfile | head -1 | \
sed -r -e 's/^\s*Message-Id:\s*<\s*//' -e 's/\s*>\s*$//' -e 's@^@https://lore.kernel.org/r/@')
# echo "testlink: $link"
if [ -n "$link" ] ; then
wget -qO - $link > /dev/null
if [[ $? == 0 ]] ; then
echo $link
fi
fi
fi
rm -f $tmpfile
}
git grep -P -o "\bhttps?://(?:www.)?lkml.org/lkml[\/\w]+" $@ |
while read line ; do
echo $line
file=$(echo $line | cut -f1 -d':')
link=$(echo $line | cut -f2- -d':')
newlink=$(cvt_lkml_to_lore $link)
if [[ -n "$newlink" ]] ; then
sed -i -e "s#\b$link\b#$newlink#" $file
fi
done
Link: https://lore.kernel.org/patchwork/patch/1265849/#1462688
Signed-off-by: Joe Perches <joe@perches.com>
Link: https://lore.kernel.org/r/77cdb7f32cfb087955bfc3600b86c40bed5d4104.camel@perches.com
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Annotate references to other documents to make them clickable.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lore.kernel.org/r/20200228000653.1572553-6-kuba@kernel.org
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Those are subsystem docs, with a mix of kABI and user-faced
docs. While they're not split, keep the dirs where they are,
adding just a pointer to the main index.
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Rename the accounting documentation files to ReST, add an
index for them and adjust in order to produce a nice html
output via the Sphinx build system.
At its new index.rst, let's add a :orphan: while this is not linked to
the main index.rst file, in order to avoid build warnings.
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Psi monitor aims to provide a low-latency short-term pressure detection
mechanism configurable by users. It allows users to monitor psi metrics
growth and trigger events whenever a metric raises above user-defined
threshold within user-defined time window.
Time window and threshold are both expressed in usecs. Multiple psi
resources with different thresholds and window sizes can be monitored
concurrently.
Psi monitors activate when system enters stall state for the monitored
psi metric and deactivate upon exit from the stall state. While system
is in the stall state psi signal growth is monitored at a rate of 10
times per tracking window. Min window size is 500ms, therefore the min
monitoring interval is 50ms. Max window size is 10s with monitoring
interval of 1s.
When activated psi monitor stays active for at least the duration of one
tracking window to avoid repeated activations/deactivations when psi
signal is bouncing.
Notifications to the users are rate-limited to one per tracking window.
Link: http://lkml.kernel.org/r/20190319235619.260832-8-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The output of the PSI files show a bunch of numbers with no unit. The
psi.txt documentation file also does not indicate what units are used.
One can only find out by looking at the source code. The units are
percentage for the averages and useconds for the total. Make the
information easier to find by documenting the units in psi.txt.
Link: http://lkml.kernel.org/r/20190402193810.3450-1-longman@redhat.com
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
On a system that executes multiple cgrouped jobs and independent
workloads, we don't just care about the health of the overall system, but
also that of individual jobs, so that we can ensure individual job health,
fairness between jobs, or prioritize some jobs over others.
This patch implements pressure stall tracking for cgroups. In kernels
with CONFIG_PSI=y, cgroup2 groups will have cpu.pressure, memory.pressure,
and io.pressure files that track aggregate pressure stall times for only
the tasks inside the cgroup.
Link: http://lkml.kernel.org/r/20180828172258.3185-10-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When systems are overcommitted and resources become contended, it's hard
to tell exactly the impact this has on workload productivity, or how close
the system is to lockups and OOM kills. In particular, when machines work
multiple jobs concurrently, the impact of overcommit in terms of latency
and throughput on the individual job can be enormous.
In order to maximize hardware utilization without sacrificing individual
job health or risk complete machine lockups, this patch implements a way
to quantify resource pressure in the system.
A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that
expose the percentage of time the system is stalled on CPU, memory, or IO,
respectively. Stall states are aggregate versions of the per-task delay
accounting delays:
cpu: some tasks are runnable but not executing on a CPU
memory: tasks are reclaiming, or waiting for swapin or thrashing cache
io: tasks are waiting for io completions
These percentages of walltime can be thought of as pressure percentages,
and they give a general sense of system health and productivity loss
incurred by resource overcommit. They can also indicate when the system
is approaching lockup scenarios and OOMs.
To do this, psi keeps track of the task states associated with each CPU
and samples the time they spend in stall states. Every 2 seconds, the
samples are averaged across CPUs - weighted by the CPUs' non-idle time to
eliminate artifacts from unused CPUs - and translated into percentages of
walltime. A running average of those percentages is maintained over 10s,
1m, and 5m periods (similar to the loadaverage).
[hannes@cmpxchg.org: doc fixlet, per Randy]
Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org
[hannes@cmpxchg.org: code optimization]
Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org
[hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter]
Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org
[hannes@cmpxchg.org: fix build]
Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org
Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Drake <drake@endlessm.com>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Move accounting tool to tools and remove it from Documentation
Makefile. Update location information for this tool. Create a
new Makefile to build accounting. It can be built from top level
directory or from accounting directory:
Run make -C tools/accounting or cd tools/accounting; make
Acked-by: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Shuah Khan <shuahkh@osg.samsung.com>
The type TASKSTATS_TYPE_NULL should always be ignored.
When jumping to the next attribute, only the length of the current
attribute should be added, not the length of all nested attributes.
This last bug was not visible before commit 80df554275, because the
kernel didn't put more than two nested attributes.
Fixes: a3baf649ca ("[PATCH] per-task-delay-accounting: documentation")
Fixes: 80df554275 ("taskstats: use the libnl API to align nlattr on 64-bit")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The script "checkpatch.pl" pointed out that assignments should usually
not be performed within condition checks.
Thus move the assignment for the variable "nl_sd" to a separate statement.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Change the Documentation makefiles from obj-m to subdir-y
to avoid generating unnecessary built-in.o files since nothing
in Documentation/ is ever linked in to vmlinux.
Signed-off-by: Peter Foley <pefoley2@pefoley.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Added a guaranteed null-terminate after call to strncpy.
This was partly found using a static code analysis program called
cppcheck.
Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
stime and utime are declared __u64 but are never used. On a glibc system
this is harmless lint, but on a uClibc system, because of the difference
in they way header files stack, including stdio.h brings in time.h and
this causes a name collision with stime. Since these are useless anyhow,
we remove them.
Signed-off-by: Anthony G. Basile <basile@opensource.dyc.edu>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
If the call to setsockopt() fails in
Documentation/accounting/getdelays.c::create_nl_socket() we return -1
without closing the socket, thus leaking it when the 'fd' variable
goes out of scope.
Easily fixed by just jumping to the 'error' label instead of returning
since we do the proper cleanup there.
While I was there I noticed that the error message that is printet if
setsockopt() fails was broken over two lines - put that on a single
line so it is easier to grep for.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
According to commit 676db4af04 ("cgroupfs: create /sys/fs/cgroup to
mount cgroupfs on") the canonical mountpoint for the cgroup filesystem
is /sys/fs/cgroup. Hence, this should be used in the documentation.
Signed-off-by: Jörg Sommer <joerg@alea.gnuu.de>
Acked-by: Paul Menage <menage@google.com>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I find it very handy to show the average delays in milliseconds.
Example output (on 100 concurrent dd reading sparse files):
CPU count real total virtual total delay total delay average
986 3223509952 3207643301 38863410579 39.415ms
IO count delay total delay average
0 0 0ms
SWAP count delay total delay average
0 0 0ms
RECLAIM count delay total delay average
1059 5131834899 4ms
dd: read=0, write=0, cancelled_write=0
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Cc: Mel Gorman <mel@linux.vnet.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Reviewed-by: Satoru Moriya <satoru.moriya@hds.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fixes
Documentation/accounting/getdelays.c: In function `get_family_id':
Documentation/accounting/getdelays.c:172:14: warning: variable `rc' set but not used [-Wunused-but-set-variable]
Reported-by: "Justin P. Mattock" <justinmattock@gmail.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fixes
Documentation/accounting/getdelays.c: In function `main':
Documentation/accounting/getdelays.c:436:7: warning: variable `i' set but not used [-Wunused-but-set-variable]
Signed-off-by: Justin P. Mattock <justinmattock@gmail.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The taskstats structure is internally aligned on 8 byte boundaries but the
layout of the aggregrate reply, with two NLA headers and the pid (each 4
bytes), actually force the entire structure to be unaligned. This causes
the kernel to issue unaligned access warnings on some architectures like
ia64. Unfortunately, some software out there doesn't properly unroll the
NLA packet and assumes that the start of the taskstats structure will
always be 20 bytes from the start of the netlink payload. Aligning the
start of the taskstats structure breaks this software, which we don't
want. So, for now the alignment only happens on architectures that
require it and those users will have to update to fixed versions of those
packages. Space is reserved in the packet only when needed. This ifdef
should be removed in several years e.g. 2012 once we can be confident
that fixed versions are installed on most systems. We add the padding
before the aggregate since the aggregate is already a defined type.
Commit 85893120 ("delayacct: align to 8 byte boundary on 64-bit systems")
previously addressed the alignment issues by padding out the pid field.
This was supposed to be a compatible change but the circumstances
described above mean that it wasn't. This patch backs out that change,
since it was a hack, and introduces a new NULL attribute type to provide
the padding. Padding the response with 4 bytes avoids allocating an
aligned taskstats structure and copying it back. Since the structure
weighs in at 328 bytes, it's too big to do it on the stack.
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Reported-by: Brian Rogers <brian@xyzw.org>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Guillaume Chazarain <guichaz@gmail.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Task delay-accounting was identified as one means of determining how long
a process spends in congestion_wait() without adding new statistics. For
example, if the workload should not be doing IO, delay-accounting could
reveal how long it was spending in unexpected IO or delays.
Unfortunately, on closer examination it was clear that getdelays does not
act as documented.
Commit a3baf649 ("per-task-delay-accounting: documentation") added
Documentation/accounting/getdelays.c with a -c switch that was documented
to fork/exec a child and report statistics on it but for reasons that are
unclear to me, commit 9e06d3f9 deleted support for this switch but did not
update the documentation. It might be an oversight or it might be because
the control flow of the program meant that accounting information would be
printed once early in the lifetime of the program making it of limited
use.
This patch reimplements -c for getdelays.c to act as documented. Unlike
the original version, it waits until the command completes before printing
any information on it. An example of it being used looks like
$ ./getdelays -d -c find /home/mel -name mel
print delayacct stats ON
/home/mel
/home/mel/.notes-wine/drive_c/windows/profiles/mel
/home/mel/.wine/drive_c/windows/profiles/mel
/home/mel/git-configs/dot.kde/share/apps/konqueror/home/mel
PID 5923
CPU count real total virtual total delay total
42779 5051232096 5164722692 564207988
IO count delay total
41727 97804147758
SWAP count delay total
0 0
RECLAIM count delay total
0 0
[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Acked-by: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix up -Wmissing-prototypes in compileable userspace code, mainly under
Documentation/.
Signed-off-by: Ladinu Chandrasinghe <ladinu.pub@gmail.com>
Signed-off-by: Trevor Keith <tsrk@tsrk.net>
Cc: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix compilation warning:
Documentation/accounting/getdelays.c: In function `main':
Documentation/accounting/getdelays.c:249: warning: `cmd_type' may be used uninitialized in this function
This is in fact a false positive.
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Acked-by: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When no option is passed to getdelays it just hangs, waiting
for a reply which will never come.
This patch prints usage() when no output marker is specified.
Signed-off-by: Marcus Meissner <meissner@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix printf format type warnings (seen on alpha & ia64):
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 6 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 7 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 8 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 9 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 12 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 13 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 16 has type '__u64'
Documentation/accounting/getdelays.c:206: warning: format '%15llu' expects type 'long long unsigned int', but argument 17 has type '__u64'
Documentation/accounting/getdelays.c:214: warning: format '%15llu' expects type 'long long unsigned int', but argument 4 has type '__u64'
Documentation/accounting/getdelays.c:214: warning: format '%15llu' expects type 'long long unsigned int', but argument 5 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 2 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 3 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 4 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 5 has type '__u64'
Documentation/accounting/getdelays.c:221: warning: format '%llu' expects type 'long long unsigned int', but argument 6 has type '__u64'
Documentation/accounting/getdelays.c:236: warning: 'cmd_type' may be used uninitialized in this function
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently source files in the Documentation/ sub-dir can easily bit-rot
since they are not generally buildable, either because they are hidden in
text files or because there are no Makefile rules for them. This needs to
be fixed so that the source files remain usable and good examples of code
instead of bad examples.
Add the ability to build source files that are in the Documentation/ dir.
Add to Kconfig as "BUILD_DOCSRC" config symbol.
Use "CONFIG_BUILD_DOCSRC=1 make ..." to build objects from the
Documentation/ sources. Or enable BUILD_DOCSRC in the *config system.
However, this symbol depends on HEADERS_CHECK since the header files need
to be installed (for userspace builds).
Built (using cross-tools) for x86-64, i386, alpha, ia64, sparc32,
sparc64, powerpc, sh, m68k, & mips.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Update document and make getdelays.c show delay accounting for memory reclaim.
For making a distinction between "swapping in pages" and "memory reclaim"
in getdelays.c, MEM is changed to SWAP.
Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add members for memory reclaim delay to taskstats, and accumulate them in
__delayacct_add_tsk() .
Signed-off-by: Keika Kobayashi <kobayashi.kk@ncos.nec.co.jp>
Cc: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Fix gcc warnings in getdelays.c:
Documentation/accounting/getdelays.c: In function 'task_context_switch_counts':
Documentation/accounting/getdelays.c:214: warning: format '%15lu' expects type 'long unsigned int', but argument 4 has type '__u64'
Documentation/accounting/getdelays.c:214: warning: format '%15lu' expects type 'long unsigned int', but argument 5 has type '__u64'
Documentation/accounting/getdelays.c: In function 'main':
Documentation/accounting/getdelays.c:402: warning: format '%d' expects type 'int', but argument 2 has type 'long unsigned int'
Documentation/accounting/getdelays.c: In function 'get_family_id':
Documentation/accounting/getdelays.c:171: warning: 'id' may be used uninitialized in this function
One warning is not a problem and can be dismissed:
Documentation/accounting/getdelays.c: In function 'main':
Documentation/accounting/getdelays.c:236: warning: 'cmd_type' may be used uninitialized in this function
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Update the getdelays utility to become cgroupstats aware. A new -C option has
been added. It takes in a control group path and prints out a summary of the
states of tasks in the control group
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch is inspired by the discussion at
http://lkml.org/lkml/2007/4/11/187 and implements per cgroup statistics
as suggested by Andrew Morton in http://lkml.org/lkml/2007/4/11/263. The
patch is on top of 2.6.21-mm1 with Paul's cgroups v9 patches (forward
ported)
This patch implements per cgroup statistics infrastructure and re-uses
code from the taskstats interface. A new set of cgroup operations are
registered with commands and attributes. It should be very easy to
*extend* per cgroup statistics, by adding members to the cgroupstats
structure.
The current model for cgroupstats is a pull, a push model (to post
statistics on interesting events), should be very easy to add. Currently
user space requests for statistics by passing the cgroup file
descriptor. Statistics about the state of all the tasks in the cgroup
is returned to user space.
TODO's/NOTE:
This patch provides an infrastructure for implementing cgroup statistics.
Based on the needs of each controller, we can incrementally add more statistics,
event based support for notification of statistics, accumulation of taskstats
into cgroup statistics in the future.
Sample output
# ./cgroupstats -C /cgroup/a
sleeping 2, blocked 0, running 1, stopped 0, uninterruptible 0
# ./cgroupstats -C /cgroup/
sleeping 154, blocked 0, running 0, stopped 0, uninterruptible 0
If the approach looks good, I'll enhance and post the user space utility for
the same
Feedback, comments, test results are always welcome!
[akpm@linux-foundation.org: build fix]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch cleans up duplicate includes in
Documentation/
Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit b663a79c19 ("taskstats: add
context-switch counters") incorrectly removed a comma from a printf
statement. This causes corruption in the output printing or a seg
fault.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
