diff --git a/mm/ksm.c b/mm/ksm.c index e2ce850c2739..599f7d209c68 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -248,6 +249,9 @@ static struct kmem_cache *rmap_item_cache; static struct kmem_cache *stable_node_cache; static struct kmem_cache *mm_slot_cache; +/* Default number of pages to scan per batch */ +#define DEFAULT_PAGES_TO_SCAN 100 + /* The number of pages scanned */ static unsigned long ksm_pages_scanned; @@ -276,7 +280,7 @@ static unsigned int ksm_stable_node_chains_prune_millisecs = 2000; static int ksm_max_page_sharing = 256; /* Number of pages ksmd should scan in one batch */ -static unsigned int ksm_thread_pages_to_scan = 100; +static unsigned int ksm_thread_pages_to_scan = DEFAULT_PAGES_TO_SCAN; /* Milliseconds ksmd should sleep between batches */ static unsigned int ksm_thread_sleep_millisecs = 20; @@ -297,6 +301,152 @@ unsigned long ksm_zero_pages; /* The number of pages that have been skipped due to "smart scanning" */ static unsigned long ksm_pages_skipped; +/* Don't scan more than max pages per batch. */ +static unsigned long ksm_advisor_max_pages_to_scan = 30000; + +/* Min CPU for scanning pages per scan */ +#define KSM_ADVISOR_MIN_CPU 10 + +/* Max CPU for scanning pages per scan */ +static unsigned int ksm_advisor_max_cpu = 70; + +/* Target scan time in seconds to analyze all KSM candidate pages. */ +static unsigned long ksm_advisor_target_scan_time = 200; + +/* Exponentially weighted moving average. */ +#define EWMA_WEIGHT 30 + +/** + * struct advisor_ctx - metadata for KSM advisor + * @start_scan: start time of the current scan + * @scan_time: scan time of previous scan + * @change: change in percent to pages_to_scan parameter + * @cpu_time: cpu time consumed by the ksmd thread in the previous scan + */ +struct advisor_ctx { + ktime_t start_scan; + unsigned long scan_time; + unsigned long change; + unsigned long long cpu_time; +}; +static struct advisor_ctx advisor_ctx; + +/* Define different advisor's */ +enum ksm_advisor_type { + KSM_ADVISOR_NONE, + KSM_ADVISOR_SCAN_TIME, +}; +static enum ksm_advisor_type ksm_advisor; + +static inline void advisor_start_scan(void) +{ + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + advisor_ctx.start_scan = ktime_get(); +} + +/* + * Use previous scan time if available, otherwise use current scan time as an + * approximation for the previous scan time. + */ +static inline unsigned long prev_scan_time(struct advisor_ctx *ctx, + unsigned long scan_time) +{ + return ctx->scan_time ? ctx->scan_time : scan_time; +} + +/* Calculate exponential weighted moving average */ +static unsigned long ewma(unsigned long prev, unsigned long curr) +{ + return ((100 - EWMA_WEIGHT) * prev + EWMA_WEIGHT * curr) / 100; +} + +/* + * The scan time advisor is based on the current scan rate and the target + * scan rate. + * + * new_pages_to_scan = pages_to_scan * (scan_time / target_scan_time) + * + * To avoid perturbations it calculates a change factor of previous changes. + * A new change factor is calculated for each iteration and it uses an + * exponentially weighted moving average. The new pages_to_scan value is + * multiplied with that change factor: + * + * new_pages_to_scan *= change facor + * + * The new_pages_to_scan value is limited by the cpu min and max values. It + * calculates the cpu percent for the last scan and calculates the new + * estimated cpu percent cost for the next scan. That value is capped by the + * cpu min and max setting. + * + * In addition the new pages_to_scan value is capped by the max and min + * limits. + */ +static void scan_time_advisor(void) +{ + unsigned int cpu_percent; + unsigned long cpu_time; + unsigned long cpu_time_diff; + unsigned long cpu_time_diff_ms; + unsigned long pages; + unsigned long per_page_cost; + unsigned long factor; + unsigned long change; + unsigned long last_scan_time; + unsigned long scan_time; + + /* Convert scan time to seconds */ + scan_time = div_s64(ktime_ms_delta(ktime_get(), advisor_ctx.start_scan), + MSEC_PER_SEC); + scan_time = scan_time ? scan_time : 1; + + /* Calculate CPU consumption of ksmd background thread */ + cpu_time = task_sched_runtime(current); + cpu_time_diff = cpu_time - advisor_ctx.cpu_time; + cpu_time_diff_ms = cpu_time_diff / 1000 / 1000; + + cpu_percent = (cpu_time_diff_ms * 100) / (scan_time * 1000); + cpu_percent = cpu_percent ? cpu_percent : 1; + last_scan_time = prev_scan_time(&advisor_ctx, scan_time); + + /* Calculate scan time as percentage of target scan time */ + factor = ksm_advisor_target_scan_time * 100 / scan_time; + factor = factor ? factor : 1; + + /* + * Calculate scan time as percentage of last scan time and use + * exponentially weighted average to smooth it + */ + change = scan_time * 100 / last_scan_time; + change = change ? change : 1; + change = ewma(advisor_ctx.change, change); + + /* Calculate new scan rate based on target scan rate. */ + pages = ksm_thread_pages_to_scan * 100 / factor; + /* Update pages_to_scan by weighted change percentage. */ + pages = pages * change / 100; + + /* Cap new pages_to_scan value */ + per_page_cost = ksm_thread_pages_to_scan / cpu_percent; + per_page_cost = per_page_cost ? per_page_cost : 1; + + pages = min(pages, per_page_cost * ksm_advisor_max_cpu); + pages = max(pages, per_page_cost * KSM_ADVISOR_MIN_CPU); + pages = min(pages, ksm_advisor_max_pages_to_scan); + + /* Update advisor context */ + advisor_ctx.change = change; + advisor_ctx.scan_time = scan_time; + advisor_ctx.cpu_time = cpu_time; + + ksm_thread_pages_to_scan = pages; +} + +static void advisor_stop_scan(void) +{ + if (ksm_advisor == KSM_ADVISOR_SCAN_TIME) + scan_time_advisor(); +} + #ifdef CONFIG_NUMA /* Zeroed when merging across nodes is not allowed */ static unsigned int ksm_merge_across_nodes = 1; @@ -2401,6 +2551,7 @@ static struct ksm_rmap_item *scan_get_next_rmap_item(struct page **page) mm_slot = ksm_scan.mm_slot; if (mm_slot == &ksm_mm_head) { + advisor_start_scan(); trace_ksm_start_scan(ksm_scan.seqnr, ksm_rmap_items); /* @@ -2558,6 +2709,8 @@ no_vmas: if (mm_slot != &ksm_mm_head) goto next_mm; + advisor_stop_scan(); + trace_ksm_stop_scan(ksm_scan.seqnr, ksm_rmap_items); ksm_scan.seqnr++; return NULL; @@ -3246,6 +3399,9 @@ static ssize_t pages_to_scan_store(struct kobject *kobj, unsigned int nr_pages; int err; + if (ksm_advisor != KSM_ADVISOR_NONE) + return -EINVAL; + err = kstrtouint(buf, 10, &nr_pages); if (err) return -EINVAL;