From 52b6f46bc163eef17ecba4cd552beeafe2b24453 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 19 May 2016 17:12:50 -0700 Subject: mm: /proc/sys/vm/stat_refresh to force vmstat update Provide /proc/sys/vm/stat_refresh to force an immediate update of per-cpu into global vmstats: useful to avoid a sleep(2) or whatever before checking counts when testing. Originally added to work around a bug which left counts stranded indefinitely on a cpu going idle (an inaccuracy magnified when small below-batch numbers represent "huge" amounts of memory), but I believe that bug is now fixed: nonetheless, this is still a useful knob. Its schedule_on_each_cpu() is probably too expensive just to fold into reading /proc/meminfo itself: give this mode 0600 to prevent abuse. Allow a write or a read to do the same: nothing to read, but "grep -h Shmem /proc/sys/vm/stat_refresh /proc/meminfo" is convenient. Oh, and since global_page_state() itself is careful to disguise any underflow as 0, hack in an "Invalid argument" and pr_warn() if a counter is negative after the refresh - this helped to fix a misaccounting of NR_ISOLATED_FILE in my migration code. But on recent kernels, I find that NR_ALLOC_BATCH and NR_PAGES_SCANNED often go negative some of the time. I have not yet worked out why, but have no evidence that it's actually harmful. Punt for the moment by just ignoring the anomaly on those. Signed-off-by: Hugh Dickins Cc: "Kirill A. Shutemov" Cc: Andrea Arcangeli Cc: Andres Lagar-Cavilla Cc: Yang Shi Cc: Ning Qu Cc: Mel Gorman Cc: Andres Lagar-Cavilla Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/vmstat.h') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 73fae8c4a5fb..02fce415b3d9 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -193,6 +193,10 @@ void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); +struct ctl_table; +int vmstat_refresh(struct ctl_table *, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); + void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); int calculate_pressure_threshold(struct zone *zone); -- cgit v1.2.3 From 060e74173f292fb3e0398b3dca8765568d195ff1 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 19 May 2016 17:13:27 -0700 Subject: mm, page_alloc: inline zone_statistics zone_statistics has one call-site but it's a public function. Make it static and inline. The performance difference on a page allocator microbenchmark is; 4.6.0-rc2 4.6.0-rc2 statbranch-v1r20 statinline-v1r20 Min alloc-odr0-1 419.00 ( 0.00%) 412.00 ( 1.67%) Min alloc-odr0-2 305.00 ( 0.00%) 301.00 ( 1.31%) Min alloc-odr0-4 250.00 ( 0.00%) 247.00 ( 1.20%) Min alloc-odr0-8 219.00 ( 0.00%) 215.00 ( 1.83%) Min alloc-odr0-16 203.00 ( 0.00%) 199.00 ( 1.97%) Min alloc-odr0-32 195.00 ( 0.00%) 191.00 ( 2.05%) Min alloc-odr0-64 191.00 ( 0.00%) 187.00 ( 2.09%) Min alloc-odr0-128 189.00 ( 0.00%) 185.00 ( 2.12%) Min alloc-odr0-256 198.00 ( 0.00%) 193.00 ( 2.53%) Min alloc-odr0-512 210.00 ( 0.00%) 207.00 ( 1.43%) Min alloc-odr0-1024 216.00 ( 0.00%) 213.00 ( 1.39%) Min alloc-odr0-2048 221.00 ( 0.00%) 220.00 ( 0.45%) Min alloc-odr0-4096 227.00 ( 0.00%) 226.00 ( 0.44%) Min alloc-odr0-8192 232.00 ( 0.00%) 229.00 ( 1.29%) Min alloc-odr0-16384 232.00 ( 0.00%) 229.00 ( 1.29%) Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 2 -- mm/page_alloc.c | 31 +++++++++++++++++++++++++++++++ mm/vmstat.c | 29 ----------------------------- 3 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include/linux/vmstat.h') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 02fce415b3d9..d2da8e053210 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -163,12 +163,10 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, #ifdef CONFIG_NUMA extern unsigned long node_page_state(int node, enum zone_stat_item item); -extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #else #define node_page_state(node, item) global_page_state(item) -#define zone_statistics(_zl, _z, gfp) do { } while (0) #endif /* CONFIG_NUMA */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7be1ce8b6be0..36384baa74e1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2354,6 +2354,37 @@ int split_free_page(struct page *page) return nr_pages; } +/* + * Update NUMA hit/miss statistics + * + * Must be called with interrupts disabled. + * + * When __GFP_OTHER_NODE is set assume the node of the preferred + * zone is the local node. This is useful for daemons who allocate + * memory on behalf of other processes. + */ +static inline void zone_statistics(struct zone *preferred_zone, struct zone *z, + gfp_t flags) +{ +#ifdef CONFIG_NUMA + int local_nid = numa_node_id(); + enum zone_stat_item local_stat = NUMA_LOCAL; + + if (unlikely(flags & __GFP_OTHER_NODE)) { + local_stat = NUMA_OTHER; + local_nid = preferred_zone->node; + } + + if (z->node == local_nid) { + __inc_zone_state(z, NUMA_HIT); + __inc_zone_state(z, local_stat); + } else { + __inc_zone_state(z, NUMA_MISS); + __inc_zone_state(preferred_zone, NUMA_FOREIGN); + } +#endif +} + /* * Allocate a page from the given zone. Use pcplists for order-0 allocations. */ diff --git a/mm/vmstat.c b/mm/vmstat.c index d585de27e960..f1a73bfb77b5 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -569,35 +569,6 @@ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) #endif #ifdef CONFIG_NUMA -/* - * zonelist = the list of zones passed to the allocator - * z = the zone from which the allocation occurred. - * - * Must be called with interrupts disabled. - * - * When __GFP_OTHER_NODE is set assume the node of the preferred - * zone is the local node. This is useful for daemons who allocate - * memory on behalf of other processes. - */ -void zone_statistics(struct zone *preferred_zone, struct zone *z, gfp_t flags) -{ - int local_nid = numa_node_id(); - enum zone_stat_item local_stat = NUMA_LOCAL; - - if (unlikely(flags & __GFP_OTHER_NODE)) { - local_stat = NUMA_OTHER; - local_nid = preferred_zone->node; - } - - if (z->node == local_nid) { - __inc_zone_state(z, NUMA_HIT); - __inc_zone_state(z, local_stat); - } else { - __inc_zone_state(z, NUMA_MISS); - __inc_zone_state(preferred_zone, NUMA_FOREIGN); - } -} - /* * Determine the per node value of a stat item. */ -- cgit v1.2.3