From 2bb921e526656556e68f99f5f15a4a1bf2691844 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Wed, 11 Sep 2013 14:21:30 -0700 Subject: vmstat: create separate function to fold per cpu diffs into local counters The main idea behind this patchset is to reduce the vmstat update overhead by avoiding interrupt enable/disable and the use of per cpu atomics. This patch (of 3): It is better to have a separate folding function because refresh_cpu_vm_stats() also does other things like expire pages in the page allocator caches. If we have a separate function then refresh_cpu_vm_stats() is only called from the local cpu which allows additional optimizations. The folding function is only called when a cpu is being downed and therefore no other processor will be accessing the counters. Also simplifies synchronization. [akpm@linux-foundation.org: fix UP build] Signed-off-by: Christoph Lameter Cc: KOSAKI Motohiro CC: Tejun Heo Cc: Joonsoo Kim Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 40 ++++++++++++++++++++++++++++++++++------ 1 file changed, 34 insertions(+), 6 deletions(-) (limited to 'mm/vmstat.c') diff --git a/mm/vmstat.c b/mm/vmstat.c index 8a8da1f9b044..aaee66330e01 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -415,11 +415,7 @@ EXPORT_SYMBOL(dec_zone_page_state); #endif /* - * Update the zone counters for one cpu. - * - * The cpu specified must be either the current cpu or a processor that - * is not online. If it is the current cpu then the execution thread must - * be pinned to the current cpu. + * Update the zone counters for the current cpu. * * Note that refresh_cpu_vm_stats strives to only access * node local memory. The per cpu pagesets on remote zones are placed @@ -432,7 +428,7 @@ EXPORT_SYMBOL(dec_zone_page_state); * with the global counters. These could cause remote node cache line * bouncing and will have to be only done when necessary. */ -void refresh_cpu_vm_stats(int cpu) +static void refresh_cpu_vm_stats(int cpu) { struct zone *zone; int i; @@ -493,6 +489,38 @@ void refresh_cpu_vm_stats(int cpu) atomic_long_add(global_diff[i], &vm_stat[i]); } +/* + * Fold the data for an offline cpu into the global array. + * There cannot be any access by the offline cpu and therefore + * synchronization is simplified. + */ +void cpu_vm_stats_fold(int cpu) +{ + struct zone *zone; + int i; + int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, }; + + for_each_populated_zone(zone) { + struct per_cpu_pageset *p; + + p = per_cpu_ptr(zone->pageset, cpu); + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (p->vm_stat_diff[i]) { + int v; + + v = p->vm_stat_diff[i]; + p->vm_stat_diff[i] = 0; + atomic_long_add(v, &zone->vm_stat[i]); + global_diff[i] += v; + } + } + + for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) + if (global_diff[i]) + atomic_long_add(global_diff[i], &vm_stat[i]); +} + /* * this is only called if !populated_zone(zone), which implies no other users of * pset->vm_stat_diff[] exsist. -- cgit v1.2.3-55-g7522