diff options
author | Christoph Lameter <cl@linux.com> | 2013-09-11 14:21:30 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-09-11 15:57:31 -0700 |
commit | 2bb921e526656556e68f99f5f15a4a1bf2691844 (patch) | |
tree | 91b009a59938d7713de0781df9d5c0c2eacfc51f /mm | |
parent | d2cf5ad6312ca9913464fac40fb47ba47ad945c4 (diff) |
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 <cl@linux.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
CC: Tejun Heo <tj@kernel.org>
Cc: Joonsoo Kim <js1304@gmail.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/page_alloc.c | 2 | ||||
-rw-r--r-- | mm/vmstat.c | 40 |
2 files changed, 35 insertions, 7 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 42c59300bac..f885eb82715 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5435,7 +5435,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, * This is only okay since the processor is dead and cannot * race with what we are doing. */ - refresh_cpu_vm_stats(cpu); + cpu_vm_stats_fold(cpu); } return NOTIFY_OK; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 8a8da1f9b04..aaee66330e0 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; @@ -494,6 +490,38 @@ void refresh_cpu_vm_stats(int cpu) } /* + * 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. */ |