From dd17c8f72993f9461e9c19250e3f155d6d99df22 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Thu, 29 Oct 2009 22:34:15 +0900 Subject: percpu: remove per_cpu__ prefix. Now that the return from alloc_percpu is compatible with the address of per-cpu vars, it makes sense to hand around the address of per-cpu variables. To make this sane, we remove the per_cpu__ prefix we used created to stop people accidentally using these vars directly. Now we have sparse, we can use that (next patch). tj: * Updated to convert stuff which were missed by or added after the original patch. * Kill per_cpu_var() macro. Signed-off-by: Rusty Russell Signed-off-by: Tejun Heo Reviewed-by: Christoph Lameter --- include/linux/vmstat.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux/vmstat.h') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d85889710f9b..3e489fda11a1 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -76,22 +76,22 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states); static inline void __count_vm_event(enum vm_event_item item) { - __this_cpu_inc(per_cpu_var(vm_event_states).event[item]); + __this_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { - this_cpu_inc(per_cpu_var(vm_event_states).event[item]); + this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { - __this_cpu_add(per_cpu_var(vm_event_states).event[item], delta); + __this_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { - this_cpu_add(per_cpu_var(vm_event_states).event[item], delta); + this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); -- cgit v1.2.2 From 748446bb6b5a9390b546af38ec899c868a9dbcf0 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:27 -0700 Subject: mm: compaction: memory compaction core This patch is the core of a mechanism which compacts memory in a zone by relocating movable pages towards the end of the zone. A single compaction run involves a migration scanner and a free scanner. Both scanners operate on pageblock-sized areas in the zone. The migration scanner starts at the bottom of the zone and searches for all movable pages within each area, isolating them onto a private list called migratelist. The free scanner starts at the top of the zone and searches for suitable areas and consumes the free pages within making them available for the migration scanner. The pages isolated for migration are then migrated to the newly isolated free pages. [aarcange@redhat.com: Fix unsafe optimisation] [mel@csn.ul.ie: do not schedule work on other CPUs for compaction] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux/vmstat.h') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 117f0dd8ad03..b421d1b22b62 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -43,6 +43,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, KSWAPD_SKIP_CONGESTION_WAIT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, +#ifdef CONFIG_COMPACTION + COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED, +#endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif -- cgit v1.2.2 From 56de7263fcf3eb10c8dcdf8d59a9cec831795f3f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 24 May 2010 14:32:30 -0700 Subject: mm: compaction: direct compact when a high-order allocation fails Ordinarily when a high-order allocation fails, direct reclaim is entered to free pages to satisfy the allocation. With this patch, it is determined if an allocation failed due to external fragmentation instead of low memory and if so, the calling process will compact until a suitable page is freed. Compaction by moving pages in memory is considerably cheaper than paging out to disk and works where there are locked pages or no swap. If compaction fails to free a page of a suitable size, then reclaim will still occur. Direct compaction returns as soon as possible. As each block is compacted, it is checked if a suitable page has been freed and if so, it returns. [akpm@linux-foundation.org: Fix build errors] [aarcange@redhat.com: fix count_vm_event preempt in memory compaction direct reclaim] Signed-off-by: Mel Gorman Acked-by: Rik van Riel Reviewed-by: Minchan Kim Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: KAMEZAWA Hiroyuki Signed-off-by: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/vmstat.h') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index b421d1b22b62..7f43ccdc1d38 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -45,6 +45,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PAGEOUTRUN, ALLOCSTALL, PGROTATED, #ifdef CONFIG_COMPACTION COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED, + COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS, #endif #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, -- cgit v1.2.2 From aa45484031ddee09b06350ab8528bfe5b2c76d1c Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 9 Sep 2010 16:38:17 -0700 Subject: mm: page allocator: calculate a better estimate of NR_FREE_PAGES when memory is low and kswapd is awake Ordinarily watermark checks are based on the vmstat NR_FREE_PAGES as it is cheaper than scanning a number of lists. To avoid synchronization overhead, counter deltas are maintained on a per-cpu basis and drained both periodically and when the delta is above a threshold. On large CPU systems, the difference between the estimated and real value of NR_FREE_PAGES can be very high. If NR_FREE_PAGES is much higher than number of real free page in buddy, the VM can allocate pages below min watermark, at worst reducing the real number of pages to zero. Even if the OOM killer kills some victim for freeing memory, it may not free memory if the exit path requires a new page resulting in livelock. This patch introduces a zone_page_state_snapshot() function (courtesy of Christoph) that takes a slightly more accurate view of an arbitrary vmstat counter. It is used to read NR_FREE_PAGES while kswapd is awake to avoid the watermark being accidentally broken. The estimate is not perfect and may result in cache line bounces but is expected to be lighter than the IPI calls necessary to continually drain the per-cpu counters while kswapd is awake. Signed-off-by: Christoph Lameter Signed-off-by: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux/vmstat.h') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 7f43ccdc1d38..eaaea37b3b75 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -170,6 +170,28 @@ static inline unsigned long zone_page_state(struct zone *zone, return x; } +/* + * More accurate version that also considers the currently pending + * deltas. For that we need to loop over all cpus to find the current + * deltas. There is no synchronization so the result cannot be + * exactly accurate either. + */ +static inline unsigned long zone_page_state_snapshot(struct zone *zone, + enum zone_stat_item item) +{ + long x = atomic_long_read(&zone->vm_stat[item]); + +#ifdef CONFIG_SMP + int cpu; + for_each_online_cpu(cpu) + x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; + + if (x < 0) + x = 0; +#endif + return x; +} + extern unsigned long global_reclaimable_pages(void); extern unsigned long zone_reclaimable_pages(struct zone *zone); -- cgit v1.2.2