linux/mm/swap.c

561 lines
14 KiB
C
Raw Normal View History

/*
* linux/mm/swap.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*/
/*
* This file contains the default values for the operation of the
* Linux VM subsystem. Fine-tuning documentation can be found in
* Documentation/sysctl/vm.txt.
* Started 18.12.91
* Swap aging added 23.2.95, Stephen Tweedie.
* Buffermem limits added 12.3.98, Rik van Riel.
*/
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm_inline.h>
#include <linux/buffer_head.h> /* for try_to_release_page() */
#include <linux/percpu_counter.h>
#include <linux/percpu.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <linux/backing-dev.h>
#include <linux/memcontrol.h>
swap: cull unevictable pages in fault path In the fault paths that install new anonymous pages, check whether the page is evictable or not using lru_cache_add_active_or_unevictable(). If the page is evictable, just add it to the active lru list [via the pagevec cache], else add it to the unevictable list. This "proactive" culling in the fault path mimics the handling of mlocked pages in Nick Piggin's series to keep mlocked pages off the lru lists. Notes: 1) This patch is optional--e.g., if one is concerned about the additional test in the fault path. We can defer the moving of nonreclaimable pages until when vmscan [shrink_*_list()] encounters them. Vmscan will only need to handle such pages once, but if there are a lot of them it could impact system performance. 2) The 'vma' argument to page_evictable() is require to notice that we're faulting a page into an mlock()ed vma w/o having to scan the page's rmap in the fault path. Culling mlock()ed anon pages is currently the only reason for this patch. 3) We can't cull swap pages in read_swap_cache_async() because the vma argument doesn't necessarily correspond to the swap cache offset passed in by swapin_readahead(). This could [did!] result in mlocking pages in non-VM_LOCKED vmas if [when] we tried to cull in this path. 4) Move set_pte_at() to after where we add page to lru to keep it hidden from other tasks that might walk the page table. We already do it in this order in do_anonymous() page. And, these are COW'd anon pages. Is this safe? [riel@redhat.com: undo an overzealous code cleanup] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:52 +00:00
#include "internal.h"
/* How many pages do we try to swap or page in/out together? */
int page_cluster;
static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
/*
* This path almost never happens for VM activity - pages are normally
* freed via pagevecs. But it gets used by networking.
*/
static void __page_cache_release(struct page *page)
{
if (PageLRU(page)) {
unsigned long flags;
struct zone *zone = page_zone(page);
spin_lock_irqsave(&zone->lru_lock, flags);
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru(zone, page);
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
free_hot_page(page);
}
static void put_compound_page(struct page *page)
{
2007-05-06 21:49:39 +00:00
page = compound_head(page);
if (put_page_testzero(page)) {
compound_page_dtor *dtor;
dtor = get_compound_page_dtor(page);
(*dtor)(page);
}
}
void put_page(struct page *page)
{
if (unlikely(PageCompound(page)))
put_compound_page(page);
else if (put_page_testzero(page))
__page_cache_release(page);
}
EXPORT_SYMBOL(put_page);
/**
* put_pages_list() - release a list of pages
* @pages: list of pages threaded on page->lru
*
* Release a list of pages which are strung together on page.lru. Currently
* used by read_cache_pages() and related error recovery code.
*/
void put_pages_list(struct list_head *pages)
{
while (!list_empty(pages)) {
struct page *victim;
victim = list_entry(pages->prev, struct page, lru);
list_del(&victim->lru);
page_cache_release(victim);
}
}
EXPORT_SYMBOL(put_pages_list);
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
/*
* pagevec_move_tail() must be called with IRQ disabled.
* Otherwise this may cause nasty races.
*/
static void pagevec_move_tail(struct pagevec *pvec)
{
int i;
int pgmoved = 0;
struct zone *zone = NULL;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
struct zone *pagezone = page_zone(page);
if (pagezone != zone) {
if (zone)
spin_unlock(&zone->lru_lock);
zone = pagezone;
spin_lock(&zone->lru_lock);
}
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:32 +00:00
int lru = page_is_file_cache(page);
list_move_tail(&page->lru, &zone->lru[lru].list);
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
pgmoved++;
}
}
if (zone)
spin_unlock(&zone->lru_lock);
__count_vm_events(PGROTATED, pgmoved);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
/*
* Writeback is about to end against a page which has been marked for immediate
* reclaim. If it still appears to be reclaimable, move it to the tail of the
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
* inactive list.
*/
void rotate_reclaimable_page(struct page *page)
{
if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
!PageUnevictable(page) && PageLRU(page)) {
struct pagevec *pvec;
unsigned long flags;
page_cache_get(page);
local_irq_save(flags);
pvec = &__get_cpu_var(lru_rotate_pvecs);
if (!pagevec_add(pvec, page))
pagevec_move_tail(pvec);
local_irq_restore(flags);
}
}
static void update_page_reclaim_stat(struct zone *zone, struct page *page,
int file, int rotated)
{
struct zone_reclaim_stat *reclaim_stat = &zone->reclaim_stat;
struct zone_reclaim_stat *memcg_reclaim_stat;
memcg_reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page);
reclaim_stat->recent_scanned[file]++;
if (rotated)
reclaim_stat->recent_rotated[file]++;
if (!memcg_reclaim_stat)
return;
memcg_reclaim_stat->recent_scanned[file]++;
if (rotated)
memcg_reclaim_stat->recent_rotated[file]++;
}
/*
* FIXME: speed this up?
*/
void activate_page(struct page *page)
{
struct zone *zone = page_zone(page);
spin_lock_irq(&zone->lru_lock);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:32 +00:00
int file = page_is_file_cache(page);
int lru = LRU_BASE + file;
del_page_from_lru_list(zone, page, lru);
SetPageActive(page);
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:32 +00:00
lru += LRU_ACTIVE;
add_page_to_lru_list(zone, page, lru);
[PATCH] Light weight event counters The remaining counters in page_state after the zoned VM counter patches have been applied are all just for show in /proc/vmstat. They have no essential function for the VM. We use a simple increment of per cpu variables. In order to avoid the most severe races we disable preempt. Preempt does not prevent the race between an increment and an interrupt handler incrementing the same statistics counter. However, that race is exceedingly rare, we may only loose one increment or so and there is no requirement (at least not in kernel) that the vm event counters have to be accurate. In the non preempt case this results in a simple increment for each counter. For many architectures this will be reduced by the compiler to a single instruction. This single instruction is atomic for i386 and x86_64. And therefore even the rare race condition in an interrupt is avoided for both architectures in most cases. The patchset also adds an off switch for embedded systems that allows a building of linux kernels without these counters. The implementation of these counters is through inline code that hopefully results in only a single instruction increment instruction being emitted (i386, x86_64) or in the increment being hidden though instruction concurrency (EPIC architectures such as ia64 can get that done). Benefits: - VM event counter operations usually reduce to a single inline instruction on i386 and x86_64. - No interrupt disable, only preempt disable for the preempt case. Preempt disable can also be avoided by moving the counter into a spinlock. - Handling is similar to zoned VM counters. - Simple and easily extendable. - Can be omitted to reduce memory use for embedded use. References: RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=113512330605497&w=2 RFC http://marc.theaimsgroup.com/?l=linux-kernel&m=114988082814934&w=2 local_t http://marc.theaimsgroup.com/?l=linux-kernel&m=114991748606690&w=2 V2 http://marc.theaimsgroup.com/?t=115014808400007&r=1&w=2 V3 http://marc.theaimsgroup.com/?l=linux-kernel&m=115024767022346&w=2 V4 http://marc.theaimsgroup.com/?l=linux-kernel&m=115047968808926&w=2 Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-30 08:55:45 +00:00
__count_vm_event(PGACTIVATE);
vmscan: split LRU lists into anon & file sets Split the LRU lists in two, one set for pages that are backed by real file systems ("file") and one for pages that are backed by memory and swap ("anon"). The latter includes tmpfs. The advantage of doing this is that the VM will not have to scan over lots of anonymous pages (which we generally do not want to swap out), just to find the page cache pages that it should evict. This patch has the infrastructure and a basic policy to balance how much we scan the anon lists and how much we scan the file lists. The big policy changes are in separate patches. [lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset] [kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru] [kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page] [hugh@veritas.com: memcg swapbacked pages active] [hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED] [akpm@linux-foundation.org: fix /proc/vmstat units] [nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration] [kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo] [kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()] Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:32 +00:00
update_page_reclaim_stat(zone, page, !!file, 1);
}
spin_unlock_irq(&zone->lru_lock);
}
/*
* Mark a page as having seen activity.
*
* inactive,unreferenced -> inactive,referenced
* inactive,referenced -> active,unreferenced
* active,unreferenced -> active,referenced
*/
void mark_page_accessed(struct page *page)
{
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
if (!PageActive(page) && !PageUnevictable(page) &&
PageReferenced(page) && PageLRU(page)) {
activate_page(page);
ClearPageReferenced(page);
} else if (!PageReferenced(page)) {
SetPageReferenced(page);
}
}
EXPORT_SYMBOL(mark_page_accessed);
void __lru_cache_add(struct page *page, enum lru_list lru)
{
struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];
page_cache_get(page);
if (!pagevec_add(pvec, page))
____pagevec_lru_add(pvec, lru);
put_cpu_var(lru_add_pvecs);
}
/**
* lru_cache_add_lru - add a page to a page list
* @page: the page to be added to the LRU.
* @lru: the LRU list to which the page is added.
*/
void lru_cache_add_lru(struct page *page, enum lru_list lru)
{
if (PageActive(page)) {
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
VM_BUG_ON(PageUnevictable(page));
ClearPageActive(page);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
} else if (PageUnevictable(page)) {
VM_BUG_ON(PageActive(page));
ClearPageUnevictable(page);
}
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page));
__lru_cache_add(page, lru);
}
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
/**
* add_page_to_unevictable_list - add a page to the unevictable list
* @page: the page to be added to the unevictable list
*
* Add page directly to its zone's unevictable list. To avoid races with
* tasks that might be making the page evictable, through eg. munlock,
* munmap or exit, while it's not on the lru, we want to add the page
* while it's locked or otherwise "invisible" to other tasks. This is
* difficult to do when using the pagevec cache, so bypass that.
*/
void add_page_to_unevictable_list(struct page *page)
{
struct zone *zone = page_zone(page);
spin_lock_irq(&zone->lru_lock);
SetPageUnevictable(page);
SetPageLRU(page);
add_page_to_lru_list(zone, page, LRU_UNEVICTABLE);
spin_unlock_irq(&zone->lru_lock);
}
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
/*
* Drain pages out of the cpu's pagevecs.
* Either "cpu" is the current CPU, and preemption has already been
* disabled; or "cpu" is being hot-unplugged, and is already dead.
*/
static void drain_cpu_pagevecs(int cpu)
{
struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu);
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
struct pagevec *pvec;
int lru;
for_each_lru(lru) {
pvec = &pvecs[lru - LRU_BASE];
if (pagevec_count(pvec))
____pagevec_lru_add(pvec, lru);
}
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
pvec = &per_cpu(lru_rotate_pvecs, cpu);
if (pagevec_count(pvec)) {
unsigned long flags;
/* No harm done if a racing interrupt already did this */
local_irq_save(flags);
pagevec_move_tail(pvec);
local_irq_restore(flags);
}
}
void lru_add_drain(void)
{
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
drain_cpu_pagevecs(get_cpu());
put_cpu();
}
static void lru_add_drain_per_cpu(struct work_struct *dummy)
{
lru_add_drain();
}
/*
* Returns 0 for success
*/
int lru_add_drain_all(void)
{
return schedule_on_each_cpu(lru_add_drain_per_cpu);
}
/*
* Batched page_cache_release(). Decrement the reference count on all the
* passed pages. If it fell to zero then remove the page from the LRU and
* free it.
*
* Avoid taking zone->lru_lock if possible, but if it is taken, retain it
* for the remainder of the operation.
*
* The locking in this function is against shrink_inactive_list(): we recheck
* the page count inside the lock to see whether shrink_inactive_list()
* grabbed the page via the LRU. If it did, give up: shrink_inactive_list()
* will free it.
*/
void release_pages(struct page **pages, int nr, int cold)
{
int i;
struct pagevec pages_to_free;
struct zone *zone = NULL;
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
unsigned long uninitialized_var(flags);
pagevec_init(&pages_to_free, cold);
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
if (unlikely(PageCompound(page))) {
if (zone) {
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
put_compound_page(page);
continue;
}
2005-10-30 01:16:12 +00:00
if (!put_page_testzero(page))
continue;
if (PageLRU(page)) {
struct zone *pagezone = page_zone(page);
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
if (pagezone != zone) {
if (zone)
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
spin_unlock_irqrestore(&zone->lru_lock,
flags);
zone = pagezone;
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
spin_lock_irqsave(&zone->lru_lock, flags);
}
VM_BUG_ON(!PageLRU(page));
__ClearPageLRU(page);
del_page_from_lru(zone, page);
}
if (!pagevec_add(&pages_to_free, page)) {
if (zone) {
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
spin_unlock_irqrestore(&zone->lru_lock, flags);
zone = NULL;
}
__pagevec_free(&pages_to_free);
pagevec_reinit(&pages_to_free);
}
}
if (zone)
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
spin_unlock_irqrestore(&zone->lru_lock, flags);
pagevec_free(&pages_to_free);
}
/*
* The pages which we're about to release may be in the deferred lru-addition
* queues. That would prevent them from really being freed right now. That's
* OK from a correctness point of view but is inefficient - those pages may be
* cache-warm and we want to give them back to the page allocator ASAP.
*
* So __pagevec_release() will drain those queues here. __pagevec_lru_add()
* and __pagevec_lru_add_active() call release_pages() directly to avoid
* mutual recursion.
*/
void __pagevec_release(struct pagevec *pvec)
{
lru_add_drain();
release_pages(pvec->pages, pagevec_count(pvec), pvec->cold);
pagevec_reinit(pvec);
}
EXPORT_SYMBOL(__pagevec_release);
/*
* Add the passed pages to the LRU, then drop the caller's refcount
* on them. Reinitialises the caller's pagevec.
*/
void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
{
int i;
struct zone *zone = NULL;
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
VM_BUG_ON(is_unevictable_lru(lru));
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
struct zone *pagezone = page_zone(page);
int file;
int active;
if (pagezone != zone) {
if (zone)
spin_unlock_irq(&zone->lru_lock);
zone = pagezone;
spin_lock_irq(&zone->lru_lock);
}
Unevictable LRU Infrastructure When the system contains lots of mlocked or otherwise unevictable pages, the pageout code (kswapd) can spend lots of time scanning over these pages. Worse still, the presence of lots of unevictable pages can confuse kswapd into thinking that more aggressive pageout modes are required, resulting in all kinds of bad behaviour. Infrastructure to manage pages excluded from reclaim--i.e., hidden from vmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to maintain "unevictable" pages on a separate per-zone LRU list, to "hide" them from vmscan. Kosaki Motohiro added the support for the memory controller unevictable lru list. Pages on the unevictable list have both PG_unevictable and PG_lru set. Thus, PG_unevictable is analogous to and mutually exclusive with PG_active--it specifies which LRU list the page is on. The unevictable infrastructure is enabled by a new mm Kconfig option [CONFIG_]UNEVICTABLE_LRU. A new function 'page_evictable(page, vma)' in vmscan.c tests whether or not a page may be evictable. Subsequent patches will add the various !evictable tests. We'll want to keep these tests light-weight for use in shrink_active_list() and, possibly, the fault path. To avoid races between tasks putting pages [back] onto an LRU list and tasks that might be moving the page from non-evictable to evictable state, the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()' -- tests the "evictability" of a page after placing it on the LRU, before dropping the reference. If the page has become unevictable, putback_lru_page() will redo the 'putback', thus moving the page to the unevictable list. This way, we avoid "stranding" evictable pages on the unevictable list. [akpm@linux-foundation.org: fix fallout from out-of-order merge] [riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build] [nishimura@mxp.nes.nec.co.jp: remove redundant mapping check] [kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework] [kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c] [kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure] [kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch] [kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch] Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 03:26:39 +00:00
VM_BUG_ON(PageActive(page));
VM_BUG_ON(PageUnevictable(page));
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
active = is_active_lru(lru);
file = is_file_lru(lru);
if (active)
SetPageActive(page);
update_page_reclaim_stat(zone, page, file, active);
add_page_to_lru_list(zone, page, lru);
}
if (zone)
spin_unlock_irq(&zone->lru_lock);
release_pages(pvec->pages, pvec->nr, pvec->cold);
pagevec_reinit(pvec);
}
EXPORT_SYMBOL(____pagevec_lru_add);
/*
* Try to drop buffers from the pages in a pagevec
*/
void pagevec_strip(struct pagevec *pvec)
{
int i;
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
if (page_has_private(page) && trylock_page(page)) {
if (page_has_private(page))
try_to_release_page(page, 0);
unlock_page(page);
}
}
}
/**
* pagevec_lookup - gang pagecache lookup
* @pvec: Where the resulting pages are placed
* @mapping: The address_space to search
* @start: The starting page index
* @nr_pages: The maximum number of pages
*
* pagevec_lookup() will search for and return a group of up to @nr_pages pages
* in the mapping. The pages are placed in @pvec. pagevec_lookup() takes a
* reference against the pages in @pvec.
*
* The search returns a group of mapping-contiguous pages with ascending
* indexes. There may be holes in the indices due to not-present pages.
*
* pagevec_lookup() returns the number of pages which were found.
*/
unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
pgoff_t start, unsigned nr_pages)
{
pvec->nr = find_get_pages(mapping, start, nr_pages, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup);
unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
pgoff_t *index, int tag, unsigned nr_pages)
{
pvec->nr = find_get_pages_tag(mapping, index, tag,
nr_pages, pvec->pages);
return pagevec_count(pvec);
}
EXPORT_SYMBOL(pagevec_lookup_tag);
#ifdef CONFIG_SMP
/*
* We tolerate a little inaccuracy to avoid ping-ponging the counter between
* CPUs
*/
#define ACCT_THRESHOLD max(16, NR_CPUS * 2)
static DEFINE_PER_CPU(long, committed_space);
void vm_acct_memory(long pages)
{
long *local;
preempt_disable();
local = &__get_cpu_var(committed_space);
*local += pages;
if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) {
atomic_long_add(*local, &vm_committed_space);
*local = 0;
}
preempt_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
/* Drop the CPU's cached committed space back into the central pool. */
static int cpu_swap_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
long *committed;
committed = &per_cpu(committed_space, (long)hcpu);
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
atomic_long_add(*committed, &vm_committed_space);
*committed = 0;
mm: use pagevec to rotate reclaimable page While running some memory intensive load, system response deteriorated just after swap-out started. The cause of this problem is that when a PG_reclaim page is moved to the tail of the inactive LRU list in rotate_reclaimable_page(), lru_lock spin lock is acquired every page writeback . This deteriorates system performance and makes interrupt hold off time longer when swap-out started. Following patch solves this problem. I use pagevec in rotating reclaimable pages to mitigate LRU spin lock contention and reduce interrupt hold off time. I did a test that allocating and touching pages in multiple processes, and pinging to the test machine in flooding mode to measure response under memory intensive load. The test result is: -2.6.23-rc5 --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53222ms rtt min/avg/max/mdev = 0.074/0.652/172.228/7.176 ms, pipe 11, ipg/ewma 17.746/0.092 ms -2.6.23-rc5-patched --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms Max round-trip-time was improved. The test machine spec is that 4CPU(3.16GHz, Hyper-threading enabled) 8GB memory , 8GB swap. I did ping test again to observe performance deterioration caused by taking a ref. -2.6.23-rc6-with-modifiedpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 53386ms rtt min/avg/max/mdev = 0.074/0.110/4.716/0.147 ms, pipe 2, ipg/ewma 17.801/0.129 ms The result for my original patch is as follows. -2.6.23-rc5-with-originalpatch --- testmachine ping statistics --- 3000 packets transmitted, 3000 received, 0% packet loss, time 51924ms rtt min/avg/max/mdev = 0.072/0.108/3.884/0.114 ms, pipe 2, ipg/ewma 17.314/0.091 ms The influence to response was small. [akpm@linux-foundation.org: fix uninitalised var warning] [hugh@veritas.com: fix locking] [randy.dunlap@oracle.com: fix function declaration] [hugh@veritas.com: fix BUG at include/linux/mm.h:220!] [hugh@veritas.com: kill redundancy in rotate_reclaimable_page] [hugh@veritas.com: move_tail_pages into lru_add_drain] Signed-off-by: Hisashi Hifumi <hifumi.hisashi@oss.ntt.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 08:24:52 +00:00
drain_cpu_pagevecs((long)hcpu);
}
return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */
#endif /* CONFIG_SMP */
/*
* Perform any setup for the swap system
*/
void __init swap_setup(void)
{
unsigned long megs = num_physpages >> (20 - PAGE_SHIFT);
#ifdef CONFIG_SWAP
bdi_init(swapper_space.backing_dev_info);
#endif
/* Use a smaller cluster for small-memory machines */
if (megs < 16)
page_cluster = 2;
else
page_cluster = 3;
/*
* Right now other parts of the system means that we
* _really_ don't want to cluster much more
*/
#ifdef CONFIG_HOTPLUG_CPU
hotcpu_notifier(cpu_swap_callback, 0);
#endif
}