Memory controller: add per cgroup LRU and reclaim
Add the page_cgroup to the per cgroup LRU. The reclaim algorithm has
been modified to make the isolate_lru_pages() as a pluggable component. The
scan_control data structure now accepts the cgroup on behalf of which
reclaims are carried out. try_to_free_pages() has been extended to become
cgroup aware.
[akpm@linux-foundation.org: fix warning]
[Lee.Schermerhorn@hp.com: initialize all scan_control's isolate_pages member]
[bunk@kernel.org: make do_try_to_free_pages() static]
[hugh@veritas.com: memcgroup: fix try_to_free order]
[kamezawa.hiroyu@jp.fujitsu.com: this unlock_page_cgroup() is unnecessary]
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
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>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e5a9597..7408a8a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -37,6 +37,7 @@
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
+#include <linux/memcontrol.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -68,6 +69,15 @@
int all_unreclaimable;
int order;
+
+ /* Which cgroup do we reclaim from */
+ struct mem_cgroup *mem_cgroup;
+
+ /* Pluggable isolate pages callback */
+ unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
+ unsigned long *scanned, int order, int mode,
+ struct zone *z, struct mem_cgroup *mem_cont,
+ int active);
};
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
@@ -626,7 +636,7 @@
*
* returns 0 on success, -ve errno on failure.
*/
-static int __isolate_lru_page(struct page *page, int mode)
+int __isolate_lru_page(struct page *page, int mode)
{
int ret = -EINVAL;
@@ -760,6 +770,21 @@
return nr_taken;
}
+static unsigned long isolate_pages_global(unsigned long nr,
+ struct list_head *dst,
+ unsigned long *scanned, int order,
+ int mode, struct zone *z,
+ struct mem_cgroup *mem_cont,
+ int active)
+{
+ if (active)
+ return isolate_lru_pages(nr, &z->active_list, dst,
+ scanned, order, mode);
+ else
+ return isolate_lru_pages(nr, &z->inactive_list, dst,
+ scanned, order, mode);
+}
+
/*
* clear_active_flags() is a helper for shrink_active_list(), clearing
* any active bits from the pages in the list.
@@ -801,11 +826,11 @@
unsigned long nr_freed;
unsigned long nr_active;
- nr_taken = isolate_lru_pages(sc->swap_cluster_max,
- &zone->inactive_list,
+ nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order,
(sc->order > PAGE_ALLOC_COSTLY_ORDER)?
- ISOLATE_BOTH : ISOLATE_INACTIVE);
+ ISOLATE_BOTH : ISOLATE_INACTIVE,
+ zone, sc->mem_cgroup, 0);
nr_active = clear_active_flags(&page_list);
__count_vm_events(PGDEACTIVATE, nr_active);
@@ -1018,8 +1043,9 @@
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
- pgmoved = isolate_lru_pages(nr_pages, &zone->active_list,
- &l_hold, &pgscanned, sc->order, ISOLATE_ACTIVE);
+ pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
+ ISOLATE_ACTIVE, zone,
+ sc->mem_cgroup, 1);
zone->pages_scanned += pgscanned;
__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
spin_unlock_irq(&zone->lru_lock);
@@ -1051,6 +1077,7 @@
ClearPageActive(page);
list_move(&page->lru, &zone->inactive_list);
+ mem_cgroup_move_lists(page_get_page_cgroup(page), false);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
@@ -1079,6 +1106,7 @@
SetPageLRU(page);
VM_BUG_ON(!PageActive(page));
list_move(&page->lru, &zone->active_list);
+ mem_cgroup_move_lists(page_get_page_cgroup(page), true);
pgmoved++;
if (!pagevec_add(&pvec, page)) {
__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
@@ -1206,7 +1234,8 @@
* holds filesystem locks which prevent writeout this might not work, and the
* allocation attempt will fail.
*/
-unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
+static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask,
+ struct scan_control *sc)
{
int priority;
int ret = 0;
@@ -1215,14 +1244,6 @@
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long lru_pages = 0;
int i;
- struct scan_control sc = {
- .gfp_mask = gfp_mask,
- .may_writepage = !laptop_mode,
- .swap_cluster_max = SWAP_CLUSTER_MAX,
- .may_swap = 1,
- .swappiness = vm_swappiness,
- .order = order,
- };
count_vm_event(ALLOCSTALL);
@@ -1237,17 +1258,22 @@
}
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
- sc.nr_scanned = 0;
+ sc->nr_scanned = 0;
if (!priority)
disable_swap_token();
- nr_reclaimed += shrink_zones(priority, zones, &sc);
- shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
+ nr_reclaimed += shrink_zones(priority, zones, sc);
+ /*
+ * Don't shrink slabs when reclaiming memory from
+ * over limit cgroups
+ */
+ if (sc->mem_cgroup == NULL)
+ shrink_slab(sc->nr_scanned, gfp_mask, lru_pages);
if (reclaim_state) {
nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
- total_scanned += sc.nr_scanned;
- if (nr_reclaimed >= sc.swap_cluster_max) {
+ total_scanned += sc->nr_scanned;
+ if (nr_reclaimed >= sc->swap_cluster_max) {
ret = 1;
goto out;
}
@@ -1259,18 +1285,18 @@
* that's undesirable in laptop mode, where we *want* lumpy
* writeout. So in laptop mode, write out the whole world.
*/
- if (total_scanned > sc.swap_cluster_max +
- sc.swap_cluster_max / 2) {
+ if (total_scanned > sc->swap_cluster_max +
+ sc->swap_cluster_max / 2) {
wakeup_pdflush(laptop_mode ? 0 : total_scanned);
- sc.may_writepage = 1;
+ sc->may_writepage = 1;
}
/* Take a nap, wait for some writeback to complete */
- if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
+ if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
congestion_wait(WRITE, HZ/10);
}
/* top priority shrink_caches still had more to do? don't OOM, then */
- if (!sc.all_unreclaimable)
+ if (!sc->all_unreclaimable && sc->mem_cgroup == NULL)
ret = 1;
out:
/*
@@ -1293,6 +1319,54 @@
return ret;
}
+unsigned long try_to_free_pages(struct zone **zones, int order, gfp_t gfp_mask)
+{
+ struct scan_control sc = {
+ .gfp_mask = gfp_mask,
+ .may_writepage = !laptop_mode,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .may_swap = 1,
+ .swappiness = vm_swappiness,
+ .order = order,
+ .mem_cgroup = NULL,
+ .isolate_pages = isolate_pages_global,
+ };
+
+ return do_try_to_free_pages(zones, gfp_mask, &sc);
+}
+
+#ifdef CONFIG_CGROUP_MEM_CONT
+
+#ifdef CONFIG_HIGHMEM
+#define ZONE_USERPAGES ZONE_HIGHMEM
+#else
+#define ZONE_USERPAGES ZONE_NORMAL
+#endif
+
+unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont)
+{
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_writepage = !laptop_mode,
+ .may_swap = 1,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .swappiness = vm_swappiness,
+ .order = 0,
+ .mem_cgroup = mem_cont,
+ .isolate_pages = mem_cgroup_isolate_pages,
+ };
+ int node;
+ struct zone **zones;
+
+ for_each_online_node(node) {
+ zones = NODE_DATA(node)->node_zonelists[ZONE_USERPAGES].zones;
+ if (do_try_to_free_pages(zones, sc.gfp_mask, &sc))
+ return 1;
+ }
+ return 0;
+}
+#endif
+
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
@@ -1328,6 +1402,8 @@
.swap_cluster_max = SWAP_CLUSTER_MAX,
.swappiness = vm_swappiness,
.order = order,
+ .mem_cgroup = NULL,
+ .isolate_pages = isolate_pages_global,
};
/*
* temp_priority is used to remember the scanning priority at which
@@ -1649,6 +1725,7 @@
.swap_cluster_max = nr_pages,
.may_writepage = 1,
.swappiness = vm_swappiness,
+ .isolate_pages = isolate_pages_global,
};
current->reclaim_state = &reclaim_state;
@@ -1834,6 +1911,7 @@
SWAP_CLUSTER_MAX),
.gfp_mask = gfp_mask,
.swappiness = vm_swappiness,
+ .isolate_pages = isolate_pages_global,
};
unsigned long slab_reclaimable;