The patch titled
per-zone and reclaim enhancements for memory controller: per zone lru for cgroup
has been added to the -mm tree. Its filename is
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: per-zone and reclaim enhancements for memory controller: per zone lru for cgroup
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
This patch implements per-zone lru for memory cgroup.
This patch makes use of mem_cgroup_per_zone struct for per zone lru.
LRU can be accessed by
mz = mem_cgroup_zoneinfo(mem_cgroup, node, zone);
&mz->active_list
&mz->inactive_list
or
mz = page_cgroup_zoneinfo(page_cgroup);
&mz->active_list
&mz->inactive_list
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Herbert Poetzl <herbert@xxxxxxxxxxxx>
Cc: Kirill Korotaev <dev@xxxxx>
Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: Pavel Emelianov <xemul@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Vaidyanathan Srinivasan <svaidy@xxxxxxxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 63 ++++++++++++++++++++++++++++------------------
1 file changed, 39 insertions(+), 24 deletions(-)
diff -puN mm/memcontrol.c~per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup mm/memcontrol.c
--- a/mm/memcontrol.c~per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup
+++ a/mm/memcontrol.c
@@ -89,6 +89,8 @@ enum mem_cgroup_zstat_index {
};
struct mem_cgroup_per_zone {
+ struct list_head active_list;
+ struct list_head inactive_list;
unsigned long count[NR_MEM_CGROUP_ZSTAT];
};
/* Macro for accessing counter */
@@ -122,10 +124,7 @@ struct mem_cgroup {
/*
* Per cgroup active and inactive list, similar to the
* per zone LRU lists.
- * TODO: Consider making these lists per zone
*/
- struct list_head active_list;
- struct list_head inactive_list;
struct mem_cgroup_lru_info info;
/*
* spin_lock to protect the per cgroup LRU
@@ -367,10 +366,10 @@ static void __mem_cgroup_add_list(struct
if (!to) {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
- list_add(&pc->lru, &pc->mem_cgroup->inactive_list);
+ list_add(&pc->lru, &mz->inactive_list);
} else {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
- list_add(&pc->lru, &pc->mem_cgroup->active_list);
+ list_add(&pc->lru, &mz->active_list);
}
mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
}
@@ -388,11 +387,11 @@ static void __mem_cgroup_move_lists(stru
if (active) {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
- list_move(&pc->lru, &pc->mem_cgroup->active_list);
+ list_move(&pc->lru, &mz->active_list);
} else {
MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
- list_move(&pc->lru, &pc->mem_cgroup->inactive_list);
+ list_move(&pc->lru, &mz->inactive_list);
}
}
@@ -518,11 +517,16 @@ unsigned long mem_cgroup_isolate_pages(u
LIST_HEAD(pc_list);
struct list_head *src;
struct page_cgroup *pc, *tmp;
+ int nid = z->zone_pgdat->node_id;
+ int zid = zone_idx(z);
+ struct mem_cgroup_per_zone *mz;
+ mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
if (active)
- src = &mem_cont->active_list;
+ src = &mz->active_list;
else
- src = &mem_cont->inactive_list;
+ src = &mz->inactive_list;
+
spin_lock(&mem_cont->lru_lock);
scan = 0;
@@ -544,13 +548,6 @@ unsigned long mem_cgroup_isolate_pages(u
continue;
}
- /*
- * Reclaim, per zone
- * TODO: make the active/inactive lists per zone
- */
- if (page_zone(page) != z)
- continue;
-
scan++;
list_move(&pc->lru, &pc_list);
@@ -832,6 +829,8 @@ mem_cgroup_force_empty_list(struct mem_c
int count;
unsigned long flags;
+ if (list_empty(list))
+ return;
retry:
count = FORCE_UNCHARGE_BATCH;
spin_lock_irqsave(&mem->lru_lock, flags);
@@ -867,20 +866,27 @@ retry:
int mem_cgroup_force_empty(struct mem_cgroup *mem)
{
int ret = -EBUSY;
+ int node, zid;
css_get(&mem->css);
/*
* page reclaim code (kswapd etc..) will move pages between
` * active_list <-> inactive_list while we don't take a lock.
* So, we have to do loop here until all lists are empty.
*/
- while (!(list_empty(&mem->active_list) &&
- list_empty(&mem->inactive_list))) {
+ while (mem->res.usage > 0) {
if (atomic_read(&mem->css.cgroup->count) > 0)
goto out;
- /* drop all page_cgroup in active_list */
- mem_cgroup_force_empty_list(mem, &mem->active_list);
- /* drop all page_cgroup in inactive_list */
- mem_cgroup_force_empty_list(mem, &mem->inactive_list);
+ for_each_node_state(node, N_POSSIBLE)
+ for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+ struct mem_cgroup_per_zone *mz;
+ mz = mem_cgroup_zoneinfo(mem, node, zid);
+ /* drop all page_cgroup in active_list */
+ mem_cgroup_force_empty_list(mem,
+ &mz->active_list);
+ /* drop all page_cgroup in inactive_list */
+ mem_cgroup_force_empty_list(mem,
+ &mz->inactive_list);
+ }
}
ret = 0;
out:
@@ -1092,15 +1098,25 @@ static struct cftype mem_cgroup_files[]
static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
{
struct mem_cgroup_per_node *pn;
+ struct mem_cgroup_per_zone *mz;
+ int zone;
pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, node);
if (!pn)
return 1;
+
mem->info.nodeinfo[node] = pn;
memset(pn, 0, sizeof(*pn));
+
+ for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+ mz = &pn->zoneinfo[zone];
+ INIT_LIST_HEAD(&mz->active_list);
+ INIT_LIST_HEAD(&mz->inactive_list);
+ }
return 0;
}
+
static struct mem_cgroup init_mem_cgroup;
static struct cgroup_subsys_state *
@@ -1119,8 +1135,7 @@ mem_cgroup_create(struct cgroup_subsys *
return NULL;
res_counter_init(&mem->res);
- INIT_LIST_HEAD(&mem->active_list);
- INIT_LIST_HEAD(&mem->inactive_list);
+
spin_lock_init(&mem->lru_lock);
mem->control_type = MEM_CGROUP_TYPE_ALL;
memset(&mem->info, 0, sizeof(mem->info));
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
memory-hotplug-fix-fix-section-mismatch-in-vmammap_allock_block.patch
memory-hotplug-x86_64-fix-section-mismatch-in-init_memory_mapping.patch
swapoff-scan-ptes-preemptibly.patch
memory-hotplug-add-removable-to-sysfs-to-show-memblock-removability.patch
add-remove_memory-for-ppc64-2.patch
enable-hotplug-memory-remove-for-ppc64.patch
add-arch-specific-walk_memory_remove-for-ppc64.patch
pie-executable-randomization.patch
pie-executable-randomization-uninlining.patch
pie-executable-randomization-checkpatch-fixes.patch
memcgroup-temporarily-revert-swapoff-mod.patch
memory-controller-make-charging-gfp-mask-aware-fix.patch
bugfix-for-memory-cgroup-controller-charge-refcnt-race-fix.patch
bugfix-for-memory-cgroup-controller-fix-error-handling-path-in-mem_charge_cgroup.patch
bugfix-for-memory-controller-add-helper-function-for-assigning-cgroup-to-page.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages-fix.patch
bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix.patch
memory-cgroup-enhancements-fix-zone-handling-in-try_to_free_mem_cgroup_page.patch
memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup.patch
memory-cgroup-enhancements-remember-a-page-is-charged-as-page-cache.patch
memory-cgroup-enhancements-remember-a-page-is-on-active-list-of-cgroup-or-not.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-checkpatch-fixes.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-fix-1.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-uninlining.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-fix-2.patch
memory-cgroup-enhancements-add-memorystat-file.patch
memory-cgroup-enhancements-add-memorystat-file-checkpatch-fixes.patch
memory-cgroup-enhancements-add-memorystat-file-printk-fix.patch
memory-cgroup-enhancements-add-pre_destroy-handler.patch
memory-cgroup-enhancements-implicit-force_empty-at-rmdir.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-add-scan_global_lru-macro.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-nid-zid-helper-function-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-active-inactive-counter.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-mapper_ratio-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-active-inactive-imbalance-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-remember-reclaim-priority-in-memory-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-calculate-the-number-of-pages-to-be-scanned-per-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-modifies-vmscanc-for-isolate-globa-cgroup-lru-activity.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lru-for-cgroup.patch
per-zone-and-reclaim-enhancements-for-memory-controller-take-3-per-zone-lock-for-cgroup.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
