memcg: add memory.vmscan_stat
The commit log of 0ae5e89c60c9 ("memcg: count the soft_limit reclaim
in...") says it adds scanning stats to memory.stat file. But it doesn't
because we considered we needed to make a concensus for such new APIs.
This patch is a trial to add memory.scan_stat. This shows
- the number of scanned pages(total, anon, file)
- the number of rotated pages(total, anon, file)
- the number of freed pages(total, anon, file)
- the number of elaplsed time (including sleep/pause time)
for both of direct/soft reclaim.
The biggest difference with oringinal Ying's one is that this file
can be reset by some write, as
# echo 0 ...../memory.scan_stat
Example of output is here. This is a result after make -j 6 kernel
under 300M limit.
[kamezawa@bluextal ~]$ cat /cgroup/memory/A/memory.scan_stat
[kamezawa@bluextal ~]$ cat /cgroup/memory/A/memory.vmscan_stat
scanned_pages_by_limit 9471864
scanned_anon_pages_by_limit 6640629
scanned_file_pages_by_limit 2831235
rotated_pages_by_limit 4243974
rotated_anon_pages_by_limit 3971968
rotated_file_pages_by_limit 272006
freed_pages_by_limit 2318492
freed_anon_pages_by_limit 962052
freed_file_pages_by_limit 1356440
elapsed_ns_by_limit 351386416101
scanned_pages_by_system 0
scanned_anon_pages_by_system 0
scanned_file_pages_by_system 0
rotated_pages_by_system 0
rotated_anon_pages_by_system 0
rotated_file_pages_by_system 0
freed_pages_by_system 0
freed_anon_pages_by_system 0
freed_file_pages_by_system 0
elapsed_ns_by_system 0
scanned_pages_by_limit_under_hierarchy 9471864
scanned_anon_pages_by_limit_under_hierarchy 6640629
scanned_file_pages_by_limit_under_hierarchy 2831235
rotated_pages_by_limit_under_hierarchy 4243974
rotated_anon_pages_by_limit_under_hierarchy 3971968
rotated_file_pages_by_limit_under_hierarchy 272006
freed_pages_by_limit_under_hierarchy 2318492
freed_anon_pages_by_limit_under_hierarchy 962052
freed_file_pages_by_limit_under_hierarchy 1356440
elapsed_ns_by_limit_under_hierarchy 351386416101
scanned_pages_by_system_under_hierarchy 0
scanned_anon_pages_by_system_under_hierarchy 0
scanned_file_pages_by_system_under_hierarchy 0
rotated_pages_by_system_under_hierarchy 0
rotated_anon_pages_by_system_under_hierarchy 0
rotated_file_pages_by_system_under_hierarchy 0
freed_pages_by_system_under_hierarchy 0
freed_anon_pages_by_system_under_hierarchy 0
freed_file_pages_by_system_under_hierarchy 0
elapsed_ns_by_system_under_hierarchy 0
total_xxxx is for hierarchy management.
This will be useful for further memcg developments and need to be
developped before we do some complicated rework on LRU/softlimit
management.
This patch adds a new struct memcg_scanrecord into scan_control struct.
sc->nr_scanned at el is not designed for exporting information. For
example, nr_scanned is reset frequentrly and incremented +2 at scanning
mapped pages.
To avoid complexity, I added a new param in scan_control which is for
exporting scanning score.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Andrew Bresticker <abrestic@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index affd5b1..b966007 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -39,6 +39,16 @@
struct mem_cgroup *mem_cont,
int active, int file);
+struct memcg_scanrecord {
+ struct mem_cgroup *mem; /* scanend memory cgroup */
+ struct mem_cgroup *root; /* scan target hierarchy root */
+ int context; /* scanning context (see memcontrol.c) */
+ unsigned long nr_scanned[2]; /* the number of scanned pages */
+ unsigned long nr_rotated[2]; /* the number of rotated pages */
+ unsigned long nr_freed[2]; /* the number of freed pages */
+ unsigned long elapsed; /* nsec of time elapsed while scanning */
+};
+
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
/*
* All "charge" functions with gfp_mask should use GFP_KERNEL or
@@ -119,6 +129,15 @@
extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
struct task_struct *p);
+extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ struct memcg_scanrecord *rec);
+extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ struct zone *zone,
+ struct memcg_scanrecord *rec,
+ unsigned long *nr_scanned);
+
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
extern int do_swap_account;
#endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 44558b6..91d5fcc 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -251,12 +251,6 @@
/* linux/mm/vmscan.c */
extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
gfp_t gfp_mask, nodemask_t *mask);
-extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap);
-extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
- gfp_t gfp_mask, bool noswap,
- struct zone *zone,
- unsigned long *nr_scanned);
extern int __isolate_lru_page(struct page *page, int mode, int file);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;