aboutsummaryrefslogtreecommitdiffstats
path: root/Documentation/cgroups
diff options
context:
space:
mode:
authorMichal Hocko <mhocko@suse.cz>2014-06-06 17:38:15 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2014-06-06 19:08:17 -0400
commit688eb988d15af55c1d1b70b1ca9f6ce58f277c20 (patch)
tree5dac60260d3c7e0f97f82f4787a046d31c75ebf5 /Documentation/cgroups
parent722773afd83209d4088d30946bc274f547528a0b (diff)
vmscan: memcg: always use swappiness of the reclaimed memcg
Memory reclaim always uses swappiness of the reclaim target memcg (origin of the memory pressure) or vm_swappiness for global memory reclaim. This behavior was consistent (except for difference between global and hard limit reclaim) because swappiness was enforced to be consistent within each memcg hierarchy. After "mm: memcontrol: remove hierarchy restrictions for swappiness and oom_control" each memcg can have its own swappiness independent of hierarchical parents, though, so the consistency guarantee is gone. This can lead to an unexpected behavior. Say that a group is explicitly configured to not swapout by memory.swappiness=0 but its memory gets swapped out anyway when the memory pressure comes from its parent with a It is also unexpected that the knob is meaningless without setting the hard limit which would trigger the reclaim and enforce the swappiness. There are setups where the hard limit is configured higher in the hierarchy by an administrator and children groups are under control of somebody else who is interested in the swapout behavior but not necessarily about the memory limit. From a semantic point of view swappiness is an attribute defining anon vs. file proportional scanning of LRU which is memcg specific (unlike charges which are propagated up the hierarchy) so it should be applied to the particular memcg's LRU regardless where the memory pressure comes from. This patch removes vmscan_swappiness() and stores the swappiness into the scan_control structure. mem_cgroup_swappiness is then used to provide the correct value before shrink_lruvec is called. The global vm_swappiness is used for the root memcg. [hughd@google.com: oopses immediately when booted with cgroup_disable=memory] Signed-off-by: Michal Hocko <mhocko@suse.cz> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'Documentation/cgroups')
-rw-r--r--Documentation/cgroups/memory.txt15
1 files changed, 7 insertions, 8 deletions
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 4937e6fff9b4..b3429aec444c 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -540,14 +540,13 @@ Note:
540 540
5415.3 swappiness 5415.3 swappiness
542 542
543Similar to /proc/sys/vm/swappiness, but only affecting reclaim that is 543Overrides /proc/sys/vm/swappiness for the particular group. The tunable
544triggered by this cgroup's hard limit. The tunable in the root cgroup 544in the root cgroup corresponds to the global swappiness setting.
545corresponds to the global swappiness setting. 545
546 546Please note that unlike during the global reclaim, limit reclaim
547Please note that unlike the global swappiness, memcg knob set to 0 547enforces that 0 swappiness really prevents from any swapping even if
548really prevents from any swapping even if there is a swap storage 548there is a swap storage available. This might lead to memcg OOM killer
549available. This might lead to memcg OOM killer if there are no file 549if there are no file pages to reclaim.
550pages to reclaim.
551 550
5525.4 failcnt 5515.4 failcnt
553 552