From: Roman Gushchin <guro@xxxxxx> Subject: mm: memcontrol: avoid workload stalls when lowering memory.high Memory.high limit is implemented in a way such that the kernel penalizes all threads which are allocating a memory over the limit. Forcing all threads into the synchronous reclaim and adding some artificial delays allows to slow down the memory consumption and potentially give some time for userspace oom handlers/resource control agents to react. It works nicely if the memory usage is hitting the limit from below, however it works sub-optimal if a user adjusts memory.high to a value way below the current memory usage. It basically forces all workload threads (doing any memory allocations) into the synchronous reclaim and sleep. This makes the workload completely unresponsive for a long period of time and can also lead to a system-wide contention on lru locks. It can happen even if the workload is not actually tight on memory and has, for example, a ton of cold pagecache. In the current implementation writing to memory.high causes an atomic update of page counter's high value followed by an attempt to reclaim enough memory to fit into the new limit. To fix the problem described above, all we need is to change the order of execution: try to push the memory usage under the limit first, and only then set the new high limit. Link: http://lkml.kernel.org/r/20200709194718.189231-1-guro@xxxxxx Signed-off-by: Roman Gushchin <guro@xxxxxx> Reported-by: Domas Mituzas <domas@xxxxxx> Acked-by: Michal Hocko <mhocko@xxxxxxxx> Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Cc: Chris Down <chris@xxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/memcontrol.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/mm/memcontrol.c~mm-memcontrol-avoid-workload-stalls-when-lowering-memoryhigh +++ a/mm/memcontrol.c @@ -6213,8 +6213,6 @@ static ssize_t memory_high_write(struct if (err) return err; - page_counter_set_high(&memcg->memory, high); - for (;;) { unsigned long nr_pages = page_counter_read(&memcg->memory); unsigned long reclaimed; @@ -6238,6 +6236,8 @@ static ssize_t memory_high_write(struct break; } + page_counter_set_high(&memcg->memory, high); + return nbytes; } _
