diff options
Diffstat (limited to 'mm/memcontrol.c')
| -rw-r--r-- | mm/memcontrol.c | 42 |
1 files changed, 37 insertions, 5 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bb0d3ac80ade..9b7a7d0592e5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -73,6 +73,7 @@ EXPORT_SYMBOL(memory_cgrp_subsys); struct mem_cgroup *root_mem_cgroup __read_mostly; +/* The number of times we should retry reclaim failures before giving up. */ #define MEM_CGROUP_RECLAIM_RETRIES 5 /* Socket memory accounting disabled? */ @@ -2363,18 +2364,23 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu) return 0; } -static void reclaim_high(struct mem_cgroup *memcg, - unsigned int nr_pages, - gfp_t gfp_mask) +static unsigned long reclaim_high(struct mem_cgroup *memcg, + unsigned int nr_pages, + gfp_t gfp_mask) { + unsigned long nr_reclaimed = 0; + do { if (page_counter_read(&memcg->memory) <= READ_ONCE(memcg->memory.high)) continue; memcg_memory_event(memcg, MEMCG_HIGH); - try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); + nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, + gfp_mask, true); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); + + return nr_reclaimed; } static void high_work_func(struct work_struct *work) @@ -2530,16 +2536,32 @@ void mem_cgroup_handle_over_high(void) { unsigned long penalty_jiffies; unsigned long pflags; + unsigned long nr_reclaimed; unsigned int nr_pages = current->memcg_nr_pages_over_high; + int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct mem_cgroup *memcg; + bool in_retry = false; if (likely(!nr_pages)) return; memcg = get_mem_cgroup_from_mm(current->mm); - reclaim_high(memcg, nr_pages, GFP_KERNEL); current->memcg_nr_pages_over_high = 0; +retry_reclaim: + /* + * The allocating task should reclaim at least the batch size, but for + * subsequent retries we only want to do what's necessary to prevent oom + * or breaching resource isolation. + * + * This is distinct from memory.max or page allocator behaviour because + * memory.high is currently batched, whereas memory.max and the page + * allocator run every time an allocation is made. + */ + nr_reclaimed = reclaim_high(memcg, + in_retry ? SWAP_CLUSTER_MAX : nr_pages, + GFP_KERNEL); + /* * memory.high is breached and reclaim is unable to keep up. Throttle * allocators proactively to slow down excessive growth. @@ -2567,6 +2589,16 @@ void mem_cgroup_handle_over_high(void) goto out; /* + * If reclaim is making forward progress but we're still over + * memory.high, we want to encourage that rather than doing allocator + * throttling. + */ + if (nr_reclaimed || nr_retries--) { + in_retry = true; + goto retry_reclaim; + } + + /* * If we exit early, we're guaranteed to die (since * schedule_timeout_killable sets TASK_KILLABLE). This means we don't * need to account for any ill-begotten jiffies to pay them off later. |