diff options
| -rw-r--r-- | Documentation/admin-guide/cgroup-v2.rst | 20 | ||||
| -rw-r--r-- | include/linux/memcontrol.h | 1 | ||||
| -rw-r--r-- | mm/memcontrol.c | 88 |
3 files changed, 102 insertions, 7 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 5f12f203822e..b8c0460730f3 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1374,6 +1374,22 @@ PAGE_SIZE multiple when read back. The total amount of swap currently being used by the cgroup and its descendants. + memory.swap.high + A read-write single value file which exists on non-root + cgroups. The default is "max". + + Swap usage throttle limit. If a cgroup's swap usage exceeds + this limit, all its further allocations will be throttled to + allow userspace to implement custom out-of-memory procedures. + + This limit marks a point of no return for the cgroup. It is NOT + designed to manage the amount of swapping a workload does + during regular operation. Compare to memory.swap.max, which + prohibits swapping past a set amount, but lets the cgroup + continue unimpeded as long as other memory can be reclaimed. + + Healthy workloads are not expected to reach this limit. + memory.swap.max A read-write single value file which exists on non-root cgroups. The default is "max". @@ -1387,6 +1403,10 @@ PAGE_SIZE multiple when read back. otherwise, a value change in this file generates a file modified event. + high + The number of times the cgroup's swap usage was over + the high threshold. + max The number of times the cgroup's swap usage was about to go over the max boundary and swap allocation diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 95a09a7ec412..bfe9533bb67e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -45,6 +45,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 08cf17b186fb..f3087e22dfa9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2354,6 +2354,22 @@ static u64 mem_find_max_overage(struct mem_cgroup *memcg) return max_overage; } +static u64 swap_find_max_overage(struct mem_cgroup *memcg) +{ + u64 overage, max_overage = 0; + + do { + overage = calculate_overage(page_counter_read(&memcg->swap), + READ_ONCE(memcg->swap.high)); + if (overage) + memcg_memory_event(memcg, MEMCG_SWAP_HIGH); + max_overage = max(overage, max_overage); + } while ((memcg = parent_mem_cgroup(memcg)) && + !mem_cgroup_is_root(memcg)); + + return max_overage; +} + /* * Get the number of jiffies that we should penalise a mischievous cgroup which * is exceeding its memory.high by checking both it and its ancestors. @@ -2415,6 +2431,9 @@ void mem_cgroup_handle_over_high(void) penalty_jiffies = calculate_high_delay(memcg, nr_pages, mem_find_max_overage(memcg)); + penalty_jiffies += calculate_high_delay(memcg, nr_pages, + swap_find_max_overage(memcg)); + /* * Clamp the max delay per usermode return so as to still keep the * application moving forwards and also permit diagnostics, albeit @@ -2605,13 +2624,32 @@ done_restock: * reclaim, the cost of mismatch is negligible. */ do { - if (page_counter_read(&memcg->memory) > - READ_ONCE(memcg->memory.high)) { - /* Don't bother a random interrupted task */ - if (in_interrupt()) { + bool mem_high, swap_high; + + mem_high = page_counter_read(&memcg->memory) > + READ_ONCE(memcg->memory.high); + swap_high = page_counter_read(&memcg->swap) > + READ_ONCE(memcg->swap.high); + + /* Don't bother a random interrupted task */ + if (in_interrupt()) { + if (mem_high) { schedule_work(&memcg->high_work); break; } + continue; + } + + if (mem_high || swap_high) { + /* + * The allocating tasks in this cgroup will need to do + * reclaim or be throttled to prevent further growth + * of the memory or swap footprints. + * + * Target some best-effort fairness between the tasks, + * and distribute reclaim work and delay penalties + * based on how much each task is actually allocating. + */ current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; @@ -5076,6 +5114,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { memcg->swappiness = mem_cgroup_swappiness(parent); memcg->oom_kill_disable = parent->oom_kill_disable; @@ -5229,6 +5268,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) page_counter_set_low(&memcg->memory, 0); page_counter_set_high(&memcg->memory, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); memcg_wb_domain_size_changed(memcg); } @@ -7142,10 +7182,13 @@ bool mem_cgroup_swap_full(struct page *page) if (!memcg) return false; - for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) - if (page_counter_read(&memcg->swap) * 2 >= - READ_ONCE(memcg->swap.max)) + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) { + unsigned long usage = page_counter_read(&memcg->swap); + + if (usage * 2 >= READ_ONCE(memcg->swap.high) || + usage * 2 >= READ_ONCE(memcg->swap.max)) return true; + } return false; } @@ -7175,6 +7218,29 @@ static u64 swap_current_read(struct cgroup_subsys_state *css, return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE; } +static int swap_high_show(struct seq_file *m, void *v) +{ + return seq_puts_memcg_tunable(m, + READ_ONCE(mem_cgroup_from_seq(m)->swap.high)); +} + +static ssize_t swap_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &high); + if (err) + return err; + + page_counter_set_high(&memcg->swap, high); + + return nbytes; +} + static int swap_max_show(struct seq_file *m, void *v) { return seq_puts_memcg_tunable(m, @@ -7202,6 +7268,8 @@ static int swap_events_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + seq_printf(m, "high %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_SWAP_HIGH])); seq_printf(m, "max %lu\n", atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX])); seq_printf(m, "fail %lu\n", @@ -7217,6 +7285,12 @@ static struct cftype swap_files[] = { .read_u64 = swap_current_read, }, { + .name = "swap.high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = swap_high_show, + .write = swap_high_write, + }, + { .name = "swap.max", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = swap_max_show, |