summaryrefslogtreecommitdiff
path: root/mm/memcontrol.c
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2014-08-06 16:05:42 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-08-06 18:01:17 -0700
commit6539cc053869bd32a2db731b215b7c73b11f68d3 (patch)
tree8dc4998ae344345bab4fd2bafeb77d5cc4e4fd85 /mm/memcontrol.c
parent2f3e442ccceb85c51c7dffd3799bfd84de213874 (diff)
downloadlwn-6539cc053869bd32a2db731b215b7c73b11f68d3.tar.gz
lwn-6539cc053869bd32a2db731b215b7c73b11f68d3.zip
mm: memcontrol: fold mem_cgroup_do_charge()
These patches rework memcg charge lifetime to integrate more naturally with the lifetime of user pages. This drastically simplifies the code and reduces charging and uncharging overhead. The most expensive part of charging and uncharging is the page_cgroup bit spinlock, which is removed entirely after this series. Here are the top-10 profile entries of a stress test that reads a 128G sparse file on a freshly booted box, without even a dedicated cgroup (i.e. executing in the root memcg). Before: 15.36% cat [kernel.kallsyms] [k] copy_user_generic_string 13.31% cat [kernel.kallsyms] [k] memset 11.48% cat [kernel.kallsyms] [k] do_mpage_readpage 4.23% cat [kernel.kallsyms] [k] get_page_from_freelist 2.38% cat [kernel.kallsyms] [k] put_page 2.32% cat [kernel.kallsyms] [k] __mem_cgroup_commit_charge 2.18% kswapd0 [kernel.kallsyms] [k] __mem_cgroup_uncharge_common 1.92% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.86% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.62% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn After: 15.67% cat [kernel.kallsyms] [k] copy_user_generic_string 13.48% cat [kernel.kallsyms] [k] memset 11.42% cat [kernel.kallsyms] [k] do_mpage_readpage 3.98% cat [kernel.kallsyms] [k] get_page_from_freelist 2.46% cat [kernel.kallsyms] [k] put_page 2.13% kswapd0 [kernel.kallsyms] [k] shrink_page_list 1.88% cat [kernel.kallsyms] [k] __radix_tree_lookup 1.67% cat [kernel.kallsyms] [k] __pagevec_lru_add_fn 1.39% kswapd0 [kernel.kallsyms] [k] free_pcppages_bulk 1.30% cat [kernel.kallsyms] [k] kfree As you can see, the memcg footprint has shrunk quite a bit. text data bss dec hex filename 37970 9892 400 48262 bc86 mm/memcontrol.o.old 35239 9892 400 45531 b1db mm/memcontrol.o This patch (of 13): This function was split out because mem_cgroup_try_charge() got too big. But having essentially one sequence of operations arbitrarily split in half is not good for reworking the code. Fold it back in. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r--mm/memcontrol.c166
1 files changed, 64 insertions, 102 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f009a14918d2..fe3ad310656d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2551,80 +2551,6 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
return NOTIFY_OK;
}
-
-/* See mem_cgroup_try_charge() for details */
-enum {
- CHARGE_OK, /* success */
- CHARGE_RETRY, /* need to retry but retry is not bad */
- CHARGE_NOMEM, /* we can't do more. return -ENOMEM */
- CHARGE_WOULDBLOCK, /* GFP_WAIT wasn't set and no enough res. */
-};
-
-static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
- unsigned int nr_pages, unsigned int min_pages,
- bool invoke_oom)
-{
- unsigned long csize = nr_pages * PAGE_SIZE;
- struct mem_cgroup *mem_over_limit;
- struct res_counter *fail_res;
- unsigned long flags = 0;
- int ret;
-
- ret = res_counter_charge(&memcg->res, csize, &fail_res);
-
- if (likely(!ret)) {
- if (!do_swap_account)
- return CHARGE_OK;
- ret = res_counter_charge(&memcg->memsw, csize, &fail_res);
- if (likely(!ret))
- return CHARGE_OK;
-
- res_counter_uncharge(&memcg->res, csize);
- mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
- flags |= MEM_CGROUP_RECLAIM_NOSWAP;
- } else
- mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
- /*
- * Never reclaim on behalf of optional batching, retry with a
- * single page instead.
- */
- if (nr_pages > min_pages)
- return CHARGE_RETRY;
-
- if (!(gfp_mask & __GFP_WAIT))
- return CHARGE_WOULDBLOCK;
-
- if (gfp_mask & __GFP_NORETRY)
- return CHARGE_NOMEM;
-
- ret = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
- if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
- return CHARGE_RETRY;
- /*
- * Even though the limit is exceeded at this point, reclaim
- * may have been able to free some pages. Retry the charge
- * before killing the task.
- *
- * Only for regular pages, though: huge pages are rather
- * unlikely to succeed so close to the limit, and we fall back
- * to regular pages anyway in case of failure.
- */
- if (nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER) && ret)
- return CHARGE_RETRY;
-
- /*
- * At task move, charge accounts can be doubly counted. So, it's
- * better to wait until the end of task_move if something is going on.
- */
- if (mem_cgroup_wait_acct_move(mem_over_limit))
- return CHARGE_RETRY;
-
- if (invoke_oom)
- mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
-
- return CHARGE_NOMEM;
-}
-
/**
* mem_cgroup_try_charge - try charging a memcg
* @memcg: memcg to charge
@@ -2641,7 +2567,11 @@ static int mem_cgroup_try_charge(struct mem_cgroup *memcg,
{
unsigned int batch = max(CHARGE_BATCH, nr_pages);
int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
- int ret;
+ struct mem_cgroup *mem_over_limit;
+ struct res_counter *fail_res;
+ unsigned long nr_reclaimed;
+ unsigned long flags = 0;
+ unsigned long long size;
if (mem_cgroup_is_root(memcg))
goto done;
@@ -2661,44 +2591,76 @@ static int mem_cgroup_try_charge(struct mem_cgroup *memcg,
if (gfp_mask & __GFP_NOFAIL)
oom = false;
-again:
+retry:
if (consume_stock(memcg, nr_pages))
goto done;
- do {
- bool invoke_oom = oom && !nr_oom_retries;
+ size = batch * PAGE_SIZE;
+ if (!res_counter_charge(&memcg->res, size, &fail_res)) {
+ if (!do_swap_account)
+ goto done_restock;
+ if (!res_counter_charge(&memcg->memsw, size, &fail_res))
+ goto done_restock;
+ res_counter_uncharge(&memcg->res, size);
+ mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
+ flags |= MEM_CGROUP_RECLAIM_NOSWAP;
+ } else
+ mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
- /* If killed, bypass charge */
- if (fatal_signal_pending(current))
- goto bypass;
+ if (batch > nr_pages) {
+ batch = nr_pages;
+ goto retry;
+ }
- ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
- nr_pages, invoke_oom);
- switch (ret) {
- case CHARGE_OK:
- break;
- case CHARGE_RETRY: /* not in OOM situation but retry */
- batch = nr_pages;
- goto again;
- case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */
- goto nomem;
- case CHARGE_NOMEM: /* OOM routine works */
- if (!oom || invoke_oom)
- goto nomem;
- nr_oom_retries--;
- break;
- }
- } while (ret != CHARGE_OK);
+ if (!(gfp_mask & __GFP_WAIT))
+ goto nomem;
- if (batch > nr_pages)
- refill_stock(memcg, batch - nr_pages);
-done:
- return 0;
+ if (gfp_mask & __GFP_NORETRY)
+ goto nomem;
+
+ nr_reclaimed = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
+
+ if (mem_cgroup_margin(mem_over_limit) >= batch)
+ goto retry;
+ /*
+ * Even though the limit is exceeded at this point, reclaim
+ * may have been able to free some pages. Retry the charge
+ * before killing the task.
+ *
+ * Only for regular pages, though: huge pages are rather
+ * unlikely to succeed so close to the limit, and we fall back
+ * to regular pages anyway in case of failure.
+ */
+ if (nr_reclaimed && batch <= (1 << PAGE_ALLOC_COSTLY_ORDER))
+ goto retry;
+ /*
+ * At task move, charge accounts can be doubly counted. So, it's
+ * better to wait until the end of task_move if something is going on.
+ */
+ if (mem_cgroup_wait_acct_move(mem_over_limit))
+ goto retry;
+
+ if (fatal_signal_pending(current))
+ goto bypass;
+
+ if (!oom)
+ goto nomem;
+
+ if (nr_oom_retries--)
+ goto retry;
+
+ mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(batch));
nomem:
if (!(gfp_mask & __GFP_NOFAIL))
return -ENOMEM;
bypass:
return -EINTR;
+
+done_restock:
+ if (batch > nr_pages)
+ refill_stock(memcg, batch - nr_pages);
+done:
+ return 0;
}
/**