summaryrefslogtreecommitdiff
path: root/mm/filemap.c
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2014-08-09 01:19:20 +0400
committerLinus Torvalds <torvalds@linux-foundation.org>2014-08-09 02:57:17 +0400
commit00501b531c4723972aa11d6d4ebcf8d6552007c8 (patch)
treeb3ad4850d58f137cf87b8424412d962fb251839f /mm/filemap.c
parent4449a51a7c281602d3a385044ab928322a122a02 (diff)
downloadlinux-00501b531c4723972aa11d6d4ebcf8d6552007c8.tar.xz
mm: memcontrol: rewrite charge API
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 4): The memcg charge API charges pages before they are rmapped - i.e. have an actual "type" - and so every callsite needs its own set of charge and uncharge functions to know what type is being operated on. Worse, uncharge has to happen from a context that is still type-specific, rather than at the end of the page's lifetime with exclusive access, and so requires a lot of synchronization. Rewrite the charge API to provide a generic set of try_charge(), commit_charge() and cancel_charge() transaction operations, much like what's currently done for swap-in: mem_cgroup_try_charge() attempts to reserve a charge, reclaiming pages from the memcg if necessary. mem_cgroup_commit_charge() commits the page to the charge once it has a valid page->mapping and PageAnon() reliably tells the type. mem_cgroup_cancel_charge() aborts the transaction. This reduces the charge API and enables subsequent patches to drastically simplify uncharging. As pages need to be committed after rmap is established but before they are added to the LRU, page_add_new_anon_rmap() must stop doing LRU additions again. Revive lru_cache_add_active_or_unevictable(). [hughd@google.com: fix shmem_unuse] [hughd@google.com: Add comments on the private use of -EAGAIN] Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@suse.cz> Cc: Tejun Heo <tj@kernel.org> Cc: Vladimir Davydov <vdavydov@parallels.com> Signed-off-by: Hugh Dickins <hughd@google.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/filemap.c')
-rw-r--r--mm/filemap.c21
1 files changed, 15 insertions, 6 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index af19a6b079f5..349a40e35545 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -31,6 +31,7 @@
#include <linux/security.h>
#include <linux/cpuset.h>
#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
+#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/cleancache.h>
#include <linux/rmap.h>
@@ -548,19 +549,24 @@ static int __add_to_page_cache_locked(struct page *page,
pgoff_t offset, gfp_t gfp_mask,
void **shadowp)
{
+ int huge = PageHuge(page);
+ struct mem_cgroup *memcg;
int error;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapBacked(page), page);
- error = mem_cgroup_charge_file(page, current->mm,
- gfp_mask & GFP_RECLAIM_MASK);
- if (error)
- return error;
+ if (!huge) {
+ error = mem_cgroup_try_charge(page, current->mm,
+ gfp_mask, &memcg);
+ if (error)
+ return error;
+ }
error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
if (error) {
- mem_cgroup_uncharge_cache_page(page);
+ if (!huge)
+ mem_cgroup_cancel_charge(page, memcg);
return error;
}
@@ -575,13 +581,16 @@ static int __add_to_page_cache_locked(struct page *page,
goto err_insert;
__inc_zone_page_state(page, NR_FILE_PAGES);
spin_unlock_irq(&mapping->tree_lock);
+ if (!huge)
+ mem_cgroup_commit_charge(page, memcg, false);
trace_mm_filemap_add_to_page_cache(page);
return 0;
err_insert:
page->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
spin_unlock_irq(&mapping->tree_lock);
- mem_cgroup_uncharge_cache_page(page);
+ if (!huge)
+ mem_cgroup_cancel_charge(page, memcg);
page_cache_release(page);
return error;
}