From: Johannes Weiner <hannes@cmpxchg.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm@kvack.org, netdev@vger.kernel.org,
cgroups@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH 10/14] mm: memcontrol: do not account memory+swap on unified hierarchy
Date: Tue, 8 Dec 2015 10:30:20 -0500 [thread overview]
Message-ID: <1449588624-9220-11-git-send-email-hannes@cmpxchg.org> (raw)
In-Reply-To: <1449588624-9220-1-git-send-email-hannes@cmpxchg.org>
The unified hierarchy memory controller doesn't expose the memory+swap
counter to userspace, but its accounting is hardcoded in all charge
paths right now, including the per-cpu charge cache ("the stock").
To avoid adding yet more pointless memory+swap accounting with the
socket memory support in unified hierarchy, disable the counter
altogether when in unified hierarchy mode.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: David S. Miller <davem@davemloft.net>
---
mm/memcontrol.c | 44 +++++++++++++++++++++++++-------------------
1 file changed, 25 insertions(+), 19 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0602bee..6b8c0f7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -87,6 +87,12 @@ int do_swap_account __read_mostly;
#define do_swap_account 0
#endif
+/* Whether legacy memory+swap accounting is active */
+static bool do_memsw_account(void)
+{
+ return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account;
+}
+
static const char * const mem_cgroup_stat_names[] = {
"cache",
"rss",
@@ -1177,7 +1183,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
if (count < limit)
margin = limit - count;
- if (do_swap_account) {
+ if (do_memsw_account()) {
count = page_counter_read(&memcg->memsw);
limit = READ_ONCE(memcg->memsw.limit);
if (count <= limit)
@@ -1280,7 +1286,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
pr_cont(":");
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
continue;
pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
K(mem_cgroup_read_stat(iter, i)));
@@ -1903,7 +1909,7 @@ static void drain_stock(struct memcg_stock_pcp *stock)
if (stock->nr_pages) {
page_counter_uncharge(&old->memory, stock->nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&old->memsw, stock->nr_pages);
css_put_many(&old->css, stock->nr_pages);
stock->nr_pages = 0;
@@ -2033,11 +2039,11 @@ retry:
if (consume_stock(memcg, nr_pages))
return 0;
- if (!do_swap_account ||
+ if (!do_memsw_account() ||
page_counter_try_charge(&memcg->memsw, batch, &counter)) {
if (page_counter_try_charge(&memcg->memory, batch, &counter))
goto done_restock;
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, batch);
mem_over_limit = mem_cgroup_from_counter(counter, memory);
} else {
@@ -2124,7 +2130,7 @@ force:
* temporarily by force charging it.
*/
page_counter_charge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_charge(&memcg->memsw, nr_pages);
css_get_many(&memcg->css, nr_pages);
@@ -2161,7 +2167,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
return;
page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
css_put_many(&memcg->css, nr_pages);
@@ -2447,7 +2453,7 @@ void __memcg_kmem_uncharge(struct page *page, int order)
page_counter_uncharge(&memcg->kmem, nr_pages);
page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
page->mem_cgroup = NULL;
@@ -3160,7 +3166,7 @@ static int memcg_stat_show(struct seq_file *m, void *v)
BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
- if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
continue;
seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
@@ -3182,14 +3188,14 @@ static int memcg_stat_show(struct seq_file *m, void *v)
}
seq_printf(m, "hierarchical_memory_limit %llu\n",
(u64)memory * PAGE_SIZE);
- if (do_swap_account)
+ if (do_memsw_account())
seq_printf(m, "hierarchical_memsw_limit %llu\n",
(u64)memsw * PAGE_SIZE);
for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
unsigned long long val = 0;
- if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+ if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
continue;
for_each_mem_cgroup_tree(mi, memcg)
val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
@@ -3320,7 +3326,7 @@ static void mem_cgroup_threshold(struct mem_cgroup *memcg)
{
while (memcg) {
__mem_cgroup_threshold(memcg, false);
- if (do_swap_account)
+ if (do_memsw_account())
__mem_cgroup_threshold(memcg, true);
memcg = parent_mem_cgroup(memcg);
@@ -4466,7 +4472,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
* we call find_get_page() with swapper_space directly.
*/
page = find_get_page(swap_address_space(ent), ent.val);
- if (do_swap_account)
+ if (do_memsw_account())
entry->val = ent.val;
return page;
@@ -4501,7 +4507,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
page = find_get_entry(mapping, pgoff);
if (radix_tree_exceptional_entry(page)) {
swp_entry_t swp = radix_to_swp_entry(page);
- if (do_swap_account)
+ if (do_memsw_account())
*entry = swp;
page = find_get_page(swap_address_space(swp), swp.val);
}
@@ -5276,7 +5282,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
if (page->mem_cgroup)
goto out;
- if (do_swap_account) {
+ if (do_memsw_account()) {
swp_entry_t ent = { .val = page_private(page), };
unsigned short id = lookup_swap_cgroup_id(ent);
@@ -5340,7 +5346,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
memcg_check_events(memcg, page);
local_irq_enable();
- if (do_swap_account && PageSwapCache(page)) {
+ if (do_memsw_account() && PageSwapCache(page)) {
swp_entry_t entry = { .val = page_private(page) };
/*
* The swap entry might not get freed for a long time,
@@ -5385,7 +5391,7 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
if (!mem_cgroup_is_root(memcg)) {
page_counter_uncharge(&memcg->memory, nr_pages);
- if (do_swap_account)
+ if (do_memsw_account())
page_counter_uncharge(&memcg->memsw, nr_pages);
memcg_oom_recover(memcg);
}
@@ -5593,7 +5599,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(page_count(page), page);
- if (!do_swap_account)
+ if (!do_memsw_account())
return;
memcg = page->mem_cgroup;
@@ -5633,7 +5639,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
struct mem_cgroup *memcg;
unsigned short id;
- if (!do_swap_account)
+ if (!do_memsw_account())
return;
id = swap_cgroup_record(entry, 0);
--
2.6.3
next prev parent reply other threads:[~2015-12-08 15:31 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-12-08 15:30 [PATCH 00/14] mm: memcontrol: account socket memory in unified hierarchy v4-RESEND Johannes Weiner
2015-12-08 15:30 ` [PATCH 01/14] mm: memcontrol: export root_mem_cgroup Johannes Weiner
2015-12-08 15:30 ` [PATCH 02/14] net: tcp_memcontrol: properly detect ancestor socket pressure Johannes Weiner
2015-12-08 15:30 ` [PATCH 03/14] net: tcp_memcontrol: remove bogus hierarchy pressure propagation Johannes Weiner
2015-12-08 15:30 ` [PATCH 04/14] net: tcp_memcontrol: protect all tcp_memcontrol calls by jump-label Johannes Weiner
2015-12-08 15:30 ` [PATCH 05/14] net: tcp_memcontrol: remove dead per-memcg count of allocated sockets Johannes Weiner
2015-12-08 15:30 ` [PATCH 06/14] net: tcp_memcontrol: simplify the per-memcg limit access Johannes Weiner
2015-12-08 15:30 ` [PATCH 07/14] net: tcp_memcontrol: sanitize tcp memory accounting callbacks Johannes Weiner
2015-12-08 15:30 ` [PATCH 08/14] net: tcp_memcontrol: simplify linkage between socket and page counter Johannes Weiner
2015-12-08 15:30 ` [PATCH 09/14] mm: memcontrol: generalize the socket accounting jump label Johannes Weiner
2015-12-08 15:30 ` Johannes Weiner [this message]
2015-12-08 15:30 ` [PATCH 11/14] mm: memcontrol: move socket code for unified hierarchy accounting Johannes Weiner
2015-12-08 15:30 ` [PATCH 12/14] mm: memcontrol: account socket memory in unified hierarchy memory controller Johannes Weiner
2015-12-15 19:50 ` Michal Hocko
2015-12-08 15:30 ` [PATCH 13/14] mm: memcontrol: hook up vmpressure to socket pressure Johannes Weiner
2015-12-08 15:30 ` [PATCH 14/14] mm: memcontrol: switch to the updated jump-label API Johannes Weiner
2015-12-08 16:28 ` David Miller
2015-12-08 16:28 ` [PATCH 00/14] mm: memcontrol: account socket memory in unified hierarchy v4-RESEND David Miller
2015-12-09 16:31 ` Arnd Bergmann
2015-12-09 16:32 ` [PATCH] mm: memcontrol: only manage socket pressure for CONFIG_INET Arnd Bergmann
2015-12-09 18:58 ` Johannes Weiner
2015-12-09 22:28 ` Andrew Morton
2015-12-09 23:05 ` Johannes Weiner
2015-12-09 23:13 ` Andrew Morton
2016-01-22 3:25 ` Masanari Iida
2015-12-09 16:32 ` [PATCH] mm: memcontrol: MEMCG no longer works with SLOB Arnd Bergmann
2015-12-09 20:01 ` Johannes Weiner
2015-12-09 21:03 ` Arnd Bergmann
2015-12-10 11:24 ` Vladimir Davydov
2015-12-09 18:17 ` [PATCH 00/14] mm: memcontrol: account socket memory in unified hierarchy v4-RESEND Johannes Weiner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1449588624-9220-11-git-send-email-hannes@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).