From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Andrea Arcangeli <aarcange@redhat.com>
Cc: linux-mm@kvack.org, Marcelo Tosatti <mtosatti@redhat.com>,
Adam Litke <agl@us.ibm.com>, Avi Kivity <avi@redhat.com>,
Izik Eidus <ieidus@redhat.com>,
Hugh Dickins <hugh.dickins@tiscali.co.uk>,
Nick Piggin <npiggin@suse.de>, Rik van Riel <riel@redhat.com>,
Mel Gorman <mel@csn.ul.ie>, Andi Kleen <andi@firstfloor.org>,
Dave Hansen <dave@linux.vnet.ibm.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Ingo Molnar <mingo@elte.hu>, Mike Travis <travis@sgi.com>,
Christoph Lameter <cl@linux-foundation.org>,
Chris Wright <chrisw@sous-sol.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 27 of 30] memcg compound
Date: Thu, 21 Jan 2010 16:07:59 +0900 [thread overview]
Message-ID: <20100121160759.3dcad6ae.kamezawa.hiroyu@jp.fujitsu.com> (raw)
In-Reply-To: <2f3ecb53039bd9ae8c7a.1264054851@v2.random>
On Thu, 21 Jan 2010 07:20:51 +0100
Andrea Arcangeli <aarcange@redhat.com> wrote:
> From: Andrea Arcangeli <aarcange@redhat.com>
>
> Teach memcg to charge/uncharge compound pages.
>
> Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
I'm sorry but I'm glad if you don't touch fast path.
if (likely(page_size == PAGE_SIZE))
if (consume_stock(mem))
goto charged;
is my recommendation.
Bye.
-Kame
> ---
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1288,15 +1288,20 @@ static atomic_t memcg_drain_count;
> * cgroup which is not current target, returns false. This stock will be
> * refilled.
> */
> -static bool consume_stock(struct mem_cgroup *mem)
> +static bool consume_stock(struct mem_cgroup *mem, int *page_size)
> {
> struct memcg_stock_pcp *stock;
> bool ret = true;
>
> stock = &get_cpu_var(memcg_stock);
> - if (mem == stock->cached && stock->charge)
> - stock->charge -= PAGE_SIZE;
> - else /* need to call res_counter_charge */
> + if (mem == stock->cached && stock->charge) {
> + if (*page_size > stock->charge) {
> + *page_size -= stock->charge;
> + stock->charge = 0;
> + ret = false;
> + } else
> + stock->charge -= *page_size;
> + } else /* need to call res_counter_charge */
> ret = false;
> put_cpu_var(memcg_stock);
> return ret;
> @@ -1401,13 +1406,13 @@ static int __cpuinit memcg_stock_cpu_cal
> * oom-killer can be invoked.
> */
> static int __mem_cgroup_try_charge(struct mm_struct *mm,
> - gfp_t gfp_mask, struct mem_cgroup **memcg,
> - bool oom, struct page *page)
> + gfp_t gfp_mask, struct mem_cgroup **memcg,
> + bool oom, struct page *page, int page_size)
> {
> struct mem_cgroup *mem, *mem_over_limit;
> int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
> struct res_counter *fail_res;
> - int csize = CHARGE_SIZE;
> + int csize = max(page_size, (int) CHARGE_SIZE);
>
> if (unlikely(test_thread_flag(TIF_MEMDIE))) {
> /* Don't account this! */
> @@ -1439,7 +1444,7 @@ static int __mem_cgroup_try_charge(struc
> int ret = 0;
> unsigned long flags = 0;
>
> - if (consume_stock(mem))
> + if (consume_stock(mem, &page_size))
> goto charged;
>
> ret = res_counter_charge(&mem->res, csize, &fail_res);
> @@ -1460,8 +1465,8 @@ static int __mem_cgroup_try_charge(struc
> res);
>
> /* reduce request size and retry */
> - if (csize > PAGE_SIZE) {
> - csize = PAGE_SIZE;
> + if (csize > page_size) {
> + csize = page_size;
> continue;
> }
> if (!(gfp_mask & __GFP_WAIT))
> @@ -1491,8 +1496,8 @@ static int __mem_cgroup_try_charge(struc
> goto nomem;
> }
> }
> - if (csize > PAGE_SIZE)
> - refill_stock(mem, csize - PAGE_SIZE);
> + if (csize > page_size)
> + refill_stock(mem, csize - page_size);
> charged:
> /*
> * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
> @@ -1512,12 +1517,12 @@ nomem:
> * This function is for that and do uncharge, put css's refcnt.
> * gotten by try_charge().
> */
> -static void mem_cgroup_cancel_charge(struct mem_cgroup *mem)
> +static void mem_cgroup_cancel_charge(struct mem_cgroup *mem, int page_size)
> {
> if (!mem_cgroup_is_root(mem)) {
> - res_counter_uncharge(&mem->res, PAGE_SIZE);
> + res_counter_uncharge(&mem->res, page_size);
> if (do_swap_account)
> - res_counter_uncharge(&mem->memsw, PAGE_SIZE);
> + res_counter_uncharge(&mem->memsw, page_size);
> }
> css_put(&mem->css);
> }
> @@ -1575,8 +1580,9 @@ struct mem_cgroup *try_get_mem_cgroup_fr
> */
>
> static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
> - struct page_cgroup *pc,
> - enum charge_type ctype)
> + struct page_cgroup *pc,
> + enum charge_type ctype,
> + int page_size)
> {
> /* try_charge() can return NULL to *memcg, taking care of it. */
> if (!mem)
> @@ -1585,7 +1591,7 @@ static void __mem_cgroup_commit_charge(s
> lock_page_cgroup(pc);
> if (unlikely(PageCgroupUsed(pc))) {
> unlock_page_cgroup(pc);
> - mem_cgroup_cancel_charge(mem);
> + mem_cgroup_cancel_charge(mem, page_size);
> return;
> }
>
> @@ -1722,7 +1728,8 @@ static int mem_cgroup_move_parent(struct
> goto put;
>
> parent = mem_cgroup_from_cont(pcg);
> - ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page);
> + ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page,
> + PAGE_SIZE);
> if (ret || !parent)
> goto put_back;
>
> @@ -1730,7 +1737,7 @@ static int mem_cgroup_move_parent(struct
> if (!ret)
> css_put(&parent->css); /* drop extra refcnt by try_charge() */
> else
> - mem_cgroup_cancel_charge(parent); /* does css_put */
> + mem_cgroup_cancel_charge(parent, PAGE_SIZE); /* does css_put */
> put_back:
> putback_lru_page(page);
> put:
> @@ -1752,6 +1759,11 @@ static int mem_cgroup_charge_common(stru
> struct mem_cgroup *mem;
> struct page_cgroup *pc;
> int ret;
> + int page_size = PAGE_SIZE;
> +
> + VM_BUG_ON(PageTail(page));
> + if (PageHead(page))
> + page_size <<= compound_order(page);
>
> pc = lookup_page_cgroup(page);
> /* can happen at boot */
> @@ -1760,11 +1772,12 @@ static int mem_cgroup_charge_common(stru
> prefetchw(pc);
>
> mem = memcg;
> - ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page);
> + ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page,
> + page_size);
> if (ret || !mem)
> return ret;
>
> - __mem_cgroup_commit_charge(mem, pc, ctype);
> + __mem_cgroup_commit_charge(mem, pc, ctype, page_size);
> return 0;
> }
>
> @@ -1773,8 +1786,6 @@ int mem_cgroup_newpage_charge(struct pag
> {
> if (mem_cgroup_disabled())
> return 0;
> - if (PageCompound(page))
> - return 0;
> /*
> * If already mapped, we don't have to account.
> * If page cache, page->mapping has address_space.
> @@ -1787,7 +1798,7 @@ int mem_cgroup_newpage_charge(struct pag
> if (unlikely(!mm))
> mm = &init_mm;
> return mem_cgroup_charge_common(page, mm, gfp_mask,
> - MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
> + MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
> }
>
> static void
> @@ -1880,14 +1891,14 @@ int mem_cgroup_try_charge_swapin(struct
> if (!mem)
> goto charge_cur_mm;
> *ptr = mem;
> - ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page);
> + ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page, PAGE_SIZE);
> /* drop extra refcnt from tryget */
> css_put(&mem->css);
> return ret;
> charge_cur_mm:
> if (unlikely(!mm))
> mm = &init_mm;
> - return __mem_cgroup_try_charge(mm, mask, ptr, true, page);
> + return __mem_cgroup_try_charge(mm, mask, ptr, true, page, PAGE_SIZE);
> }
>
> static void
> @@ -1903,7 +1914,7 @@ __mem_cgroup_commit_charge_swapin(struct
> cgroup_exclude_rmdir(&ptr->css);
> pc = lookup_page_cgroup(page);
> mem_cgroup_lru_del_before_commit_swapcache(page);
> - __mem_cgroup_commit_charge(ptr, pc, ctype);
> + __mem_cgroup_commit_charge(ptr, pc, ctype, PAGE_SIZE);
> mem_cgroup_lru_add_after_commit_swapcache(page);
> /*
> * Now swap is on-memory. This means this page may be
> @@ -1952,11 +1963,12 @@ void mem_cgroup_cancel_charge_swapin(str
> return;
> if (!mem)
> return;
> - mem_cgroup_cancel_charge(mem);
> + mem_cgroup_cancel_charge(mem, PAGE_SIZE);
> }
>
> static void
> -__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
> +__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype,
> + int page_size)
> {
> struct memcg_batch_info *batch = NULL;
> bool uncharge_memsw = true;
> @@ -1989,14 +2001,14 @@ __do_uncharge(struct mem_cgroup *mem, co
> if (batch->memcg != mem)
> goto direct_uncharge;
> /* remember freed charge and uncharge it later */
> - batch->bytes += PAGE_SIZE;
> + batch->bytes += page_size;
> if (uncharge_memsw)
> - batch->memsw_bytes += PAGE_SIZE;
> + batch->memsw_bytes += page_size;
> return;
> direct_uncharge:
> - res_counter_uncharge(&mem->res, PAGE_SIZE);
> + res_counter_uncharge(&mem->res, page_size);
> if (uncharge_memsw)
> - res_counter_uncharge(&mem->memsw, PAGE_SIZE);
> + res_counter_uncharge(&mem->memsw, page_size);
> return;
> }
>
> @@ -2009,6 +2021,11 @@ __mem_cgroup_uncharge_common(struct page
> struct page_cgroup *pc;
> struct mem_cgroup *mem = NULL;
> struct mem_cgroup_per_zone *mz;
> + int page_size = PAGE_SIZE;
> +
> + VM_BUG_ON(PageTail(page));
> + if (PageHead(page))
> + page_size <<= compound_order(page);
>
> if (mem_cgroup_disabled())
> return NULL;
> @@ -2016,6 +2033,8 @@ __mem_cgroup_uncharge_common(struct page
> if (PageSwapCache(page))
> return NULL;
>
> + VM_BUG_ON(PageTail(page));
> +
> /*
> * Check if our page_cgroup is valid
> */
> @@ -2048,7 +2067,7 @@ __mem_cgroup_uncharge_common(struct page
> }
>
> if (!mem_cgroup_is_root(mem))
> - __do_uncharge(mem, ctype);
> + __do_uncharge(mem, ctype, page_size);
> if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
> mem_cgroup_swap_statistics(mem, true);
> mem_cgroup_charge_statistics(mem, pc, false);
> @@ -2217,7 +2236,7 @@ int mem_cgroup_prepare_migration(struct
>
> if (mem) {
> ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false,
> - page);
> + page, PAGE_SIZE);
> css_put(&mem->css);
> }
> *ptr = mem;
> @@ -2260,7 +2279,7 @@ void mem_cgroup_end_migration(struct mem
> * __mem_cgroup_commit_charge() check PCG_USED bit of page_cgroup.
> * So, double-counting is effectively avoided.
> */
> - __mem_cgroup_commit_charge(mem, pc, ctype);
> + __mem_cgroup_commit_charge(mem, pc, ctype, PAGE_SIZE);
>
> /*
> * Both of oldpage and newpage are still under lock_page().
>
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@kvack.org. For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2010-01-21 7:11 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-21 6:20 [PATCH 00 of 30] Transparent Hugepage support #3 Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 01 of 30] define MADV_HUGEPAGE Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 02 of 30] compound_lock Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 03 of 30] alter compound get_page/put_page Andrea Arcangeli
2010-01-21 17:35 ` Dave Hansen
2010-01-23 17:39 ` Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 04 of 30] clear compound mapping Andrea Arcangeli
2010-01-21 17:43 ` Dave Hansen
2010-01-23 17:55 ` Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 05 of 30] add native_set_pmd_at Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 06 of 30] add pmd paravirt ops Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 07 of 30] no paravirt version of pmd ops Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 08 of 30] export maybe_mkwrite Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 09 of 30] comment reminder in destroy_compound_page Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 10 of 30] config_transparent_hugepage Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 11 of 30] add pmd mangling functions to x86 Andrea Arcangeli
2010-01-21 17:47 ` Dave Hansen
2010-01-21 19:14 ` Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 12 of 30] add pmd mangling generic functions Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 13 of 30] special pmd_trans_* functions Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 14 of 30] bail out gup_fast on splitting pmd Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 15 of 30] pte alloc trans splitting Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 16 of 30] add pmd mmu_notifier helpers Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 17 of 30] clear page compound Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 18 of 30] add pmd_huge_pte to mm_struct Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 19 of 30] ensure mapcount is taken on head pages Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 20 of 30] split_huge_page_mm/vma Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 21 of 30] split_huge_page paging Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 22 of 30] pmd_trans_huge migrate bugcheck Andrea Arcangeli
2010-01-21 20:40 ` Christoph Lameter
2010-01-21 23:01 ` Andrea Arcangeli
2010-01-21 23:17 ` Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 23 of 30] clear_copy_huge_page Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 24 of 30] kvm mmu transparent hugepage support Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 25 of 30] transparent hugepage core Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 26 of 30] madvise(MADV_HUGEPAGE) Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 27 of 30] memcg compound Andrea Arcangeli
2010-01-21 7:07 ` KAMEZAWA Hiroyuki [this message]
2010-01-21 15:44 ` Andrea Arcangeli
2010-01-21 23:55 ` KAMEZAWA Hiroyuki
2010-01-21 6:20 ` [PATCH 28 of 30] memcg huge memory Andrea Arcangeli
2010-01-21 7:16 ` KAMEZAWA Hiroyuki
2010-01-21 16:08 ` Andrea Arcangeli
2010-01-22 0:13 ` KAMEZAWA Hiroyuki
2010-01-27 11:27 ` Balbir Singh
2010-01-28 0:50 ` Daisuke Nishimura
2010-01-28 11:39 ` Andrea Arcangeli
2010-01-28 12:23 ` Balbir Singh
2010-01-28 12:36 ` Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 29 of 30] transparent hugepage vmstat Andrea Arcangeli
2010-01-21 6:20 ` [PATCH 30 of 30] khugepaged Andrea Arcangeli
2010-01-22 14:46 ` [PATCH 00 of 30] Transparent Hugepage support #3 Christoph Lameter
2010-01-22 15:19 ` Andrea Arcangeli
2010-01-22 16:51 ` Christoph Lameter
2010-01-23 17:58 ` Andrea Arcangeli
2010-01-25 21:50 ` Christoph Lameter
2010-01-25 22:46 ` Andrea Arcangeli
2010-01-26 15:47 ` Christoph Lameter
2010-01-26 16:11 ` Andrea Arcangeli
2010-01-26 16:30 ` Christoph Lameter
2010-01-26 16:45 ` Andrea Arcangeli
2010-01-26 18:23 ` Christoph Lameter
2010-01-26 17:09 ` Avi Kivity
2010-01-26 0:52 ` Rik van Riel
2010-01-26 6:53 ` Gleb Natapov
2010-01-26 12:35 ` Andrea Arcangeli
2010-01-26 15:55 ` Christoph Lameter
2010-01-26 16:19 ` Andrea Arcangeli
2010-01-26 15:54 ` Christoph Lameter
2010-01-26 16:16 ` Andrea Arcangeli
2010-01-26 16:24 ` Andi Kleen
2010-01-26 16:37 ` Christoph Lameter
2010-01-26 16:42 ` Mel Gorman
2010-01-26 16:52 ` Andrea Arcangeli
2010-01-26 17:26 ` Mel Gorman
2010-01-26 19:46 ` Andrea Arcangeli
2010-01-26 23:07 ` Rik van Riel
2010-01-27 18:33 ` Christoph Lameter
2010-01-26 11:24 ` Mel Gorman
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=20100121160759.3dcad6ae.kamezawa.hiroyu@jp.fujitsu.com \
--to=kamezawa.hiroyu@jp.fujitsu.com \
--cc=aarcange@redhat.com \
--cc=agl@us.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=andi@firstfloor.org \
--cc=avi@redhat.com \
--cc=benh@kernel.crashing.org \
--cc=chrisw@sous-sol.org \
--cc=cl@linux-foundation.org \
--cc=dave@linux.vnet.ibm.com \
--cc=hugh.dickins@tiscali.co.uk \
--cc=ieidus@redhat.com \
--cc=linux-mm@kvack.org \
--cc=mel@csn.ul.ie \
--cc=mingo@elte.hu \
--cc=mtosatti@redhat.com \
--cc=npiggin@suse.de \
--cc=riel@redhat.com \
--cc=travis@sgi.com \
/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