| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20090828135342.276ac003.kamezawa.hiroyu@jp.fujitsu.com>
Date: Fri, 28 Aug 2009 13:53:42 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc: "linux-mm@...ck.org" <linux-mm@...ck.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"balbir@...ux.vnet.ibm.com" <balbir@...ux.vnet.ibm.com>,
"nishimura@....nes.nec.co.jp" <nishimura@....nes.nec.co.jp>
Subject: Re: [RFC][PATCH 2/5] memcg: uncharge in batched manner
On Fri, 28 Aug 2009 13:24:38 +0900
KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com> wrote:
>
> In massive parallel enviroment, res_counter can be a performance bottleneck.
> This patch is a trial for reducing lock contention.
> One strong techinque to reduce lock contention is reducing calls by
> batching some amount of calls int one.
>
> Considering charge/uncharge chatacteristic,
> - charge is done one by one via demand-paging.
> - uncharge is done by
> - in chunk at munmap, truncate, exit, execve...
> - one by one via vmscan/paging.
>
> It seems we hace a chance to batched-uncharge.
> This patch is a base patch for batched uncharge. For avoiding
> scattering memcg's structure, this patch adds memcg batch uncharge
> information to the task. please see start/end usage in next patch.
>
> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
> ---
> include/linux/memcontrol.h | 12 +++++++
> include/linux/sched.h | 7 ++++
> mm/memcontrol.c | 70 +++++++++++++++++++++++++++++++++++++++++----
> 3 files changed, 83 insertions(+), 6 deletions(-)
>
> Index: mmotm-2.6.31-Aug27/include/linux/memcontrol.h
> ===================================================================
> --- mmotm-2.6.31-Aug27.orig/include/linux/memcontrol.h
> +++ mmotm-2.6.31-Aug27/include/linux/memcontrol.h
> @@ -54,6 +54,10 @@ extern void mem_cgroup_rotate_lru_list(s
> extern void mem_cgroup_del_lru(struct page *page);
> extern void mem_cgroup_move_lists(struct page *page,
> enum lru_list from, enum lru_list to);
> +
> +extern void mem_cgroup_uncharge_batch_start(void);
> +extern void mem_cgroup_uncharge_batch_end(void);
> +
> extern void mem_cgroup_uncharge_page(struct page *page);
> extern void mem_cgroup_uncharge_cache_page(struct page *page);
> extern int mem_cgroup_shmem_charge_fallback(struct page *page,
> @@ -151,6 +155,14 @@ static inline void mem_cgroup_cancel_cha
> {
> }
>
> +static inline void mem_cgroup_uncharge_batch_start(void)
> +{
> +}
> +
> +static inline void mem_cgroup_uncharge_batch_start(void)
> +{
> +}
> +
> static inline void mem_cgroup_uncharge_page(struct page *page)
> {
> }
> Index: mmotm-2.6.31-Aug27/mm/memcontrol.c
> ===================================================================
> --- mmotm-2.6.31-Aug27.orig/mm/memcontrol.c
> +++ mmotm-2.6.31-Aug27/mm/memcontrol.c
> @@ -1837,7 +1837,35 @@ void mem_cgroup_cancel_charge_swapin(str
> css_put(&mem->css);
> }
>
> +static bool
> +__do_batch_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
> +{
> + struct memcg_batch_info *batch = NULL;
> + bool uncharge_memsw;
> + /* If swapout, usage of swap doesn't decrease */
> + if (do_swap_account && (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
> + uncharge_memsw = false;
> + else
> + uncharge_memsw = true;
>
> + if (current->memcg_batch.do_batch) {
> + batch = ¤t->memcg_batch;
> + if (batch->memcg == NULL) {
> + batch->memcg = mem;
> + css_get(&mem->css);
> + }
> + }
> + if (!batch || batch->memcg != mem) {
> + res_counter_uncharge(&mem->res, PAGE_SIZE);
> + if (uncharge_memsw)
> + res_counter_uncharge(&mem->memsw, PAGE_SIZE);
> + } else {
> + batch->pages += PAGE_SIZE;
> + if (uncharge_memsw)
> + batch->memsw += PAGE_SIZE;
> + }
> + return soft_limit_excess;
> +}
> /*
> * uncharge if !page_mapped(page)
> */
> @@ -1886,12 +1914,8 @@ __mem_cgroup_uncharge_common(struct page
> break;
> }
>
> - if (!mem_cgroup_is_root(mem)) {
> - res_counter_uncharge(&mem->res, PAGE_SIZE);
> - if (do_swap_account &&
> - (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
> - res_counter_uncharge(&mem->memsw, PAGE_SIZE);
> - }
> + if (!mem_cgroup_is_root(mem))
> + __do_batch_uncharge(mem, ctype);
> if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
> mem_cgroup_swap_statistics(mem, true);
> mem_cgroup_charge_statistics(mem, pc, false);
> @@ -1938,6 +1962,40 @@ void mem_cgroup_uncharge_cache_page(stru
> __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
> }
>
> +void mem_cgroup_uncharge_batch_start(void)
> +{
> + VM_BUG_ON(current->memcg_batch.do_batch);
> + /* avoid batch if killed by OOM */
> + if (test_thread_flag(TIF_MEMDIE))
> + return;
> + current->memcg_batch.do_batch = 1;
> + current->memcg_batch.memcg = NULL;
> + current->memcg_batch.pages = 0;
> + current->memcg_batch.memsw = 0;
> +}
> +
> +void mem_cgroup_uncharge_batch_end(void)
> +{
> + struct mem_cgroup *mem;
> +
> + if (!current->memcg_batch.do_batch)
> + return;
> +
> + current->memcg_batch.do_batch = 0;
> +
> + mem = current->memcg_batch.memcg;
> + if (!mem)
> + return;
> + if (current->memcg_batch.pages)
> + res_counter_uncharge(&mem->res,
> + current->memcg_batch.pages, NULL);
> + if (current->memcg_batch.memsw)
> + res_counter_uncharge(&mem->memsw,
> + current->memcg_batch.memsw, NULL);
quilt refresh miss....above 2 NULL are unnecesary.
sorry,
-Kame
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists