From: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: linux-mm@kvack.org, "balbir@linux.vnet.ibm.com" <balbir@linux.vnet.ibm.com>, gthelen@google.com, m-ikeda@ds.jp.nec.com, "akpm@linux-foundation.org" <akpm@linux-foundation.org>, "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>, kamezawa.hiroyuki@gmail.com, Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Subject: Re: [PATCH] memcg: use ID in page_cgroup Date: Mon, 23 Aug 2010 14:32:37 +0900 [thread overview] Message-ID: <20100823143237.b7822ffc.nishimura@mxp.nes.nec.co.jp> (raw) In-Reply-To: <20100820190132.43684862.kamezawa.hiroyu@jp.fujitsu.com> On Fri, 20 Aug 2010 19:01:32 +0900 KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote: > > I have an idea to remove page_cgroup->page pointer, 8bytes reduction per page. > But it will be after this work. Another off topic. I think we can reduce the size of mem_cgroup by packing some boolean members into one "unsinged long flags". > @@ -300,12 +300,13 @@ static atomic_t mem_cgroup_num; > #define NR_MEMCG_GROUPS (CONFIG_MEM_CGROUP_MAX_GROUPS + 1) > static struct mem_cgroup *mem_cgroups[NR_MEMCG_GROUPS] __read_mostly; > > -/* Must be called under rcu_read_lock */ > -static struct mem_cgroup *id_to_memcg(unsigned short id) > +/* Must be called under rcu_read_lock, set safe==true if under lock */ Do you mean, "Set safe==true if we can ensure by some locks that the id can be safely dereferenced without rcu_read_lock", right ? > +static struct mem_cgroup *id_to_memcg(unsigned short id, bool safe) > { > struct mem_cgroup *ret; > /* see mem_cgroup_free() */ > - ret = rcu_dereference_check(mem_cgroups[id], rch_read_lock_held()); > + ret = rcu_dereference_check(mem_cgroups[id], > + rch_read_lock_held() || safe); > if (likely(ret && ret->valid)) > return ret; > return NULL; (snip) > @@ -723,6 +729,11 @@ static inline bool mem_cgroup_is_root(st > return (mem == root_mem_cgroup); > } > > +static inline bool mem_cgroup_is_rootid(unsigned short id) > +{ > + return (id == 1); > +} > + It might be better to add BUG_ON(newid->id != 1) in cgroup.c::cgroup_init_idr(). Thanks, Daisuke Nishimura.
WARNING: multiple messages have this Message-ID (diff)
From: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: linux-mm@kvack.org, "balbir@linux.vnet.ibm.com" <balbir@linux.vnet.ibm.com>, gthelen@google.com, m-ikeda@ds.jp.nec.com, "akpm@linux-foundation.org" <akpm@linux-foundation.org>, "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>, kamezawa.hiroyuki@gmail.com, Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Subject: Re: [PATCH] memcg: use ID in page_cgroup Date: Mon, 23 Aug 2010 14:32:37 +0900 [thread overview] Message-ID: <20100823143237.b7822ffc.nishimura@mxp.nes.nec.co.jp> (raw) In-Reply-To: <20100820190132.43684862.kamezawa.hiroyu@jp.fujitsu.com> On Fri, 20 Aug 2010 19:01:32 +0900 KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote: > > I have an idea to remove page_cgroup->page pointer, 8bytes reduction per page. > But it will be after this work. Another off topic. I think we can reduce the size of mem_cgroup by packing some boolean members into one "unsinged long flags". > @@ -300,12 +300,13 @@ static atomic_t mem_cgroup_num; > #define NR_MEMCG_GROUPS (CONFIG_MEM_CGROUP_MAX_GROUPS + 1) > static struct mem_cgroup *mem_cgroups[NR_MEMCG_GROUPS] __read_mostly; > > -/* Must be called under rcu_read_lock */ > -static struct mem_cgroup *id_to_memcg(unsigned short id) > +/* Must be called under rcu_read_lock, set safe==true if under lock */ Do you mean, "Set safe==true if we can ensure by some locks that the id can be safely dereferenced without rcu_read_lock", right ? > +static struct mem_cgroup *id_to_memcg(unsigned short id, bool safe) > { > struct mem_cgroup *ret; > /* see mem_cgroup_free() */ > - ret = rcu_dereference_check(mem_cgroups[id], rch_read_lock_held()); > + ret = rcu_dereference_check(mem_cgroups[id], > + rch_read_lock_held() || safe); > if (likely(ret && ret->valid)) > return ret; > return NULL; (snip) > @@ -723,6 +729,11 @@ static inline bool mem_cgroup_is_root(st > return (mem == root_mem_cgroup); > } > > +static inline bool mem_cgroup_is_rootid(unsigned short id) > +{ > + return (id == 1); > +} > + It might be better to add BUG_ON(newid->id != 1) in cgroup.c::cgroup_init_idr(). Thanks, Daisuke Nishimura. -- 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:[~2010-08-23 5:52 UTC|newest] Thread overview: 87+ messages / expand[flat|nested] mbox.gz Atom feed top 2010-08-20 9:55 [PATCH] memcg: towards I/O aware memcg v5 KAMEZAWA Hiroyuki 2010-08-20 9:55 ` KAMEZAWA Hiroyuki 2010-08-20 9:58 ` [PATCH 1/5] cgroup: ID notification call back KAMEZAWA Hiroyuki 2010-08-20 9:58 ` KAMEZAWA Hiroyuki 2010-08-24 7:19 ` Greg Thelen 2010-08-24 7:19 ` Greg Thelen 2010-08-24 7:18 ` KAMEZAWA Hiroyuki 2010-08-24 7:18 ` KAMEZAWA Hiroyuki 2010-08-24 9:04 ` Li Zefan 2010-08-24 9:04 ` Li Zefan 2010-08-24 23:58 ` KAMEZAWA Hiroyuki 2010-08-24 23:58 ` KAMEZAWA Hiroyuki 2010-08-25 0:11 ` Paul Menage 2010-08-25 0:11 ` Paul Menage 2010-08-25 0:17 ` KAMEZAWA Hiroyuki 2010-08-25 0:17 ` KAMEZAWA Hiroyuki 2010-08-25 0:25 ` Paul Menage 2010-08-25 0:25 ` Paul Menage 2010-08-25 0:09 ` Paul Menage 2010-08-25 0:09 ` Paul Menage 2010-08-25 0:20 ` KAMEZAWA Hiroyuki 2010-08-25 0:20 ` KAMEZAWA Hiroyuki 2010-08-25 0:34 ` Paul Menage 2010-08-25 0:34 ` Paul Menage 2010-08-25 0:37 ` KAMEZAWA Hiroyuki 2010-08-25 0:37 ` KAMEZAWA Hiroyuki 2010-08-25 0:46 ` Paul Menage 2010-08-25 0:46 ` Paul Menage 2010-08-25 1:03 ` KAMEZAWA Hiroyuki 2010-08-25 1:03 ` KAMEZAWA Hiroyuki 2010-08-25 1:35 ` Paul Menage 2010-08-25 1:35 ` Paul Menage 2010-08-25 1:42 ` KAMEZAWA Hiroyuki 2010-08-25 1:42 ` KAMEZAWA Hiroyuki 2010-08-25 1:52 ` Paul Menage 2010-08-25 1:52 ` Paul Menage 2010-08-25 2:29 ` KAMEZAWA Hiroyuki 2010-08-25 2:29 ` KAMEZAWA Hiroyuki 2010-08-20 9:59 ` [PATCH 2/5] memcg: use array and ID for quick look up KAMEZAWA Hiroyuki 2010-08-20 9:59 ` KAMEZAWA Hiroyuki 2010-08-23 3:35 ` Daisuke Nishimura 2010-08-23 3:35 ` Daisuke Nishimura 2010-08-23 23:51 ` KAMEZAWA Hiroyuki 2010-08-23 23:51 ` KAMEZAWA Hiroyuki 2010-08-24 0:19 ` Daisuke Nishimura 2010-08-24 0:19 ` Daisuke Nishimura 2010-08-24 7:44 ` Greg Thelen 2010-08-24 7:44 ` Greg Thelen 2010-08-24 7:42 ` KAMEZAWA Hiroyuki 2010-08-24 7:42 ` KAMEZAWA Hiroyuki 2010-08-20 10:01 ` [PATCH] memcg: use ID in page_cgroup KAMEZAWA Hiroyuki 2010-08-20 10:01 ` KAMEZAWA Hiroyuki 2010-08-20 10:05 ` KAMEZAWA Hiroyuki 2010-08-23 5:32 ` Daisuke Nishimura [this message] 2010-08-23 5:32 ` Daisuke Nishimura 2010-08-23 23:52 ` KAMEZAWA Hiroyuki 2010-08-23 23:52 ` KAMEZAWA Hiroyuki 2010-08-24 1:14 ` Daisuke Nishimura 2010-08-24 1:14 ` Daisuke Nishimura 2010-08-24 1:54 ` KAMEZAWA Hiroyuki 2010-08-24 1:54 ` KAMEZAWA Hiroyuki 2010-08-24 4:04 ` Daisuke Nishimura 2010-08-24 4:04 ` Daisuke Nishimura 2010-08-24 6:05 ` KAMEZAWA Hiroyuki 2010-08-24 6:05 ` KAMEZAWA Hiroyuki 2010-08-24 7:47 ` Greg Thelen 2010-08-24 7:47 ` Greg Thelen 2010-08-24 7:51 ` KAMEZAWA Hiroyuki 2010-08-24 7:51 ` KAMEZAWA Hiroyuki 2010-08-24 8:35 ` Greg Thelen 2010-08-24 8:35 ` Greg Thelen 2010-08-24 8:38 ` KAMEZAWA Hiroyuki 2010-08-24 8:38 ` KAMEZAWA Hiroyuki 2010-08-20 10:02 ` [PATCH 4/5] memcg: lockless update of file_mapped KAMEZAWA Hiroyuki 2010-08-20 10:02 ` KAMEZAWA Hiroyuki 2010-08-23 8:50 ` Daisuke Nishimura 2010-08-23 8:50 ` Daisuke Nishimura 2010-08-23 23:49 ` KAMEZAWA Hiroyuki 2010-08-23 23:49 ` KAMEZAWA Hiroyuki 2010-08-24 0:19 ` Daisuke Nishimura 2010-08-24 0:19 ` Daisuke Nishimura 2010-08-20 10:03 ` [PATCH 5/5] memcg: generic file accounting update function KAMEZAWA Hiroyuki 2010-08-20 10:03 ` KAMEZAWA Hiroyuki 2010-08-24 7:46 ` [PATCH] memcg: towards I/O aware memcg v5 Balbir Singh 2010-08-24 7:46 ` Balbir Singh 2010-08-24 7:59 ` KAMEZAWA Hiroyuki 2010-08-24 7:59 ` KAMEZAWA Hiroyuki
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=20100823143237.b7822ffc.nishimura@mxp.nes.nec.co.jp \ --to=nishimura@mxp.nes.nec.co.jp \ --cc=akpm@linux-foundation.org \ --cc=balbir@linux.vnet.ibm.com \ --cc=gthelen@google.com \ --cc=kamezawa.hiroyu@jp.fujitsu.com \ --cc=kamezawa.hiroyuki@gmail.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=m-ikeda@ds.jp.nec.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.