From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: linux-mm@kvack.org, Sudhir Kumar <skumar@linux.vnet.ibm.com>,
YAMAMOTO Takashi <yamamoto@valinux.co.jp>,
Bharata B Rao <bharata@in.ibm.com>,
Paul Menage <menage@google.com>,
lizf@cn.fujitsu.com, linux-kernel@vger.kernel.org,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
David Rientjes <rientjes@google.com>,
Pavel Emelianov <xemul@openvz.org>,
Dhaval Giani <dhaval@linux.vnet.ibm.com>,
Rik van Riel <riel@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 0/4] Memory controller soft limit patches (v3)
Date: Mon, 2 Mar 2009 11:35:19 +0530 [thread overview]
Message-ID: <20090302060519.GG11421@balbir.in.ibm.com> (raw)
In-Reply-To: <20090302143250.f47758f9.kamezawa.hiroyu@jp.fujitsu.com>
* KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> [2009-03-02 14:32:50]:
> On Mon, 2 Mar 2009 10:10:43 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
>
> > * KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> [2009-03-02 09:24:04]:
> >
> > > On Sun, 01 Mar 2009 11:59:59 +0530
> > > Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
> > >
> > > >
> > > > From: Balbir Singh <balbir@linux.vnet.ibm.com>
>
> > >
> > > At first, it's said "When cgroup people adds something, the kernel gets slow".
> > > This is my start point of reviewing. Below is comments to this version of patch.
> > >
> > > 1. I think it's bad to add more hooks to res_counter. It's enough slow to give up
> > > adding more fancy things..
> >
> > res_counters was desgined to be extensible, why is adding anything to
> > it going to make it slow, unless we turn on soft_limits?
> >
> You inserted new "if" logic in the core loop.
> (What I want to say here is not that this is definitely bad but that "isn't there
> any alternatives which is less overhead.)
>
>
> > >
> > > 2. please avoid to add hooks to hot-path. In your patch, especially a hook to
> > > mem_cgroup_uncharge_common() is annoying me.
> >
> > If soft limits are not enabled, the function does a small check and
> > leaves.
> >
> &soft_fail_res is passed always even if memory.soft_limit==ULONG_MAX
> res_counter_soft_limit_excess() adds one more function call and spinlock, and irq-off.
>
OK, I see that overhead.. I'll figure out a way to work around it.
> > >
> > > 3. please avoid to use global spinlock more.
> > > no lock is best. mutex is better, maybe.
> > >
> >
> > No lock to update a tree which is update concurrently?
> >
> Using tree/sort itself is nonsense, I believe.
>
I tried using prio trees in the past, but they are not easy to update
either. I won't mind asking for suggestions for a data structure that
can scaled well, allow quick insert/delete and search.
>
> > > 4. RB-tree seems broken. Following is example. (please note you do all ops
> > > in lazy manner (once in HZ/4.)
> > >
> > > i). while running, the tree is constructed as following
> > >
> > > R R=exceed=300M
> > > / \
> > > A B A=exceed=200M B=exceed=400M
> > > ii) A process B exits, but and usage goes down.
> >
> > That is why we have the hook in uncharge. Even if we update and the
> > usage goes down, the tree is ordered by usage_in_excess which is
> > updated only when the tree is updated. So what you show below does not
> > occur. I think I should document the design better.
> >
>
> time_check==true. So, update-tree at uncharge() only happens once in HZ/4
No.. you are missing the point
==
if (updated_tree) {
spin_lock_irqsave(&memcg_soft_limit_tree_lock, flags);
mem->last_tree_update = jiffies;
mem->usage_in_excess = new_usage_in_excess;
spin_unlock_irqrestore(&memcg_soft_limit_tree_lock,
flags);
}
==
mem->usage_in_excess is the key for the RB-Tree and is updated only
when the tree is updated.
> ==
> @@ -1422,6 +1520,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
> mz = page_cgroup_zoneinfo(pc);
> unlock_page_cgroup(pc);
>
> + mem_cgroup_check_and_update_tree(mem, true);
> /* at swapout, this memcg will be accessed to record to swap */
> if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
> css_put(&mem->css);
> ==
> Then, not-sorted RB-tree can be there.
>
> BTW,
> time_after(jiffies, 0)
> is buggy (see definition). If you want make this true always,
> time_after(jiffies, jiffies +1)
>
HZ/4 is 250/4 jiffies in the worst case (62). We have
time_after(jiffies, next_update_interval) and next_update_interval is
set to last_tree_update + 62. Not sure if I got what you are pointing
to.
--
Balbir
next prev parent reply other threads:[~2009-03-02 6:05 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-01 6:29 [PATCH 0/4] Memory controller soft limit patches (v3) Balbir Singh
2009-03-01 6:30 ` [PATCH 1/4] Memory controller soft limit documentation (v3) Balbir Singh
2009-03-01 6:30 ` [PATCH 2/4] Memory controller soft limit interface (v3) Balbir Singh
2009-03-02 2:03 ` KAMEZAWA Hiroyuki
2009-03-02 4:46 ` Balbir Singh
2009-03-02 5:35 ` KAMEZAWA Hiroyuki
2009-03-02 6:07 ` Balbir Singh
2009-03-02 6:19 ` KAMEZAWA Hiroyuki
2009-03-02 6:29 ` Balbir Singh
2009-03-01 6:30 ` [PATCH 3/4] Memory controller soft limit organize cgroups (v3) Balbir Singh
2009-03-01 6:30 ` [PATCH 4/4] Memory controller soft limit reclaim on contention (v3) Balbir Singh
2009-03-02 3:08 ` KOSAKI Motohiro
2009-03-02 4:44 ` Balbir Singh
2009-03-03 2:43 ` KOSAKI Motohiro
2009-03-03 11:17 ` Balbir Singh
2009-03-04 0:07 ` KOSAKI Motohiro
2009-03-02 0:24 ` [PATCH 0/4] Memory controller soft limit patches (v3) KAMEZAWA Hiroyuki
2009-03-02 4:40 ` Balbir Singh
2009-03-02 5:32 ` KAMEZAWA Hiroyuki
2009-03-02 6:05 ` Balbir Singh [this message]
2009-03-02 6:18 ` KAMEZAWA Hiroyuki
2009-03-02 17:52 ` Balbir Singh
2009-03-03 0:03 ` KAMEZAWA Hiroyuki
2009-03-03 11:23 ` Balbir Singh
2009-03-02 6:21 ` KAMEZAWA Hiroyuki
2009-03-02 6:36 ` Balbir Singh
2009-03-02 7:06 ` KAMEZAWA Hiroyuki
2009-03-02 7:17 ` KAMEZAWA Hiroyuki
2009-03-02 12:42 ` Balbir Singh
2009-03-02 14:04 ` KAMEZAWA Hiroyuki
2009-03-02 17:41 ` Balbir Singh
2009-03-02 23:59 ` KAMEZAWA Hiroyuki
2009-03-03 11:12 ` Balbir Singh
2009-03-03 11:50 ` KAMEZAWA Hiroyuki
2009-03-03 13:14 ` Balbir Singh
2009-03-05 9:04 ` KAMEZAWA Hiroyuki
2009-03-05 9:13 ` KAMEZAWA Hiroyuki
2009-03-05 15:26 ` Balbir Singh
2009-03-05 23:53 ` KAMEZAWA Hiroyuki
2009-03-06 3:23 ` 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=20090302060519.GG11421@balbir.in.ibm.com \
--to=balbir@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=bharata@in.ibm.com \
--cc=dhaval@linux.vnet.ibm.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizf@cn.fujitsu.com \
--cc=menage@google.com \
--cc=riel@redhat.com \
--cc=rientjes@google.com \
--cc=skumar@linux.vnet.ibm.com \
--cc=xemul@openvz.org \
--cc=yamamoto@valinux.co.jp \
/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).