From: Arun Sharma <asharma@fb.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Balbir Singh <bsingharora@gmail.com>,
akpm@linux-foundation.org
Subject: Re: [PATCH] mm: Enable MAP_UNINITIALIZED for archs with mmu
Date: Tue, 24 Jan 2012 17:45:28 -0800 [thread overview]
Message-ID: <4F1F5EB8.3000407@fb.com> (raw)
In-Reply-To: <20120124120704.3f09b206.kamezawa.hiroyu@jp.fujitsu.com>
On 1/23/12 7:07 PM, KAMEZAWA Hiroyuki wrote:
> You can see reduction of clear_page() cost by removing GFP_ZERO but
> what's your application's total performance ? Is it good enough considering
> many risks ?
I see 90k calls/sec to clear_page_c when running our application. I
don't have data on the impact of GFP_ZERO alone, but an earlier
experiment when we tuned malloc to not call madvise(MADV_DONTNEED)
aggressively saved us 3% CPU. So I'm expecting this to be a 1-2% win.
But not calling madvise() increases our RSS and increases the risk of OOM.
Agree with your analysis that removing the cache misses at clear_page()
is not always a win, since it moves the misses to the code where the app
first touches the data.
-Arun
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Arun Sharma <asharma@fb.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org>,
Balbir Singh <bsingharora@gmail.com>, <akpm@linux-foundation.org>
Subject: Re: [PATCH] mm: Enable MAP_UNINITIALIZED for archs with mmu
Date: Tue, 24 Jan 2012 17:45:28 -0800 [thread overview]
Message-ID: <4F1F5EB8.3000407@fb.com> (raw)
In-Reply-To: <20120124120704.3f09b206.kamezawa.hiroyu@jp.fujitsu.com>
On 1/23/12 7:07 PM, KAMEZAWA Hiroyuki wrote:
> You can see reduction of clear_page() cost by removing GFP_ZERO but
> what's your application's total performance ? Is it good enough considering
> many risks ?
I see 90k calls/sec to clear_page_c when running our application. I
don't have data on the impact of GFP_ZERO alone, but an earlier
experiment when we tuned malloc to not call madvise(MADV_DONTNEED)
aggressively saved us 3% CPU. So I'm expecting this to be a 1-2% win.
But not calling madvise() increases our RSS and increases the risk of OOM.
Agree with your analysis that removing the cache misses at clear_page()
is not always a win, since it moves the misses to the code where the app
first touches the data.
-Arun
next prev parent reply other threads:[~2012-01-25 1:45 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-01-18 18:51 [PATCH] mm: Enable MAP_UNINITIALIZED for archs with mmu Arun Sharma
2012-01-18 18:51 ` Arun Sharma
2012-01-19 2:42 ` KAMEZAWA Hiroyuki
2012-01-19 2:42 ` KAMEZAWA Hiroyuki
2012-01-24 0:54 ` Arun Sharma
2012-01-24 0:54 ` Arun Sharma
2012-01-24 3:07 ` KAMEZAWA Hiroyuki
2012-01-24 3:07 ` KAMEZAWA Hiroyuki
2012-01-25 1:45 ` Arun Sharma [this message]
2012-01-25 1:45 ` Arun Sharma
2012-02-22 0:34 ` Arun Sharma
2012-02-22 0:34 ` Arun Sharma
2012-02-23 7:45 ` Balbir Singh
2012-02-23 7:45 ` Balbir Singh
2012-02-23 18:42 ` Arun Sharma
2012-02-23 18:42 ` Arun Sharma
2012-02-24 2:47 ` KAMEZAWA Hiroyuki
2012-02-24 2:47 ` KAMEZAWA Hiroyuki
2012-02-24 14:51 ` Balbir Singh
2012-02-24 14:51 ` Balbir Singh
2012-02-24 19:11 ` Arun Sharma
2012-02-24 19:11 ` Arun Sharma
2012-02-25 4:13 ` Balbir Singh
2012-02-25 4:13 ` Balbir Singh
2012-02-27 18:32 ` Arun Sharma
2012-02-27 18:32 ` Arun Sharma
2012-02-24 19:26 ` Arun Sharma
2012-02-24 19:26 ` Arun Sharma
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=4F1F5EB8.3000407@fb.com \
--to=asharma@fb.com \
--cc=akpm@linux-foundation.org \
--cc=bsingharora@gmail.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.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 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.