From: Andrea Arcangeli <aarcange@redhat.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Tim LaBerge <tim.laberge@quantum.com>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org
Subject: Re: Corruption with O_DIRECT and unaligned user buffers
Date: Sat, 20 Dec 2008 16:55:36 +0100 [thread overview]
Message-ID: <20081220155536.GD6383@random.random> (raw)
In-Reply-To: <20081219161911.dcf15331.kamezawa.hiroyu@jp.fujitsu.com>
On Fri, Dec 19, 2008 at 04:19:11PM +0900, KAMEZAWA Hiroyuki wrote:
> Result of cost-of-fork() on ia64.
> ==
> size of memory before after
> Anon=1M , 0.07ms, 0.08ms
> Anon=10M , 0.17ms, 0.22ms
> Anon=100M , 1.15ms, 1.64ms
> Anon=1000M , 11.5ms, 15.821ms
> ==
>
> fork() cost is 135% when the process has 1G of Anon.
Not sure where the 135% number comes from. The above number shows a
performance decrease of 27% or a time increase of 37% which I hope is
inline with the overhead introduced by the TestSetPageLocked in the
fast path (which I didn't expect to be so bad), but that it's almost
trivial to eliminate with a smb_wmb in add_to_swap_cache and a smb_rmb
in fork. So we'll need to repeat this measurement after replacing the
TestSetPageLocked with smb_rmb.
WARNING: multiple messages have this Message-ID (diff)
From: Andrea Arcangeli <aarcange@redhat.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Tim LaBerge <tim.laberge@quantum.com>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org
Subject: Re: Corruption with O_DIRECT and unaligned user buffers
Date: Sat, 20 Dec 2008 16:55:36 +0100 [thread overview]
Message-ID: <20081220155536.GD6383@random.random> (raw)
In-Reply-To: <20081219161911.dcf15331.kamezawa.hiroyu@jp.fujitsu.com>
On Fri, Dec 19, 2008 at 04:19:11PM +0900, KAMEZAWA Hiroyuki wrote:
> Result of cost-of-fork() on ia64.
> ==
> size of memory before after
> Anon=1M , 0.07ms, 0.08ms
> Anon=10M , 0.17ms, 0.22ms
> Anon=100M , 1.15ms, 1.64ms
> Anon=1000M , 11.5ms, 15.821ms
> ==
>
> fork() cost is 135% when the process has 1G of Anon.
Not sure where the 135% number comes from. The above number shows a
performance decrease of 27% or a time increase of 37% which I hope is
inline with the overhead introduced by the TestSetPageLocked in the
fast path (which I didn't expect to be so bad), but that it's almost
trivial to eliminate with a smb_wmb in add_to_swap_cache and a smb_rmb
in fork. So we'll need to repeat this measurement after replacing the
TestSetPageLocked with smb_rmb.
--
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:[~2008-12-20 15:55 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-11-14 17:04 Corruption with O_DIRECT and unaligned user buffers Tim LaBerge
2008-11-19 4:25 ` Nick Piggin
2008-11-19 4:25 ` Nick Piggin
2008-11-19 6:52 ` Nick Piggin
2008-11-19 6:52 ` Nick Piggin
2008-11-19 16:58 ` Andrea Arcangeli
2008-11-19 16:58 ` Andrea Arcangeli
2008-12-18 15:29 ` Andrea Arcangeli
2008-12-19 2:21 ` KAMEZAWA Hiroyuki
2008-12-19 5:06 ` KAMEZAWA Hiroyuki
2008-12-19 5:06 ` KAMEZAWA Hiroyuki
2008-12-19 6:34 ` KOSAKI Motohiro
2008-12-20 16:02 ` Andrea Arcangeli
2008-12-20 16:02 ` Andrea Arcangeli
2008-12-19 7:19 ` KAMEZAWA Hiroyuki
2008-12-19 7:44 ` Li Zefan
2008-12-19 8:45 ` Li Zefan
2008-12-19 8:45 ` Li Zefan
2008-12-19 20:27 ` Andrea Arcangeli
2008-12-19 20:27 ` Andrea Arcangeli
2008-12-20 15:55 ` Andrea Arcangeli [this message]
2008-12-20 15:55 ` Andrea Arcangeli
2008-12-19 11:51 ` Li Zefan
2008-12-19 11:51 ` Li Zefan
2008-12-19 12:14 ` KOSAKI Motohiro
2008-12-19 12:14 ` KOSAKI Motohiro
2008-12-19 12:58 ` Hugh Dickins
2008-12-19 20:34 ` Andrea Arcangeli
2008-12-19 20:34 ` Andrea Arcangeli
-- strict thread matches above, loose matches on Subject: below --
2014-06-27 2:08 Xiaoguang Wang
2014-07-01 4:18 ` Hugh Dickins
2014-07-02 11:39 ` Xiaoguang Wang
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=20081220155536.GD6383@random.random \
--to=aarcange@redhat.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nickpiggin@yahoo.com.au \
--cc=tim.laberge@quantum.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 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.