From: Rik van Riel <riel@redhat.com>
To: Michel Lespinasse <walken@google.com>
Cc: linux-mm@kvack.org,
Linus Torvalds <torvalds@linux-foundation.org>,
Ying Han <yinghan@google.com>,
linux-kernel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Nick Piggin <npiggin@kernel.dk>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH 2/3] Retry page fault when blocking on disk transfer.
Date: Tue, 05 Oct 2010 13:38:21 -0400 [thread overview]
Message-ID: <4CAB628D.3030205@redhat.com> (raw)
In-Reply-To: <1286265215-9025-3-git-send-email-walken@google.com>
On 10/05/2010 03:53 AM, Michel Lespinasse wrote:
> This change reduces mmap_sem hold times that are caused by waiting for
> disk transfers when accessing file mapped VMAs. It introduces the
> VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants
> mmap_sem to be released if blocking on a pending disk transfer.
> In that case, filemap_fault() returns the VM_FAULT_RETRY status bit
> and do_page_fault() will then re-acquire mmap_sem and retry the page fault.
> It is expected that the retry will hit the same page which will now be
> cached, and thus it will complete with a low mmap_sem hold time.
>
> Signed-off-by: Michel Lespinasse<walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Looks like it should be relatively easy to do something
similar in do_swap_page also.
WARNING: multiple messages have this Message-ID (diff)
From: Rik van Riel <riel@redhat.com>
To: Michel Lespinasse <walken@google.com>
Cc: linux-mm@kvack.org,
Linus Torvalds <torvalds@linux-foundation.org>,
Ying Han <yinghan@google.com>,
linux-kernel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Nick Piggin <npiggin@kernel.dk>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH 2/3] Retry page fault when blocking on disk transfer.
Date: Tue, 05 Oct 2010 13:38:21 -0400 [thread overview]
Message-ID: <4CAB628D.3030205@redhat.com> (raw)
In-Reply-To: <1286265215-9025-3-git-send-email-walken@google.com>
On 10/05/2010 03:53 AM, Michel Lespinasse wrote:
> This change reduces mmap_sem hold times that are caused by waiting for
> disk transfers when accessing file mapped VMAs. It introduces the
> VM_FAULT_ALLOW_RETRY flag, which indicates that the call site wants
> mmap_sem to be released if blocking on a pending disk transfer.
> In that case, filemap_fault() returns the VM_FAULT_RETRY status bit
> and do_page_fault() will then re-acquire mmap_sem and retry the page fault.
> It is expected that the retry will hit the same page which will now be
> cached, and thus it will complete with a low mmap_sem hold time.
>
> Signed-off-by: Michel Lespinasse<walken@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Looks like it should be relatively easy to do something
similar in do_swap_page also.
--
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:[~2010-10-05 17:39 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-05 7:53 [PATCH 0/3] V2: Reduce mmap_sem hold times during file backed page faults Michel Lespinasse
2010-10-05 7:53 ` Michel Lespinasse
2010-10-05 7:53 ` [PATCH 1/3] filemap_fault: unique path for locking page Michel Lespinasse
2010-10-05 7:53 ` Michel Lespinasse
2010-10-05 17:07 ` Rik van Riel
2010-10-05 17:07 ` Rik van Riel
2010-10-05 7:53 ` [PATCH 2/3] Retry page fault when blocking on disk transfer Michel Lespinasse
2010-10-05 7:53 ` Michel Lespinasse
2010-10-05 17:33 ` Linus Torvalds
2010-10-05 17:33 ` Linus Torvalds
2010-10-05 17:38 ` Rik van Riel [this message]
2010-10-05 17:38 ` Rik van Riel
2010-10-05 22:44 ` Michel Lespinasse
2010-10-05 22:44 ` Michel Lespinasse
2010-10-08 4:39 ` Michel Lespinasse
2010-10-08 4:39 ` Michel Lespinasse
2010-10-08 13:24 ` Rik van Riel
2010-10-08 13:24 ` Rik van Riel
2010-10-08 20:06 ` Michel Lespinasse
2010-10-08 20:06 ` Michel Lespinasse
2010-10-09 1:22 ` Michel Lespinasse
2010-10-09 1:22 ` Michel Lespinasse
2010-10-11 22:25 ` Andrew Morton
2010-10-11 22:25 ` Andrew Morton
2010-10-11 22:43 ` Michel Lespinasse
2010-10-11 22:43 ` Michel Lespinasse
2010-10-13 23:17 ` Andrew Morton
2010-10-13 23:17 ` Andrew Morton
2010-11-02 20:05 ` Michel Lespinasse
2010-11-02 20:11 ` Rik van Riel
2010-10-06 4:02 ` H. Peter Anvin
2010-10-06 4:02 ` H. Peter Anvin
2010-10-05 7:53 ` [PATCH 3/3] access_error API cleanup Michel Lespinasse
2010-10-05 7:53 ` Michel Lespinasse
2010-10-05 19:44 ` Rik van Riel
2010-10-05 19:44 ` Rik van Riel
2010-10-06 4:02 ` H. Peter Anvin
2010-10-06 4:02 ` H. Peter Anvin
2010-10-06 4:14 ` Michel Lespinasse
2010-10-06 4:14 ` Michel Lespinasse
2010-10-06 4:18 ` Andrew Morton
2010-10-06 4:18 ` Andrew Morton
2010-10-06 4:20 ` H. Peter Anvin
2010-10-06 4:20 ` H. Peter Anvin
2010-10-05 14:55 ` [PATCH 0/3] V2: Reduce mmap_sem hold times during file backed page faults Rik van Riel
2010-10-05 14:55 ` Rik van Riel
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=4CAB628D.3030205@redhat.com \
--to=riel@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=npiggin@kernel.dk \
--cc=peterz@infradead.org \
--cc=torvalds@linux-foundation.org \
--cc=walken@google.com \
--cc=yinghan@google.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.