From: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
To: Steve French <smfrench-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Cc: Jeff Layton <jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
Suresh Jayaraman <sjayaraman-l3A5Bk7waGM@public.gmane.org>,
linux-cifs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [PATCH 13/15] cifs: convert cifsFileInfo->count to non-atomic counter
Date: Thu, 7 Oct 2010 14:05:44 -0400 [thread overview]
Message-ID: <20101007180544.GA18764@lst.de> (raw)
In-Reply-To: <AANLkTi=MMzU6nr6+19PKW=gPKTdk9e-O5pjrYWmbV4AJ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Thu, Oct 07, 2010 at 10:37:54AM -0500, Steve French wrote:
>
> I doubt that a spinlock vs. a rwlock makes much difference,
> but a rwlock lock for list insertion/removal seems more intuitive
> and overloading it to also protect a counter adds complexity.
> Seems more natural to leave it as an atomic counter.
The rwlock here is rather non-sensical. A shared/exclusie lock only
makes sense if the critical section is large enough to actually
benefit from concurrency. With a short critical section like here
you still pay the same price in terms of cache line effects, and
operations on rwlocks actually are more expensive than on a normal
spinlock. We don't actually hae a lot of places where the plain
rwlock makes any sense at all - if there's enough reason for concurreny
you're better off doing RCU locking anyway.
next prev parent reply other threads:[~2010-10-07 18:05 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-10-06 19:54 [PATCH 00/15] cifs: clean up management of open filehandle (try #2) Jeff Layton
[not found] ` <1286394857-32541-1-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2010-10-06 19:54 ` [PATCH 01/15] cifs: keep dentry reference in cifsFileInfo instead of inode reference Jeff Layton
2010-10-06 19:54 ` [PATCH 02/15] cifs: don't use vfsmount to pin superblock for oplock breaks Jeff Layton
2010-10-06 19:54 ` [PATCH 03/15] cifs: eliminate cifs_posix_open_inode_helper Jeff Layton
2010-10-06 19:54 ` [PATCH 04/15] cifs: eliminate oflags option from cifs_new_fileinfo Jeff Layton
2010-10-06 19:54 ` [PATCH 05/15] cifs: eliminate the inode argument " Jeff Layton
2010-10-06 19:54 ` [PATCH 06/15] cifs: clean up cifs_reopen_file Jeff Layton
2010-10-06 19:54 ` [PATCH 07/15] cifs: cifs_write argument change and cleanup Jeff Layton
2010-10-06 19:54 ` [PATCH 08/15] cifs: eliminate pfile pointer from cifsFileInfo Jeff Layton
2010-10-06 19:54 ` [PATCH 09/15] cifs: move cifs_new_fileinfo to file.c Jeff Layton
2010-10-06 19:54 ` [PATCH 10/15] cifs: rename GlobalSMBSeslock to cifs_file_list_lock Jeff Layton
2010-10-06 19:54 ` [PATCH 11/15] cifs: move cifsFileInfo_put to file.c Jeff Layton
2010-10-06 19:54 ` [PATCH 12/15] cifs: move close processing from cifs_close to cifsFileInfo_put Jeff Layton
[not found] ` <1286394857-32541-13-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2010-10-07 7:07 ` Suresh Jayaraman
[not found] ` <4CAD71A7.20808-l3A5Bk7waGM@public.gmane.org>
2010-10-07 11:07 ` Jeff Layton
[not found] ` <20101007070726.0ef1b1a8-xSBYVWDuneFaJnirhKH9O4GKTjYczspe@public.gmane.org>
2010-10-08 9:34 ` Suresh Jayaraman
2010-10-06 19:54 ` [PATCH 13/15] cifs: convert cifsFileInfo->count to non-atomic counter Jeff Layton
[not found] ` <1286394857-32541-14-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2010-10-07 8:48 ` Suresh Jayaraman
[not found] ` <4CAD8972.9090406-l3A5Bk7waGM@public.gmane.org>
2010-10-07 11:18 ` Jeff Layton
[not found] ` <20101007071819.2446312b-xSBYVWDuneFaJnirhKH9O4GKTjYczspe@public.gmane.org>
2010-10-07 12:12 ` Suresh Jayaraman
[not found] ` <4CADB949.2070205-l3A5Bk7waGM@public.gmane.org>
2010-10-07 12:43 ` Jeff Layton
[not found] ` <20101007084334.0e03f586-xSBYVWDuneFaJnirhKH9O4GKTjYczspe@public.gmane.org>
2010-10-07 15:37 ` Steve French
[not found] ` <AANLkTi=MMzU6nr6+19PKW=gPKTdk9e-O5pjrYWmbV4AJ-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-10-07 16:59 ` Jeff Layton
[not found] ` <20101007125932.4506f3e6-xSBYVWDuneFaJnirhKH9O4GKTjYczspe@public.gmane.org>
2010-10-07 17:42 ` Jeff Layton
2010-10-07 18:05 ` Christoph Hellwig [this message]
2010-10-06 19:54 ` [PATCH 14/15] cifs: wait for writeback to complete in cifs_flush Jeff Layton
2010-10-06 19:54 ` [PATCH 15/15] cifs: eliminate cifsInodeInfo->write_behind_rc Jeff Layton
2010-10-08 9:40 ` [PATCH 00/15] cifs: clean up management of open filehandle (try #2) Suresh Jayaraman
-- strict thread matches above, loose matches on Subject: below --
2010-10-08 17:30 [PATCH 00/15] cifs: clean up management of open filehandle (try #3) Jeff Layton
[not found] ` <1286559072-29032-1-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2010-10-08 17:31 ` [PATCH 13/15] cifs: convert cifsFileInfo->count to non-atomic counter Jeff Layton
[not found] ` <1286559072-29032-14-git-send-email-jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2010-10-11 5:46 ` Suresh Jayaraman
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=20101007180544.GA18764@lst.de \
--to=hch-jcswghmuv9g@public.gmane.org \
--cc=jlayton-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=linux-cifs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=sjayaraman-l3A5Bk7waGM@public.gmane.org \
--cc=smfrench-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.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.