From: Andi Kleen <andi@firstfloor.org>
To: Sage Weil <sage@newdream.net>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>,
linux-fsdevel@vger.kernel.org, Andi Kleen <andi@firstfloor.org>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 08/19] ceph: address space operations
Date: Fri, 24 Jul 2009 08:56:03 +0200 [thread overview]
Message-ID: <20090724065603.GA2045@basil.fritz.box> (raw)
In-Reply-To: <Pine.LNX.4.64.0907231642590.2930@cobra.newdream.net>
> The part I don't understand is what actually happens to pages after the
> error flag set. They're still uptodate, but no longer dirty? And can be
> overwritten/redirtied? There's also an error flag on the address_space.
> Are there any guidelines as far as which should be used?
Ideally both. The Page error flag prevents the data from being
consumed and the address space error flag makes sure errors are
getting reported on fsync()/close() etc. Also AS error is useful when
you don't have a clear page to assign the error to, e.g. if you
get an error indication that's not tied to a read operation.
BTW the upcoming hwpoison code can set such errors asynchronously
under you.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2009-07-24 6:56 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-22 19:51 [PATCH 00/19] ceph: Ceph distributed file system client v0.11 Sage Weil
2009-07-22 19:51 ` [PATCH 01/19] ceph: documentation Sage Weil
2009-07-22 19:51 ` [PATCH 02/19] ceph: on-wire types Sage Weil
2009-07-22 19:51 ` [PATCH 03/19] ceph: client types Sage Weil
2009-07-22 19:51 ` [PATCH 04/19] ceph: super.c Sage Weil
2009-07-22 19:51 ` [PATCH 05/19] ceph: inode operations Sage Weil
2009-07-22 19:51 ` [PATCH 06/19] ceph: directory operations Sage Weil
2009-07-22 19:51 ` [PATCH 07/19] ceph: file operations Sage Weil
2009-07-22 19:51 ` [PATCH 08/19] ceph: address space operations Sage Weil
2009-07-22 19:51 ` [PATCH 09/19] ceph: MDS client Sage Weil
2009-07-22 19:51 ` [PATCH 10/19] ceph: OSD client Sage Weil
2009-07-22 19:51 ` [PATCH 11/19] ceph: CRUSH mapping algorithm Sage Weil
2009-07-22 19:51 ` [PATCH 12/19] ceph: monitor client Sage Weil
2009-07-22 19:51 ` [PATCH 13/19] ceph: capability management Sage Weil
2009-07-22 19:51 ` [PATCH 14/19] ceph: snapshot management Sage Weil
2009-07-22 19:51 ` [PATCH 15/19] ceph: messenger library Sage Weil
2009-07-22 19:51 ` [PATCH 16/19] ceph: nfs re-export support Sage Weil
2009-07-22 19:51 ` [PATCH 17/19] ceph: ioctls Sage Weil
2009-07-22 19:51 ` [PATCH 18/19] ceph: debugfs Sage Weil
2009-07-22 19:51 ` [PATCH 19/19] ceph: Kconfig, Makefile Sage Weil
2009-07-25 5:31 ` [PATCH 18/19] ceph: debugfs Greg KH
2009-07-27 17:06 ` Sage Weil
2009-07-22 22:39 ` [PATCH 17/19] ceph: ioctls Andi Kleen
2009-07-22 23:52 ` Sage Weil
2009-07-23 6:24 ` Andi Kleen
2009-07-23 18:42 ` Sage Weil
2009-07-23 10:25 ` [PATCH 08/19] ceph: address space operations Andi Kleen
2009-07-23 18:22 ` Sage Weil
2009-07-23 19:16 ` Andi Kleen
2009-07-24 4:48 ` Sage Weil
2009-07-23 19:17 ` Andi Kleen
2009-07-23 18:26 ` Sage Weil
2009-07-23 18:47 ` Trond Myklebust
2009-07-24 4:44 ` Sage Weil
2009-07-24 6:56 ` Andi Kleen [this message]
2009-07-24 16:52 ` Sage Weil
2009-07-24 19:40 ` J. Bruce Fields
-- strict thread matches above, loose matches on Subject: below --
2009-08-05 22:30 [PATCH 00/19] ceph distributed file system client Sage Weil
2009-08-05 22:30 ` [PATCH 01/19] ceph: documentation Sage Weil
2009-08-05 22:30 ` [PATCH 02/19] ceph: on-wire types Sage Weil
2009-08-05 22:30 ` [PATCH 03/19] ceph: client types Sage Weil
2009-08-05 22:30 ` [PATCH 04/19] ceph: super.c Sage Weil
2009-08-05 22:30 ` [PATCH 05/19] ceph: inode operations Sage Weil
2009-08-05 22:30 ` [PATCH 06/19] ceph: directory operations Sage Weil
2009-08-05 22:30 ` [PATCH 07/19] ceph: file operations Sage Weil
2009-08-05 22:30 ` [PATCH 08/19] ceph: address space operations Sage Weil
2008-11-14 0:55 [PATCH 00/19] ceph: Ceph distributed file system client Sage Weil
2008-11-14 0:56 ` [PATCH 01/19] ceph: documentation Sage Weil
2008-11-14 0:56 ` [PATCH 02/19] ceph: on-wire types Sage Weil
2008-11-14 0:56 ` [PATCH 03/19] ceph: client types Sage Weil
2008-11-14 0:56 ` [PATCH 04/19] ceph: super.c Sage Weil
2008-11-14 0:56 ` [PATCH 05/19] ceph: inode operations Sage Weil
2008-11-14 0:56 ` [PATCH 06/19] ceph: directory operations Sage Weil
2008-11-14 0:56 ` [PATCH 07/19] ceph: file operations Sage Weil
2008-11-14 0:56 ` [PATCH 08/19] ceph: address space operations Sage Weil
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=20090724065603.GA2045@basil.fritz.box \
--to=andi@firstfloor.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=sage@newdream.net \
--cc=trond.myklebust@fys.uio.no \
/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).