linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ric Wheeler <rwheeler@redhat.com>
To: Dave Chinner <david@fromorbit.com>
Cc: "Loke, Chetan" <Chetan.Loke@netscout.com>,
	Tom Coughlan <coughlan@redhat.com>,
	Hannes Reinecke <hare@suse.de>,
	tasleson@redhat.com, Shyam_Iyer@Dell.com, vgoyal@redhat.com,
	linux-fsdevel@vger.kernel.org, linux-scsi@vger.kernel.org
Subject: Re: [LSF/MM TOPIC] linux servers as a storage server - what'smissing?
Date: Thu, 26 Jan 2012 17:29:02 -0500	[thread overview]
Message-ID: <4F21D3AE.80806@redhat.com> (raw)
In-Reply-To: <20120126222428.GX15102@dastard>

On 01/26/2012 05:24 PM, Dave Chinner wrote:
> On Tue, Jan 24, 2012 at 12:05:23PM -0500, Loke, Chetan wrote:
>>>> But writes that have to fetch the non-cached data, will
>> unnecessarily
>>>> issue I/O to the fabric. These orphaned I/O's cause more pain in the
>>>> cleanup.
>>>> And if caching is enabled on the front-side then it's all the more
>>>> painful.
>>>>
>>>> We can go one extra step and make FS fail read I/O for non-cached
>> data
>>>> too to avoid more orphan IOs.
>>> I don't really see this as a useful state. Read-only without a real
>>> backing file
>>> system or LUN is hit or miss, that file system should go offline :)
>>>
>> Last year when I checked, I forget but I think xfs(or ext4) was going
>> read-only.
>> If this is still the case then you are basically asking FS's to modify
>> that behavior.
> ext4 goes read only on erro by default. I think that behaviour can
> be changed by a mount option.
>
> XFS shuts the filesystem down (takes it offline) preventing all
> dirty data and metadata from being issued to disk, aborts any
> journal IO that might be going on, etc. It the returns fatal errors
> (EIO or EUCLEAN "structure needs cleaning" errors) to all callers
> that attempt to write or modify the filesystem, and EIO to all
> attempts to read from it.
>
> IOWs, the XFS filesystem is *gone* once it shuts down and requires
> administrator intervention to get it back to a working state....
>
> Cheers,
>
> Dave.

If it isn't obvious, I like the XFS approach :)

Ric


  reply	other threads:[~2012-01-26 22:29 UTC|newest]

Thread overview: 41+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-21 15:59 [LSF/MM TOPIC] linux servers as a storage server - what's missing? Ric Wheeler
2011-12-22  8:14 ` Shyam_Iyer
2011-12-22 15:58   ` Vivek Goyal
2011-12-22 20:54     ` Shyam_Iyer
2011-12-23  3:06       ` Vivek Goyal
2011-12-23  4:35         ` Shyam_Iyer
2012-01-09 12:18       ` Hannes Reinecke
2012-01-09 12:59         ` Tom Coughlan
2012-01-10  6:53           ` Ric Wheeler
2012-01-20  8:55             ` Hannes Reinecke
2012-01-19 16:17           ` [LSF/MM TOPIC] linux servers as a storage server - what'smissing? Loke, Chetan
2012-01-19 16:19             ` Ric Wheeler
2012-01-19 16:26               ` Loke, Chetan
2012-01-19 16:29                 ` Ric Wheeler
2012-01-19 17:32                   ` Loke, Chetan
2012-01-19 17:44                     ` Ric Wheeler
2012-01-19 21:30                       ` Loke, Chetan
2012-01-19 21:39                         ` Ric Wheeler
2012-01-24 17:05                           ` Loke, Chetan
2012-01-24 18:13                             ` Ric Wheeler
2012-01-26 22:24                             ` Dave Chinner
2012-01-26 22:29                               ` Ric Wheeler [this message]
2012-01-03 19:26 ` [LSF/MM TOPIC][ATTEND] linux servers as a storage server - what's missing? Jeff Layton
2012-01-03 19:32   ` Chuck Lever
2012-01-17 21:16     ` J. Bruce Fields
2012-01-17 21:25       ` Chuck Lever
2012-01-24 21:36   ` J. Bruce Fields
2012-01-24 23:13     ` Ric Wheeler
2012-01-25 19:05       ` Christopher R. Hertel
2012-01-25 20:25       ` Christopher R. Hertel
2012-01-25 21:56         ` Roland Dreier
2012-01-25 22:09           ` Christopher R. Hertel
2012-01-26 21:52             ` Andy Grover
2012-01-26 11:15         ` Bart Van Assche
2012-01-18 17:00 ` [LSF/MM TOPIC] " Roland Dreier
2012-01-18 17:51   ` Ric Wheeler
2012-01-18 18:46     ` Roland Dreier
2012-01-18 18:51       ` Bart Van Assche
2012-01-18 19:00         ` Roland Dreier
2012-01-19  8:16         ` Rolf Eike Beer
2012-01-19 17:50       ` Loke, Chetan

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=4F21D3AE.80806@redhat.com \
    --to=rwheeler@redhat.com \
    --cc=Chetan.Loke@netscout.com \
    --cc=Shyam_Iyer@Dell.com \
    --cc=coughlan@redhat.com \
    --cc=david@fromorbit.com \
    --cc=hare@suse.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=tasleson@redhat.com \
    --cc=vgoyal@redhat.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 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).