linux-ext4.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Theodore Ts'o <tytso@mit.edu>
To: Andreas Dilger <adilger@dilger.ca>
Cc: Laurent GUERBY <laurent@guerby.net>, Jan Kara <jack@suse.cz>,
	"linux-ext4@vger.kernel.org" <linux-ext4@vger.kernel.org>,
	"sage@redhat.com" <sage@redhat.com>,
	Abaakouk Mehdi <sileht@sileht.net>,
	Loic Dachary <loic@dachary.org>
Subject: Re: [PATCH] Remove ext4 xattr mbcache to fix CPU lockup when using ceph #107301
Date: Fri, 20 Nov 2015 23:22:08 -0500	[thread overview]
Message-ID: <20151121042208.GC350@thunk.org> (raw)
In-Reply-To: <DD9C7131-404D-4873-A240-349F4E34E2BD@dilger.ca>

On Fri, Nov 20, 2015 at 06:08:15PM -0700, Andreas Dilger wrote:
> 
> I'm definitely not in favor of deleting mbcache entirely, just having the
> mount option to disable it in cases where it is known not to be useful,
> such as Ceph or Lustre backing stores that never have shared xattrs.
> 
> In some cases mbcache can be useful, since it allows sharing xattrs
> between inodes. 
> 
> I thought you would update our patch to add the mount option to disable
> mbcache?

And better yet would be if there was a blacklist of Lustre and Ceph
xattr type/keys that will never have shared attrs, so that mbcache is
not used for those xattrs automatically, *without* using a mount
option.  Can someone at least start help creating that list?

But yeah, a complete deletion of mbcache is a non-starter.

Regards,

						- Ted

      reply	other threads:[~2015-11-21  4:22 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-20  9:43 [PATCH] Remove ext4 xattr mbcache to fix CPU lockup when using ceph #107301 Laurent GUERBY
2015-11-21  1:08 ` Andreas Dilger
2015-11-21  4:22   ` Theodore Ts'o [this message]

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=20151121042208.GC350@thunk.org \
    --to=tytso@mit.edu \
    --cc=adilger@dilger.ca \
    --cc=jack@suse.cz \
    --cc=laurent@guerby.net \
    --cc=linux-ext4@vger.kernel.org \
    --cc=loic@dachary.org \
    --cc=sage@redhat.com \
    --cc=sileht@sileht.net \
    /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).