All of lore.kernel.org
 help / color / mirror / Atom feed
From: Zdenek Kabelac <zkabelac@redhat.com>
To: lvm-devel@redhat.com
Subject: dm-thinp feature request: skip allocation on writes of all zeroes
Date: Tue, 30 Sep 2014 21:30:15 +0200	[thread overview]
Message-ID: <542B04C7.8000708@redhat.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1409301121470.26721@ware.dreamhost.com>

Dne 30.9.2014 v 20:38 Eric Wheeler napsal(a):
> Hello all,
>
> We have been testing dm-thinp for the last couple years and it has been stable
> for the most part.
>
> I have always wondered, does LVM ignore writes with blocks of all zeroes when
> the destination address is unallocated? From experience, it does not appear
> that this is so (or I cannot find the config option). This would reduce IOs,
> particularily when importing VM disk images from other sources. Currently, we
> must import, allocate lots of zeroes, then fstrim after the fact.

If you use thinpool with enabled zeroing of provisioned chunks -
then you always get 'zeroed' thin-volume device in all parts -
so you don't need to zero anything in such block device.

Now if you 'skip' writing zeroes (like i.e. cp -a  does when copying files),
you get your  'skip' zero writes.

Note - if your original source device would be already an LV - it might be 
then probably more efficient to either use such LV as an external origin, or 
implement support for merging LV into thin-pool.


Regards

Zdenek




  reply	other threads:[~2014-09-30 19:30 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-09-30 18:38 dm-thinp feature request: skip allocation on writes of all zeroes Eric Wheeler
2014-09-30 19:30 ` Zdenek Kabelac [this message]
2014-09-30 20:13 ` Mike Snitzer
2014-09-30 22:38   ` Eric Wheeler
2014-12-04  7:05 ` [PATCH] dm-thinp: skip allocation on writes of all zeros to unallocated blocks Eric Wheeler
2014-12-04  7:25   ` Eric Wheeler
2014-12-04 15:33     ` [PATCH] dm thin: optimize away writing all zeroes to unprovisioned blocks Mike Snitzer
2014-12-04 15:33       ` Mike Snitzer
2014-12-04 15:43       ` Mike Snitzer
2014-12-04 15:43         ` Mike Snitzer
2014-12-06 22:33         ` Eric Wheeler
2014-12-06 22:33           ` Eric Wheeler
2014-12-05 14:47       ` Mike Snitzer
2014-12-05 14:47         ` Mike Snitzer
2014-12-06 22:36         ` Eric Wheeler
2014-12-06 22:36           ` Eric Wheeler
2014-12-05 17:27       ` [PATCH] " Jens Axboe
2014-12-05 17:27         ` Jens Axboe
2014-12-05 18:33         ` Mike Snitzer
2014-12-05 18:33           ` Mike Snitzer
2014-12-06 22:40           ` Eric Wheeler
2014-12-06 22:40             ` Eric Wheeler
2014-12-07  1:41             ` [lvm-devel] " Jens Axboe
2014-12-07  1:41               ` Jens Axboe
2014-12-07  6:30               ` Eric Wheeler
2014-12-07  6:30                 ` Eric Wheeler
2014-12-07  6:45                 ` Eric Wheeler
2014-12-07  6:45                   ` Eric Wheeler
2014-12-08 16:57                 ` [lvm-devel] " Jens Axboe
2014-12-08 16:57                   ` Jens Axboe
2014-12-09  8:02                   ` Eric Wheeler
2014-12-09  8:02                     ` Eric Wheeler
2014-12-09 15:31                     ` [lvm-devel] " Jens Axboe
2014-12-09 15:31                       ` Jens Axboe
2014-12-09 15:41                       ` [lvm-devel] " Jens Axboe
2014-12-09 15:41                         ` Jens Axboe
2014-12-10  2:52                         ` [PATCH] " Eric Wheeler
2014-12-10  2:52                           ` Eric Wheeler
2015-01-26  2:53                       ` Eric Wheeler
2015-01-26  2:53                         ` Eric Wheeler
2015-02-15  0:31                         ` [lvm-devel] " Eric Wheeler
2015-02-15  0:31                           ` Eric Wheeler
2014-12-09 14:38                   ` Marian Csontos
2014-12-09 14:38                     ` Marian Csontos
2014-12-07  1:36           ` Jens Axboe
2014-12-07  1:36             ` Jens Axboe

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=542B04C7.8000708@redhat.com \
    --to=zkabelac@redhat.com \
    --cc=lvm-devel@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 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.