From: Zdenek Kabelac <zkabelac@redhat.com>
To: LVM general discussion and development <linux-lvm@redhat.com>,
Gionatan Danti <g.danti@assyoma.it>,
"Stuart D. Gathman" <stuart@gathman.org>
Cc: "Dalebjörk, Tomas" <tomas.dalebjork@gmail.com>
Subject: Re: [linux-lvm] exposing snapshot block device
Date: Wed, 23 Oct 2019 14:59:50 +0200 [thread overview]
Message-ID: <0dd80515-d4db-273f-2ee4-78981c11b2c8@redhat.com> (raw)
In-Reply-To: <f73ab6ce-ba22-34f8-7153-e876b13fab5c@assyoma.it>
Dne 23. 10. 19 v 13:08 Gionatan Danti napsal(a):
> On 23/10/19 12:46, Zdenek Kabelac wrote:
>> Just few 'comments' - it's not really comparable - the efficiency of
>> thin-pool metadata outperforms old snapshot in BIG way (there is no point to
>> talk about snapshots that takes just couple of MiB)
>
> Yes, this matches my experience.
>
>> There is also BIG difference about the usage of old snapshot origin and
>> snapshot.
>>
>> COW of old snapshot effectively cuts performance 1/2 if you write to origin.
>
> If used without non-volatile RAID controller, 1/2 is generous - I measured
> performance as low as 1/5 (with fat snapshot).
>
> Talking about thin snapshot, an obvious performance optimization which seems
> to not be implemented is to skip reading source data when overwriting in
> larger-than-chunksize blocks.
Hi
There is no such optimization possible for old snapshots.
You would need to write ONLY to snapshots.
As soon as you start to write to origin - you have to 'read' original data
from origin, copy them to COW storage, once this is finished, you can
overwrite origin data area with your writing I/O.
This is simply never going to work fast ;) - the fast way is thin-pool...
Old snapshots were designed for 'short' lived snapshots (so you can take
a backup of volume which is not being modified underneath).
Any idea of improving this old snapshots target are sooner or later going to
end-up with thin-pool anyway :) (we've been in this river many many years
back in time...)
> For example, consider a completely filled 64k chunk thin volume (with thinpool
> having ample free space). Snapshotting it and writing a 4k block on origin
There is no support of snapshot of snapshot with old snaps...
It would be extremely slow to use...
> However, my testing shows that source chunks are always read, even when
> completely overwritten.
>
> Am I missing something?
Yep - you would need to always jump to your 'snapshot' - so instead of
keeping 'origin' on major:minor - it would need to become a 'snapshot'...
Seriously complex concept to work with - especially when there is thin-pool...
Regards
Zdenek
next prev parent reply other threads:[~2019-10-23 12:59 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-22 10:47 [linux-lvm] exposing snapshot block device Dalebjörk, Tomas
2019-10-22 13:57 ` Zdenek Kabelac
2019-10-22 15:29 ` Dalebjörk, Tomas
2019-10-22 15:36 ` Zdenek Kabelac
2019-10-22 16:13 ` Dalebjörk, Tomas
2019-10-23 10:26 ` Zdenek Kabelac
2019-10-23 10:56 ` Tomas Dalebjörk
2019-10-22 16:15 ` Stuart D. Gathman
2019-10-22 17:02 ` Tomas Dalebjörk
2019-10-22 21:38 ` Gionatan Danti
2019-10-22 22:53 ` Stuart D. Gathman
2019-10-23 6:58 ` Gionatan Danti
2019-10-23 10:06 ` Tomas Dalebjörk
2019-10-23 10:12 ` Zdenek Kabelac
2019-10-23 10:46 ` Zdenek Kabelac
2019-10-23 11:08 ` Gionatan Danti
2019-10-23 11:24 ` Tomas Dalebjörk
2019-10-23 11:26 ` Tomas Dalebjörk
2019-10-24 16:01 ` Zdenek Kabelac
2019-10-25 16:31 ` Tomas Dalebjörk
2019-11-04 5:54 ` Tomas Dalebjörk
2019-11-04 10:07 ` Zdenek Kabelac
2019-11-04 14:40 ` Tomas Dalebjörk
2019-11-04 15:04 ` Zdenek Kabelac
2019-11-04 17:28 ` Tomas Dalebjörk
2019-11-05 16:24 ` Zdenek Kabelac
2019-11-05 16:40 ` Mikulas Patocka
2019-11-05 20:56 ` Tomas Dalebjörk
2019-11-06 9:22 ` Zdenek Kabelac
2019-11-07 16:54 ` Mikulas Patocka
2019-11-07 17:29 ` Tomas Dalebjörk
2020-09-04 12:09 ` Tomas Dalebjörk
2020-09-04 12:37 ` Zdenek Kabelac
2020-09-07 13:09 ` Mikulas Patocka
2020-09-07 14:14 ` Dalebjörk, Tomas
2020-09-07 14:17 ` Zdenek Kabelac
2020-09-07 16:34 ` Tomas Dalebjörk
2020-09-07 16:42 ` Zdenek Kabelac
2020-09-07 17:37 ` Tomas Dalebjörk
2020-09-07 17:50 ` Zdenek Kabelac
2020-09-08 12:32 ` Dalebjörk, Tomas
2020-09-07 19:56 ` Tomas Dalebjörk
2020-09-07 20:22 ` Tomas Dalebjörk
2020-09-07 21:02 ` Tomas Dalebjörk
2019-10-23 12:12 ` Ilia Zykov
2019-10-23 12:20 ` Ilia Zykov
2019-10-23 13:05 ` Zdenek Kabelac
2019-10-23 14:40 ` Gionatan Danti
2019-10-23 15:46 ` Ilia Zykov
2019-10-23 12:59 ` Zdenek Kabelac [this message]
2019-10-23 14:37 ` Gionatan Danti
2019-10-23 15:37 ` Zdenek Kabelac
2019-10-23 17:16 ` Gionatan Danti
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=0dd80515-d4db-273f-2ee4-78981c11b2c8@redhat.com \
--to=zkabelac@redhat.com \
--cc=g.danti@assyoma.it \
--cc=linux-lvm@redhat.com \
--cc=stuart@gathman.org \
--cc=tomas.dalebjork@gmail.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).