linux-lvm.redhat.com archive mirror
 help / color / mirror / Atom feed
From: Zdenek Kabelac <zkabelac@redhat.com>
To: LVM general discussion and development <linux-lvm@redhat.com>,
	Gionatan Danti <g.danti@assyoma.it>, Xen <list@xenhideout.nl>
Subject: Re: [linux-lvm] Reserve space for specific thin logical volumes
Date: Tue, 12 Sep 2017 23:57:01 +0200	[thread overview]
Message-ID: <1da2cfbb-4443-b8fa-8a61-55a8c6574db7@redhat.com> (raw)
In-Reply-To: <bd0c1d0e-172a-f6c1-039f-8724dc8d007e@assyoma.it>

Dne 12.9.2017 v 19:14 Gionatan Danti napsal(a):
> On 12/09/2017 16:37, Zdenek Kabelac wrote:
>> ZFS with zpolls with thin with thinpools running directly on top of device.
>>
>> If zpools - are 'equally' fast as thins� - and gives you better protection,
>> and more sane logic the why is still anyone using thins???
>>
>> I'd really love to see some benchmarks....
>>
>> Of course if you slow down speed of thin-pool and add way more 
>> synchronization points and consume 10x more memory :) you can get better 
>> behavior in those exceptional cases which are only hit by unexperienced 
>> users who tends to intentionally use thin-pools in incorrect way.....
> 
> Having benchmarked them, I can reply :)
> 
> ZFS/ZVOLs surely are slower than thinp, full stop.
> However, they are not *massively* slower.

Users interested in thin-provisioning are really mostly interested in 
performance - especially on multicore machines with lots of fast storage with 
high IOPS throughput  (some of them even expect it should be at least as good 
as linear....)

So ATM it's preferred to have more complex 'corner-case' which really mostly 
never happens when thin-pool is operated properly and the remaining use case 
you don't pay higher price for having all data always in sync and also you get 
way lower memory foot-print
(I think especially ZFS is well known for nontrivial memory resource consumption)

As has been pointed already few times in this thread - lots of those
'reserved space' ideas can be already easily handled by just more advanced 
scripting around notification from dmeventd - if you will keep thinking for a 
while you will at some point see the reasoning.

There is no difference if you start to solve problem around 70% fullness then
100%  - the main difference is - with some 'free-space' in thin-pool you can 
resolve problem way more easily and correctly.

Repeated again - whoever targets for 100% full thin-pool usage has 
misunderstood purpose of thin-provisioning.....

Regards

Zdenek

  reply	other threads:[~2017-09-12 21:57 UTC|newest]

Thread overview: 91+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-08 10:35 [linux-lvm] Reserve space for specific thin logical volumes Gionatan Danti
2017-09-08 11:06 ` Xen
2017-09-09 22:04 ` Gionatan Danti
2017-09-11 10:35   ` Zdenek Kabelac
2017-09-11 10:55     ` Xen
2017-09-11 11:20       ` Zdenek Kabelac
2017-09-11 12:06         ` Xen
2017-09-11 12:45           ` Xen
2017-09-11 13:11           ` Zdenek Kabelac
2017-09-11 13:46             ` Xen
2017-09-12 11:46               ` Zdenek Kabelac
2017-09-12 12:37                 ` Xen
2017-09-12 14:37                   ` Zdenek Kabelac
2017-09-12 16:44                     ` Xen
2017-09-12 17:14                     ` Gionatan Danti
2017-09-12 21:57                       ` Zdenek Kabelac [this message]
2017-09-13 17:41                         ` Xen
2017-09-13 19:17                           ` Zdenek Kabelac
2017-09-14  3:19                             ` Xen
2017-09-12 17:00                 ` Gionatan Danti
2017-09-12 23:25                   ` Brassow Jonathan
2017-09-13  8:15                     ` Gionatan Danti
2017-09-13  8:33                       ` Zdenek Kabelac
2017-09-13 18:43                     ` Xen
2017-09-13 19:35                       ` Zdenek Kabelac
2017-09-14  5:59                         ` Xen
2017-09-14 19:05                           ` Zdenek Kabelac
2017-09-15  2:06                             ` Brassow Jonathan
2017-09-15  6:02                               ` Gionatan Danti
2017-09-15  8:37                               ` Xen
2017-09-15  7:34                             ` Xen
2017-09-15  9:22                               ` Zdenek Kabelac
2017-09-16 22:33                                 ` Xen
2017-09-17  6:31                                   ` Xen
2017-09-17  7:10                                     ` Xen
2017-09-18 19:20                                       ` Gionatan Danti
2017-09-20 13:05                                         ` Xen
2017-09-21  9:49                                           ` Zdenek Kabelac
2017-09-21 10:22                                             ` Xen
2017-09-21 13:02                                               ` Zdenek Kabelac
2017-09-21 14:34                                                 ` [linux-lvm] Clarification (and limitation) of the kernel feature I proposed Xen
2017-09-21 14:49                                                 ` [linux-lvm] Reserve space for specific thin logical volumes Xen
2017-09-21 20:32                                                   ` Zdenek Kabelac
2017-09-18  8:56                                   ` Zdenek Kabelac
2017-09-11 14:00             ` Xen
2017-09-11 17:34               ` Zdenek Kabelac
2017-09-11 15:31             ` Eric Ren
2017-09-11 15:52               ` Zdenek Kabelac
2017-09-11 21:35                 ` Eric Ren
2017-09-11 17:41               ` David Teigland
2017-09-11 21:08                 ` Eric Ren
2017-09-11 16:55             ` David Teigland
2017-09-11 17:43               ` Zdenek Kabelac
2017-09-11 21:59     ` Gionatan Danti
2017-09-12 11:01       ` Zdenek Kabelac
2017-09-12 11:34         ` Gionatan Danti
2017-09-12 12:03           ` Zdenek Kabelac
2017-09-12 12:47             ` Xen
2017-09-12 13:51               ` pattonme
2017-09-12 14:57               ` Zdenek Kabelac
2017-09-12 16:49                 ` Xen
2017-09-12 16:57             ` Gionatan Danti
     [not found] <832949972.1610294.1505170613541.ref@mail.yahoo.com>
2017-09-11 22:56 ` matthew patton
2017-09-12  5:28   ` Gionatan Danti
     [not found] <1806055156.426333.1505228581063.ref@mail.yahoo.com>
2017-09-12 15:03 ` matthew patton
2017-09-12 17:09   ` Gionatan Danti
2017-09-12 22:41     ` Zdenek Kabelac
2017-09-12 22:55       ` Gionatan Danti
2017-09-12 23:11         ` Zdenek Kabelac
     [not found] <418002318.647314.1505245480415.ref@mail.yahoo.com>
     [not found] ` <418002318.647314.1505245480415@mail.yahoo.com>
2017-09-12 21:36   ` Gionatan Danti
2017-09-12 22:16     ` Zdenek Kabelac
2017-09-12 22:41       ` Gionatan Danti
2017-09-12 23:02         ` Zdenek Kabelac
2017-09-12 23:15           ` Gionatan Danti
2017-09-12 23:31             ` Zdenek Kabelac
2017-09-13  8:21               ` Gionatan Danti
     [not found] <1575245610.821680.1505258554456.ref@mail.yahoo.com>
2017-09-12 23:22 ` matthew patton
2017-09-13  7:53   ` Gionatan Danti
2017-09-13  8:15     ` Zdenek Kabelac
2017-09-13  8:28       ` Gionatan Danti
2017-09-13  8:44         ` Zdenek Kabelac
2017-09-13 10:46           ` Gionatan Danti
     [not found] <691633892.829188.1505258696384.ref@mail.yahoo.com>
2017-09-12 23:24 ` matthew patton
     [not found] <57374453.843393.1505261050977.ref@mail.yahoo.com>
2017-09-13  0:04 ` matthew patton
2017-09-13  7:10   ` Zdenek Kabelac
     [not found] <1771452279.913055.1505269434212.ref@mail.yahoo.com>
2017-09-13  2:23 ` matthew patton
2017-09-13  7:25   ` Zdenek Kabelac
     [not found] <498090067.1559855.1505338608244.ref@mail.yahoo.com>
2017-09-13 21:36 ` matthew patton
     [not found] <914479528.2618507.1505463313888.ref@mail.yahoo.com>
2017-09-15  8:15 ` matthew patton
2017-09-15 10:01   ` Zdenek Kabelac
2017-09-15 18:35   ` Xen

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=1da2cfbb-4443-b8fa-8a61-55a8c6574db7@redhat.com \
    --to=zkabelac@redhat.com \
    --cc=g.danti@assyoma.it \
    --cc=linux-lvm@redhat.com \
    --cc=list@xenhideout.nl \
    /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).