All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mikulas Patocka <mpatocka@redhat.com>
To: device-mapper development <dm-devel@redhat.com>,
	Frank Mayhar <fmayhar@google.com>
Cc: Mike Snitzer <msnitzer@redhat.com>, linux-kernel@vger.kernel.org
Subject: Re: [dm-devel] [PATCH] dm: Make MIN_IOS, et al, tunable via sysctl.
Date: Tue, 20 Aug 2013 17:47:39 -0400 (EDT)	[thread overview]
Message-ID: <alpine.LRH.2.02.1308201745130.8826@file01.intranet.prod.int.rdu2.redhat.com> (raw)
In-Reply-To: <1377034118.24869.48.camel@bobble.lax.corp.google.com>



On Tue, 20 Aug 2013, Frank Mayhar wrote:

> On Tue, 2013-08-20 at 17:22 -0400, Mikulas Patocka wrote:
> > On Fri, 16 Aug 2013, Frank Mayhar wrote:
> > > The device mapper and some of its modules allocate memory pools at
> > > various points when setting up a device.  In some cases, these pools are
> > > fairly large, for example the multipath module allocates a 256-entry
> > > pool and the dm itself allocates three of that size.  In a
> > > memory-constrained environment where we're creating a lot of these
> > > devices, the memory use can quickly become significant.  Unfortunately,
> > > there's currently no way to change the size of the pools other than by
> > > changing a constant and rebuilding the kernel.
> > I think it would be better to set the values to some low value (1 should 
> > be enough, there is 16 in some places that is already low enough). There 
> > is no need to make it user-configurable, because the user will see no 
> > additional benefit from bigger mempools.
> > 
> > Maybe multipath is the exception - but other dm targets don't really need 
> > big mempools so there is no need to make the size configurable.
> 
> The point is not to make the mempools bigger, the point is to be able to
> make them _smaller_ for memory-constrained environments.  In some cases,
> even 16 can be too big, especially when creating a large number of
> devices.
> 
> In any event, it seems unfortunate to me that these values are
> hard-coded.  One shouldn't have to rebuild the kernel to change them,
> IMHO.

So make a patch that changes 16 to 1 if it helps on your system (I'd like 
to ask - what is the configuration where this kind of change helps?). 
There is no need for that to be tunable, anyone can live with mempool size 
being 1.

Mikulas

  reply	other threads:[~2013-08-20 21:47 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-08-09 17:48 [PATCH] dm: Make MIN_IOS, et al, tunable via sysctl Frank Mayhar
2013-08-13 16:41 ` Frank Mayhar
2013-08-16 22:58 ` Frank Mayhar
2013-08-17 12:30 ` [dm-devel] " Alasdair G Kergon
2013-08-19 13:40   ` Mike Snitzer
2013-08-19 15:04     ` Frank Mayhar
2013-08-19 14:00 ` Mike Snitzer
2013-08-19 14:00   ` Mike Snitzer
2013-08-19 17:54   ` [dm-devel] " Frank Mayhar
2013-08-19 18:15     ` Mike Snitzer
2013-08-20 21:44     ` [dm-devel] " Mikulas Patocka
2013-08-20 21:52       ` Frank Mayhar
2013-08-20 21:41   ` Mikulas Patocka
2013-08-20 21:22 ` [dm-devel] [PATCH] " Mikulas Patocka
2013-08-20 21:28   ` Frank Mayhar
2013-08-20 21:47     ` Mikulas Patocka [this message]
2013-08-20 21:57       ` Frank Mayhar
2013-08-20 22:24         ` Mike Snitzer
2013-08-20 22:52           ` Mikulas Patocka
2013-08-20 23:14           ` Frank Mayhar
2013-08-22 17:26             ` Frank Mayhar
2013-08-26 14:28             ` Mikulas Patocka
2013-09-12 22:24               ` [PATCH 0/7] dm: allow mempool and bioset reserves to be tuned Mike Snitzer
2013-09-12 22:24                 ` [PATCH 1/7] dm: lower bio-based mempool reservation Mike Snitzer
2013-09-12 22:40                   ` Mikulas Patocka
2013-09-12 22:24                 ` [PATCH 2/7] dm: add reserved_rq_based_ios module parameter Mike Snitzer
2013-09-12 22:45                   ` Mikulas Patocka
2013-09-12 23:15                     ` Mike Snitzer
2013-09-12 23:27                       ` Mikulas Patocka
2013-09-12 23:32                         ` Mike Snitzer
2013-09-12 22:24                 ` [PATCH 3/7] dm: add reserved_bio_based_ios " Mike Snitzer
2013-09-12 22:47                   ` Mikulas Patocka
2013-09-12 23:11                     ` Mike Snitzer
2013-09-12 23:17                       ` Mikulas Patocka
2013-09-18 15:17                         ` Frank Mayhar
2013-09-12 22:24                 ` [PATCH 4/7] dm io: use dm_get_reserved_bio_based_ios to size reserves Mike Snitzer
2013-09-12 22:48                   ` Mikulas Patocka
2013-09-12 22:24                 ` [PATCH 5/7] dm mpath: use dm_get_reserved_rq_based_ios to size mempool Mike Snitzer
2013-09-12 22:48                   ` Mikulas Patocka
2013-09-12 22:24                 ` [PATCH 6/7] dm: track the maximum number of bios in a cloned request Mike Snitzer
2013-09-12 22:55                   ` Mikulas Patocka
2013-09-12 23:09                     ` Mike Snitzer
2013-09-12 22:24                 ` [PATCH 7/7] dm: optimize clone_rq() when track_peak_rq_based_ios is disabled Mike Snitzer
2013-09-12 23:00                   ` Mikulas Patocka
2013-09-12 23:06                     ` Mike Snitzer
2013-09-12 23:30                       ` Mikulas Patocka
2013-09-12 23:53                         ` Mike Snitzer
2013-09-13  4:46                           ` Jun'ichi Nomura
2013-09-13 13:04                             ` Mike Snitzer
2013-09-13 14:34                             ` Mikulas Patocka
2013-09-13 18:59                 ` [PATCH v2 0/3] dm: allow mempool and bioset reserves to be tuned Mike Snitzer
2013-09-13 18:59                   ` [PATCH v2 1/3] dm: lower bio-based mempool reservation Mike Snitzer
2013-09-13 18:59                   ` [PATCH v2 2/3] dm: add reserved_rq_based_ios module parameter Mike Snitzer
2013-09-13 18:59                   ` [PATCH v2 3/3] dm: add reserved_bio_based_ios " Mike Snitzer
2013-09-13 19:22                   ` [PATCH v2 0/3] dm: allow mempool and bioset reserves to be tuned Mike Snitzer
2013-09-13 20:30                     ` Mike Snitzer
2013-09-13 21:08                       ` [PATCH v3 " Mike Snitzer
2013-09-13 21:08                         ` [PATCH v3 1/3] dm: lower bio-based mempool reservation Mike Snitzer
2013-09-13 21:08                         ` [PATCH v3 2/3] dm: add reserved_rq_based_ios module parameter Mike Snitzer
2013-09-13 21:08                         ` [PATCH v3 3/3] dm: add reserved_bio_based_ios " Mike Snitzer
2013-09-18 15:10                         ` [PATCH v3 0/3] dm: allow mempool and bioset reserves to be tuned Frank Mayhar

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=alpine.LRH.2.02.1308201745130.8826@file01.intranet.prod.int.rdu2.redhat.com \
    --to=mpatocka@redhat.com \
    --cc=dm-devel@redhat.com \
    --cc=fmayhar@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=msnitzer@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.