qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Lieven <pl@kamp.de>
To: Stefan Hajnoczi <stefanha@gmail.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>
Subject: Re: [Qemu-devel] Qemu and heavily increased RSS usage
Date: Wed, 22 Jun 2016 21:55:51 +0200	[thread overview]
Message-ID: <576AED47.4010504@kamp.de> (raw)
In-Reply-To: <20160622105656.GC11330@stefanha-x1.localdomain>

Am 22.06.2016 um 12:56 schrieb Stefan Hajnoczi:
> On Tue, Jun 21, 2016 at 05:12:57PM +0200, Peter Lieven wrote:
>>  - We changed the coroutine pool to a per thread model. I disabled the pool. This seems
>>    to cut the max used RSS to about 150MB which is still a lot more than qemu-2.2.0
> The per-thread coroutine pools only grow when a thread creates/destroys
> coroutines.
>
> The QEMU main loop, iothread, and maybe vcpus should use coroutines.
> The numerous thread-pool worker threads should not use coroutines IIRC.
>
> Creating coroutines is expensive and the pools improve performance a
> lot.  Maybe you can make observations about how to manage pool size more
> efficiently for your VM?

I did not want to blame the coroutine pool. Its a good thing. I just wanted to
mention that we changed from a global pool (with a global mutex) to a thread
based pool. This might influence memory consumption. But the increased RSS
usage I observe is also there with disable coroutine pool.

What makes the coroutine pool memory intensive is the stack size of 1MB per
coroutine. Is it really necessary to have such a big stack?

Peter

  reply	other threads:[~2016-06-22 19:56 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-21  8:21 [Qemu-devel] Qemu and heavily increased RSS usage Peter Lieven
2016-06-21 13:18 ` Dr. David Alan Gilbert
2016-06-21 15:12   ` Peter Lieven
2016-06-22 10:56     ` Stefan Hajnoczi
2016-06-22 19:55       ` Peter Lieven [this message]
2016-06-22 20:56         ` Peter Maydell
2016-06-24  9:37           ` Stefan Hajnoczi
2016-06-24  9:53             ` Peter Lieven
2016-06-24  9:57               ` Dr. David Alan Gilbert
2016-06-24  9:58             ` Peter Maydell
2016-06-24 10:45               ` Peter Lieven
2016-06-27 12:39                 ` Stefan Hajnoczi
2016-06-27 13:33                   ` Peter Lieven
2016-06-23  9:57   ` Peter Lieven
2016-06-24 22:57     ` Michael S. Tsirkin
2016-06-23 14:58   ` Peter Lieven
2016-06-23 15:00     ` Dr. David Alan Gilbert
2016-06-23 15:02       ` Peter Lieven
2016-06-23 15:21     ` Paolo Bonzini
2016-06-23 15:31       ` Peter Lieven
2016-06-23 15:47         ` Paolo Bonzini
2016-06-23 16:19           ` Peter Lieven
2016-06-23 16:53             ` Paolo Bonzini
2016-06-23 21:28               ` Peter Lieven
2016-06-24  4:10                 ` Paolo Bonzini
2016-06-24  8:11                   ` Peter Lieven
2016-06-24  8:20                     ` Paolo Bonzini
2016-06-24  8:45                       ` Peter Lieven

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=576AED47.4010504@kamp.de \
    --to=pl@kamp.de \
    --cc=dgilbert@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@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).