qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Daniel P. Berrange" <berrange@redhat.com>
To: Pavel Fedin <p.fedin@samsung.com>
Cc: "Peter Crosthwaite" <peter.crosthwaite@xilinx.com>,
	qemu-devel@nongnu.org, "Andreas Färber" <afaerber@suse.de>
Subject: Re: [Qemu-devel] [PATCH v4 0/2] QOM: object_property_add() performance improvement
Date: Mon, 27 Jul 2015 12:19:01 +0100	[thread overview]
Message-ID: <20150727111901.GA18731@redhat.com> (raw)
In-Reply-To: <cover.1436866326.git.p.fedin@samsung.com>

On Tue, Jul 14, 2015 at 12:38:59PM +0300, Pavel Fedin wrote:
> The function originally behaves very badly when adding properties with "[*]"
> suffix. Normally these are used for numbering IRQ pins. In order to find the
> correct starting number the function started from zero and checked for
> duplicates. This takes incredibly long time with large number of CPUs because
> number of IRQ pins on some architectures (like ARM GICv3) gets multiplied by
> number of CPUs.
> 
> The solution is to add one more property which caches last used index so that
> duplication check is not repeated thousands of times. Every time an array is
> expanded the index is picked up from this cache.
> 
> The modification decreases qemu startup time with 32 CPUs by a factor of 2
> (~10 sec vs ~20 sec).

10 seconds to start a QEMU with a mere 32 cpus is still a totally
ridiculous amount of time. Do you know why it is still so slow even
after your suggested patch ? Is it still related to the method
object_property_add(), or are there other areas of code with bad
scalability affecting arm ?

Regards,
Daniel
-- 
|: http://berrange.com      -o-    http://www.flickr.com/photos/dberrange/ :|
|: http://libvirt.org              -o-             http://virt-manager.org :|
|: http://autobuild.org       -o-         http://search.cpan.org/~danberr/ :|
|: http://entangle-photo.org       -o-       http://live.gnome.org/gtk-vnc :|

      parent reply	other threads:[~2015-07-27 11:19 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-14  9:38 [Qemu-devel] [PATCH v4 0/2] QOM: object_property_add() performance improvement Pavel Fedin
2015-07-14  9:39 ` [Qemu-devel] [PATCH v4 1/2] QOM: Introduce object_property_add_single() Pavel Fedin
2015-07-14  9:39 ` [Qemu-devel] [PATCH v4 2/2] QOM: object_property_add() performance improvement Pavel Fedin
2015-07-27 11:42   ` Daniel P. Berrange
2015-07-27 14:36     ` Pavel Fedin
2015-07-27 13:03   ` Markus Armbruster
2015-07-27 13:23     ` Daniel P. Berrange
2015-07-27 13:46       ` Paolo Bonzini
2015-07-27 14:36     ` Pavel Fedin
2015-07-27 14:57       ` Andreas Färber
2015-07-27 15:06         ` Paolo Bonzini
2015-07-27 15:09           ` Paolo Bonzini
2015-07-27 15:19           ` Pavel Fedin
2015-07-27 15:22             ` Paolo Bonzini
2015-07-28  6:45               ` Pavel Fedin
2015-07-28  7:06                 ` Paolo Bonzini
2015-07-27 11:19 ` Daniel P. Berrange [this message]

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=20150727111901.GA18731@redhat.com \
    --to=berrange@redhat.com \
    --cc=afaerber@suse.de \
    --cc=p.fedin@samsung.com \
    --cc=peter.crosthwaite@xilinx.com \
    --cc=qemu-devel@nongnu.org \
    /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).