All of lore.kernel.org
 help / color / mirror / Atom feed
From: Avi Kivity <avi@redhat.com>
To: Udo Lembke <ulembke@polarzone.de>
Cc: kvm@vger.kernel.org, qemu-devel@nongnu.org
Subject: Re: [PATCH 10/12] kvm: enable smp > 1
Date: Thu, 20 May 2010 09:12:56 +0300	[thread overview]
Message-ID: <4BF4D2E8.2090607@redhat.com> (raw)
In-Reply-To: <4BF443EA.3020405@polarzone.de>

On 05/19/2010 11:02 PM, Udo Lembke wrote:
>> Unrelated, what are your smp issues?
>>
>
> If i use one cpu i got a good io-performance:
> e.g. over 500MB/s at the profile "install" of the io-benchmark 
> h2benchw.exe.
> ( aio=threads | SAS-Raid-0 | 
> ftp://ftp.heise.de/pub/ct/ctsi/h2benchw.zip | hwbenchw.exe -p -w 
> iotest 0)
> The same test but with two cpus gives results between 27 and 298 MB/s!
>
> Also in real life it's noticeable not only with an benchmark. I use a 
> win-vm with two cpu for postscript-ripping and have a performance drop 
> due to the bad io.

What's your block device model?  virtio or ide?

What does cpu usage look like on guest or host?

-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.


WARNING: multiple messages have this Message-ID (diff)
From: Avi Kivity <avi@redhat.com>
To: Udo Lembke <ulembke@polarzone.de>
Cc: qemu-devel@nongnu.org, kvm@vger.kernel.org
Subject: [Qemu-devel] Re: [PATCH 10/12] kvm: enable smp > 1
Date: Thu, 20 May 2010 09:12:56 +0300	[thread overview]
Message-ID: <4BF4D2E8.2090607@redhat.com> (raw)
In-Reply-To: <4BF443EA.3020405@polarzone.de>

On 05/19/2010 11:02 PM, Udo Lembke wrote:
>> Unrelated, what are your smp issues?
>>
>
> If i use one cpu i got a good io-performance:
> e.g. over 500MB/s at the profile "install" of the io-benchmark 
> h2benchw.exe.
> ( aio=threads | SAS-Raid-0 | 
> ftp://ftp.heise.de/pub/ct/ctsi/h2benchw.zip | hwbenchw.exe -p -w 
> iotest 0)
> The same test but with two cpus gives results between 27 and 298 MB/s!
>
> Also in real life it's noticeable not only with an benchmark. I use a 
> win-vm with two cpu for postscript-ripping and have a performance drop 
> due to the bad io.

What's your block device model?  virtio or ide?

What does cpu usage look like on guest or host?

-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.

  reply	other threads:[~2010-05-20  6:13 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-05-12 21:24 [PATCH 00/12] [PULL] qemu-kvm.git uq/master queue Marcelo Tosatti
2010-05-12 21:24 ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:24 ` [PATCH 01/12] Fix -mem-path with hugetlbfs Marcelo Tosatti
2010-05-12 21:24   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:24 ` [PATCH 02/12] kvm: set cpu_single_env around KVM_RUN ioctl Marcelo Tosatti
2010-05-12 21:24   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:24 ` [PATCH 03/12] make SIG_IPI to tcg vcpu thread reliable Marcelo Tosatti
2010-05-12 21:24   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:24 ` [PATCH 04/12] standardize on qemu_cpu_kick for signalling cpu thread(s) Marcelo Tosatti
2010-05-12 21:24   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:24 ` [PATCH 05/12] port qemu-kvm's on_vcpu code Marcelo Tosatti
2010-05-12 21:24   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:25 ` [PATCH 06/12] kvm: synchronize state from cpu context Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:25 ` [PATCH 07/12] add cpu_is_stopped helper Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:25 ` [PATCH 08/12] move stop/stopped CPU_COMMON fields after area zeroed by reset Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:25 ` [PATCH 09/12] kvm: validate context for kvm cpu get/put operations Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:25 ` [PATCH 10/12] kvm: enable smp > 1 Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-14 14:06   ` Alexander Graf
2010-05-14 14:06     ` [Qemu-devel] " Alexander Graf
2010-05-14 15:48     ` Avi Kivity
2010-05-14 15:48       ` [Qemu-devel] " Avi Kivity
2010-05-14 15:49       ` Alexander Graf
2010-05-14 15:49         ` [Qemu-devel] " Alexander Graf
2010-05-14 15:54         ` Jan Kiszka
2010-05-14 15:54           ` [Qemu-devel] " Jan Kiszka
2010-05-14 15:58           ` Alexander Graf
2010-05-14 15:58             ` [Qemu-devel] " Alexander Graf
2010-05-19  9:57           ` Udo Lembke
2010-05-19  9:57             ` [Qemu-devel] " Udo Lembke
2010-05-19 16:21             ` Avi Kivity
2010-05-19 16:21               ` [Qemu-devel] " Avi Kivity
2010-05-19 20:02               ` Udo Lembke
2010-05-19 20:02                 ` [Qemu-devel] " Udo Lembke
2010-05-20  6:12                 ` Avi Kivity [this message]
2010-05-20  6:12                   ` Avi Kivity
2010-05-20  7:01                   ` Udo Lembke
2010-05-20  7:01                     ` [Qemu-devel] " Udo Lembke
2010-05-12 21:25 ` [PATCH 11/12] Do not stop VM if emulation failed in userspace Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-12 21:25 ` [PATCH 12/12] kvm: fix 80000001.EDX supported bit filtering Marcelo Tosatti
2010-05-12 21:25   ` [Qemu-devel] " Marcelo Tosatti
2010-05-17 18:10 ` [Qemu-devel] [PATCH 00/12] [PULL] qemu-kvm.git uq/master queue Anthony Liguori

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=4BF4D2E8.2090607@redhat.com \
    --to=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=qemu-devel@nongnu.org \
    --cc=ulembke@polarzone.de \
    /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.