All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>,
	Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Hildenbrand <dahi@linux.vnet.ibm.com>,
	KVM <kvm@vger.kernel.org>, Gleb Natapov <gleb@kernel.org>,
	jfrei@linux.vnet.ibm.com,
	Cornelia Huck <cornelia.huck@de.ibm.com>,
	Michael Mueller <mimu@linux.vnet.ibm.com>,
	raghavendra.kt.linux@gmail.com
Subject: Re: [PATCH RFC 1/2] KVM: don't check for PF_VCPU when yielding
Date: Wed, 03 Dec 2014 13:53:11 +0100	[thread overview]
Message-ID: <547F07B7.6020902@redhat.com> (raw)
In-Reply-To: <54785F29.1060506@linux.vnet.ibm.com>



On 28/11/2014 12:40, Raghavendra K T wrote:
> I am seeing very small improvement in <= 1x commit cases
> and for >1x overcommit, a very slight regression. But considering the
> test environment noises, I do not see much effect from the
> patch.

I think these results are the only one that could be statisically significant:

                   base     %stdev      patched     %stdev    %improvement
kernbench 1x    53.1421     2.3086      54.6671     2.9673      -2.86966
dbench    1x  6386.4737     1.0487    6703.9113     1.2298       4.97047

and, of course :) one of them says things get worse and the other
says things get better.

Paolo

> But I admit, I have not explored deeply about,
> 1. assumption of preempted approximately equals PF_VCPU case logic,
> 2. whether it helps for any future usages of yield_to against current
> sole usage of virtualization.
> 
> 
> 

  parent reply	other threads:[~2014-12-03 12:53 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-11-25 16:04 [PATCH RFC 0/2] assign each vcpu an owning thread and improve yielding David Hildenbrand
2014-11-25 16:04 ` [PATCH RFC 1/2] KVM: don't check for PF_VCPU when yielding David Hildenbrand
2014-11-26  7:51   ` Christian Borntraeger
2014-11-26  9:23     ` David Hildenbrand
2014-11-26  9:31       ` Christian Borntraeger
2014-11-28 10:08         ` Raghavendra KT
2014-11-28 10:58           ` Christian Borntraeger
2014-11-28 11:40             ` Raghavendra K T
2014-12-01  9:54               ` David Hildenbrand
2014-12-03 12:53               ` Paolo Bonzini [this message]
2014-12-03 13:02   ` Paolo Bonzini
2014-12-03 13:04     ` David Hildenbrand
2014-11-25 16:04 ` [PATCH RFC 2/2] KVM: thread creating a vcpu is the owner of that vcpu David Hildenbrand
2014-11-26  7:54   ` Christian Borntraeger
2014-12-03 12:53   ` Paolo Bonzini
2014-12-03 12:12 ` [PATCH RFC 0/2] assign each vcpu an owning thread and improve yielding David Hildenbrand
2014-12-03 12:54   ` Paolo Bonzini
2014-12-03 13:00     ` David Hildenbrand
2014-12-03 13:00     ` Christian Borntraeger
2014-12-03 13:06       ` Paolo Bonzini

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=547F07B7.6020902@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=borntraeger@de.ibm.com \
    --cc=cornelia.huck@de.ibm.com \
    --cc=dahi@linux.vnet.ibm.com \
    --cc=gleb@kernel.org \
    --cc=jfrei@linux.vnet.ibm.com \
    --cc=kvm@vger.kernel.org \
    --cc=mimu@linux.vnet.ibm.com \
    --cc=raghavendra.kt.linux@gmail.com \
    --cc=raghavendra.kt@linux.vnet.ibm.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.