From mboxrd@z Thu Jan  1 00:00:00 1970
From: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Subject: Re: [PATCH RFC V8 0/17] Paravirtualized ticket spinlocks
Date: Mon, 07 May 2012 19:23:59 +0530
Message-ID: <4FA7D3F7.9080005@linux.vnet.ibm.com>
References: <20120502100610.13206.40.sendpatchset@codeblue.in.ibm.com> <20120507082928.GI16608@gmail.com> <4FA7888F.80505@redhat.com> <4FA7AAD8.6050003@linux.vnet.ibm.com> <4FA7BABA.4040700@redhat.com> <4FA7CC05.50808@linux.vnet.ibm.com> <4FA7CCA2.4030408@redhat.com> <4FA7D06B.60005@linux.vnet.ibm.com> <20120507134611.GB5533@linux.vnet.ibm.com> <4FA7D2E5.1020607@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Return-path: <linux-doc-owner@vger.kernel.org>
In-Reply-To: <4FA7D2E5.1020607@redhat.com>
Sender: linux-doc-owner@vger.kernel.org
To: Avi Kivity <avi@redhat.com>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>, Ingo Molnar <mingo@kernel.org>, Linus Torvalds <torvalds@linux-foundation.org>, Andrew Morton <akpm@linux-foundation.org>, Jeremy Fitzhardinge <jeremy@goop.org>, Greg Kroah-Hartman <gregkh@suse.de>, Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>, "H. Peter Anvin" <hpa@zytor.com>, Marcelo Tosatti <mtosatti@redhat.com>, X86 <x86@kernel.org>, Gleb Natapov <gleb@redhat.com>, Ingo Molnar <mingo@redhat.com>, Attilio Rao <attilio.rao@citrix.com>, Virtualization <virtualization@lists.linux-foundation.org>, Xen Devel <xen-devel@lists.xensource.com>, linux-doc@vger.kernel.org, KVM <kvm@vger.kernel.org>, Andi Kleen <andi@firstfloor.org>, Stefano Stabellini <stefano.stabellini@eu.citrix.com>, Stephan Diestelhorst <stephan.diestelhorst@amd.com>, LKML <linux-kernel@vger.kernel.org>, Peter Zijlstra <a.p.zijlstra@chello.nl>, Thomas
List-Id: xen-devel@lists.xenproject.org

On 05/07/2012 07:19 PM, Avi Kivity wrote:
> On 05/07/2012 04:46 PM, Srivatsa Vaddagiri wrote:
>> * Raghavendra K T<raghavendra.kt@linux.vnet.ibm.com>  [2012-05-07 19:08:51]:
>>
>>> I 'll get hold of a PLE mc  and come up with the numbers soon. but I
>>> 'll expect the improvement around 1-3% as it was in last version.
>>
>> Deferring preemption (when vcpu is holding lock) may give us better than 1-3%
>> results on PLE hardware. Something worth trying IMHO.
>
> Is the improvement so low, because PLE is interfering with the patch, or
> because PLE already does a good job?
>

It is because PLE already does a good job (of not burning cpu). The
1-3% improvement is because, patchset knows atleast who is next to hold
lock, which is lacking in PLE.