From: Avi Kivity <avi@redhat.com>
To: "Nikunj A. Dadhania" <nikunj@linux.vnet.ibm.com>
Cc: mtosatti@redhat.com, raghukt@linux.vnet.ibm.com,
alex.shi@intel.com, kvm@vger.kernel.org,
stefano.stabellini@eu.citrix.com, peterz@infradead.org,
hpa@zytor.com, vsrivatsa@gmail.com, mingo@elte.hu
Subject: Re: [PATCH v4 0/8] KVM paravirt remote flush tlb
Date: Mon, 03 Sep 2012 18:27:02 +0300 [thread overview]
Message-ID: <5044CC46.1010200@redhat.com> (raw)
In-Reply-To: <5044BFCA.7060303@redhat.com>
On 09/03/2012 05:33 PM, Avi Kivity wrote:
> On 08/21/2012 02:25 PM, Nikunj A. Dadhania wrote:
>>
>> kernbench(lower is better)
>> ==========================
>> base pvflushv4 %improvement
>> 1VM 48.5800 46.8513 3.55846
>> 2VM 108.1823 104.6410 3.27346
>> 3VM 183.2733 163.3547 10.86825
>>
>> ebizzy(higher is better)
>> ========================
>> base pvflushv4 %improvement
>> 1VM 2414.5000 2089.8750 -13.44481
>> 2VM 2167.6250 2371.7500 9.41699
>> 3VM 1600.1111 2102.5556 31.40060
>>
>
> The regression is worrying. We're improving the contended case at the
> cost of the non-contended case, this is usually the wrong thing to do.
> Do we have any clear idea of the cause of the regression?
For that matter, why do we get an improvement in the 1VM kbuild test?
All vcpus should be running most of the time, barring I/O thread activity.
--
error compiling committee.c: too many arguments to function
next prev parent reply other threads:[~2012-09-03 15:27 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-21 11:25 [PATCH v4 0/8] KVM paravirt remote flush tlb Nikunj A. Dadhania
2012-08-21 11:26 ` [PATCH v4 1/8] mm, x86: Add HAVE_RCU_TABLE_FREE support Nikunj A. Dadhania
2012-08-21 11:26 ` [PATCH v4 2/8] mm: Add missing TLB invalidate to RCU page-table freeing Nikunj A. Dadhania
2012-08-21 11:26 ` [PATCH v4 3/8] KVM Guest: Add VCPU running/pre-empted state for guest Nikunj A. Dadhania
2012-08-23 9:36 ` Marcelo Tosatti
2012-08-24 5:39 ` Nikunj A Dadhania
2012-08-24 15:02 ` Marcelo Tosatti
2012-08-27 4:24 ` Nikunj A Dadhania
2012-08-21 11:26 ` [PATCH v4 4/8] KVM-HV: " Nikunj A. Dadhania
2012-08-23 11:46 ` Marcelo Tosatti
2012-08-24 5:19 ` Nikunj A Dadhania
2012-08-24 15:02 ` Marcelo Tosatti
2012-08-21 11:27 ` [PATCH v4 5/8] KVM Guest: Add paravirt kvm_flush_tlb_others Nikunj A. Dadhania
2012-08-21 11:27 ` [PATCH v4 6/8] KVM-HV: Add flush_on_enter before guest enter Nikunj A. Dadhania
2012-08-21 11:27 ` [PATCH v4 7/8] Enable HAVE_RCU_TABLE_FREE for kvm when PARAVIRT_TLB_FLUSH is enabled Nikunj A. Dadhania
2012-08-21 11:28 ` [PATCH v4 8/8] KVM-doc: Add paravirt tlb flush document Nikunj A. Dadhania
2012-08-23 11:48 ` [PATCH v4 0/8] KVM paravirt remote flush tlb Marcelo Tosatti
2012-09-03 14:33 ` Avi Kivity
2012-09-03 15:27 ` Avi Kivity [this message]
2012-09-04 1:30 ` Nikunj A Dadhania
2012-09-04 7:51 ` Avi Kivity
2012-09-04 8:08 ` Nikunj A Dadhania
2012-09-04 10:37 ` Avi Kivity
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=5044CC46.1010200@redhat.com \
--to=avi@redhat.com \
--cc=alex.shi@intel.com \
--cc=hpa@zytor.com \
--cc=kvm@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mtosatti@redhat.com \
--cc=nikunj@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=raghukt@linux.vnet.ibm.com \
--cc=stefano.stabellini@eu.citrix.com \
--cc=vsrivatsa@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 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.