From mboxrd@z Thu Jan 1 00:00:00 1970 From: Fasiha Ashraf Subject: Re: Re: [Xen-users] About profiling xen Date: Mon, 5 Oct 2009 17:08:54 +0530 (IST) Message-ID: <197376.79799.qm@web94607.mail.in2.yahoo.com> References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0195339711==" Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Jeremy Fitzhardinge , Marco Tizzoni Cc: "Fajar A." , xen , xen-users@lists.xensource.com List-Id: xen-devel@lists.xenproject.org --===============0195339711== Content-Type: multipart/alternative; boundary="0-2037764076-1254742734=:79799" --0-2037764076-1254742734=:79799 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Is this the issue that is affecting guest to guest throughput? Since I have= timer frequency 1000Hz and high resolution timer both enabled in my dom0. = Also i am using cup cores pinned for each VM an Dom0. Please guide me some = more about getting increased throughput between guests.=20 Could it be an ebtable filter issue? Regards, Fasiha Ashraf --- On Fri, 2/10/09, Marco Tizzoni wrote: From: Marco Tizzoni Subject: Re: [Xen-devel] Re: [Xen-users] About profiling xen To: "Jeremy Fitzhardinge" Cc: "Fajar A." , "Fasiha Ashraf" , "x= en" , xen-users@lists.xensource.com Date: Friday, 2 October, 2009, 3:20 AM On Fri, Oct 2, 2009 at 12:01 AM, Jeremy Fitzhardinge wrot= e: > On 10/01/09 14:55, Marco Tizzoni wrote: >> Sorry, I was not clear. It works as I expect, i.e going not over 1000 >> hz (my dom0 kernel has been compiled with 1000hz). >> > > OK, that's definitely *not* expected. =A0If you're running with > CONFIG_NO_HZ and HIGH_RES_TIMERS then timer resolution should have > nothing to do with your HZ configuration. > 100kHz is also very demanding. > How does it work with 2kHz? 10kHz? hal9k-dom0 ~ # ./testtimer .0001 |head -n10 1000 iterations at=A0 0.000100 sec 0.000051 0.000885 0.000890 0.000892 0.000891 0.000892 0.000893 0.000893 0.000879 0.000893 hal9k-dom0 ~ # ./testtimer .002 |head -n10 1000 iterations at=A0 0.002000 sec 0.000744 0.000978 0.000990 0.000990 0.000990 0.000991 0.000992 0.000991 0.000992 0.000990 m- =0A=0A=0A From cricket scores to your friends. Try the Yahoo! India Ho= mepage! http://in.yahoo.com/trynew --0-2037764076-1254742734=:79799 Content-Type: text/html; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable
Is this the issue that is affecting guest to = guest throughput? Since I have timer frequency 1000Hz and high resolution t= imer both enabled in my dom0. Also i am using cup cores pinned for each VM = an Dom0. Please guide me some more about getting increased throughput betwe= en guests.
Could it be an ebtable filter issue?
Regards,
Fasiha A= shraf

--- On Fri, 2/10/09, Marco Tizzoni <marco.tizzoni@gma= il.com> wrote:

From: Marco Tizzo= ni <marco.tizzoni@gmail.com>
Subject: Re: [Xen-devel] Re: [Xen-use= rs] About profiling xen
To: "Jeremy Fitzhardinge" <jeremy@goop.org>= ;
Cc: "Fajar A." <fajar@fajar.net>, "Fasiha Ashraf" <feehapk@ya= hoo.co.in>, "xen" <xen-devel@lists.xensource.com>, xen-users@lists.xensource.com
Date: Friday, 2 October, 2009, 3:20 AM
On Fri, Oct 2, 2009 at 12:01 AM, Jeremy Fitzh= ardinge <jeremy@goop.org> wrote:
> On 10/01/09 14:55, = Marco Tizzoni wrote:
>> Sorry, I was not clear. It works as I expe= ct, i.e going not over 1000
>> hz (my dom0 kernel has been compile= d with 1000hz).
>>
>
> OK, that's definitely *not* exp= ected.  If you're running with
> CONFIG_NO_HZ and HIGH_RES_TIMER= S then timer resolution should have
> nothing to do with your HZ conf= iguration.

> 100kHz is also very demanding.
> How does it w= ork with 2kHz? 10kHz?

hal9k-dom0 ~ # ./testtimer .0001 |head -n101000 iterations at  0.000100 sec
0.000051
0.000885
0.000890
0.000892
0.000891
0.00089= 2
0.000893
0.000893
0.000879
0.000893
hal9k-dom0 ~ # ./testt= imer .002 |head -n10
1000 iterations at  0.002000 sec
0.0007440.000978
0.000990
0.000990
0.000990
0.000991
0.000992
0= .000991
0.000992
0.000990


m-

=0A
Yahoo! India has a new l= ook. Take a sneak peek. --0-2037764076-1254742734=:79799-- --===============0195339711== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel --===============0195339711==--