All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shirley Ma <xma@us.ibm.com>
To: Krishna Kumar2 <krkumar2@in.ibm.com>
Cc: habanero@linux.vnet.ibm.com, lguest@lists.ozlabs.org,
	kvm@vger.kernel.org, Carsten Otte <cotte@de.ibm.com>,
	linux-s390@vger.kernel.org, "Michael S. Tsirkin" <mst@redhat.com>,
	Heiko Carstens <heiko.carstens@de.ibm.com>,
	linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org,
	Steve Dobbelstein <steved@us.ibm.com>,
	Christian Borntraeger <borntraeger@de.ibm.com>,
	Tom Lendacky <tahm@linux.vnet.ibm.com>,
	netdev@vger.kernel.org,
	Martin Schwidefsky <schwidefsky@de.ibm.com>,
	linux390@de.ibm.com
Subject: Re: [PERF RESULTS] virtio and vhost-net performance enhancements
Date: Thu, 26 May 2011 08:42:22 -0700	[thread overview]
Message-ID: <OFE30C8D78.526FF88D-ON8725789C.00563B8C-8825789C.0056469F@us.ibm.com> (raw)
In-Reply-To: <OF0EFA7BA9.BB2C2860-ON6525789C.0053EE3A-6525789C.005513CC@in.ibm.com>


[-- Attachment #1.1.1: Type: text/plain, Size: 4977 bytes --]


Hello KK,

	Could you please try TCP_RRs as well?

Thanks
Shirley


                                                                       
             Krishna Kumar2                                            
             <krkumar2@in.ibm.                                         
             com>                                                       To
                                       "Michael S. Tsirkin"            
             05/26/2011 08:32          <mst@redhat.com>                
             AM                                                         cc
                                       Christian Borntraeger           
                                       <borntraeger@de.ibm.com>, Carsten
                                       Otte <cotte@de.ibm.com>,        
                                       habanero@linux.vnet.ibm.com, Heiko
                                       Carstens                        
                                       <heiko.carstens@de.ibm.com>,    
                                       kvm@vger.kernel.org,            
                                       lguest@lists.ozlabs.org,        
                                       linux-kernel@vger.kernel.org,   
                                       linux-s390@vger.kernel.org,     
                                       linux390@de.ibm.com,            
                                       netdev@vger.kernel.org, Rusty   
                                       Russell <rusty@rustcorp.com.au>,
                                       Martin Schwidefsky              
                                       <schwidefsky@de.ibm.com>, Steve 
                                       Dobbelstein/Austin/IBM@IBMUS, Tom
                                       Lendacky <tahm@linux.vnet.ibm.com>,
                                       virtualization@lists.linux-foundati
                                       on.org, Shirley                 
                                       Ma/Beaverton/IBM@IBMUS          
                                                                   Subject
                                       [PERF RESULTS] virtio and vhost-net
                                       performance enhancements        
                                                                       
                                                                       
                                                                       
                                                                       
                                                                       
                                                                       




"Michael S. Tsirkin" <mst@redhat.com> wrote on 05/20/2011 04:40:07 AM:

> OK, here is the large patchset that implements the virtio spec update
> that I sent earlier (the spec itself needs a minor update, will send
> that out too next week, but I think we are on the same page here
> already). It supercedes the PUBLISH_USED_IDX patches I sent
> out earlier.

I was able to get this tested by applying the v2 patches
to git-next tree (somehow MST's git tree hung on my guest
which never got resolved). Testing was from Guest -> Remote
node, using an ixgbe 10g card. The test results are
*excellent* (table: #netperf sesssions, BW% improvement,
SD% improvement, CPU% improvement):

___________________________________
           512 byte I/O
#     BW%     SD%      CPU%
____________________________________
1     151.6   -65.1    -10.7
2     180.6   -66.6    -6.4
4     15.5    -35.8    -26.1
8     1.8     -28.4    -26.7
16    3.1     -29.0    -26.5
32    1.1     -27.4    -27.5
64    3.8     -30.9    -26.7
96    5.4     -21.7    -24.2
128   5.7     -24.4    -25.5
____________________________________
BW: 16.6%   SD: -24.6%    CPU: -25.5%


____________________________________
            1K I/O
#     BW%     SD%      CPU%
____________________________________
1     233.9   -76.5    -18.0
2     112.2   -64.0    -23.2
4     9.2     -31.6    -26.1
8    -1.7     -26.8    -30.3
16    3.5     -31.5    -30.6
32    4.8     -25.2    -30.5
64    5.7     -31.0    -28.9
96    5.3     -32.2    -31.7
128   4.6     -38.2    -33.6
____________________________________
BW: 16.4%   SD: -35.%    CPU: -31.5%


____________________________________
             16K I/O
#     BW%     SD%      CPU%
____________________________________
1     18.8    -27.2    -18.3
2     14.8    -36.7    -27.7
4     12.7    -45.2    -38.1
8     4.4     -56.4    -54.4
16    4.8     -38.3    -36.1
32    0        78.0     79.2
64    3.8     -38.1    -37.5
96    7.3     -35.2    -31.1
128   3.4     -31.1    -32.1
____________________________________
BW: 7.6%   SD: -30.1%   CPU: -23.7%


I plan to run some more tests tomorrow. Please let
me know if any other scenario will help.

Thanks,

- KK


[-- Attachment #1.1.2: Type: text/html, Size: 6741 bytes --]

[-- Attachment #1.2: graycol.gif --]
[-- Type: image/gif, Size: 105 bytes --]

[-- Attachment #1.3: pic17152.gif --]
[-- Type: image/gif, Size: 1255 bytes --]

[-- Attachment #1.4: ecblank.gif --]
[-- Type: image/gif, Size: 45 bytes --]

[-- Attachment #2: Type: text/plain, Size: 184 bytes --]

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/virtualization

  reply	other threads:[~2011-05-26 15:42 UTC|newest]

Thread overview: 132+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-19 23:10 [PATCHv2 00/14] virtio and vhost-net performance enhancements Michael S. Tsirkin
2011-05-19 23:10 ` Michael S. Tsirkin
2011-05-19 23:10 ` [PATCHv2 01/14] virtio: event index interface Michael S. Tsirkin
2011-05-19 23:10   ` Michael S. Tsirkin
2011-05-21  2:29   ` Rusty Russell
2011-05-21  2:29   ` Rusty Russell
2011-05-21  2:29     ` Rusty Russell
2011-05-19 23:10 ` Michael S. Tsirkin
2011-05-19 23:10 ` [PATCHv2 02/14] virtio ring: inline function to check for events Michael S. Tsirkin
2011-05-19 23:10   ` Michael S. Tsirkin
2011-05-21  2:29   ` Rusty Russell
2011-05-21  2:29     ` Rusty Russell
2011-05-21  2:29   ` Rusty Russell
2011-05-19 23:10 ` Michael S. Tsirkin
2011-05-19 23:10 ` [PATCHv2 03/14] virtio_ring: support event idx feature Michael S. Tsirkin
2011-05-19 23:10 ` Michael S. Tsirkin
2011-05-19 23:10   ` Michael S. Tsirkin
2011-05-21  2:31   ` Rusty Russell
2011-05-21  2:31   ` Rusty Russell
2011-05-21  2:31     ` Rusty Russell
2011-05-19 23:10 ` [PATCHv2 04/14] vhost: support event index Michael S. Tsirkin
2011-05-19 23:10   ` Michael S. Tsirkin
2011-05-21  2:31   ` Rusty Russell
2011-05-21  2:31   ` Rusty Russell
2011-05-21  2:31     ` Rusty Russell
2011-05-19 23:10 ` Michael S. Tsirkin
2011-05-19 23:11 ` [PATCHv2 05/14] virtio_test: " Michael S. Tsirkin
2011-05-19 23:11 ` Michael S. Tsirkin
2011-05-19 23:11   ` Michael S. Tsirkin
2011-05-21  2:32   ` Rusty Russell
2011-05-21  2:32   ` Rusty Russell
2011-05-21  2:32     ` Rusty Russell
2011-05-19 23:11 ` [PATCHv2 06/14] virtio: add api for delayed callbacks Michael S. Tsirkin
2011-05-19 23:11 ` Michael S. Tsirkin
2011-05-19 23:11   ` Michael S. Tsirkin
2011-05-21  2:33   ` Rusty Russell
2011-05-21  2:33   ` Rusty Russell
2011-05-21  2:33     ` Rusty Russell
2011-05-19 23:11 ` [PATCHv2 07/14] virtio_net: delay TX callbacks Michael S. Tsirkin
2011-05-19 23:11   ` Michael S. Tsirkin
2011-05-19 23:11 ` Michael S. Tsirkin
2011-05-19 23:11 ` [PATCHv2 08/14] virtio_ring: Add capacity check API Michael S. Tsirkin
2011-05-19 23:11   ` Michael S. Tsirkin
2011-05-19 23:11 ` Michael S. Tsirkin
2011-05-19 23:11 ` [PATCHv2 09/14] virtio_net: fix TX capacity checks using new API Michael S. Tsirkin
2011-05-19 23:11   ` Michael S. Tsirkin
2011-05-21  2:13   ` Rusty Russell
2011-05-21  2:13   ` Rusty Russell
2011-05-21  2:13     ` Rusty Russell
2011-05-19 23:11 ` Michael S. Tsirkin
2011-05-19 23:11 ` [PATCHv2 10/14] virtio_net: limit xmit polling Michael S. Tsirkin
2011-05-19 23:11   ` Michael S. Tsirkin
2011-05-21  2:19   ` Rusty Russell
2011-05-21  2:19   ` Rusty Russell
2011-05-21  2:19     ` Rusty Russell
2011-05-22 12:10     ` Michael S. Tsirkin
2011-05-22 12:10       ` Michael S. Tsirkin
2011-05-23  2:07       ` Rusty Russell
2011-05-23  2:07         ` Rusty Russell
2011-05-23 11:19         ` Michael S. Tsirkin
2011-05-23 11:19         ` Michael S. Tsirkin
2011-05-23 11:19           ` Michael S. Tsirkin
2011-05-24  7:54           ` Krishna Kumar2
2011-05-24  7:54             ` Krishna Kumar2
2011-05-24  9:12             ` Michael S. Tsirkin
2011-05-24  9:12             ` Michael S. Tsirkin
2011-05-24  9:12               ` Michael S. Tsirkin
2011-05-24  9:27               ` Krishna Kumar2
2011-05-24  9:27               ` Krishna Kumar2
2011-05-24 11:29                 ` Michael S. Tsirkin
2011-05-24 11:29                   ` Michael S. Tsirkin
2011-05-24 12:50                   ` Krishna Kumar2
2011-05-24 12:50                     ` Krishna Kumar2
2011-05-24 13:52                     ` Michael S. Tsirkin
2011-05-24 13:52                       ` Michael S. Tsirkin
2011-05-24 13:52                     ` Michael S. Tsirkin
2011-05-24 12:50                   ` Krishna Kumar2
2011-05-24 11:29                 ` Michael S. Tsirkin
2011-05-24  7:54           ` Krishna Kumar2
2011-05-25  1:28           ` Rusty Russell
2011-05-25  1:28             ` Rusty Russell
2011-05-25  5:50             ` Michael S. Tsirkin
2011-05-25  5:50             ` Michael S. Tsirkin
2011-05-25  5:50               ` Michael S. Tsirkin
2011-05-25  1:28           ` Rusty Russell
2011-05-25  1:35           ` Rusty Russell
2011-05-25  1:35           ` Rusty Russell
2011-05-25  1:35             ` Rusty Russell
2011-05-25  6:07             ` Michael S. Tsirkin
2011-05-25  6:07               ` Michael S. Tsirkin
2011-05-26  3:28               ` Rusty Russell
2011-05-26  3:28               ` Rusty Russell
2011-05-26  3:28                 ` Rusty Russell
2011-05-28 20:02                 ` Michael S. Tsirkin
2011-05-28 20:02                   ` Michael S. Tsirkin
2011-05-30  6:27                   ` Rusty Russell
2011-05-30  6:27                     ` Rusty Russell
2011-05-30  6:27                   ` Rusty Russell
2011-05-28 20:02                 ` Michael S. Tsirkin
2011-05-25  6:07             ` Michael S. Tsirkin
2011-05-23  2:07       ` Rusty Russell
2011-05-22 12:10     ` Michael S. Tsirkin
2011-05-19 23:11 ` Michael S. Tsirkin
2011-05-19 23:12 ` [PATCHv2 11/14] virtio: don't delay avail index update Michael S. Tsirkin
2011-05-19 23:12   ` Michael S. Tsirkin
2011-05-21  2:26   ` Rusty Russell
2011-05-21  2:26   ` Rusty Russell
2011-05-21  2:26     ` Rusty Russell
2011-05-19 23:12 ` Michael S. Tsirkin
2011-05-19 23:12 ` [PATCHv2 12/14] virtio: 64 bit features Michael S. Tsirkin
2011-05-19 23:12 ` Michael S. Tsirkin
2011-05-19 23:12   ` Michael S. Tsirkin
2011-05-19 23:12 ` [PATCHv2 13/14] virtio_test: update for " Michael S. Tsirkin
2011-05-19 23:12 ` Michael S. Tsirkin
2011-05-19 23:12   ` Michael S. Tsirkin
2011-05-19 23:12 ` [PATCHv2 14/14] vhost: fix " Michael S. Tsirkin
2011-05-19 23:12   ` Michael S. Tsirkin
2011-05-19 23:12 ` Michael S. Tsirkin
2011-05-19 23:20 ` [PATCHv2 00/14] virtio and vhost-net performance enhancements David Miller
2011-05-19 23:20 ` David Miller
2011-05-20  7:51 ` Rusty Russell
2011-05-20  7:51   ` Rusty Russell
2011-05-20  7:51 ` Rusty Russell
2011-05-26 15:32 ` [PERF RESULTS] " Krishna Kumar2
2011-05-26 15:32   ` Krishna Kumar2
2011-05-26 15:42   ` Shirley Ma [this message]
2011-05-26 16:21     ` Krishna Kumar2
2011-05-26 16:21     ` Krishna Kumar2
     [not found]     ` <OFF9D0E604.B865A006-ON6525789C.00597010-6525789C.0059987A@LocalDomain>
2011-05-26 16:29       ` Krishna Kumar2
2011-05-26 16:29       ` Krishna Kumar2
2011-05-26 16:29         ` Krishna Kumar2
2011-05-26 15:32 ` Krishna Kumar2

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=OFE30C8D78.526FF88D-ON8725789C.00563B8C-8825789C.0056469F@us.ibm.com \
    --to=xma@us.ibm.com \
    --cc=borntraeger@de.ibm.com \
    --cc=cotte@de.ibm.com \
    --cc=habanero@linux.vnet.ibm.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=krkumar2@in.ibm.com \
    --cc=kvm@vger.kernel.org \
    --cc=lguest@lists.ozlabs.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-s390@vger.kernel.org \
    --cc=linux390@de.ibm.com \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=schwidefsky@de.ibm.com \
    --cc=steved@us.ibm.com \
    --cc=tahm@linux.vnet.ibm.com \
    --cc=virtualization@lists.linux-foundation.org \
    /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.