Re: [PATCH 0/15] KVM: optimize for MMIO handled

public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed

From: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
To: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Cc: Avi Kivity <avi@redhat.com>,
	Marcelo Tosatti <mtosatti@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>, KVM <kvm@vger.kernel.org>
Subject: Re: [PATCH 0/15] KVM: optimize for MMIO handled
Date: Wed, 08 Jun 2011 13:16:07 +0800	[thread overview]
Message-ID: <4DEF0597.9030101@cn.fujitsu.com> (raw)
In-Reply-To: <20110608124740.14c807f7.yoshikawa.takuya@oss.ntt.co.jp>

On 06/08/2011 11:47 AM, Takuya Yoshikawa wrote:

>>> Sure, KVM guest is the client, and it uses e1000 NIC, and uses NAT
>>> network connect to the netperf server, the bandwidth of our network
>>> is 100M.
>>>
> 
> I see the reason, thank you!
> 
> I used virtio-net and you used e1000.
> You are using e1000 to see the MMIO performance change, right?
> 

Hi Takuya,

Please applied my fix path when you test it again, thanks! :-)
(http://www.spinics.net/lists/kvm/msg56017.html)

Just then, in order to affirm the performance result, i tested it again,
and do not use our office network(since such many boxes in this network),
just boot two guests, one runs netperf server, one runs netperf client,
both use e1000 and NAT network.

I'll test the performance of virtio-net!

This is the result:

ept = 1:
============================
Before patch:
--------------
TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1182.27   
16384  87380 

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1185.84   
16384  87380 

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1181.58   
16384  87380 

After patch:
--------------
TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1205.65   
16384  87380 

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1216.06   
16384  87380

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1215.70   
16384  87380 

ept = 0, bypass_guest_pf=0:
============================
Before patch:
--------------
TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1169.70   
16384  87380 

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1160.82   
16384  87380 

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1168.01   
16384  87380 

After patch:
--------------
TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1266.28   
16384  87380 

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1268.16  

TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 192.168.122.247 (192.168.122.247) port 0 AF_INET
Local /Remote
Socket Size   Request  Resp.   Elapsed  Trans.
Send   Recv   Size     Size    Time     Rate         
bytes  Bytes  bytes    bytes   secs.    per sec   

16384  87380  1        1       60.00    1267.18   
16384  87380 

To my surprise is: after patch, the performance of ept = 0, bypass_guest_pf=0 is better than
the performance of ept = 1, maybe it is because MMIO is too much in network guests :-)

next prev parent reply	other threads:[~2011-06-08  5:14 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-06-07 12:58 [PATCH 0/15] KVM: optimize for MMIO handled Xiao Guangrong
2011-06-07 12:58 ` [PATCH 01/15] KVM: MMU: fix walking shadow page table Xiao Guangrong
2011-06-07 12:59 ` [PATCH 02/15] KVM: MMU: do not update slot bitmap if spte is nonpresent Xiao Guangrong
2011-06-20 16:28   ` Marcelo Tosatti
2011-06-20 18:32     ` Xiao Guangrong
2011-06-07 12:59 ` [PATCH 03/15] KVM: x86: avoid unnecessarily guest page table walking Xiao Guangrong
2011-06-09  6:59   ` Avi Kivity
2011-06-10  3:51     ` Xiao Guangrong
2011-06-07 13:00 ` [PATCH 04/15] KVM: MMU: cache mmio info on page fault path Xiao Guangrong
2011-06-08  8:22   ` Alexander Graf
2011-06-08  8:58     ` Xiao Guangrong
2011-06-08  9:18       ` Alexander Graf
2011-06-08  9:33         ` Xiao Guangrong
2011-06-08  9:39           ` Alexander Graf
2011-06-20 16:14   ` Marcelo Tosatti
2011-06-20 16:16     ` Marcelo Tosatti
2011-06-07 13:01 ` [PATCH 05/15] KVM: MMU: optimize to handle dirty bit Xiao Guangrong
2011-06-08  3:16   ` Xiao Guangrong
2011-06-07 13:01 ` [PATCH 06/15] KVM: MMU: cleanup for FNAME(fetch) Xiao Guangrong
2011-06-07 13:02 ` [PATCH 07/15] KVM: MMU: rename 'pt_write' to 'emulate' Xiao Guangrong
2011-06-07 13:02 ` [PATCH 08/15] KVM: MMU: count used shadow pages on preparing path Xiao Guangrong
2011-06-07 13:03 ` [PATCH 09/15] KVM: MMU: split kvm_mmu_free_page Xiao Guangrong
2011-06-09  7:07   ` Avi Kivity
2011-06-10  3:50     ` Xiao Guangrong
2011-06-12  8:33       ` Avi Kivity
2011-06-13  3:15         ` Xiao Guangrong
2011-06-07 13:04 ` [PATCH 10/15] KVM: MMU: lockless walking shadow page table Xiao Guangrong
2011-06-09 20:09   ` Paul E. McKenney
2011-06-10  4:23     ` Xiao Guangrong
2011-06-20 16:37   ` Marcelo Tosatti
2011-06-20 18:54     ` Xiao Guangrong
2011-06-07 13:05 ` [PATCH 11/15] KVM: MMU: filter out the mmio pfn from the fault pfn Xiao Guangrong
2011-06-07 13:05 ` [PATCH 12/15] KVM: MMU: abstract some functions to handle " Xiao Guangrong
2011-06-07 13:06 ` [PATCH 13/15] KVM: VMX: modify the default value of nontrap shadow pte Xiao Guangrong
2011-06-09  7:14   ` Avi Kivity
2011-06-07 13:07 ` [PATCH 14/15] KVM: MMU: mmio page fault support Xiao Guangrong
2011-06-09  7:28   ` Avi Kivity
2011-06-10  3:47     ` Xiao Guangrong
2011-06-12  8:38       ` Avi Kivity
2011-06-13  3:38         ` Xiao Guangrong
2011-06-13  8:10           ` Avi Kivity
2011-06-07 13:07 ` [PATCH 15/15] KVM: MMU: trace mmio page fault Xiao Guangrong
2011-06-08  3:11 ` [PATCH 0/15] KVM: optimize for MMIO handled Takuya Yoshikawa
2011-06-08  3:25   ` Xiao Guangrong
2011-06-08  3:32     ` Xiao Guangrong
2011-06-08  3:47       ` Takuya Yoshikawa
2011-06-08  5:16         ` Xiao Guangrong [this message]
2011-06-08  6:22         ` Xiao Guangrong
2011-06-08  8:33           ` Takuya Yoshikawa
2011-06-09  7:39 ` Avi Kivity
2011-06-10  4:05   ` Xiao Guangrong
2011-06-12  8:47     ` Avi Kivity
2011-06-13  4:46       ` Xiao Guangrong
2011-06-13  8:06         ` 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=4DEF0597.9030101@cn.fujitsu.com \
    --to=xiaoguangrong@cn.fujitsu.com \
    --cc=avi@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtosatti@redhat.com \
    --cc=yoshikawa.takuya@oss.ntt.co.jp \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox