DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Wang, Zhihong" <zhihong.wang@intel.com>
To: Maxime Coquelin <maxime.coquelin@redhat.com>,
	Yuanhan Liu <yuanhan.liu@linux.intel.com>
Cc: "stephen@networkplumber.org" <stephen@networkplumber.org>,
	"Pierre Pfister (ppfister)" <ppfister@cisco.com>,
	"Xie, Huawei" <huawei.xie@intel.com>,
	"dev@dpdk.org" <dev@dpdk.org>,
	"vkaplans@redhat.com" <vkaplans@redhat.com>,
	"mst@redhat.com" <mst@redhat.com>
Subject: Re: [dpdk-dev] [PATCH v4] vhost: Add indirect descriptors support to the TX path
Date: Fri, 4 Nov 2016 12:30:51 +0000	[thread overview]
Message-ID: <8F6C2BD409508844A0EFC19955BE09414E7DC66F@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <cf5e40da-0201-8c89-5314-96c87894da12@redhat.com>



> -----Original Message-----
> From: Maxime Coquelin [mailto:maxime.coquelin@redhat.com]
> Sent: Friday, November 4, 2016 7:23 PM
> To: Wang, Zhihong <zhihong.wang@intel.com>; Yuanhan Liu
> <yuanhan.liu@linux.intel.com>
> Cc: stephen@networkplumber.org; Pierre Pfister (ppfister)
> <ppfister@cisco.com>; Xie, Huawei <huawei.xie@intel.com>; dev@dpdk.org;
> vkaplans@redhat.com; mst@redhat.com
> Subject: Re: [dpdk-dev] [PATCH v4] vhost: Add indirect descriptors support to the
> TX path
> 
> 
> 
> >>>> Hi Maxime,
> >>>>
> >>>> I did a little more macswap test and found out more stuff here:
> >>> Thanks for doing more tests.
> >>>
> >>>>
> >>>>  1. I did loopback test on another HSW machine with the same H/W,
> >>>>     and indirect_desc on and off seems have close perf
> >>>>
> >>>>  2. So I checked the gcc version:
> >>>>
> >>>>      *  Previous: gcc version 6.2.1 20160916 (Fedora 24)
> >>>>
> >>>>      *  New: gcc version 5.4.0 20160609 (Ubuntu 16.04.1 LTS)
> >>>
> >>> On my side, I tested with RHEL7.3:
> >>>  - gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-11)
> >>>
> >>> It certainly contains some backports from newer GCC versions.
> >>>
> >>>>
> >>>>     On previous one indirect_desc has 20% drop
> >>>>
> >>>>  3. Then I compiled binary on Ubuntu and scp to Fedora, and as
> >>>>     expected I got the same perf as on Ubuntu, and the perf gap
> >>>>     disappeared, so gcc is definitely one factor here
> >>>>
> >>>>  4. Then I use the Ubuntu binary on Fedora for PVP test, then the
> >>>>     perf gap comes back again and the same with the Fedora binary
> >>>>     results, indirect_desc causes about 20% drop
> >>>
> >>> Let me know if I understand correctly:
> >
> > Yes, and it's hard to breakdown further at this time.
> >
> > Also we may need to check whether it's caused by certain NIC
> > model. Unfortunately I don't have the right setup right now.
> >
> >>> Loopback test with macswap:
> >>>  - gcc version 6.2.1 : 20% perf drop
> >>>  - gcc version 5.4.0 : No drop
> >>>
> >>> PVP test with macswap:
> >>>  - gcc version 6.2.1 : 20% perf drop
> >>>  - gcc version 5.4.0 : 20% perf drop
> >>
> >> I forgot to ask, did you recompile only host, or both host and guest
> >> testmpd's in your test?
> 
> > Both.
> 
> I recompiled testpmd on a Fedora 24 machine using GCC6:
> gcc (GCC) 6.1.1 20160621 (Red Hat 6.1.1-3)
> Testing loopback with macswap on my Haswell RHEL7.3 machine gives me the
> following results:
>   - indirect on: 7.75Mpps
>   - indirect off: 7.35Mpps
> 
> Surprisingly, I get better results with indirect on my setup (I
> reproduced the tests multiple times).
> 
> Do you have a document explaining the tuning/config you apply to both
> the host and the guest (isolation, HT, hugepage size, ...) in your
> setup?


The setup where it goes wrong:
 1. Xeon E5-2699, HT on, turbo off, 1GB hugepage for both host and guest
 2. Fortville 40G
 3. Fedora 4.7.5-200.fc24.x86_64
 4. gcc version 6.2.1
 5. 16.11 RC2 for both host and guest
 6. PVP, testpmd macswap for both host and guest

BTW, I do see indirect_desc gives slightly better performance for loopback
in tests on other platforms, but don't know how PVP performs yet.


> 
> Regards,
> Maxime

  parent reply	other threads:[~2016-11-04 12:30 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-23  8:28 [dpdk-dev] [PATCH v3] " Maxime Coquelin
2016-09-23 15:49 ` Michael S. Tsirkin
2016-09-23 18:02   ` Maxime Coquelin
2016-09-23 18:06     ` Michael S. Tsirkin
2016-09-23 18:16       ` Maxime Coquelin
2016-09-23 18:22         ` Michael S. Tsirkin
2016-09-23 20:24           ` Stephen Hemminger
2016-09-26  3:03             ` Yuanhan Liu
2016-09-26 12:25               ` Michael S. Tsirkin
2016-09-26 13:04                 ` Yuanhan Liu
2016-09-27  4:15 ` Yuanhan Liu
2016-09-27  7:25   ` Maxime Coquelin
2016-09-27  8:42 ` [dpdk-dev] [PATCH v4] " Maxime Coquelin
2016-09-27 12:18   ` Yuanhan Liu
2016-10-14  7:24   ` Wang, Zhihong
2016-10-14  7:34     ` Wang, Zhihong
2016-10-14 15:50     ` Maxime Coquelin
2016-10-17 11:23       ` Maxime Coquelin
2016-10-17 13:21         ` Yuanhan Liu
2016-10-17 14:14           ` Maxime Coquelin
2016-10-27  9:00             ` Wang, Zhihong
2016-10-27  9:10               ` Maxime Coquelin
2016-10-27  9:55                 ` Maxime Coquelin
2016-10-27 10:19                   ` Wang, Zhihong
2016-10-28  7:32                     ` Pierre Pfister (ppfister)
2016-10-28  7:58                       ` Maxime Coquelin
2016-11-01  8:15                         ` Yuanhan Liu
2016-11-01  9:39                           ` Thomas Monjalon
2016-11-02  2:44                             ` Yuanhan Liu
2016-10-27 10:33                 ` Yuanhan Liu
2016-10-27 10:35                   ` Maxime Coquelin
2016-10-27 10:46                     ` Yuanhan Liu
2016-10-28  0:49                       ` Wang, Zhihong
2016-10-28  7:42                         ` Maxime Coquelin
2016-10-31 10:01                           ` Wang, Zhihong
2016-11-02 10:51                             ` Maxime Coquelin
2016-11-03  8:11                               ` Maxime Coquelin
2016-11-04  6:18                                 ` Xu, Qian Q
2016-11-04  7:41                                   ` Maxime Coquelin
2016-11-04  7:20                                 ` Wang, Zhihong
2016-11-04  7:57                                   ` Maxime Coquelin
2016-11-04  7:59                                     ` Maxime Coquelin
2016-11-04 10:43                                       ` Wang, Zhihong
2016-11-04 11:22                                         ` Maxime Coquelin
2016-11-04 11:36                                           ` Yuanhan Liu
2016-11-04 11:39                                             ` Maxime Coquelin
2016-11-04 12:30                                           ` Wang, Zhihong [this message]
2016-11-04 12:54                                             ` Maxime Coquelin
2016-11-04 13:09                                               ` Wang, Zhihong
2016-11-08 10:51                                                 ` Wang, Zhihong
2016-10-27 10:53                   ` Maxime Coquelin
2016-10-28  6:05                     ` Xu, Qian Q

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=8F6C2BD409508844A0EFC19955BE09414E7DC66F@SHSMSX103.ccr.corp.intel.com \
    --to=zhihong.wang@intel.com \
    --cc=dev@dpdk.org \
    --cc=huawei.xie@intel.com \
    --cc=maxime.coquelin@redhat.com \
    --cc=mst@redhat.com \
    --cc=ppfister@cisco.com \
    --cc=stephen@networkplumber.org \
    --cc=vkaplans@redhat.com \
    --cc=yuanhan.liu@linux.intel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).