From: "Hunt, David" <david.hunt@intel.com>
To: Jerin Jacob <jerin.jacob@caviumnetworks.com>,
Olivier Matz <olivier.matz@6wind.com>
Cc: dev@dpdk.org, thomas.monjalon@6wind.com,
bruce.richardson@intel.com, konstantin.ananyev@intel.com
Subject: Re: [dpdk-dev] [PATCH] mbuf: replace c memcpy code semantics with optimized rte_memcpy
Date: Fri, 27 May 2016 14:45:19 +0100 [thread overview]
Message-ID: <57484F6F.40204@intel.com> (raw)
In-Reply-To: <57482079.1050605@intel.com>
On 5/27/2016 11:24 AM, Hunt, David wrote:
>
>
> On 5/24/2016 4:17 PM, Jerin Jacob wrote:
>> On Tue, May 24, 2016 at 04:59:47PM +0200, Olivier Matz wrote:
>>
>>> Are you seeing some performance improvement by using rte_memcpy()?
>> Yes, In some case, In default case, It was replaced with memcpy by the
>> compiler itself(gcc 5.3). But when I tried external mempool manager
>> patch and
>> then performance dropped almost 800Kpps. Debugging further it turns
>> out that
>> external mempool managers unrelated change was knocking out the memcpy.
>> explicit rte_memcpy brought back 500Kpps. Remaing 300Kpps drop is still
>> unknown(In my test setup, packets are in the local cache, so it must be
>> something do with __mempool_put_bulk text alignment change or similar.
>>
>> Anyone else observed performance drop with external poolmanager?
>>
>> Jerin
>
> Jerin,
> I'm seeing a 300kpps drop in throughput when I apply this on top
> of the external
> mempool manager patch. If you're seeing an increase if you apply this
> patch first, then
> a drop when applying the mempool manager, the two patches must be
> conflicting in
> some way. We probably need to investigate further.
> Regards,
> Dave.
>
On further investigation, I now have a setup with no performance
degradation. My previous tests
were accessing the NICS on a different NUMA node. Once I initiated
testPMD with the correct coremask,
the difference between pre and post rte_memcpy patch is negligible
(maybe 0.1% drop).
Regards,
Dave.
next prev parent reply other threads:[~2016-05-27 13:45 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-24 14:50 Jerin Jacob
2016-05-24 14:59 ` Olivier Matz
2016-05-24 15:17 ` Jerin Jacob
2016-05-27 10:24 ` Hunt, David
2016-05-27 11:42 ` Jerin Jacob
2016-05-27 15:05 ` Thomas Monjalon
2016-05-30 8:44 ` Olivier Matz
2016-05-27 13:45 ` Hunt, David [this message]
2016-06-24 15:56 ` Hunt, David
2016-06-24 16:02 ` Olivier Matz
2016-05-26 8:07 ` [dpdk-dev] [PATCH v2] mempool: " Jerin Jacob
2016-05-30 8:45 ` Olivier Matz
2016-05-31 12:58 ` Jerin Jacob
2016-05-31 21:05 ` Olivier MATZ
2016-06-01 7:00 ` Jerin Jacob
2016-06-02 7:36 ` Olivier MATZ
2016-06-02 9:39 ` Jerin Jacob
2016-06-02 21:16 ` Olivier MATZ
2016-06-03 7:02 ` Jerin Jacob
2016-06-17 10:40 ` Olivier Matz
2016-06-24 16:04 ` Olivier Matz
2016-06-30 9:41 ` Thomas Monjalon
2016-06-30 11:38 ` Jerin Jacob
2016-06-30 12:16 ` [dpdk-dev] [PATCH v3] " Jerin Jacob
2016-06-30 17:28 ` Thomas Monjalon
2016-07-05 8:43 ` Ferruh Yigit
2016-07-05 11:32 ` Yuanhan Liu
2016-07-05 13:13 ` Jerin Jacob
2016-07-05 13:42 ` Yuanhan Liu
2016-07-05 14:09 ` Ferruh Yigit
2016-07-06 16:21 ` Ferruh Yigit
2016-07-07 13:51 ` Ferruh Yigit
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=57484F6F.40204@intel.com \
--to=david.hunt@intel.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--cc=jerin.jacob@caviumnetworks.com \
--cc=konstantin.ananyev@intel.com \
--cc=olivier.matz@6wind.com \
--cc=thomas.monjalon@6wind.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).