From: Shahaf Shuler <shahafs@mellanox.com>
To: Ferruh Yigit <ferruh.yigit@intel.com>, "dev@dpdk.org" <dev@dpdk.org>
Subject: Re: [dpdk-dev] [PATCH] doc: announce ABI change on ethdev
Date: Tue, 9 May 2017 16:55:33 +0000 [thread overview]
Message-ID: <AM4PR05MB1505743F97FE80EC7D609F4FC3EF0@AM4PR05MB1505.eurprd05.prod.outlook.com> (raw)
In-Reply-To: <1d625f78-e6e4-c4c3-9775-e5c59666e5fa@intel.com>
Tuesday, May 9, 2017 4:49 PM, Ferruh Yigit:
> On 5/1/2017 7:58 AM, Shahaf Shuler wrote:
>
> I understand the consistency part, but why PMD performs better when Tx
> offload disabled?
>
Well Adrien pretty much summarized it [1].
Tx offload consumes cycles, for examples checksum or TSO.
Since those offloads are enabled by default, the application will need to pay for them, even if they are not used.
True, it is possible to disable them, however when new offloads are introduced the application will need to be constantly modified in order to disable the new ones.
A better approach will be to disable all the Tx offload by default, and enable them according to the application needs.
This will enable to the PMD to provide the Tx burst function which suits the most to the application specific needs, with no extra overhead.
[1] http://dpdk.org/ml/archives/dev/2017-May/065509.html
next prev parent reply other threads:[~2017-05-09 16:55 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-05-01 6:58 Shahaf Shuler
2017-05-09 10:24 ` Shahaf Shuler
2017-05-09 13:40 ` Adrien Mazarguil
2017-05-09 17:04 ` Jerin Jacob
2017-05-10 23:17 ` Thomas Monjalon
2017-05-09 13:49 ` Ferruh Yigit
2017-05-09 16:55 ` Shahaf Shuler [this message]
2017-05-09 18:09 ` Ananyev, Konstantin
2017-05-10 14:29 ` Bruce Richardson
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=AM4PR05MB1505743F97FE80EC7D609F4FC3EF0@AM4PR05MB1505.eurprd05.prod.outlook.com \
--to=shahafs@mellanox.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@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).