From: jamal <hadi@cyberus.ca>
To: Changli Gao <xiaosuo@gmail.com>
Cc: netdev@vger.kernel.org
Subject: Re: [PATCH 3/3] ifb: move tq from ifb_private
Date: Sat, 04 Dec 2010 09:42:36 -0500 [thread overview]
Message-ID: <1291473756.2159.31.camel@mojatatu> (raw)
In-Reply-To: <1291472282.2159.8.camel@mojatatu>
On Sat, 2010-12-04 at 09:18 -0500, jamal wrote:
> I like the splice idea but this patch makes me twitch
> a little. What test setup did you use to check it?
Ok, here's one thing you changed which is important. We do:
-->XXX-->rq-->tq-->XXX-->
rq is controlled by queue limit.
We only load rq to tq if all of tq is empty. If it is not
we dont move things over. Essentially this is a flow
control scheme. We dont want many sources to be overwhelming
us with packets and every time we grab a txqlen number of packets.
For this reason:
I would be comfortable if all you did was to add the splice
after you skb_peek() - i think that would be a good improvement
which is not bound to break anything else.
cheers,
jamal
next prev parent reply other threads:[~2010-12-04 14:42 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-12-04 5:55 [PATCH 1/3] ifb: remove the useless debug stats Changli Gao
2010-12-04 5:55 ` [PATCH 2/3] ifb: remove unused macro TX_TIMEOUT Changli Gao
2010-12-04 14:13 ` jamal
2010-12-04 5:55 ` [PATCH 3/3] ifb: move tq from ifb_private Changli Gao
2010-12-04 13:15 ` Jarek Poplawski
2010-12-04 13:29 ` Changli Gao
2010-12-04 14:28 ` jamal
2010-12-04 14:45 ` Changli Gao
2010-12-04 14:55 ` jamal
2010-12-04 15:01 ` Changli Gao
2010-12-04 15:09 ` jamal
2010-12-04 14:48 ` jamal
2010-12-04 15:40 ` Jarek Poplawski
2010-12-04 16:08 ` jamal
2010-12-04 16:56 ` Jarek Poplawski
2010-12-05 0:22 ` Changli Gao
2010-12-05 1:13 ` Changli Gao
2010-12-05 14:30 ` jamal
2010-12-05 14:40 ` Changli Gao
2010-12-05 15:13 ` Eric Dumazet
2010-12-05 15:16 ` Changli Gao
2010-12-05 15:13 ` jamal
2010-12-05 15:22 ` Changli Gao
2010-12-05 15:31 ` jamal
2010-12-05 14:27 ` jamal
2010-12-05 19:09 ` Jarek Poplawski
2010-12-04 14:18 ` jamal
2010-12-04 14:20 ` Changli Gao
2010-12-04 14:42 ` jamal [this message]
2010-12-04 14:50 ` Changli Gao
2010-12-04 14:59 ` jamal
2010-12-04 15:07 ` Changli Gao
2010-12-04 15:11 ` jamal
2010-12-04 14:12 ` [PATCH 1/3] ifb: remove the useless debug stats jamal
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=1291473756.2159.31.camel@mojatatu \
--to=hadi@cyberus.ca \
--cc=netdev@vger.kernel.org \
--cc=xiaosuo@gmail.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).