From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: "Tom Herbert" <therbert@google.com>,
"David Miller" <davem@davemloft.net>,
"Linux Netdev List" <netdev@vger.kernel.org>,
"Eric Dumazet" <eric.dumazet@gmail.com>,
"Hannes Frederic Sowa" <hannes@stressinduktion.org>,
"Florian Westphal" <fw@strlen.de>,
"Daniel Borkmann" <dborkman@redhat.com>,
"Alexander Duyck" <alexander.duyck@gmail.com>,
"John Fastabend" <john.r.fastabend@intel.com>,
"Dave Taht" <dave.taht@gmail.com>,
"Toke Høiland-Jørgensen" <toke@toke.dk>,
brouer@redhat.com
Subject: Re: [net-next PATCH V5] qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE
Date: Wed, 1 Oct 2014 21:47:00 +0200 [thread overview]
Message-ID: <20141001214700.18b16387@redhat.com> (raw)
In-Reply-To: <542C4E0D.4050404@mojatatu.com>
On Wed, 01 Oct 2014 14:55:09 -0400
Jamal Hadi Salim <jhs@mojatatu.com> wrote:
> On 10/01/14 13:28, Jesper Dangaard Brouer wrote:
>
> > Thus, code is activated only when q->qlen is >= 1. And I have already
> > shown that we see a win with just bulking 2 packets:
>
> If you can get 2 packets, indeed you win. If you can on average get >1
> over a long period, you still win.
> You have clearly demonstrated you can do that with traffic
> generators (udp or in kernel pktgen). I was more worried about the
> common use case scenario (handwaved as 1-24 TCP streams).
>
> The key here is: *if you never hit bulking* then the cost is
> _per packet_ for sch_direct_xmit bypass.
> Question is what is that cost for the common case as defined above?
> Can you hit a bulk level >1 on 1-24 TCP streams?
> I would be happy if your answer is *yes*.
Answer is yes. It is very easy with simple netperf TCP_STREAM to cause
queueing >1 packet in the qdisc layer. If tuned (according to my blog,
unloading netfilter etc.) then a single netperf TCP_STREAM will max out
10Gbit/s and cause a standing queue.
I'm monitoring backlog of qdiscs, and I always see >1 backlog, I never
saw a standing queue of 1 packet in my testing. Either the backlog
area is high 100-200 packets, or 0 backlog. (With fake pktgen/trafgen
style tests, it's possible to cause 1000 backlog).
> If your answer is no (since
> it is hard to achieve) - then how far off is it from before your
> patches (since now you have added at minimal a branch check).
> I think it is fair for you to quantify that, no?
> Feature is still useful for the other cases.
>
> Note:
> This is what i referred to as the "no animals were hurt during the
> making of these patches" statement. I am sorry again for raining on
> the parade.
I'm starting to think this patch is the most carefully tested patch on
netdev for a very very long time... I'm getting tired of this testing
going on for so long.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Sr. Network Kernel Developer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
next prev parent reply other threads:[~2014-10-01 19:47 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-30 8:53 [net-next PATCH V5] qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Jesper Dangaard Brouer
2014-09-30 11:07 ` Jamal Hadi Salim
2014-09-30 18:20 ` David Miller
2014-10-01 13:17 ` Jamal Hadi Salim
2014-10-01 14:55 ` Tom Herbert
2014-10-01 15:34 ` Jamal Hadi Salim
2014-10-01 17:28 ` Jesper Dangaard Brouer
2014-10-01 18:55 ` Jamal Hadi Salim
2014-10-01 19:47 ` Jesper Dangaard Brouer [this message]
2014-10-01 20:05 ` Jamal Hadi Salim
2014-10-01 20:32 ` Jesper Dangaard Brouer
2014-10-02 5:18 ` Dave Taht
2014-10-02 7:44 ` Jesper Dangaard Brouer
2014-10-02 10:08 ` Toke Høiland-Jørgensen
2014-10-02 13:02 ` Jamal Hadi Salim
2014-10-02 12:53 ` Jamal Hadi Salim
2014-10-01 19:47 ` David Miller
2014-09-30 11:48 ` Eric Dumazet
2014-09-30 12:25 ` Florian Westphal
2014-09-30 12:38 ` Eric Dumazet
2014-09-30 12:41 ` Florian Westphal
2014-09-30 22:07 ` Jesper Dangaard Brouer
2014-09-30 22:15 ` Eric Dumazet
2014-09-30 12:34 ` Eric Dumazet
2014-09-30 12:51 ` [net-next PATCH] dql: add a burst attribute Eric Dumazet
2014-09-30 13:46 ` Florian Westphal
2014-09-30 14:17 ` Eric Dumazet
2014-09-30 14:26 ` Tom Herbert
2014-09-30 14:49 ` Eric Dumazet
2014-09-30 15:05 ` Tom Herbert
2014-09-30 14:31 ` Florian Westphal
2014-09-30 14:55 ` Eric Dumazet
2014-09-30 21:46 ` Jesper Dangaard Brouer
2014-10-01 4:44 ` Tom Herbert
2014-09-30 15:26 ` Florian Westphal
2014-09-30 15:39 ` Dave Taht
2014-09-30 15:41 ` Eric Dumazet
2014-09-30 21:29 ` Jesper Dangaard Brouer
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=20141001214700.18b16387@redhat.com \
--to=brouer@redhat.com \
--cc=alexander.duyck@gmail.com \
--cc=dave.taht@gmail.com \
--cc=davem@davemloft.net \
--cc=dborkman@redhat.com \
--cc=eric.dumazet@gmail.com \
--cc=fw@strlen.de \
--cc=hannes@stressinduktion.org \
--cc=jhs@mojatatu.com \
--cc=john.r.fastabend@intel.com \
--cc=netdev@vger.kernel.org \
--cc=therbert@google.com \
--cc=toke@toke.dk \
/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).