From: Jesper Dangaard Brouer <brouer@redhat•com>
To: David Miller <davem@davemloft•net>
Cc: eric.dumazet@gmail•com, hannes@stressinduktion•org,
netdev@vger•kernel.org, therbert@google•com, fw@strlen•de,
dborkman@redhat•com, jhs@mojatatu•com, alexander.duyck@gmail•com,
john.r.fastabend@intel•com, dave.taht@gmail•com, toke@toke•dk,
brouer@redhat•com
Subject: Re: Quota in __qdisc_run()
Date: Tue, 7 Oct 2014 20:03:29 +0200 [thread overview]
Message-ID: <20141007200329.5d20a27e@redhat.com> (raw)
In-Reply-To: <20141007.131938.1410434352331637585.davem@davemloft.net>
On Tue, 07 Oct 2014 13:19:38 -0400 (EDT)
David Miller <davem@davemloft•net> wrote:
> From: Eric Dumazet <eric.dumazet@gmail•com>
> Date: Tue, 07 Oct 2014 08:01:20 -0700
>
> > On Tue, 2014-10-07 at 16:43 +0200, Hannes Frederic Sowa wrote:
> >
> >> This needs to be:
> >>
> >> do
> >> ...
> >> while ((iskb = iskb->next))
> >
> > I do not feel needed to break the bulk dequeue at precise quota
> > boundary. These quotas are advisory, and bql prefers to get its full
> > budget for appropriate feedback from TX completion.
> >
> > Quota was a packet quota, which was quite irrelevant if segmentation had
> > to be done, so I would just let the dequeue be done so that we benefit
> > from optimal xmit_more.
>
> Yes, this makes sense, do a full qdisc_restart() cycle without boundaries,
> then check how much quota was used afterwards to guard the outermost loop.
According to my measurements, at 10Gbit/s TCP_STREAM test the BQL limit
is 381528 bytes / 1514 = 252 packets, that will (potentially) be bulk
dequeued at once (with your version of the patch).
It seems to have the potential to exceed the weight_p(64) quite a lot.
And with e.g. TX ring size 512, we also also challenge the drivers at
this early adoption phase of tailptr writes. Just saying...
--
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:[~2014-10-07 18:22 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-01 20:35 [net-next PATCH V6 0/2] qdisc: bulk dequeue support Jesper Dangaard Brouer
2014-10-01 20:35 ` [net-next PATCH V6 1/2] qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Jesper Dangaard Brouer
2014-10-01 20:36 ` [net-next PATCH V6 2/2] qdisc: dequeue bulking also pickup GSO/TSO packets Jesper Dangaard Brouer
2014-10-02 14:35 ` Eric Dumazet
2014-10-02 14:38 ` Daniel Borkmann
2014-10-02 14:42 ` [net-next PATCH V6 0/2] qdisc: bulk dequeue support Tom Herbert
2014-10-02 15:04 ` Eric Dumazet
2014-10-02 15:24 ` [PATCH net-next] mlx4: add a new xmit_more counter Eric Dumazet
2014-10-05 0:04 ` David Miller
2014-10-02 15:27 ` [net-next PATCH V6 0/2] qdisc: bulk dequeue support Tom Herbert
2014-10-02 16:52 ` Florian Westphal
2014-10-02 17:32 ` Eric Dumazet
2014-10-02 17:35 ` Tom Herbert
2014-10-03 19:38 ` David Miller
2014-10-03 20:57 ` Eric Dumazet
2014-10-03 21:56 ` David Miller
2014-10-03 21:57 ` Eric Dumazet
2014-10-03 22:15 ` Eric Dumazet
2014-10-03 22:19 ` Tom Herbert
2014-10-03 22:56 ` Eric Dumazet
2014-10-03 22:30 ` David Miller
2014-10-03 22:31 ` [PATCH net-next] qdisc: validate skb without holding lock Eric Dumazet
2014-10-03 22:36 ` David Miller
2014-10-03 23:30 ` Eric Dumazet
2014-10-07 7:34 ` Quota in __qdisc_run() (was: qdisc: validate skb without holding lock) Jesper Dangaard Brouer
2014-10-07 12:47 ` Eric Dumazet
2014-10-07 13:30 ` Jesper Dangaard Brouer
2014-10-07 14:43 ` Hannes Frederic Sowa
2014-10-07 15:01 ` Eric Dumazet
2014-10-07 15:06 ` Eric Dumazet
2014-10-07 17:19 ` Quota in __qdisc_run() David Miller
2014-10-07 17:32 ` Eric Dumazet
2014-10-07 18:37 ` Jesper Dangaard Brouer
2014-10-07 20:07 ` Jesper Dangaard Brouer
2014-10-07 18:03 ` Jesper Dangaard Brouer [this message]
2014-10-07 19:10 ` Eric Dumazet
2014-10-07 19:34 ` Jesper Dangaard Brouer
2014-10-07 15:26 ` Quota in __qdisc_run() (was: qdisc: validate skb without holding lock) Jesper Dangaard Brouer
2014-10-08 17:38 ` Quota in __qdisc_run() John Fastabend
2014-10-06 14:12 ` [PATCH net-next] qdisc: validate skb without holding lock Jesper Dangaard Brouer
2014-10-04 3:59 ` [PATCH net-next] net: skb_segment() provides list head and tail Eric Dumazet
2014-10-06 4:38 ` David Miller
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=20141007200329.5d20a27e@redhat.com \
--to=brouer@redhat$(echo .)com \
--cc=alexander.duyck@gmail$(echo .)com \
--cc=dave.taht@gmail$(echo .)com \
--cc=davem@davemloft$(echo .)net \
--cc=dborkman@redhat$(echo .)com \
--cc=eric.dumazet@gmail$(echo .)com \
--cc=fw@strlen$(echo .)de \
--cc=hannes@stressinduktion$(echo .)org \
--cc=jhs@mojatatu$(echo .)com \
--cc=john.r.fastabend@intel$(echo .)com \
--cc=netdev@vger$(echo .)kernel.org \
--cc=therbert@google$(echo .)com \
--cc=toke@toke$(echo .)dk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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