netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jesper Dangaard Brouer <brouer@redhat.com>
To: David Miller <davem@davemloft.net>
Cc: eric.dumazet@gmail.com, netdev@vger.kernel.org,
	therbert@google.com, hannes@stressinduktion.org, 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: [PATCH net-next] qdisc: validate skb without holding lock
Date: Mon, 6 Oct 2014 16:12:35 +0200	[thread overview]
Message-ID: <20141006161235.010033f5@redhat.com> (raw)
In-Reply-To: <20141003.153645.72976986956341944.davem@davemloft.net>

On Fri, 03 Oct 2014 15:36:45 -0700 (PDT)
David Miller <davem@davemloft.net> wrote:

> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Fri, 03 Oct 2014 15:31:07 -0700
> 
> > From: Eric Dumazet <edumazet@google.com>
> > 
> > Validation of skb can be pretty expensive :
> > 
> > GSO segmentation and/or checksum computations.
> > 
> > We can do this without holding qdisc lock, so that other cpus
> > can queue additional packets.
> > 
[...]
> > 
> > Turning TSO on or off had no effect on throughput, only few more cpu
> > cycles. Lock contention on qdisc lock disappeared.

This is good work! Lock contention significantly reduced!

My 10G tests just 2x 10G netperf TCP_STREAM shows:

 With GSO=off TSO=off, _raw_spin_lock is now only at perf top#13 with
1.44% (80% from qdisc calls, 60% is from __dev_queue_xmit and 20% from
sch_direct_xmit) (before with qdisc bulking is was 2.66%).

 The "show off" case is GSO=on TSO=off, where raw_spin_lock is now only
at perf top#26 with 0.85% and only 54.74% comes from qdisc calls
(52.07% sch_direct_xmit and 2.67% __dev_queue_xmit).


This is some significant improvements to the kernels xmit layer,
me very happy!!! :-))) Thanks everyone!

-- 
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

  parent reply	other threads:[~2014-10-06 14:13 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
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             ` Jesper Dangaard Brouer [this message]
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=20141006161235.010033f5@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).