From: Eric Dumazet <eric.dumazet@gmail.com>
To: Patrick McHardy <kaber@trash.net>
Cc: Christoph Lameter <cl@linux-foundation.org>,
Mark Smith <lk-netdev@lk-netdev.nosense.org>,
Jarek Poplawski <jarkao2@gmail.com>,
netdev@vger.kernel.org, davem@linux-foundation.org
Subject: Re: UDP is bypassing qdisc statistics ....
Date: Tue, 01 Sep 2009 16:58:15 +0200 [thread overview]
Message-ID: <4A9D3687.2020101@gmail.com> (raw)
In-Reply-To: <4A9D2DBF.8030200@trash.net>
Patrick McHardy a écrit :
> Christoph Lameter wrote:
>> Eric: This occurs with a Broadcom driver (bnx2). There is only one
>> network device up and the IP statistics are correctly incremented.
>
> That explains it. The bnx2 driver uses multiple TX queues, but
> tc_dump_qdisc() only dumps the statistics from queue number 0.
>
> Not sure whether we should sum them up or dump the statistics
> from each queue (or both). Summing them up avoids userspace
> visible changes when drivers are converted to multiq.
Ok mystery solved, partially at least :)
Hmm, my bnx2 still displays correct info here (BCM5708S) ; so maybe Christoph has a
real multiqueue NIC adapter ? I thought he mentioned a mono queue NIC earlier.
Dumping stats for each queue would be better for admin point of view IMHO
(restricted to real_num_tx_queues I guess, since bnx2 allocates 8 queues per device.
next prev parent reply other threads:[~2009-09-01 14:58 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-08-31 21:46 UDP is bypassing qdisc statistics Christoph Lameter
2009-08-31 19:54 ` Eric Dumazet
2009-08-31 20:58 ` Mark Smith
2009-09-01 6:37 ` Jarek Poplawski
2009-09-01 7:00 ` Eric Dumazet
2009-09-01 9:37 ` Mark Smith
2009-09-01 18:03 ` Christoph Lameter
2009-09-01 14:20 ` Patrick McHardy
2009-09-01 14:58 ` Eric Dumazet [this message]
2009-09-01 19:05 ` Christoph Lameter
2009-09-01 15:28 ` Eric Dumazet
2009-09-01 19:35 ` Christoph Lameter
2009-09-01 15:43 ` Eric Dumazet
2009-09-01 15:58 ` Eric Dumazet
2009-09-01 20:13 ` Christoph Lameter
2009-09-01 21:55 ` Christoph Lameter
2009-09-01 20:24 ` Jarek Poplawski
2009-09-02 1:36 ` Christoph Lameter
2009-09-01 18:29 ` Christoph Lameter
2009-09-01 19:30 ` Christoph Lameter
2009-09-01 15:34 ` Eric Dumazet
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=4A9D3687.2020101@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=cl@linux-foundation.org \
--cc=davem@linux-foundation.org \
--cc=jarkao2@gmail.com \
--cc=kaber@trash.net \
--cc=lk-netdev@lk-netdev.nosense.org \
--cc=netdev@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.