From: David Miller <davem@davemloft.net>
To: mpatocka@redhat.com
Cc: netdev@vger.kernel.org, kaber@trash.net
Subject: Re: crash with bridge and inconsistent handling of NETDEV_TX_OK
Date: Tue, 20 Apr 2010 18:02:53 -0700 (PDT) [thread overview]
Message-ID: <20100420.180253.159346294.davem@davemloft.net> (raw)
In-Reply-To: <Pine.LNX.4.64.1004202018100.16302@hs20-bc2-1.build.redhat.com>
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 20 Apr 2010 20:23:57 -0400 (EDT)
> I have two NICs, each with 1500 MTU. The stack trace indicates that a
> packet was received by one NIC and bridged to the other. The stack trace
> also indicates that it went through GSO code path. The question is why?
> How could a forwarded packet be so large to use GSO?
GRO automatically accumulates packets together, accumulating them into
larger super-packets. This is done regardless of input device feeding
it.
Can you understand this now? In software, we accumulate all incoming
packets for a TCP stream into larger super-packets. Just because it's
a bridging scenerio doesn't mean we disable GRO.
These super-packets are being bridged, then forwarded out your
destination device and GSO has to de-segment these GRO frames.
GRO is done unconditionally, all the time, for all packets.
next prev parent reply other threads:[~2010-04-21 1:02 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-20 23:40 crash with bridge and inconsistent handling of NETDEV_TX_OK Mikulas Patocka
2010-04-20 23:45 ` David Miller
2010-04-20 23:48 ` David Miller
2010-04-20 23:57 ` Mikulas Patocka
2010-04-21 0:00 ` David Miller
2010-04-21 0:12 ` Mikulas Patocka
2010-04-21 0:15 ` David Miller
2010-04-21 0:23 ` Mikulas Patocka
2010-04-21 1:02 ` David Miller [this message]
2010-04-21 1:10 ` Mikulas Patocka
2010-04-21 1:14 ` David Miller
2010-04-21 1:16 ` David Miller
2010-04-21 1:21 ` Mikulas Patocka
2010-04-21 1:24 ` David Miller
2010-04-21 2:01 ` David Miller
2010-04-21 13:21 ` Mikulas Patocka
2010-04-29 22:14 ` RCU error in networking (was: crash with bridge and inconsistent handling of NETDEV_TX_OK) Mikulas Patocka
2010-04-29 23:04 ` RCU error in networking David Miller
2010-04-21 1:20 ` crash with bridge and inconsistent handling of NETDEV_TX_OK Mikulas Patocka
2010-04-21 1:22 ` David Miller
2010-04-21 1:24 ` Mikulas Patocka
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=20100420.180253.159346294.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=kaber@trash.net \
--cc=mpatocka@redhat.com \
--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 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).