netdev
[Top] [All Lists]

Re: bad TSO performance in 2.6.9-rc2-BK

To: Andi Kleen <ak@xxxxxxx>
Subject: Re: bad TSO performance in 2.6.9-rc2-BK
From: "David S. Miller" <davem@xxxxxxxxxxxxx>
Date: Tue, 28 Sep 2004 16:35:09 -0700
Cc: herbert@xxxxxxxxxxxxxxxxxxx, niv@xxxxxxxxxx, andy.grover@xxxxxxxxx, anton@xxxxxxxxx, netdev@xxxxxxxxxxx
In-reply-to: <20040929012757.5d0dff61.ak@suse.de>
References: <20040923164149.5368d291.davem@davemloft.net> <E1CBkIW-0001dF-00@gondolin.me.apana.org.au> <20040927025048.GA6723@gondor.apana.org.au> <20040926210029.22750d47.davem@davemloft.net> <20040927054541.GA8858@gondor.apana.org.au> <20040927120154.09fdcadf.davem@davemloft.net> <20040927213233.GC7243@gondor.apana.org.au> <20040928141002.164c60af.davem@davemloft.net> <20040928213415.GA4646@wotan.suse.de> <20040928145345.2530d30e.davem@davemloft.net> <20040928223344.GC2975@wotan.suse.de> <20040928155706.65405e88.davem@davemloft.net> <20040929012757.5d0dff61.ak@suse.de>
Sender: netdev-bounce@xxxxxxxxxxx
On Wed, 29 Sep 2004 01:27:57 +0200
Andi Kleen <ak@xxxxxxx> wrote:

> I tried to re-test it but I didn't get very far because the kernel
> with your patch crashes regularly during netperf. No serial console,
> but the backtrace is {tcp_ack+877} {tcp_rcv_established+350} ... 
> Before that there are a few "retrans out leaked" messages.

You might be missing the topmost part of the backtrace which is probably
in tcp_clean_rtx_queue() or even more likely tcp_tso_acked() where there
are several assertions present.

I guess your compiler is auto-inlining those functions for you,
can you reproduce the crash with perhaps the noinline attribute
added to those two functions I mention above so we can get a
precise backtrace?

<Prev in Thread] Current Thread [Next in Thread>