netdev
[Top] [All Lists]

Re: patch for common networking error messages

To: Janice M Girouard <janiceg@xxxxxxxxxx>
Subject: Re: patch for common networking error messages
From: Jeff Garzik <jgarzik@xxxxxxxxx>
Date: Tue, 17 Jun 2003 15:23:09 -0400
Cc: "David S. Miller" <davem@xxxxxxxxxx>, shemminger@xxxxxxxx, Valdis.Kletnieks@xxxxxx, Janice Girouard <girouard@xxxxxxxxxx>, Daniel Stekloff <stekloff@xxxxxxxxxx>, Larry Kessler <lkessler@xxxxxxxxxx>, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, niv@xxxxxxxxxx
In-reply-to: <3EEF66AA.3000509@us.ibm.com>
Organization: none
References: <OFCA1A4F38.D782F1D3-ON85256D48.000A5CED@us.ibm.com> <200306170434.h5H4YZPZ003025@turing-police.cc.vt.edu> <20030617090859.0ffa0ca8.shemminger@osdl.org> <20030617.090930.102574393.davem@redhat.com> <3EEF620A.40608@pobox.com> <3EEF66AA.3000509@us.ibm.com>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2.1) Gecko/20021213 Debian/1.2.1-2.bunk
Janice M Girouard wrote:
2) events that drive load balancing software. Right now if we need to throttle the card, we don't send events up to indicate we have reached capacity.


Question related to this item specifically :)

Do you want to individually send 4000 - 16000 (or more) TX stop / start events per second to userspace? :) At some point Heisenburg defeats low latency :)

If not (and I hope not), perhaps also look into the net stack statistics already kept (or add more sampling stats if necessary), and instead trigger events based on sampling those statistics.

        Jeff




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