netdev
[Top] [All Lists]

Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000

To: akpm@xxxxxxxxxx
Subject: Re: Early SPECWeb99 results on 2.5.33 with TSO on e1000
From: "David S. Miller" <davem@xxxxxxxxxx>
Date: Fri, 06 Sep 2002 00:22:53 -0700 (PDT)
Cc: Martin.Bligh@xxxxxxxxxx, hadi@xxxxxxxxxx, tcw@xxxxxxxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, niv@xxxxxxxxxx, Robert.Olsson@xxxxxxxxxxx
In-reply-to: <3D785AE4.A7E3DF2D@xxxxxxxxxx>
References: <18563262.1031269721@[10.10.2.3]> <20020905.235159.128049953.davem@xxxxxxxxxx> <3D785AE4.A7E3DF2D@xxxxxxxxxx>
Sender: netdev-bounce@xxxxxxxxxxx
   From: Andrew Morton <akpm@xxxxxxxxxx>
   Date: Fri, 06 Sep 2002 00:36:04 -0700

   "David S. Miller" wrote:
   > NAPI is also not the panacea to all problems in the world.
   
   Mala did some testing on this a couple of weeks back.  It appears that
   NAPI damaged performance significantly.

   
http://www-124.ibm.com/developerworks/opensource/linuxperf/netperf/results/july_02/netperf2.5.25results.htm

Unfortunately it is not listed what e1000 and core NAPI
patch was used.  Also, not listed, are the RX/TX mitigation
and ring sizes given to the kernel module upon loading.

Robert can comment on optimal settings

Robert and Jamal can make a more detailed analysis of Mala's
graphs than I.


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