netdev
[Top] [All Lists]

SPECWeb99 Data -- tcp-wakeups

To: akpm@xxxxxxxxx
Subject: SPECWeb99 Data -- tcp-wakeups
From: Troy Wilson <tcw@xxxxxxxxxxxxxxxxxxxx>
Date: Wed, 25 Sep 2002 10:47:53 -0500 (CDT)
Cc: linux-kernel@xxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx, lse-tech@xxxxxxxxxxxxxxxxxxxxx
Sender: netdev-bounce@xxxxxxxxxxx
   ********************************************************************
   *  SPEC(tm) and the benchmark name SPECweb(tm) are registered      *
   *  trademarks of the Standard Performance Evaluation Corporation.  *
   *  This benchmarking was performed for research purposes only,     *
   *  and is non-compliant, with the following deviations from the    *
   *  rules -                                                         *
   *                                                                  *
   *    1 - It was run on hardware that does not meed the SPEC        *
   *        availability-to-the-public criteria.  The machine is      *
   *        an engineering sample.                                    *
   *                                                                  *
   *    2 - access_log wasn't kept for full accounting.  It was       *
   *        being written, but deleted every 200 seconds.             *
   ********************************************************************

  I've done some testing with SPECWeb99 on 2.5.35 mm1 with and without 
the tcp-wakeups patch backed out.  The addition of tcp-wakeups makes a 2%
improvement in performance.

                           mm1              mm1 without tcp-wakeup
                         -----------------------------------------
Simultaneous connections   3049             2982


  The system is an 8-way, 900MHz, Profusion-based P3 box with 32GB memory.
It's connected to 16 SPECWeb client machines via 4 e1000 gigabit adapters.
I'm using Apache 2.0.36 as the webserver.

- Troy




<Prev in Thread] Current Thread [Next in Thread>
  • SPECWeb99 Data -- tcp-wakeups, Troy Wilson <=