From owner-freebsd-hackers Sat Mar 1 16:51:57 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id QAA09661 for hackers-outgoing; Sat, 1 Mar 1997 16:51:57 -0800 (PST) Received: from caipfs.rutgers.edu (root@caipfs.rutgers.edu [128.6.37.100]) by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id QAA09648 for ; Sat, 1 Mar 1997 16:51:51 -0800 (PST) Received: from jenolan.caipgeneral (jenolan.rutgers.edu [128.6.111.5]) by caipfs.rutgers.edu (8.8.5/8.8.5) with SMTP id TAA08897; Sat, 1 Mar 1997 19:50:07 -0500 (EST) Received: by jenolan.caipgeneral (SMI-8.6/SMI-SVR4) id TAA09426; Sat, 1 Mar 1997 19:49:54 -0500 Date: Sat, 1 Mar 1997 19:49:54 -0500 Message-Id: <199703020049.TAA09426@jenolan.caipgeneral> From: "David S. Miller" To: bakul@chai.plexuscom.com CC: dennis@etinc.com, dg@root.com, proff@iq.org, hackers@FreeBSD.ORG In-reply-to: <199703012242.RAA04265@chai.plexuscom.com> (message from Bakul Shah on Sat, 01 Mar 1997 17:42:33 -0500) Subject: Re: optimised ip_input Sender: owner-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk Date: Sat, 01 Mar 1997 17:42:33 -0500 From: Bakul Shah 2) Profiling the networking code in a production environment ought to point out the `hot spots' where much of the time is spent under various conditions. Measure various costs by changing data structure sizes and feeding similar traffic. Find out *why* the hot spots are the way they are; gain a deeper understanding of the structure and behavior of the networking code. Just a heads up, and this is from my own experience profiling this stuff. For freely running connections (ie. application at receiving end or sending end is continually filling a healthy pipe which is being kept reasonably full) the kernel spends a significant portion of time in soreceive() and sosend(). Unfortunatly, last time I checked, those are not fun functions to hack on and optimize due to their complexity. ---------------------------------------------//// Yow! 11.26 MB/s remote host TCP bandwidth & //// 199 usec remote TCP latency over 100Mb/s //// ethernet. Beat that! //// -----------------------------------------////__________ o David S. Miller, davem@caip.rutgers.edu /_____________/ / // /_/ ><