From owner-freebsd-smp@FreeBSD.ORG Tue Jul 8 05:22:18 2003 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4520837B404; Tue, 8 Jul 2003 05:22:18 -0700 (PDT) Received: from franky.speednet.com.au (franky.speednet.com.au [203.57.65.5]) by mx1.FreeBSD.org (Postfix) with ESMTP id 282FB43FE0; Tue, 8 Jul 2003 05:22:17 -0700 (PDT) (envelope-from andyf@speednet.com.au) Received: from hewey.af.speednet.com.au (hewey.af.speednet.com.au [203.38.96.242])h68CM9sw018182; Tue, 8 Jul 2003 22:22:10 +1000 (EST) (envelope-from andyf@speednet.com.au) Received: from hewey.af.speednet.com.au (hewey.af.speednet.com.au [172.22.2.17])h68CM72b009049; Tue, 8 Jul 2003 22:22:08 +1000 (EST) (envelope-from andyf@speednet.com.au) Date: Tue, 8 Jul 2003 22:22:07 +1000 (EST) From: Andy Farkas X-X-Sender: andyf@hewey.af.speednet.com.au To: Terry Lambert In-Reply-To: <3F0AA444.28EC5A8E@mindspring.com> Message-ID: <20030708215553.F8850-100000@hewey.af.speednet.com.au> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: freebsd-smp@freebsd.org cc: freebsd-current@freebsd.org cc: Dan Nelson Subject: Re: whats going on with the scheduler? X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 08 Jul 2003 12:22:18 -0000 On Tue, 8 Jul 2003, Terry Lambert wrote: > Dan Nelson wrote: > > In the last episode (Jul 08), Andy Farkas said: > > > If setiathome is making lots of syscalls, then running the 3 instanses > > > should already show a problem, no? > > > > Not if it's ssh that's holding Giant for longer than it should. The > > setiathome processes may be calling some really fast syscall 500 times > > a second which doesn't cause a problem until ssh comes along and calls > > some other syscall that takes .1 ms to return but also locks Giant long > > enough to cause the other processes to all back up behind it. > > Specifically, if it's sleeping with Giant held because the > Send-Q is full (use netstat to check) it could block things > for a long time, waiting for the queue to drain. scp was retrieving a file, not sending, and it was bandwidth limited. Any other ideas? Why would 3 (niced) cpu intensive processes suddenly get reduced cpu time (on a 4 cpu system) when a 4th non-resource intensive process gets started? Also, from something that BDE said once, this command will produce unexpected results when run for more than a few hours: for i in `jot -n -s ' ' 20 0 19 1` do nice -$i sh -c "while :; do echo -n;done" & done -- :{ andyf@speednet.com.au Andy Farkas System Administrator Speednet Communications http://www.speednet.com.au/