From owner-freebsd-hackers Thu Oct 26 20:51:52 1995 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.6.12/8.6.6) id UAA21974 for hackers-outgoing; Thu, 26 Oct 1995 20:51:52 -0700 Received: from blob.best.net (blob.best.net [204.156.128.88]) by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id UAA21965 for ; Thu, 26 Oct 1995 20:51:49 -0700 Received: from geli.clusternet (rcarter.vip.best.com [204.156.137.2]) by blob.best.net (8.6.12/8.6.5) with ESMTP id UAA26076; Thu, 26 Oct 1995 20:51:21 -0700 Received: from localhost (localhost [127.0.0.1]) by geli.clusternet (8.6.12/8.6.9) with SMTP id UAA04313; Thu, 26 Oct 1995 20:48:57 -0700 Message-Id: <199510270348.UAA04313@geli.clusternet> X-Authentication-Warning: geli.clusternet: Host localhost didn't use HELO protocol X-Mailer: exmh version 1.6.4 10/10/95 To: Nate Williams cc: Brian Tao , FREEBSD-HACKERS-L , Larry McVoy Subject: Re: New lmbench available (fwd) In-reply-to: Your message of "Thu, 26 Oct 1995 10:39:31 MDT." <199510261639.KAA01143@rocky.sri.MT.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 26 Oct 1995 20:48:56 -0700 From: "Russell L. Carter" Sender: owner-hackers@freebsd.org Precedence: bulk > > I think we should get the biggest, baddest FreeBSD machines around > > and submit lmbench results for them... Russell Carter, you there? :) Sorry folks, my ISP is downgrading from FreeBSD Pentiums to SGI multiprocessor boxes (no offense Larry ;-), so guess what, I've been basically hosed for the last three days. But of course, I'll run lmbench on my systems, currently 1 P54C-100-PB256K-32MB FBSD 2.1 and 1 P54CS-133-PB512K-32MB-FBSD-current. (Another P54-C100 WINDOZE-NT box is the accounting system, can't touch it...) Where's this problem code at? I'll have a crack at it. The previous lmbench was very bsd friendly... Russell > > I got a pretty nasty one sitting here that Rod put together for me, but > I can't get the lmbench stuff working. I don't have time to mess around > with it either, so if it doesn't work I'm not going to take the time to > figure it out. Even minimal instructions would be helpful... > > Hmm, I used RCS to checkout the top-level files, and it now requires > something called rccs. This is really standardized. ;( Ahh, I see it > requires that . is in your path. > > Still going. The build blew up when the Makefile attempted to copy > /bin/true, which is /usr/bin/true on BSD systems. In any case, I've got > it working now. I'm running it first to make sure I don't have any > bogus answers, at which point I'll have it sent off to the list. > > > Nate > > > > Subject: New lmbench available > > > > > > P.S. Almost forgot. I stuck the latest on ftp.sgi.com:/pub/lmb.tgz. You > > need gunzip to unpack it and rcs to build it, and perl to see the results. > > If you have a linux box, all of the scripts for making fancy graphs work. > > Cd to lmbench/Results and say "make ps", and then look at the ps files > > in PS/*. > > > > Drafts of the usenix paper are in ftp.sgi.com:/pub/lmbench.ps. Comments > > welcome, remember this is an as of yet unpublished document.... >