From owner-freebsd-current Mon Apr 21 14:46:43 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.5/8.8.5) id OAA16307 for current-outgoing; Mon, 21 Apr 1997 14:46:43 -0700 (PDT) Received: from rover.village.org (rover.village.org [204.144.255.49]) by freefall.freebsd.org (8.8.5/8.8.5) with SMTP id OAA16299 for ; Mon, 21 Apr 1997 14:46:37 -0700 (PDT) Received: from rover.village.org [127.0.0.1] by rover.village.org with esmtp (Exim 1.60 #1) id 0wJQuE-00028q-00; Mon, 21 Apr 1997 15:45:50 -0600 To: Amancio Hasty Subject: Re: Speed deamons: How to build a build box? Cc: Chris Timmons , current@freebsd.org In-reply-to: Your message of "Mon, 21 Apr 1997 14:41:08 PDT." <199704212141.OAA04284@rah.star-gate.com> References: <199704212141.OAA04284@rah.star-gate.com> Date: Mon, 21 Apr 1997 15:45:50 -0600 From: Warner Losh Message-Id: Sender: owner-current@freebsd.org X-Loop: FreeBSD.org Precedence: bulk In message <199704212141.OAA04284@rah.star-gate.com> Amancio Hasty writes: : Don't forget to do a time command so we can tell how much disk, system : time, etc.. is taken up. Ah. I haven't been doing that. Will do it for these two runs. The power on the system I'm doing it on will be out while I move it to its new home, so it won't be this afternoon :-). : Also, what I would like to see done is for the results to be published : in a web page preferably FreeBSD.org . It should include hardware : setup , anything special in the way of hardware optimization, mount : flags, make world flags. Comments on which options or features : improves the most for instance -pipe vs. async , etc... OK. I'll write up something for the handbook. : If we do a good job , it will go a long way to establish a base : level performance at least with respect to make world. Yes. BTW, this sounds like you had in mind more than I'm doing. I'm going to just run 4 or so make worlds on the same source base with different settings on my machine. I'm not going to try different disks (because I don't have anything faster/slower) or other CPUs or other SCSI controllers. Just a "Here's the relative difference that this or that or the other thing made to the run" on basically constant hardware (but I will do the overclocking thing too). Warner