Date: Mon, 21 Apr 1997 14:56:40 -0700 From: Amancio Hasty <hasty@rah.star-gate.com> To: Warner Losh <imp@village.org> Cc: Chris Timmons <skynyrd@opus.cts.cwu.edu>, current@FreeBSD.ORG Subject: Re: Speed deamons: How to build a build box? Message-ID: <199704212156.OAA04372@rah.star-gate.com> In-Reply-To: Your message of "Mon, 21 Apr 1997 15:45:50 MDT." <E0wJQuE-00028q-00@rover.village.org>
next in thread | previous in thread | raw e-mail | index | archive | help
>From The Desk Of Warner Losh : > 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). > This sounds really good . Now if the kernel and/or file system gurus can make their recommendations 4 or 5 runs should be all that we need. Once is documented others I am sure will be happy to add to the document their own experiments 8) Regards, Amancio
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199704212156.OAA04372>