Date: Tue, 11 Nov 1997 17:39:28 -0800 (PST) From: Simon Shapiro <Shimon@i-Connect.Net> To: Julian Elischer <julian@whistle.com> Cc: current@FreeBSD.ORG, Burton Sampley <bsampley@bsampley.vip.best.com>, John-Mark Gurney <gurney_j@resnet.uoregon.edu> Subject: Re: make world time???/ Message-ID: <XFMail.971111173928.Shimon@i-Connect.Net> In-Reply-To: <3468FAB7.FF6D5DF@whistle.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi Julian Elischer; On 12-Nov-97 you wrote: ... Looks to me that, for a full, plain build, the limit has stabilized arount the 100 minutes. I perfored some I/O testing, and I think the problem is not I/O releated. It may be that we are CPU bound, but will not be surprized if we are actually memory bandwidth limited. Having more memory than about 256MB seems wasteful (using up 64MB for tmp filesystems). Swap activity was at zero, disk I/O at about 480 I/O's per second, which is less than 1/3 of what the system is capable of, but CPU utilization was at 96% user peak, about 80% average. I wonder how CPU utilization is computed. It may actually be measuring memory, not CPU. Setting the F/S to async may improve I/O processing in the kernel more than on the disks. I'll have to wait for Goliath to arrive... --- If Microsoft Built Cars: Every time they repainted the lines on the road, you'd have to buy a new car. Sincerely Yours, Simon Shapiro Atlas Telecom Senior Architect 14355 SW Allen Blvd., Suite 130 Beaverton OR 97005 Shimon@i-Connect.Net Voice: 503.799.2313
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.971111173928.Shimon>