Date: Fri, 31 Oct 1997 18:30:12 -0800 (PST) From: Simon Shapiro <Shimon@i-Connect.Net> To: "John S. Dyson" <toor@dyson.iquest.net> Cc: hackers@FreeBSD.ORG, (Jamil J. Weatherbee) <jamil@trojanhorse.ml.org> Subject: Re: Memory VS. Performance under FreeBSD Message-ID: <XFMail.971031183012.Shimon@i-Connect.Net> In-Reply-To: <199710312143.QAA25551@dyson.iquest.net>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi "John S. Dyson"; On 31-Oct-97 you wrote: > Jamil J. Weatherbee said: > > > > Does anybody have any statistics on memory vs. performance as you go to > > large memory configurations (>64MB), also what is the biggest RAM > > configuration possible on a FreeBSD machine? > > > > Kind of something like: > > > > > > RAM for x USERS for x MEAN PROCESSES vs x DISK ACCESS > > > Can't answer that specific question. However, there is kind of a design > "idea" that it should work with 3GB of RAM. That would require > significant > kernel tuning, because few of us have any experience with machines that > large. > > We have avoided or fixed terrible algorithms like O(n^2,3,4) stuff. We > still have > stuff that can be improved, but we are making continual progress. Old, old yardsticks for timeshare and RDBMS (very arguable) 64k per char mode user 1MB per X user 1MB per xterm screen 1MB per seat for RDBMS engine 1MB per MIPS There are not necessarily cumulative, but are definitely speculative :-) --- 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.971031183012.Shimon>