Date: Mon, 6 Apr 1998 01:09:32 -0500 (EST) From: "John S. Dyson" <toor@dyson.iquest.net> To: joelh@gnu.org Cc: dyson@FreeBSD.ORG, dswartz@druber.com, dg@root.com, dag-erli@ifi.uio.no, stable@FreeBSD.ORG, current@FreeBSD.ORG Subject: Re: swap-leak in 2.2.5 ? Message-ID: <199804060609.BAA09011@dyson.iquest.net> In-Reply-To: <199804060556.AAA02073@detlev.UUCP> from Joel Ray Holveck at "Apr 6, 98 00:56:49 am"
next in thread | previous in thread | raw e-mail | index | archive | help
> > > The needed amount of physical memory is best judged by paging activity, > > but again, the system doesn't tell you directly. > > Perhaps I'm confused, then... Doesn't vmstat tell you paging activity? > Granted, it doesn't tell you whether it's paging to get rid of unused > pages, or whether it's paging to free up needed memory, but at least > it's a start. > It doesn't quantify the amount of paging that is excessive. How does one judge that a certain amount of paging is too much? The work would be to quantify and interpret the raw status that the system provides. It is similar to the difference between "understanding" and "being able to design." I suggest that this would be a good project, but creating a reliable measure of system paging load where a measurement of excessive paging is translated into an understandable and accurage judgement is interesting, and the information is not provided directly by the system. It would have to be calculated somehow. John To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199804060609.BAA09011>