Date: Fri, 1 Aug 2003 09:41:09 -0500 From: Dan Nelson <dnelson@allantgroup.com> To: Poul-Henning Kamp <phk@phk.freebsd.dk> Cc: Peter Jeremy <PeterJeremy@optushome.com.au> Subject: Re: headsup: swap_pager.c Message-ID: <20030801144109.GG13080@dan.emsphone.com> In-Reply-To: <7379.1059732120@critter.freebsd.dk> References: <xzpel0568cn.fsf@dwp.des.no> <7379.1059732120@critter.freebsd.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
In the last episode (Aug 01), Poul-Henning Kamp said: > In message <xzpel0568cn.fsf@dwp.des.no>, Dag-Erling =?iso-8859-1?q?Sm=F8rgrav?= > writes: > >"Poul-Henning Kamp" <phk@phk.freebsd.dk> writes: > >> The thing you overlook is that often when things gets paged out, > >> the system is short on memory and therefore more likely to not do > >> anything productive, whereas when things gets paged in, there are > >> a better chance of some other process being able to use the CPU > >> time productively. If we did predictive pageouts like some of the > >> "serious" mainfram OS's this would be less true. > > > >How hard would it be to get the kernel to write the pages "most > >likely to be swapped out" to swap in the idle loop, to save time if > >/ when they actually need to be swapped out later? > > I don't know :-) > > Quite frankly, given the sizes of RAM we see these days, I think that > paging optimizations may be largely a thing of the past. RAM is like disk space; if it's there, users will consume it. If you have 8GB of RAM, someone will write a program that needs 2gb of RAM, then someone else will decide to run that program in 5 vtys (speaking from experience here). Predictive swapping would be neat. -- Dan Nelson dnelson@allantgroup.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030801144109.GG13080>