Date: Thu, 13 Mar 2003 03:07:19 -0500 (EST) From: Jeff Roberson <jroberson@chesapeake.net> To: Alfred Perlstein <bright@mu.org> Cc: Jeff Roberson <jeff@FreeBSD.org>, <src-committers@FreeBSD.org>, <cvs-src@FreeBSD.org>, <cvs-all@FreeBSD.org> Subject: Re: cvs commit: src/sys/fs/specfs spec_vnops.c src/sys/kern kern_physio.c vfs_bio.c src/sys/sys buf.h Message-ID: <20030313030532.A43514-100000@mail.chesapeake.net> In-Reply-To: <20030313075317.GL4145@elvis.mu.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 12 Mar 2003, Alfred Perlstein wrote: > * Jeff Roberson <jroberson@chesapeake.net> [030312 23:34] wrote: > > These are the last of my local diffs for buf cache locking. I have only > > the background write code left to lock. > > > > Most of these patches have been running on my laptop, a dual alpha, a dual > > x86, and a quad alpha for two weeks or so. One of the alphas is an nfs > > server and the others are clients. I've done some buildworlds along with > > normal desktop use. > > how does this impact doing things like playing mp3s and such while doing > disk IO? Any less hiccupy? :) > There should be no effect other than the extra lock overhead. There is still a small bit of the buffer cache that is not smp safe and then it's blocked on the vm. Soon we should be able to start pushing giant down into VFS which will eventually lead us to a Giant free path up to the VM. I think before we get there we'll have a giant free bufdone(). That will reduce latency for some operations such as you have mentioned. Cheers, Jeff To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-src" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030313030532.A43514-100000>