Date: Fri, 21 Mar 2008 01:04:35 -1000 (HST) From: Jeff Roberson <jroberson@chesapeake.net> To: Poul-Henning Kamp <phk@phk.freebsd.dk> Cc: cvs-src@FreeBSD.org, Jeff Roberson <jeff@FreeBSD.org>, src-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/kern vfs_bio.c Message-ID: <20080321010256.J910@desktop> In-Reply-To: <4851.1206094122@critter.freebsd.dk> References: <4851.1206094122@critter.freebsd.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 21 Mar 2008, Poul-Henning Kamp wrote: > In message <200803211000.m2LA05KN096467@repoman.freebsd.org>, Jeff Roberson wri > tes: >> jeff 2008-03-21 10:00:05 UTC >> >> FreeBSD src repository >> >> Modified files: >> sys/kern vfs_bio.c >> Log: >> - Reduce contention on the global bdonelock and bpinlock by using >> a pool mutex to protect these sleep/wakeup/counter races. This >> still is preferable to bloating each bio with a mtx. > > Shouldn't this be the BOLOCK ? As mentioned on irc; I believe these originally were not done this way because we may have a buf without a bufobj. I think that happens when we use a pager buf for physio. The other reason not to do that would be to attempt to reduce contention on the bo lock which is increasingly becoming a problem. Patches are underway to address that. Thanks, Jeff > > -- > Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 > phk@FreeBSD.ORG | TCP/IP since RFC 956 > FreeBSD committer | BSD since 4.3-tahoe > Never attribute to malice what can adequately be explained by incompetence. >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080321010256.J910>