Date: Thu, 9 Jun 2005 12:39:27 -0400 (EDT) From: Jeff Roberson <jroberson@chesapeake.net> To: Alfred Perlstein <alfred@FreeBSD.org> 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: <20050609123920.T16943@mail.chesapeake.net> In-Reply-To: <20050609135438.GS17867@elvis.mu.org> References: <200506082026.j58KQ6cT052316@repoman.freebsd.org> <20050609135438.GS17867@elvis.mu.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, 9 Jun 2005, Alfred Perlstein wrote: > MFC? :D Yes, after a few weeks. > > * Jeff Roberson <jeff@FreeBSD.org> [050608 13:26] wrote: > > jeff 2005-06-08 20:26:06 UTC > > > > FreeBSD src repository > > > > Modified files: > > sys/kern vfs_bio.c > > Log: > > - Under heavy IO load the buf daemon can run for many hundereds of > > milliseconds due to what is essentially n^2 algorithmic complexity. This > > change makes the algorithm N*2 instead. This heavy processing manifested > > itself as skipping in audio and video playback due to the long scheduling > > latencies and contention on giant by pcm. > > - flushbufqueues() is now responsible for flushing multiple buffers > > rather than one at a time. This allows us to save our progress in the > > list by using a sentinal. We must do the numdirtywakeup() and > > waitrunningbufspace() here now rather than in buf_daemon(). > > - Also add a uio_yield() after we have processed the list once for bufs > > without deps and again for bufs with deps. This is to release Giant > > and allow any other giant locked code to proceed. > > > > Tested by: Many users on current@ > > Revealed by: schedgraph traces sent by Emil Mikulic & Anthony Ginepro > > > > Revision Changes Path > > 1.487 +28 -6 src/sys/kern/vfs_bio.c > > -- > - Alfred Perlstein > - email: bright@mu.org cell: 408-480-4684 >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050609123920.T16943>