Date: Tue, 21 Jun 2005 09:42:48 -0400 From: Mike Tancsa <mike@sentex.net> To: eng@donut.ugcs.caltech.edu, freebsd-performance@freebsd.org Subject: Re: sustained sequential disk IO runs interactivity into the ground Message-ID: <6.2.1.2.0.20050621092842.05c8cd30@64.7.153.2> In-Reply-To: <20050621025727.GI24844@philemon.async.caltech.edu> References: <20050621025727.GI24844@philemon.async.caltech.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
At 10:57 PM 20/06/2005, eng@donut.ugcs.caltech.edu wrote: >I was doing a dd of dev/zero into a file on a UFS2 filesystem >(softupdates disabled) on a clean 5.4-R system. I see the same issue on RELENG_5 with IDE disk. However, on FreeBSD nfs.sentex.ca 6.0-CURRENT FreeBSD 6.0-CURRENT #1: Fri Jun 17 No such issue against an IDE drive as well as an ARECA RAID5 array. The box is quite responsive while blasting the disks Also just tested against a RELENG_5 box and a twe RAID1 array and no problems. The system is totally responsive while doing So it might be the IDE drivers on RELENG_5 ? Perhaps try sos@freebsd.org's backport of the CURRENT IDE drivers to stable. ---Mike
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?6.2.1.2.0.20050621092842.05c8cd30>