Date: Fri, 18 Dec 2009 14:01:06 +0200 From: Alexander Motin <mav@FreeBSD.org> To: Alexander Zagrebin <alexz@visp.ru> Cc: freebsd-current@freebsd.org, 'Benjamin Close' <Benjamin.Close@clearchain.com> Subject: Re: 8.0-RELEASE: disk IO temporarily hangs up (ZFS or ATA related problem) Message-ID: <4B2B6F02.9050404@FreeBSD.org> In-Reply-To: <1261135381.00196302.1261124403@10.7.7.3> References: <1261066981.00195934.1261053602@10.7.7.3> <1261070581.00195950.1261057201@10.7.7.3> <1261135381.00196302.1261124403@10.7.7.3>
next in thread | previous in thread | raw e-mail | index | archive | help
Alexander Zagrebin wrote: > May be a problem is in ata? WD15EADS is a "green" series of drives. If you don't receive TIMEOUT messages, then commands probably complete successfully. Loads above 100% may mean that requests are running for few seconds. It shouldn't happen normally. Have you tried to check whole drive surface? Have you checked SMART reports? I had a drive onece, which had so many media problems and relocated sectors, that I was unable to burn CD from it, so slow it was. Same time there was no bad sectors on that drive, reported to OS, drive handled everything. It was just extremely slow. Have you tried to rewrite _while_ drive media with dd? Some media errors could only be resolved only during write operation. > Is there a method to completely reset sata channel and drive? > atacontrol reinit will do it? Yes. -- Alexander Motin
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4B2B6F02.9050404>