Date: Sat, 5 Jun 2010 19:49:15 -0700 From: Artem Belevich <fbsdlist@src.cx> To: Matthew Jacob <mj@feral.com> Cc: freebsd-scsi@freebsd.org Subject: Re: mpt request timed out Message-ID: <AANLkTinB4niHfSETvYJ0eLxE9LmwhQ_f1DMmW-0SIMkn@mail.gmail.com> In-Reply-To: <4C0B07C6.3090804@feral.com> References: <20100606014516.GA53735@putsch.kolbu.ws> <4C0B064A.3060206@feral.com> <20100606022651.GB53735@putsch.kolbu.ws> <4C0B07C6.3090804@feral.com>
next in thread | previous in thread | raw e-mail | index | archive | help
SATA cables were the first thing I suspected. Changed them few times with no impact on the issue. Forcing SATA to 1.5G helped a bit, but the errors still showed up, though not as frequently. I've read a theory on OpenSolaris mailing list where folks were discussing strikingly similar issue with LSI controllers throwing up bus reset errors when used with ZFS. The gist was that IR firmware is rather buggy and sometimes hangs under heavy load. It does have some sort of watchdog, so the chip eventually restarts. It reports an error to the driver and it may abort (or forget to finish) current transaction so it sometimes looks like an error to hard disk as well. --Artem On Sat, Jun 5, 2010 at 7:28 PM, Matthew Jacob <mj@feral.com> wrote: > Okay, good, my best guess is that that SATA signals past the STP bridge got > jammed up and a PHY reset was issued by the firmware. > >> Yes, everything works fine after the reset. >> > > _______________________________________________ > freebsd-scsi@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-scsi > To unsubscribe, send any mail to "freebsd-scsi-unsubscribe@freebsd.org" >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTinB4niHfSETvYJ0eLxE9LmwhQ_f1DMmW-0SIMkn>