Date: Wed, 12 May 2010 20:25:29 -0300 (ADT) From: "A. Wright" <andrew@qemg.org> To: Chuck Swiger <cswiger@mac.com> Cc: FreeBSD - <freebsd-questions@freebsd.org> Subject: Re: Long I/O pauses on same mass storage Message-ID: <alpine.BSF.2.00.1005122021320.64303@qemg.org> In-Reply-To: <F73FFDAB-EB1F-4775-9D3A-66A03CE39803@mac.com> References: <alpine.BSF.2.00.1005121035480.64303@qemg.org> <201005121456.o4CEurEZ078671@lava.sentex.ca> <alpine.BSF.2.00.1005121632520.64303@qemg.org> <BDDFA682-70FC-4240-AF3C-6AE03168FFE7@mac.com> <alpine.BSF.2.00.1005121726090.64303@qemg.org> <F73FFDAB-EB1F-4775-9D3A-66A03CE39803@mac.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 12 May 2010, Chuck Swiger wrote: > > Thanks for real data to work from. Thanks for the assistance! > There's no signs of surface failure with high reallocated > sectors or anything, but your drive is parking it's heads nearly > 100 times an hour. Someone else suggested this was a "green > firmware" drive, so it might be spinning down and so forth > trying to save power, and the OS is complaining because it takes > a while to spin back up and become online. Thanks for reading the tea-leaves for me and pointing that out. I'm sure that that is the problem, as this would explain all the symptoms, as I am guessing that quite a large I/O queue can be generated if it is insisting on going into park that often. > I've heard rumors that there exists an WDIDLE utility which > might be able to tweak the firmware which might help. I will look into it, and see if there is a path out of the woods here. I'll report back once something else is known. Thanks all, for the help. A.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.BSF.2.00.1005122021320.64303>