Apparently spurious ZFS CRC errors (was Re: ZFS data error
without reasons)
Mark Powell
M.S.Powell at salford.ac.uk
Thu Mar 26 01:56:25 PDT 2009
On Wed, 25 Mar 2009, Bernd Walter wrote:
> WC is on, prefetch is off, but only because it had bad performance with
> MySQL.
> Drives are <WDC WD3200AAKS-00SBA0/12.01B01> Serial ATA II
Hmmm. Strange. My previous array was primarily WD5000AAKS, but I didn't
have these issues with those.
I actually had 6xWD5000AAKS and 6 more old drives (200GB, 3x250GB, 320GB
& 400GB) joined together with gstripe and gconcat to make 3x500GB, for a
total 9x500GB RAIDZ2. With some pretty old PATA Maxtor 200GB and 250GB in
there; spread across ICH9, JMB363 and Sil3132; I'd've expected CRC issues
then. I scrubbed my pool every week for 18 months or so, with no errors to
report.
However, it's only since I got these 6xWD10EADS that problems have
occurred. Perhaps the higher throughput of these drives is highlighting
issues elsewhere?
> I don't know if it is with the drives, but other reasons are less
> likely in my opinion.
> The system is located in a data center and since I only get a few errors
> I decided to live with it and not to debug it further.
I've decided to split my drives in two pools; 5x500GB RAIDZ1 of WD5000AAKS
and the 6x1TB RAIDZ2 of WD10EADS. I'll see if they perform differently.
I'm using the defaults of WC on, with all ZFS options enabled.
Cheers.
--
Mark Powell - UNIX System Administrator - The University of Salford
Information & Learning Services, Clifford Whitworth Building,
Salford University, Manchester, M5 4WT, UK.
Tel: +44 161 295 6843 Fax: +44 161 295 5888 www.pgp.com for PGP key
More information about the freebsd-current
mailing list