On Thu, 9 Sep 2010 14:05:51 +0000, Markus Kovero <markus.kov...@nebula.fi> wrote: > On Sep 9, 2010, at 8:27 AM, Fei Xu <twinse...@hotmail.com> wrote: > > >> This might be the dreaded WD TLER issue. Basically the drive keeps retrying >> a read operation over and over after a bit error trying to recover from a > >> read error themselves. With ZFS one really needs to disable this and have >> the drives fail immediately. > >> Check your drives to see if they have this feature, if so think about >> replacing the drives in the source pool that have long service times and >> make sure this feature is disabled on the destination pool drives. > >> -Ross > > > It might be due tler-issues, but I'd try to pin greens down to > SATA1-mode (use jumper, or force via controller). It might help a bit > with these disks, although these are not really suitable disks for any > use in any raid configurations due tler issue, which cannot be > disabled in later firmware versions. > > Yours > Markus Kovero >
Just to clarify - do you mean TLER should be off or on? TLER = Time Limited Error Recovery so the drive only takes a max time (eg: 7 seconds) to retrieve data or returns an error. So you say 'cannot be disabled' but I think you mean 'cannot be ENABLED' ? I've been doing a lot of research for a new storage box at work, and from reading a lot of the info available in the Storage forum on hardforum.com, the experts there seem to recommend NOT having TLER enabled when using ZFS as ZFS can be configured for its timeouts, etc, and the main reason to use TLER is when using those drives with hardware RAID cards which will kick a drive out of the array if it takes longer than 10 seconds. Can anyone else here comment if they have had experience with the WD drives and ZFS and if they have TLER enabled or disabled? Cheers, Mark _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
