On Saturday 19 June 2010 12:40, Miles Fidelman wrote:
> The last comes to mind as a result of learning, the hard way, that a
> failing disk can manifest by slowing a server to a crawl, as the drivers
> keep retrying operations until they succeed, rather than declaring an
> error and dropping a drive from a RAID array. (Anybody know if this is
> tunable - I've yet to find anything about this around the net.)
E.g. if you see something like
kernel: ata1.00: status: { DRDY ERR }
kernel: ata1.00: error: { UNC }
kernel: ata1: soft resetting link
kernel: ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
in the logs. (If that is tunable, it'll be inside the sata kernel driver, not
in mdadm.) Replace the disk, it is dying.
> - beyond the complexity and load, can you say a little more about why
> "RAID6 on software is not a good idea, even worse with that hardware."
One theory out there is that parity-based raids really depend on all data and
checksums being written to disk at the same time. Which does not happen with
today's smart drives, what with caching and head movement optimizers and
whatever else's in there. Most everyone recommends raid-10 on sata drives --
they're cheap and raid-0,1,10 is fast and very safe.
I'd set it up as 1 system disk + 2 raid-1 vm/data space + 1 spare for the
raid. And buy a seagate, wd, and a hitachi for those last 3.
Dima
--
Dimitri Maziuk
Programmer/sysadmin
BioMagResBank, UW-Madison -- http://www.bmrb.wisc.edu
_______________________________________________
Linux-HA mailing list
[email protected]
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
