Richard Elling wrote:
Danger Will Robinson...
Jeff Victor wrote:
Jeff Bonwick wrote:
If one host failed I want to be able to do a manual mount on the
other host.
Multiple hosts writing to the same pool won't work, but you could
indeed
have two pools, one for each host, in a dual active-passive
arrangement.
That is, you dual-attach the storage with host A talking to pool A and
host B talking to pool B. If host A fails, it can 'zpool import -f B'
to start serving up the B data. HA-ZFS (part of SunCluster 3.2) will
automate this, but for now you can roll your own along these lines.
Cool. Does this method require assigning each disk to one pool or
the other, or can disks be divided into partitions before pool
assignment?
The problem with slicing disks and sharing the slices is that you are
more prone to fatal operational mistakes. For storage where isolation
is enforced, SCSI reservations are often used. SCSI reservations work
on a per-LUN basis, not a per-slice basis because SCSI has no concept
of slices (or partitions). A safer approach is to work only at a per-LUN
level for sharing disks.
Also from a performance point of view...
If the LUN is a local disk, sharing slices can turn what would be
sequential disk I/O into random I/O, not a good thing if the slices are
used concurrently. If the LUN is on a storage array, then per-LUN
caching, read-ahead, write-behind, RAID overhead, striped sized I/Os,
are all impacted.
Sharing slices on a single LUN can and does cause unforeseen performance
problems, often very hard to diagnose. The old KISS policy of creating
one big LUN, then carving it up into disk slices or volume manager
controlled volumes, often causes problems later on in the LUN's life.
Jim
-- richard
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
