Hello Greg,
Thursday, February 12, 2009, 8:24:38 PM, you wrote:
GM> well, since the write cache flush command is disabled, I would like this
GM> to happen as early as practically possible in the bootup process, as ZFS
GM> will not be issuing the cache flush commands to the disks.
GM> I'm not really sure what happens in the case where the write flush
GM> command is disabled, something makes its way into the write cache, then
GM> the cache is disabled. Does this mean the write cache is flushed to disk
GM> when the cache is disabled? If so, then I guess it's less critical when
GM> it happens in the bootup process or if it's permanent...
Then do not disable cache flushes via /etc/system but rather via mdb
in your script. So for a moment after a reboot you will have a pool
with some caches still enabled but zfs will send cache flushes so it's
fine. After your script disabled all caches then you disable cache
flushes in zfs.
The other question actually is - what exaclty is turning your caches
back on after a reboot? It's not ZFS so it is probably a driver - I
would check if there is a tunable to the driver so it won't enable
write caches on reboot. I believe it would be a better solution.
--
Best regards,
Robert Milkowski
http://milek.blogspot.com
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
