I'm not sure where this issue stands now (am just now checking
mail after being out for a few days), but here are the block sizes
used when the install software creates swap and dump zvols:
swap: block size is set to PAGESIZE (4K for x86, 8K for sparc)
dump: block size is set to 128 KB
Liveupgrade should use the same characteristics, though I think
there was a bug at one time where it did not.
If that does not improve dump/swap zvol performance, further
investigation should be done. Perhaps file a bug.
Lori
On 03/31/09 03:02, casper....@sun.com wrote:
I've upgraded my system from ufs to zfs (root pool).
By default, it creates a zvol for dump and swap.
It's a 4GB Ultra-45 and every late night/morning I run a job which takes
around 2GB of memory.
With a zvol swap, the system becomes unusable and the Sun Ray client often
goes into "26B".
So I removed the zvol swap and now I have a standard swap partition.
The performance is much better (night and day). The system is usable and
I don't know the job is running.
Is this expected?
Casper
_______________________________________________
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
