ZFS and mdconfig -t vnode - Unexpected behavior

[Bob Friesenhahn]

On Thu, 8 Mar 2012, Dan Rue wrote:
>
> Under ZFS, it can take as long as 30 seconds before the block size as
> reported by du -k has been updated. The fsync appears to be a noop.

Zfs under Solaris has the same behavior.  This data is only assured to 
be available after the current zfs TXG has been synced, which may take 
a long time.  It also becomes available after the 'sync' system call 
has completed (because the current TXG is flushed).

> Are there any ZFS tunables that could be related to this? What could be
> the cause of this behavior?

You could adjust the tunings for zfs transaction groups but this will 
decrease system performance and increase pool fragmentation.

Bob
-- 
Bob Friesenhahn
bfriesen at simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/
GraphicsMagick Maintainer,    http://www.GraphicsMagick.org/