[OpenIndiana-discuss] What happens when a ZIL drive dies?

[Bob Friesenhahn]

On Tue, 5 Jun 2012, Jan Owoc wrote:
> Some applications may depend on the files (or portions thereof) making
> it out to disk in a specific order. The example you gave is perfect.
> Let's say file "A" needs to exist before a change in file "B" happens.
> A properly written program would write out file "A", fsync, wait for
> fsync to complete, then change file "B". A properly written filesystem
> will wait for the data from "A" to hit physical, permanent, storage
> before allowing the change to "B". This can be slow on mechanical
> storage, so you put the ZIL on a separate SLOG.

Both ZFS normal writes and zil-based recovery are ordered.  I don't 
see how you could have "B" updated but "A" not updated.  As far as ZFS 
is concerned, the ZIL is persistent storage and no less reliable than 
other storage units in the pool.

This is radically different from a filesystem like EXT4 where some 
sorts of updates (e.g. create/delete file or directory) take priority 
over others.  Ad hoc approaches are often used to improve the 
appearance of performance, or because the filesystem "knows" that one 
sort of metadata or data is more important than another.

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