Yeah, that's what I assumed. I'm suggesting breaking the full volumes
into several smaller parts (say 3 1000 cylinder chunks) and aggregating
the smaller chunks with LVM. You end up with more effective spindles,
which allow more I/Os to be in flight at the same time for the same
filesystem. Works really well, especially for databases with fairly
random query patterns.

-- db

David Boyes
Sine Nomine Associates

>

Reply via email to