> I don't believe it's a performance issue, I believe it's that
> writes to
> blocks greater than 8k cannot be guaranteed 'atomic' by the operating
> system. Hence, 32k blocks would break the transactions system. (Or
> something like that - am I correct?)
First, 8k are not atomic eighter. Second, the page layout in PostgreSQL has been
designed to not care about the atomicity of IO. This design might have been
compromised for index pages recently, to optimize index performance,
but data pages are perfectly safe.
Andreas