On 06/26/2013 04:01 PM, ktm@rice.edu wrote:
> I think he is referring to the fact that with parallel query execution,
> multiple partitions can be processed simultaneously instead of serially
> as they are now with the resulting speed increase.
Processing simultaneously is the purpose of parallel query execution,
yes. But I see no reason for that not to work equally well for
unpartitioned tables.
Disk I/O is already pretty well optimized and parallelized, I think.
Trying to parallelize a seq scan on the Postgres side is likely to yield
far inferior performance.
Regards
Markus Wanner
