Hi,
I'm playing with OSDB (http://osdb.sf.net/) and trying to get
the best numbers possible out of it.
I haven't been able to find anything resembling a performance
tuning document. Does such a thing exist?
Bruce's "Hardware performance tuning" guide mentions a bunch
of options but doesn't suggest what they should be set to. It
also implies that, simplistically stated, "bigger is better,
until it makes you swap", but that seems not to be always true:
Under the "crossSectionTests(Mixed IR)" part of an OSDB run, a
large number of shared_buffers causes severe slowdown on one of
the tests -- it goes from a little over 200 seconds to nearly
2000. I suspect internal lock contention, or maybe it's just
that the read() path in Linux is quicker than PG's own cache?
Any tips and tricks available? Thus far, I have tried:
tcpip_socket = true
shared_buffers = {1024,10240,102400}
max_fsm_relations = 100
max_fsm_pages = 10000
max_locks_per_transaction = 256
wal_buffers = 1024
and haven't really been able to explain the numbers (which I
will post shortly, once I have been able to try a few more
parameters).
Matthew.