On Nov 13, 2007 12:30 AM, Christopher Browne <cbbrowne@acm.org> wrote:
> Something I found *really* interesting was that whenever we pushed any
> "high traffic" systems onto PostgreSQL 8.1, I kept seeing measurable
> performance improvements taking place every day for a week.
>
> Evidently, it took that long for cache to *truly* settle down.
>
> Given that, and given that we've gotten a couple of good steps *more*
> sophisticated than mere LRU, I'm fairly willing to go pretty far down
> the "trust the shared memory cache" road.
>
> The scenario described certainly warrants doing some benchmarking; it
> warrants analyzing the state of the internal buffers over a period of
> time to see what is actually in them.
kinda along those lines I was wondering if you (or anybody else) could
refer me to some recent results demonstrating the good or bad effects
of going with low or high shared buffers settings. there is a huge
amount of anecdotal lore on the topic that I have found more or less
impossible to measure on production systems, especially considering a
page fault to disk is much more interesting.
so, I personally configure buffers for what I think the fsm is going
to need plus a fudge, and that's about it...would love to see some
results supporting or refuting that methodology.
merlin
