>Another though. If postgres has one of my CPU's at near 100%, does that
>mean I can't get any more performance out of it? Still, how big can I
>make sort_mem?
I regularly have one CPU pegged at 100% with PostgreSQL on my queries
(tables of 4m-ish rows and up). (Dual P3 1ghz 2GB, Linux 2.2, PG 7.2.1)
I believe it cannot multithread individual queries using several processors.
I believe IBM DB2 Enterprise _can_ do that - but it also costs $20,000 per
CPU and damned if I can figure out how to install it even for the trial.
Let me ask a similar question:
If I ran PostgreSQL with a Linux 2.4 kernel and 6GB of RAM with dual P4 Xeons:
a) Could PostgreSQL use all the RAM?
b) The RAM paging would incur a 2-4% slowdown, any other noted speed
reductions?
c) Could PostgreSQL use this "hyperthreading" that apparently is in these
P4 Xeons making dual processors look like four processors (obviously, on
four separate queries)?
d) How much extra performance does having the log or indices on a different
disk buy you, esp. in the instance where you are inserting millions of
records into a table? An indexed table?
I ask "d" above because as I am considering upgrading to such a box, it
will have an 8-disk RAID controller, and I'm wondering if it is a better
idea to:
a) Run everything on one 7-drive RAID 5 partition (8th drive as hot spare)
b) Run logs as a 2-drive mirror and the rest on a 5-drive RAID 5
c) Run logs on a 2-drive mirror, indices on a 2-drive mirror, and the rest
on a 3-drive RAID5?
d) Run logs & indices on a 2-drive mirror and the rest on a 5-drive RAID 5
Thanks,
Doug