"Joshua D. Drake" <[EMAIL PROTECTED]> writes: > Tom Lane <[EMAIL PROTECTED]> wrote: >> Some vmstat and oprofile investigation seems called for. Right now >> we're just guessing about what the bottleneck is.
> vmstat -adSK 5 > ... Looks to me like you're disk-bound (and your kernel is pretty bad at distinguishing "idle" from "disk wait" states). Plain COPY into an index-less table ought to be writing fairly linearly, so I'm surprised you aren't able to get more out of the disk. Have you got WAL on a separate spindle from the database? regards, tom lane ---------------------------(end of broadcast)--------------------------- TIP 5: don't forget to increase your free space map settings