Josh Berkus <josh@agliodbs.com> writes:
>> Rather, what you need to be thinking about is how
>> come vacuum seems to be making lots of pages dirty on only one of these
>> machines.
> This is an anti-wraparound vacuum, so it could have something to do with
> the hint bits. Maybe it's setting the freeze bit on every page, and
> writing them one page at a time?
That would explain all the writes, but it doesn't seem to explain why
your two servers aren't behaving similarly.
> Still don't understand the call to pollsys, even so, though.
Most likely that's the libc implementation of the select()-based sleeps
for vacuum_cost_delay. I'm still suspicious that the writes are eating
more cost_delay points than you think.
regards, tom lane