"Logan Bowers" <logan@zillow.com> writes:
> I'm potentially having a strange performance problem. I have a BIG table:
> ~100M, ~1KB rows. I do a SELECT count(*) from it (I know it will be slow)
> and as I watch procinfo on my DB server I see a huge amount of write
> activity. Thus,
The only thing I can think of is that you have a lot of dirty page
buffers (either in PG's shared buffer area or the kernel's page cache)
due to prior write activity, and they are getting written out to make
room for the sequential scan's incoming buffers.
> 3) Are my tools lying to me (i.e. procinfo is wrong)?
Perhaps; if you're on Linux try 'vmstat' instead of procinfo as a
check.
-Doug
