Sunday, September 28, 2008

Re: [PERFORM] Slow updates, poor IO

I've canned the db and got rid my of data.
I'm in the midst of doing some other benchmarking for a possible change
to the bacula database.

Loading up 1M records into a table of 60M records complete with indexes.
It's still going...


Dan Langille wrote:
> On Sep 28, 2008, at 10:01 PM, John Huttley wrote:
>> Greg Smith wrote:
>>> On Mon, 29 Sep 2008, John Huttley wrote:
>>>> checkpoint _segments=16 is fine, going to 64 made no improvement.
>>> You might find that it does *after* increasing shared_buffers. If
>>> the buffer cache is really small, the checkpoints can't have very
>>> much work to do, so their impact on performance is smaller. Once
>>> you've got a couple of hundred MB on there, the per-checkpoint
>>> overhead can be considerable.
>> Ahh bugger, I've just trashed my test setup.
> Pardon? How did you do that?

Sent via pgsql-performance mailing list (
To make changes to your subscription:

No comments: