> That's a speedup of nearly a factor of two, so clearly fsync-related
> stalls are a big problem here, even with wal_buffers cranked up
> through the ceiling.

Hmmmm.   Do you have any ability to test on XFS?

-- 
Josh Berkus
PostgreSQL Experts Inc.
http://pgexperts.com

In response to

• Re: wal_buffers, redux at 2012-03-13 19:48:32 from Robert Haas

Responses

• Re: wal_buffers, redux at 2012-03-14 03:18:59 from Robert Haas

pgsql-hackers by date

Next:	From: Kevin Grittner	Date: 2012-03-13 22:50:36
	Subject: Re: INHERIT vs INHERITS
Previous:	From: Kevin Grittner	Date: 2012-03-13 22:40:53
	Subject: Re: pg_upgrade and statistics