On Fri, 2009-06-19 at 22:03 -0400, Greg Smith wrote:
> This makes me wonder if in addition to the ring buffering issue, there
> isn't just plain more writing per average completed transaction in 8.4
> with this type of COPY.
I would suggest that we check how much WAL has been written. There may
be a secondary effect or a different regression hidden in these results.
Simon Riggs www.2ndQuadrant.com
PostgreSQL Training, Services and Support
In response to
pgsql-hackers by date
|Next:||From: Markus Wanner||Date: 2009-06-20 09:05:29|
|Subject: Re: Synch Rep: communication between backends and walsender|
|Previous:||From: Simon Riggs||Date: 2009-06-20 08:22:20|
|Subject: Re: 8.4 open item: copy performance regression?|