Luke Lonergan wrote:
> So that leaves the question - why not more than 64% of the I/O scan rate?
> And why is it a flat 64% as the I/O subsystem increases in speed from
It might be interesting to see what effect reducing the cpu consumption
entailed by the count aggregation has - by (say) writing a little bit
of code to heap scan the desired relation (sample attached).
Description: text/plain (978 bytes)
In response to
pgsql-performance by date
|Next:||From: Qingqing Zhou||Date: 2005-11-22 07:21:12|
|Subject: Re: weird performances problem|
|Previous:||From: Luke Lonergan||Date: 2005-11-22 04:35:26|
|Subject: Re: Hardware/OS recommendations for large databases (|