Subsequent to my presentation of the new annotated.conf at pgCon last week,
there's been some argument about the utility of certain memory settings
above 2GB. I'd like to hash those out on this list so that we can make
some concrete recomendations to users.
shared_buffers: according to witnesses, Greg Smith presented at East that
based on PostgreSQL's buffer algorithms, buffers above 2GB would not
really receive significant use. However, Jignesh Shah has tested that on
workloads with large numbers of connections, allocating up to 10GB
sort_mem: My tests with 8.2 and DBT3 seemed to show that, due to
limitations of our tape sort algorithm, allocating over 2GB for a single
sort had no benefit. However, Magnus and others have claimed otherwise.
Has this improved in 8.3?
So, can we have some test evidence here? And workload descriptions?
PostgreSQL @ Sun
pgsql-performance by date
|Next:||From: Steve Crawford||Date: 2008-05-29 00:04:37|
|Subject: Re: 2GB or not 2GB|
|Previous:||From: Tom Lane||Date: 2008-05-28 23:41:46|
|Subject: Re: Creating large database of MD5 hash values |