On Apr 14, 2011, at 2:49 AM, Claudio Freire <klaussfreire(at)gmail(dot)com> wrote:
> This particular factor is not about an abstract and opaque "Workload"
> the server can't know about. It's about cache hit rate, and the server
> can indeed measure that.

The server can and does measure hit rates for the PG buffer pool, but to my knowledge there is no clear-cut way for PG to know whether read() is satisfied from the OS cache or a drive cache or the platter.

...Robert

In response to

• Re: Performance at 2011-04-14 06:49:56 from Claudio Freire

Responses

• Re: Performance at 2011-04-26 07:49:39 from Claudio Freire
• Re: Performance at 2011-04-29 08:25:00 from James Mansion

pgsql-performance by date

Next:	From: Robert Haas	Date: 2011-04-26 05:35:35
	Subject: Re: Performance
Previous:	From: Rob Wultsch	Date: 2011-04-26 03:04:57
	Subject: Re: Time to put theory to the test?