Date: Wed, 24 Aug 2005 15:57:44 -0500
From: "Jim C. Nasby" <jnasby@pervasive.com>
To: Chris Browne <cbbrowne@acm.org>
Cc: pgsql-performance@postgresql.org
Subject: Re: Read/Write block sizes
Message-ID: <20050824205744.GX96732@pervasive.com>
References: <d4b67d7c2b.d7c2bd4b67@bur-mail1.east.sun.com>
	<60k6icpapm.fsf@dba2.int.libertyrms.com>
	<1124846743.12045.94.camel@amd64-laptop-spoe>
	<60br3npb4p.fsf@dba2.int.libertyrms.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <60br3npb4p.fsf@dba2.int.libertyrms.com>
User-Agent: Mutt/1.5.9i

On Wed, Aug 24, 2005 at 12:12:22PM -0400, Chris Browne wrote:
> Everyone involved in development seems to me to have a reasonably keen
> understanding as to what the potential benefits of threading are; the
> value is that there fall out plenty of opportunities to parallelize
> the evaluation of portions of queries.  Alas, it wouldn't be until
> *after* all the effort goes in that we would get any idea as to what
> kinds of speedups this would provide.

My understanding is that the original suggestion was to use threads
within individual backends to allow for parallel query execution, not
swiching to a completely thread-based model.

In any case, there are other ways to enable parallelism without using
threads, such as handing actual query execution off to a set of
processes.
-- 
Jim C. Nasby, Sr. Engineering Consultant      jnasby@pervasive.com
Pervasive Software        http://pervasive.com        512-569-9461