From: Josh Berkus <josh@agliodbs.com>
Organization: PostgreSQL @ Sun
To: pgsql-performance@postgresql.org
Subject: Re: [HACKERS] 8.3beta1 testing on Solaris
Date: Thu, 25 Oct 2007 19:56:56 -0700
User-Agent: KMail/1.8.2
Cc: Tom Lane <tgl@sss.pgh.pa.us>, Gregory Stark <stark@enterprisedb.com>,
	"Jignesh K. Shah" <J.K.Shah@sun.com>, pgsql-hackers@postgresql.org
References: <4720FB72.8060800@sun.com> <871wbi95nb.fsf@oxford.xeocode.com>
	<29721.1193359867@sss.pgh.pa.us>
In-Reply-To: <29721.1193359867@sss.pgh.pa.us>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="utf-8"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
Message-Id: <200710251956.56744.josh@agliodbs.com>

Tom,

> It's still true that I'm leery of a large increase in the number of
> buffers without reengineering slru.c.  That code was written on the
> assumption that there were few enough buffers that a linear search
> would be fine.  I'd hold still for 16, or maybe even 32, but I dunno
> how much impact that will have for such a test case.

Actually, 32 made a significant difference as I recall ... do you still have 
the figures for that, Jignesh?

The test case is a workload called "iGen" which is a "fixed" TPCC-like 
workload.  I've been trying to talk Sun into open-sourcing it, but no dice so 
far.  It is heavy on writes, and (like TPCC) consists mostly of one-line 
transactions.

-- 
Josh Berkus
PostgreSQL @ Sun
San Francisco