Horton

Re: Seq scans roadmap

Zeugswetter Andreas DCP SD <zeugswettera@spardat.at>

View thread View on postgr.es
From: "Zeugswetter Andreas ADI SD" <ZeugswetterA@spardat.at>
To: "Jim C. Nasby" <decibel@decibel.org>, "Jeff Davis" <pgsql@j-davis.com>
Cc: "Heikki Linnakangas" <heikki@enterprisedb.com>, "Luke Lonergan" <LLonergan@greenplum.com>, "PostgreSQL-development" <pgsql-hackers@postgresql.org>, "Simon Riggs" <simon@enterprisedb.com>, "CK.Tan" <cktan@greenplum.com>
Date: 2007-05-16T08:31:30Z
Lists: pgsql-hackers 
> > > > 32 buffers = 1MB with 32KB blocksize, which spoils the CPU L2 
> > > > cache effect.

I'd say in a scenario where 32k pages are indicated you will also want
larger than average L2 caches.

> > > > 
> > > > How about using 256/blocksize?

The reading ahead uses 1/4 ring size. To the best of our knowledge, this
1/4 needs to be 128k for reading.
So I'd say we need 512/blocksize.

Andreas