Re: Reduce heap tuple header size

From: Bruce Momjian <pgman(at)candle(dot)pha(dot)pa(dot)us>
To: Alvaro Herrera <alvherre(at)atentus(dot)com>
Cc: Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, Jan Wieck <JanWieck(at)Yahoo(dot)com>, Manfred Koizar <mkoi-pg(at)aon(dot)at>, pgsql-patches(at)postgresql(dot)org
Subject: Re: Reduce heap tuple header size
Date: 2002-06-22 03:57:15
Message-ID: 200206220357.g5M3vGJ13783@candle.pha.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers pgsql-patches

Alvaro Herrera wrote:
> Tom Lane dijo:
>
> > Jan Wieck <JanWieck(at)Yahoo(dot)com> writes:
> > > Here are some numbers:
> >
> > > Current CVS tip: tps 34.1, 38.7, 36.6
> > > avg(tps) 36.4
> >
> > > With patch: tps 37.0, 41.1, 41.1
> > > avg(tps) 39.7
> >
> > > So it saves less than 3% disk space at the cost of about 9% performance
> > > loss.
> >
> > Uh ... isn't more TPS better?

9%, that is a dramatic difference. Is it caused by the reduced disk
space (Jan's numbers are correct) or by the extra overhead in the merged
fields (Jan's numbers are backwards)? Jan will tell us soon.

> Also, is that 3% in disk space savings the actual number, or just copied
> from the "anawhat"?

The 3% is savings from a sample database. Header size is 11% reduced.

--
Bruce Momjian | http://candle.pha.pa.us
pgman(at)candle(dot)pha(dot)pa(dot)us | (610) 853-3000
+ If your life is a hard drive, | 830 Blythe Avenue
+ Christ can be your backup. | Drexel Hill, Pennsylvania 19026

In response to

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message Bruce Momjian 2002-06-22 04:01:02 Re: What is wrong with hashed index usage?
Previous Message Larry Rosenman 2002-06-22 03:12:22 Re: test 2, first failed ...

Browse pgsql-patches by date

  From Date Subject
Next Message Bruce Momjian 2002-06-22 04:02:36 Re: ODBC Patch to prevent setting of KSQO on 7.3+ servers
Previous Message Joe Conway 2002-06-22 03:17:40 show() function