Re: dbt2 NOTPM numbers - Mailing list pgsql-performance

From Heikki Linnakangas
Subject Re: dbt2 NOTPM numbers
Date
Msg-id 4664748B.2060304@enterprisedb.com
Whole thread Raw
In response to Re: dbt2 NOTPM numbers  (Markus Schiltknecht <markus@bluegap.ch>)
Responses Re: dbt2 NOTPM numbers
List pgsql-performance
Markus Schiltknecht wrote:
> Hi,
>
> Heikki Linnakangas wrote:
>> There's clearly something wrong. The response times are ridiculously
>> high, they should be < 5 seconds (except for stock level transaction)
>> to pass a TPC-C test. I wonder if you built any indexes at all?
>
> Hm.. according to the output/5/db/plan0.out, all queries use index
> scans, so that doesn't seem to be the problem.

I still suspect there's something wrong with plans, I doubt you can get
that bad performance unless it's doing something really stupid. I'd
suggest setting log_min_duration_statement = 5000, and seeing what you
get. Also check pg_stat_user_table.seq_scan just to be extra sure
there's no seq scans.

--
   Heikki Linnakangas
   EnterpriseDB   http://www.enterprisedb.com

pgsql-performance by date:

Previous
From: Scott Marlowe
Date:
Subject: Re: Thousands of tables versus on table?
Next
From: Gregory Stark
Date:
Subject: Re: upgraded to pgsql 8.2.4, getting worse performance then 7.4.x