Dbt2 with postgres issues on CentOS-5.3‏

From: MUHAMMAD ASIF <anaeem(dot)it(at)hotmail(dot)com>
To: <pgsql-performance(at)postgresql(dot)org>
Subject: Dbt2 with postgres issues on CentOS-5.3‏
Date: 2010-04-20 12:38:27
Message-ID: SNT122-W1949AA5E9DC08783F41BB7FF0A0@phx.gbl
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-performance


Hi,

I am using dbt2 on Linux 64 (CentOS release 5.3 (Final)) . I have compiled latest postgresql-8.4.3 code on the machine and run dbt2 against it. I am little confused about the results. I ran dbt2 with the following configuration i.e.

DBT2 Options :
WAREHOUSES=75
DB_CONNECTIONS=20
REGRESS_DURATION=1 #HOURS
REGRESS_DURATION_SEC=$((60*60*$REGRESS_DURATION))

DBT2 Command :
./dbt2-pgsql-create-db
./dbt2-pgsql-build-db -d $DBDATA -g -r -w $WAREHOUSES
./dbt2-run-workload -a pgsql -c $DB_CONNECTIONS -d $REGRESS_DURATION_SEC -w $WAREHOUSES -o $OUTPUT_DIR
./dbt2-pgsql-stop-db

I am not able to understand the sar related graphs. Iostat,mpstat and vmstat results are similar but sar results are strange. I tried to explore the dbt2 source code to find out the how graphs are drawn and why sar results differ.DBT2.pm : 189 reads sar.out and parse it and consider 1 minute elapsed time between each record i.e.
ActivePerl-5.10.1.1007-i686-linux-glibc-2.3.2-291969/inst/lib/Test/Parser/Sar.pm : 266
elapsed_time is a counter, with every record it increment to 1 (++$elapsed_time)

Sar.out shows the following results i.e.

08:54:47 PM cswch/s
..
..
09:21:47 PM 1809.46
09:22:47 PM 2251.26
09:23:47 PM 2151.27
09:24:47 PM 2217.33
09:27:01 PM 2189.83
09:29:02 PM 2155.13
09:30:02 PM 2048.04
09:32:19 PM 2033.16
09:34:20 PM 2032.47
09:36:20 PM 2006.02
09:37:20 PM 1966.03
09:39:35 PM 1974.77
09:41:37 PM 1973.88
09:42:37 PM 1960.65
09:44:56 PM 1993.15
09:45:56 PM 1989.46
09:47:57 PM 2430.77
09:48:57 PM 2416.64
09:51:08 PM 2330.02
09:53:19 PM 1738.46
09:54:19 PM 2182.27
09:55:19 PM 2221.31
09:56:19 PM 2131.81
09:57:19 PM 2183.47
09:59:31 PM 2156.70
10:01:32 PM 2114.38
10:02:32 PM 2030.05
10:04:51 PM 2059.56
10:05:51 PM 1995.06
10:08:09 PM 1355.43
10:09:09 PM 218.73
10:10:09 PM 175.13
10:11:09 PM 168.30
10:12:09 PM 168.58
..
..
It shows that sar results for each record is not after every 1 minute duration, it varies. Is it expected or there are some bugs in CentOS default sar package (sysstat-7.0.2-3.el5). I tried latest package sysstat-9.0.6.1 from but it behaving the same. Systat utilities depends on procfs, is there something wrong with the system ?. Thanks.

Best Regards,
Asif Naeem

_________________________________________________________________
Your E-mail and More On-the-Go. Get Windows Live Hotmail Free.
https://signup.live.com/signup.aspx?id=60969

Responses

Browse pgsql-performance by date

  From Date Subject
Next Message Kevin Grittner 2010-04-20 14:28:15 SOLVED ... Re: Getting rid of a cursor from JDBC .... Re: [PERFORM] Re: HELP: How to tame the 8.3.x JDBC driver with a biq guery result set
Previous Message Dave Crooke 2010-04-19 23:33:24 SOLVED ... Re: Getting rid of a cursor from JDBC .... Re: [PERFORM] Re: HELP: How to tame the 8.3.x JDBC driver with a biq guery result set