× The internal search function is temporarily non-functional. The current search engine is no longer viable and we are researching alternatives.
As a stop gap measure, we are using Google's custom search engine service.
If you know of an easy to use, open source, search engine ... please contact support@midrange.com.


  1.  Home
  2. JAVA400-L
  3. November 1999

toolbox benchmark improvements

  • Subject: toolbox benchmark improvements
  • From: "Alex Garrison" <agarrison@xxxxxxxxxxx>
  • Date: Fri, 5 Nov 1999 10:14:55 -0500
 
We have been doing some internal benchmarks for the java toolbox on our as/400 under somewhat controlled conditions and found results I wanted to share with the group.  The test cases used record-level keyed and sequential file access modeling some of the typical processes we do in our web application. 
 
The tests were run as batch programs on our as/400 system during a period of low utilization when I had the system pretty much to myself.  The test application reads records from many different tables, parses the fields converting them to strings, and then loads the strings into vectors.  The numbers shown reflect the averages of many repetitions over a variety of tables in our database.  The actual times are not important; the differences in the times between the three test cases is very interesting.  We see up to a 41% improvement in the i/o time.  The parsing time (ie getField(), getFields()) changed little, and the vector processing was really statistically unchanged (to be expected since that is done by the java base classes, not the toolbox).
 
Three toolbox configurations were evaluated:
    1. mod2 GA release of the toolbox compiled to optimization level 30.
    2. mod2 toolbox with SF59086 service pack compiled to optimization level 30.
    3. mod2 toolbox with SF59086 service pack compiled to optimization level 40 using licopt(NOPRERESOLVEEXTREF)
 
Test CASE 1: Toolbox Mod2 GA                   
Category    time(ms)    %tot time
I/O         1586        60
Parse        683        26
Vector       363        14
 
Test CASE 2: Toolbox MOD2 SF59086 level 30
Category    time(ms)    %tot time
I/O          888        43
Parse        763        37
Vector       395        20
 
Test CASE 3 : Toolbox Mod2 SF59086 level 40
Category    time(ms)    %tot time
I/O          656        35
Parse        796        43
Vector       404        22
 
                   %difference
Category    test case 1-2   test case 2-3  test case 1-3
I/O         -28             -15            -41
Parse       +05             +02            +08
Vector      +04             +01            +04
 
 
 
Alex Garrison
agarrison@logtech.com
(423)636-7213

As an Amazon Associate we earn from qualifying purchases.

This thread ...
Follow-Ups:
Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.