RE: Benchmarks: Catalina M5 vs. Apache 1.3.12
Hello, OpenSta seems to be a good harness test with multiple client. You can find it at http://sourceforge.net/projects/opensta/ Eric -Original Message- From: Curtis Dougherty [mailto:[EMAIL PROTECTED]] Sent: mardi 5 décembre 2000 20:32 To: '[EMAIL PROTECTED]' Subject: RE: Benchmarks: Catalina M5 vs. Apache 1.3.12 Jason - I am attempting to generate some server performance numbers as well. What tool would you recommend to test TOMCAT vs. WebLogic JRun et al.??? If you can point me in the right direction for a good test harness to plug-in I would be very grateful. Thank you for your time and consideration of this matter. Regards, Curtis QA Engineer BusinessThreads -Original Message- From: Jason Brittain [mailto:[EMAIL PROTECTED]] Sent: Tuesday, December 05, 2000 12:48 PM To: [EMAIL PROTECTED] Subject: Benchmarks: Catalina M5 vs. Apache 1.3.12 I wrote up a text file about benchmarking and comparing Tomcat-4.0-M5 (pre-release) and Apache 1.3.12. It's attached to this message. I wrote it for anyone who is interested (even non-Java-saavy people) to know how the raw content serving performance of Catalina and its built-in web server compares to that of Apache 1.3.12. It contains lots of information to help people understand some of the important differences between the two servers. Feedback, flames, reproduced test results, etc. are welcome! :) Cheers. -- Jason Brittain Software Engineer, Olliance Inc.http://www.Olliance.com Current Maintainer, Locomotive Project http://www.Locomotive.org
Re: Benchmarks: Catalina M5 vs. Apache 1.3.12
Hi there Chris. You can certainly do just what I did, use ApacheBench and see what numbers you get with each server. There's also another tester called Apache JMeter, which will show you graphical views of the tests as they're happening. JMeter has some bugs, but it's good anyway. You can find it here: http://java.apache.org/jmeter/index.html Try that out too. And, it would be great if you could share your results, even if you don't go into the depth about your tests as I did.. Have fun! -- Jason Curtis Dougherty wrote: Jason - I am attempting to generate some server performance numbers as well. What tool would you recommend to test TOMCAT vs. WebLogic JRun et al.??? If you can point me in the right direction for a good test harness to plug-in I would be very grateful. Thank you for your time and consideration of this matter. Regards, Curtis QA Engineer BusinessThreads -Original Message- From: Jason Brittain [mailto:[EMAIL PROTECTED]] Sent: Tuesday, December 05, 2000 12:48 PM To: [EMAIL PROTECTED] Subject: Benchmarks: Catalina M5 vs. Apache 1.3.12 I wrote up a text file about benchmarking and comparing Tomcat-4.0-M5 (pre-release) and Apache 1.3.12. It's attached to this message. I wrote it for anyone who is interested (even non-Java-saavy people) to know how the raw content serving performance of Catalina and its built-in web server compares to that of Apache 1.3.12. It contains lots of information to help people understand some of the important differences between the two servers. Feedback, flames, reproduced test results, etc. are welcome! :) Cheers.
AW: Benchmarks: Catalina M5 vs. Apache 1.3.12
Hi, The notion of "tomcat is fast enough" used to be a dream but we`re getting there. I am going to run a few big sites on a combo of apache and tomcat, since there are a lot of PHP and mod_perl scripts in use. That means that for a given period of time Apache needs to sit in front of Tomcat to do a lot of work. This amount of work gets smaller and smaller during a period of about 12 months. Plans are to shift slowly to Servlets/JSP only, buts its not easy to get the right programmers for that purpose. In this timeframe we hopefully will see further improvements in regards to stability and performance of tomcat. And i personally hope that the unofficial battle between all the versions of tomcat (3.1, 3.2, 4.x) will improve the overall quality of Tomcat but finally end up in just one version. Tomcat is already the only server for the intranet application server which runs an publishing/content management system. Here we see an performance of up to 25-35 request/s (500 MHz Pii, Suse Linux, 512 MByte, IBM JDK 1.3) including an XML-RPC protocol, which is reason for quite an hefty overhead but its worth it. The real server will have an 1 Gz CPU and 1 GByte of RAM so i expect some more possible request/s. Juergen Fey "don`t drive when you`re dead, tom waits" The box said "Win95 or better", so i installed Linux -Ursprüngliche Nachricht- Von: Jason Brittain [mailto:[EMAIL PROTECTED]] Gesendet: Dienstag, 5. Dezember 2000 19:48 An: [EMAIL PROTECTED] Betreff: Benchmarks: Catalina M5 vs. Apache 1.3.12 I wrote up a text file about benchmarking and comparing Tomcat-4.0-M5 (pre-release) and Apache 1.3.12. It's attached to this message. I wrote it for anyone who is interested (even non-Java-saavy people) to know how the raw content serving performance of Catalina and its built-in web server compares to that of Apache 1.3.12. It contains lots of information to help people understand some of the important differences between the two servers. Feedback, flames, reproduced test results, etc. are welcome! :) Cheers. -- Jason Brittain Software Engineer, Olliance Inc.http://www.Olliance.com Current Maintainer, Locomotive Project http://www.Locomotive.org
Re: Benchmarks: Catalina M5 vs. Apache 1.3.12
I wrote up a text file about benchmarking and comparing Tomcat-4.0-M5 (pre-release) and Apache 1.3.12. It's attached to this message. I wrote it for anyone who is interested (even non-Java-saavy people) to know how the raw content serving performance of Catalina and its built-in web server compares to that of Apache 1.3.12. It contains lots of information to help people understand some of the important differences between the two servers. may I suggest the same test against the tomcat 3.2 release ;-)
Re: Benchmarks: Catalina M5 vs. Apache 1.3.12
Eric Hartmann [EMAIL PROTECTED] wrote: Hello, OpenSta seems to be a good harness test with multiple client. You can find it at http://sourceforge.net/projects/opensta/ And there's always Apache Jmeter http://java.apache.org/jmeter Pier -- Pier P. Fumagalli Apache Software Foundation mailto:[EMAIL PROTECTED] Neque porro quisquam est qui dolorem ipsum quia dolor sit amet, consectetur, adipisci velit... (Cicero: "De Finibus" 1.10.32)
Re: Benchmarks: Catalina M5 vs. Apache 1.3.12
Quoting Jason Brittain [EMAIL PROTECTED]: I wrote up a text file about benchmarking and comparing Tomcat-4.0-M5 (pre-release) and Apache 1.3.12. It's attached to this message. I wrote it for anyone who is interested (even non-Java-saavy people) to know how the raw content serving performance of Catalina and its built-in web server compares to that of Apache 1.3.12. It contains lots of information to help people understand some of the important differences between the two servers. Feedback, flames, reproduced test results, etc. are welcome! :) I'm glad it's not too bad (right now the static file serving is very badly optimized). There are some optimizations in, but we also do lots of unnecessary IO operations for each request. We won't do further optimizations on this before TC 4.0 is released, because we might get rid of the whole resources package after 4.0 (more on this after M5 is out). Remy
