thanks all, the comments given here have been great toward selecting hardware for Tomcat/Apache web server in the following ways:
* super fast and heavy hard disk access not so important if no database on same machine * 64-bit cpu (such as opteron) could be quite significant choice (where hard disk access is not primary) * load testing on development machine useful measurement in choosing hardware for production system -pl ----- Original Message ----- From: "Paul Sundling" <[EMAIL PROTECTED]> To: "Tomcat Users List" <[EMAIL PROTECTED]> Sent: Wednesday, August 13, 2003 5:38 PM Subject: Re: hardware recommendation, Tomcat with Apache web server > I forgot to point out that in the test where opteron was beating xeon 2 > to 1, it was a 2.8 Ghz Xeon losing to a 1.6 Ghz Opteron!!! So with > almost half the clock speed it was twice as good as a Xeon. That's > impressive.... > > > I found some benchmarks that used another app server, but it's the > > same kind of software as tomcat, so it's a good comparison. The clear > > answer is that a new opteron is what you should get and it's LITERALLY > > twice as good in the role of an application server(like tomcat): > > > > http://www.extremetech.com/article2/0,3973,1149817,00.asp > > > > "Our most important server test for comparing the Opteron to the Xeon > > in an application server scenario is our 32-bit "Nile" application > > server benchmark. The test is both CPU and disk-intensive, and it > > emulates a book-ordering transaction-processing environment modeled on > > Amazon.com. The test uses Oracle 9i as the back-end, running on a Xeon > > 4P server, and uses BEA WebLogic Server 7.0.2 application server > > software. The BEA application server software runs on the test > > equipment – in this case we loaded it on both the 2P Opteron and 2P > > Xeon systems, with Windows 2000 with SP3 as the OS. " > > > > " Results on the Nile benchmark showed the dual Opteron system > > outperforming the dual Xeon by a fairly wide margin. Across a 300 to > > 500 virtual user load, where transaction processing stabilized with > > both high disk and CPU utilization, the Xeon averaged 7.6 Pages > > Received per second, and the Opteron averaged 15.2 Pages Received per > > second, double the Xeon. In the response time measurements, at the 200 > > user load, average transaction time (start to finish) was > > approximately 34 seconds on the Xeon and 30 seconds on Opteron, but > > moving to 300 users, Opteron stayed at 30 seconds, and Xeon moved to > > 50 seconds. At 400 users, Opteron was 35 seconds, and Xeon was near 80 > > seconds. And at 500 users Opteron was about 50 seconds, and Xeon was > > near 100 seconds. See Nile Benchmark charts below." > > > > 20-30 simultaneous users doesn't sound like much. Personally, I'd love > > to get one of those new Opteron servers! 64 bit processor and when the > > real 64 bit windows becomes available in a couple months it could > > really scream and it'd scale up to huge levels of ram if you ever > > needed it. Or it'd be 64 bit already with linux/bsd/solaris/.... > > > > [you know you've been programming too long when you almost do Ctrl-s > > (like in eclipse) when you're finished with something instead of > > clickong on send] > > > > Paul wrote: > > > > > > --------------------------------------------------------------------- > To unsubscribe, e-mail: [EMAIL PROTECTED] > For additional commands, e-mail: [EMAIL PROTECTED] > > --------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
