WebBench lets you measure
Web server software performance by running different
Web server packages on the same server hardware or by running a given Web server
package on different hardware platforms. The latest version of WebBench answers
user requests for more connections and other facilities for putting more stress
on bigger servers and more accurately modeling real-world server
workloads. WebBench's standard test suites produce two overall scores for the
server: requests per second and throughput as measured in bytes per second.
WebBench provides both static standard test suites and dynamic standard test
suites (which execute applications that actually run on the server). In
addition, you can easily create your own test suites. No matter which test
suites you use, your PC clients must be running either Windows
95/98 or Windows NT/2000 and the controller must be running Windows NT or
Windows 2000.
WebBench |
static_mt_wb401 |
Throughput |
Dual CPU's HT Enabled
Dual CPU's HT
Disabled
Single CPU HT Disabled
Single CPU HT Disabled
It seems WebBench's static_mt_wb401 test is a bit more volatile,
when using two CPU's (HT on or off) we get consistent performance, With only one
CPU and HT enabled, performance is a bit shaky and with one CPU and no
HyperTreading, performance is unpredictable!