!
&
ECG082/0898
Load Simulator creates a highly accurate simulation of reality. It mimics the full Microsoft
Exchange Client in many respects. First, it uses .MSG files, the same format used by the
Exchange Client. This guarantees that messages generated by Load Simulator have the same
properties as those sent by real users of the Exchange Client. Second, Load Simulator uses the
same MAPI remote procedure call (RPC) semantics as those used by the Client. Third, Load
Simulator registers MAPI change notifications in the same manner as they are registered by the
Client. Finally, Load Simulator even emulates the Microsoft Exchange Client list box cache,
which the Client uses for folder and message panes in the viewer when a user browses and selects
messages on the server. For more information on LoadSim Medium canonical profiles, refer to
the LoadSim documentation at
http://www.microsoft.com/exchange/library/loadsim55x86.exe
.
Table 5. TEST DISCLOSURE
LoadSim Clients
Configuration
Network Topology (100Base T, Token Ring, etc.)
100 Base-TX
Number and type of clients
(
≤
40) 2x5/133, 128 MB RAM (
≤
400 users each)
or better (indicates minimum configuration)
Number and type of hubs/concentrators (full
duplex, switching, etc.)
Compaq Netelligent 5708 Switch and Netelligent
2624 Hubs
Number of clients/segment
20
Client CPU type and speed in percentages
2P/133-MHz Pentium
processors or better
Client network controller broken down by
percentages
Compaq Netelligent 10/100
Client network software name and version (drivers,
protocols, redirector)
Microsoft Windows NT Workstation 4.0 with SP3
TCP/IP
Size of any client network cache
None
Network controller software
Compaq Netelligent 10/100 driver
LoadSim version
5.5 (Build 2187)
Note: Response time measurements were taken from a LoadSim Control Client simulating 100
users configured with 96 MB RAM and a Pentium/166 CPU. The client is located on an isolated
network segment connected to a 100-Mb/s switch.
Benchmark Tuning
Table 6 shows tuning parameters for Exchange Server that varied from default settings for
purposes of the benchmark exercise. Compaq recommends using the default settings specified by
the Microsoft Exchange Performance Optimizer for production server deployments.
Table 6. Benchmark Tuning
Parameter
Default Setting
Benchmark Setting
IS Buffers (4K each)
524,000
375,000
Max Open Tables
32,000
200,000
IS Send Threads
4
8
