Calibrating Replay Clients

Since one replay client can initiate multiple sessions with the database, it is not necessary to start a replay client for each session that was captured. The number of replay clients that need to be started depends on the number of workload streams, the number of hosts, and the number of replay clients for each host.

To estimate the number of replay clients and hosts that are required to replay a particular workload, run the wrc executable in calibrate mode.

In calibration mode, the wrc executable accepts the following keywords:

• replaydir specifies the directory that contains the preprocessed workload capture you want to replay. If unspecified, it defaults to the current directory.

• process_per_cpu specifies the maximum number of client processes that can run per CPU. The default value is 4.

• threads_per_process specifies the maximum number of thread that can run within a client process. The default value is 50.

The following example shows how to run the wrc executable in calibrate mode:

%> wrc mode=calibrate replaydir=./replay

In this example, the wrc executable is executed to estimate the number of replay clients and hosts that are required to replay the workload capture stored in a subdirectory named replay under the current directory. In the following sample output, the recommendation is to use at least 21 replay clients divided among 6 CPUs:

Workload Replay Client: Release 11.2.0.0.2 - Production on Fri May 1
13:06:33 2009
 
Copyright (c) 1982, 2009, Oracle.  All rights reserved.
 
Report for Workload in: /oracle/replay/
-----------------------
 
Recommendation:
Consider using at least 21 clients divided among 6 CPU(s).
 
Workload Characteristics:
- max concurrency: 1004 sessions
- total number of sessions: 1013
 
Assumptions:
- 1 client process per 50 concurrent sessions
- 4 client process per CPU
- think time scale = 100
- connect time scale = 100
- synchronization = TRUE