1 files changed, 96 insertions, 0 deletions
diff --git a/java/perftests/RunningPerformanceTests.txt b/java/perftests/RunningPerformanceTests.txt
new file mode 100644
index 0000000000..0b1d6d4f90
--- /dev/null
+++ b/java/perftests/RunningPerformanceTests.txt
@@ -0,0 +1,96 @@
+Running Performance Tests
+-------------------------
+
+This performance test suite contains a number of tests.
+
+- Service request-reply
+- Ping-Pong 
+- Headers
+
+Service request-reply
+---------------------
+
+Description:
+This is the simplest test to ensure everything is working. This involves 
+one client that is known as a "service provider" and it listens on a 
+well-known queue for requests. Another client, known as the "service requester"
+creates a private (temporary) response queue, creates a message with the 
+private response queue set as the "reply to" field and then publishes the 
+message to the well known service queue. The test allows you to time how long 
+it takes to send messages and receive the response back. It also allows varying 
+of the message size.
+
+QuickRun:
+
+./serviceRequestReply-QuickTest.sh <brokerdetails> <number of messages>
+
+This provides a quick test to run everything against a running broker. Simply specify broker and number of messages to run.
+
+
+Detailed Run:
+
+You must start the service provider first:
+
+serviceProvidingClient.sh <brokerdetails> [<P[ersistent]|N[onPersistent]> <T[ransacted]|N[onTransacted]>] [selector]
+
+where Brokerdetails is the connection information to the broker you are running on; e.g. localhost or localhost:5670 or tcp://10.10.10.10:5677.
+By default Non Persistent, Non Transaction messages are used in the response. A selector may also be specified.
+
+
+To run the service requester:
+
+serviceRequestingClient.sh <Brokerdetails> <Number of Messages> [<Message Size>] [<P[ersistent]|N[onPersistent]> <T[ransacted]|N[onTransacted]>]
+
+This requests the <number of messages> of a <Message Size (default 4096 bytes>. By default the connection is Non Persistent and Non Transactional.
+
+After receiving all the messages the client outputs the rate it achieved.
+
+
+Ping-Pong
+---------
+
+
+
+
+Headers
+-------
+
+
+A more realistic test is the "headers test", which tests the
+performance of routing messages based on message headers to a
+configurable number of clients (e.g. 50). A publisher sends 10000
+messages to each client and waits to receive a message from each
+client when it has received all the messages.
+
+You run the listener processes first:
+
+run_many.sh 10 header "headersListener.sh -host 10.0.0.1 -port 5672"
+
+In this command, the first argument means start 10 processes, the
+second is just a name use in the log files generated and the third
+argument is the command to run. In this case it runs another shell
+script but it could be anything.
+
+Then run the publisher process:
+
+headersPublisher.sh -host 10.0.0.1 -port 5672 10000 10
+
+The last two arguments are: the number of messages to send to each
+client, and the number of clients.
+
+Note that before starting the publisher you should wait about 30
+seconds to ensure all the clients are registered with the broker (you
+can see this from the broker output). Otherwise the numbers will be
+slightly skewed.
+
+A third useful test, which can easily be ported to other JMS
+implementations is the "topic test". It does the same as the headers
+test but using a standard topic (e.g. pub sub).
+
+To run the listeners:
+
+run_many.sh 10 topic "topicListener.sh -host 10.0.0.1 -port 5672"
+
+and to run the publisher:
+
+topicPublisher.sh -host 10.0.0.1 -port 5672 -clients 10 -messages 10000
+\ No newline at end of file