Widget Gallery

The following tables summarize the graphs that are available in the gallery.

Client side measurements

Graph name Description What does it tell me about my test?
Running Vusers

The number of running Vusers during the test.

 

Failed Vusers The number of Vusers that terminated unexpectedly during the test. This shows how many virtual users terminate unexpectedly. Typically this value should be 0 or near 0. A high value indicates a problem in the load test. In such instances, we recommend that you check the script and the environment.
Hits Per Second

The number of hits (HTTP requests) to the Web server per second.

This illustrates the work load level on the server.
Throughput

The amount of data received from the server every second.

Measured in bytes.

Compare this graph to the Transaction Response Time graph to see how the throughput affects transaction performance.
Errors The number of errors encountered by Vusers during the run of the test. A large number of errors during a specific time period of the test can indicate a performance problem with the application.
Errors per second The number of errors encountered by Vusers per second during the run of the test.  
Connections The number of open TCP/IP connections at each point of time in the load test scenario. This graph is useful in indicating when additional connections are needed. For example, if the number of connections reaches a plateau and the transaction response time increases sharply, adding connections would probably cause a dramatic improvement in performance (reduction in the transaction response time).

Back to top

Transaction measurements

Note:  

  • For custom widgets, the average value may be different due to a difference in granularity and the number of data points.
  • If you selected General Settings > Group Transactions when you configured the load test, measurements for the transaction groups are also displayed.
Graph name Description What does it tell me about my test?
Transaction Response Time [X percentile]

The maximum time it takes for X percent of transactions to complete.

Note: X is defined in the Load Test > SLA pane for the test.

Highlights transaction behavior during run time.

 

Transaction Response Time [Average]

The average time taken to perform transactions during the load test run.

Measured in seconds.

Highlights transaction behavior during run time.

Compare the TRT (Average) graph to the Running Vusers graph to see if there is an impact on performance.

Transaction Response Time [Min]

The minimum time taken to perform transactions during the load test run.

Measured in seconds.

Compare the TRT (Min) and TRT (Max) graphs with the TRT (Average) graph to help you determine the quality and stability of transactions.

A large variance may indicate unstable behavior of requests to the server.

Transaction Response Time [Max]

The maximum time taken to perform transactions during the load test run.

Measured in seconds.

Compare the TRT (Min) and TRT (Max) graphs with the TRT (Average) graph to help you determine the quality and stability of transactions.

A large variance may indicate unstable behavior of requests to the server.

Total Transactions The total number of transactions during the load test run. Helps you determine the actual transaction load on your system at any given moment.
Total Transactions per Second The total number of transactions during each second of the load test run. Helps you determine the actual transaction load on your system at any given moment.
Passed Transactions The total number of transactions that completed successfully during the load test run.  
Passed Transactions per Second The total number of transactions that completed successfully during each second of the load test run.

Compare this graph to the Running Vusers graph to determine if there is a drop in server performance.

For example, if the number of running Vusers is stable but the transaction per second drops, this may indicate a problem with the server.

Failed Transactions The number of times a transaction failed during the load test run.

Can be an indication that the business process is failing.

Failed Transactions per Second The number of transactions that failed per second.  
SLA Breakers The percentage of transactions that broke the SLA threshold at any given time in the load test run.  

Back to top

Monitors

Graph name Description What does it tell me?
CPU

How much processing power is required at any given time.

Measured in percentage.

This metric can identify a business process that is overloading the server.

Used memory The percentage of memory being used at any given time. This metric tells me if my server is overloaded.
Free memory

The amount of memory available at any given time.

Measured in bytes.

This metric tells me if my server is overloaded.
Disk utilization The percentage of the file system that is full. This metric tells me if the disk operation causes a bottleneck or causes a performance hit.
Free disk space

The amount of available disk space at any given time.

Measured in bytes.

Can indicate that there is not enough disk space on the server.
Network Utilization

The total size of packets exchanged between client and server.

Measured in bytes.

When network utilization is not correlated with running Vusers, this may indicate that the application is not scalable.

Back to top

Breakdown

For every transaction in the breakdown script(s), the following metrics are displayed in the Transaction Response Time (TRT) graph.

 

Metric Description What does it tell me?
Blocked

Average amount of time for all HTTP(s) requests in the queue waiting for a network connection.

This stacked widget displays transaction performance breakdown for a specific transaction.

 

 

DNS Average amount of time taken for all HTTP(s) requests to resolve a host name.
Connection Average amount of time taken for all HTTP(s) to create a TCP connection.
SSL Average amount of time for all HTTP(s) requests to negotiate SSL/TLS.
Send Average amount of time taken to send all HTTP(s) requests to the server.
Wait Average amount of time taken for all HTTP(s) waiting for a response from the server.
Receive Average amount of time taken for all HTTP(s) requests to read an entire response from the server (or cache).
Client Transaction response time minus the sum of all the metrics above

Back to top

Mobile

Graph name Description What does it tell me?
Total Consumed Memory

The amount of memory consumed on the mobile device.

This metric tells me if my mobile device is overloaded.

Total CPU Utilization Percentage The percentage of CPU being used on the mobile device at any given time. This metric tells me if my mobile device is overloaded.
Total Free Memory

The amount of memory available on the mobile device at any given time.

Measured in bytes.

This metric tells me if my mobile device is overloaded.

Back to top

Flex

Graph name Description What does it tell me?

Average Buffering Time - RTMP over HTTP / TCP

Average buffering time for RTMP streams. Helps evaluate the amount of load that Vusers generate, in terms of time spent for streams in the buffer.

Average RTMP / RTMP over HTTP handshake duration

Average RTMP handshake duration. Shows the time taken to perform various RTMP tasks.
Average TCP socket connect duration Average TCP socket connect duration. Shows the time taken to perform various RTMP tasks.

RTMP over HTTP / TCP Connections

The number of open RTMP connections at any time during the load test run.

Useful in indicating when additional connections are needed.

For example, if both the number of connections reaches a plateau and the transaction response time increases sharply, adding connections improvement in performance. Thus reducing transaction response time.

RTMP over HTTP / TCP Throughput / upload throughput

The amount of data Vusers received from the server or sent to the server at any given second. Can be compared with the Transaction Response Time graph to see how the throughput affects transaction performance.

Total number of successfully delivered streams - RTMP over HTTP / TCP

Total number of streams successfully delivered by the server. Helps evaluate the performance of your server by indicating the number of successfully delivered streams.

Back to top

MQTT

Graph name Description What does it tell me?
MQTT Message Rate Published/Received message rate. Displays the number of messages published or received at any given time during the load test run.
MQTT Throughput Published/Received throughput. Displays the amount of data (in bytes) that Vusers received from, or published to, the MQTT broker at any given second of the load test run.
MQTT Active Connections Active connections to the MQTT broker. Displays the number of active connections to the MQTT broker at any given moment of the load test run.
MQTT In-flight Messages The number of in-flight messages on the MQTT broker. Displays the number of in-flight messages on the MQTT broker at any given second of the load test run. In-flight messages are QoS 1 or 2 messages that can be in the process of being transmitted, including messages currently going through handshakes and messages that are being retried.

Back to top