Introduction

The purpose of JOC Cockpit performance tests is to verify for a given hardware/software system the maximum parallelism of user sessions and operations that will not cause delays and slowness.

Any results from performance tests executed for Controller and Agent necessarily include JOC Cockpit, see JS7 - Performance Tests for Agents.

Performance tests specific for JOC Cockpit include

  • verifying the maximum number of applicable, parallel user sessions,
  • verifying performance of the JS7 - History Service and JS7 - Database for operations from parallel user sessions.

Test Metrics

Scenarios are based on increase of parallelism by iterations.

  • Each iteration doubles the number of parallel user sessions and operations.
  • White background numbers represent test parameters, blue background numbers represent typical test results that can be expected on average hardware.
  • The performance test is executed for JOC Cockpit default settings of 512 MB heap space.


ScenarioIterationUser SessionsMax. Start Time DelayTest 

BaseStartStopParallelismTotalDurationDelayDuration
Low247

Iteration 4: 16

24046s0s3s




Iteration 5: 32

0s

5s





Iteration 6: 64

2s

10s





Iteration 7: 128

5s

17s

Medium289

Iteration 8: 256

768114s

21s

39s





Iteration 9: 512

56s68s
High21011

Iteration 10: 1024

3072414s129s135s




Iteration 11: 2048

232s269s


Explanations:

  • Iteration:
    • Iterations by default use base 2 and the power of the iteration: 2<iteration>
      • An iteration of 4 means 24 and will start 16 parallel sessions.
      • An  iteration of 11 means 211 and will start 2048 parallel sessions.
    • Each of the low, medium and high scenarios performs the indicated iterations.
  • User Sessions: 
    • The Parallelism indicates the number of parallel sessions per iteration.
    • The Total gives the overall number of sessions with the iterations of the given scenario.
    • The Duration per session is longer for higher parallelism to guarantee that sessions run in parallel for some time in case of delayed session starts.
  • Max. Start Time Delay
    • Numbers represent the delay between start times of parallely launched sessions per iteration.
    • Larger delays indicate exhaustion of the underlying hardware/software system to start sessions in parallel.
  • Test Duration:
    • The duration is calculated from the earliest start time to the latest end time indicated by the JS7 - Order History.

Test Runs

The JS7 - Running Performance Tests for JOC Cockpit article explains test case execution.

The following chapters explain expectations and possible results per test scenario.

Performance Checks

Parallel Sessions

The  number of concurrent user sessions in JOC Cockpit affects its performance.

The test is executed using JOC Cockpit default settings. Increasing the Java heap space can provide better results.

History Service Throughput

The History Service receives events for JS7 - Order State Transitions and for log output from the Controller. The History Service will collect such data and will write the data to the database.

  • Performance of the JOC Cockpit is measured from API requests to the order history that return 1000 hits each, typically consuming <500ms.
  • Performance of the databasse is relevant when selecting records in parallel to updating and inserting records from the History Service.

Resources


  • No labels