Skip to content

Load Generator Saturation

Load is produced by machines too. If a load generator spends the run near 100% CPU, it cannot send requests at the configured rate, and the response times it records include time spent waiting for its own CPU. The numbers then describe the generator, not your application.

The Overview shows a warning banner when any load generator peaked at or above 80% CPU during the run, naming it and its peak ("engine 2 peaked at 91% CPU"). For JMeter runs, the full CPU, memory, network and disk series are on the Engine Health tab.

  • Response time climbs with the number of virtual users, but the target's own monitoring shows it idle.
  • Throughput flattens although the error rate stays at zero.
  • One location is slower than the others and it is the one whose load generator was hot.

Treat every response time from a saturated run as pessimistic: your application's real response time is the same or lower, and the warning banner calls this a lower bound on how well the app performs.

  • Spread the same number of users across more load generators or locations, so each one does less work.
  • Remove expensive per-request work from the script: large regular-expression extractors, JSON parsing of big bodies, per-request logging.
  • Lower the number of users per load generator and raise the ramp-up instead of starting everyone at once.
  • Re-run and confirm the banner is gone before trusting the response time vs. virtual users chart.

See also load generators hardware and infrastructure.