In this chapter, we'll learn how to control the parallel execution of cluster tasks. Only a centralized cluster manager with global knowledge (i.e. Helix) is capable of coordinating this decision.

Throttling

Since all state changes in the system are triggered through transitions, Helix can control the number of transitions that can happen in parallel. Some of the transitions may be lightweight, but some might involve moving data, which is quite expensive from a network and IOPS perspective.

Helix allows applications to set a threshold on transitions. The threshold can be set at multiple scopes:

  • MessageType e.g STATE_TRANSITION
  • TransitionType e.g SLAVE-MASTER
  • Resource e.g database
  • Node i.e per-node maximum transitions in parallel

Back to top

Reflow Maven skin by Andrius Velykis.

Apache Helix, Apache, the Apache feather logo, and the Apache Helix project logos are trademarks of The Apache Software Foundation. All other marks mentioned may be trademarks or registered trademarks of their respective owners.
Privacy Policy