Home

Identifying rogue apps

Rogue apps can affect cluster health and lead to missed SLAs. Therefore, it is best practice to identify and eliminate them. Symptoms of a cluster with rogue apps include jobs that take too long to run or apps that use too many vCores. Unravel Web UI makes identifying rogue apps easy:

  1. Click Clusters > Overview.

  2. In the Cluster vCores or Cluster Memory MB graph, click on a spike.

    Unravel's Web UI displays the list of apps running or pending in the cluster at the spike's timestamp at the bottom of the page.

    usecase-IdRogue-Vcores.png
  3. Click on the app which has allocated the highest number of vCores. In this example, there is a MapReduce app which has allocated 240 vCores of the cluster.

    usecase-IdRogue-Vcores-find.png
  4. Check the event panel in the app's APM to see Unravel's recommendations for improving the efficiency of this MapReduce app. For example:

    usecase-IdRogue-insights.png
  5. Set up an AutoAction to proactively alert if a rogue app is occupying the cluster.

    usecase-IdRogue-autoactions.png
    usecase-IdRogue-autoactions-define.png