Cloudera Docs

Launching profilers in Compute Cluster enabled environments

In Compute Cluster enabled environments, after you set up the profiler, the Profiler Launcher Services automatically starts the profiler Kubernetes containers.

How to launch the profiler for Compute Cluster enabled environments

  1. On the Profilers page, select the data lake from which you want to launch the profiler cluster.
  2. Click Setup Profiler, to start the profiler cluster setup.
  3. In Setup Cluster, search for the required instance types:
    The available instance types depend on the cloud provider of the underlying environment. Choose from them based on your performance and cost requirements.
  4. Select your required instances and set the Autoscaling instance count to define maximum number of workers. The underlying Apache Spark service will manage the actual number of used instances based on workload.
  5. Click Next.
  6. Select the necessary profilers to be launched.
  7. Once the cluster is ready, you can start the individual profilers by clicking Launch.

Verifying the profiler cluster for Compute Cluster enabled environments

As a final step, you can verify that the node group is ready for the profiler jobs under the Cloudera Management Console > Environments > Compute Clusters > Node Groups pane.