Stopping Machine Learning

edit

An orderly shutdown of machine learning ensures that:

  • Datafeeds are stopped
  • Buffers are flushed
  • Model history is pruned
  • Final results are calculated
  • Model snapshots are saved
  • Jobs are closed

This process ensures that jobs are in a consistent state in case you want to subsequently re-open them.

Stopping Datafeeds

edit

When you stop a datafeed, it ceases to retrieve data from Elasticsearch. You can stop a datafeed by using Kibana or the stop datafeeds API. For example, the following request stops the feed1 datafeed:

POST _xpack/ml/datafeeds/feed1/_stop

You must have manage_ml, or manage cluster privileges to stop datafeeds. For more information, see Security Privileges.

A datafeed can be started and stopped multiple times throughout its lifecycle.

For examples of stopping datafeeds in Kibana, see Managing Jobs.

Stopping All Datafeeds

edit

If you are upgrading your cluster, you can use the following request to stop all datafeeds:

POST _xpack/ml/datafeeds/_all/_stop

Closing Jobs

edit

When you close a job, it cannot receive data or perform analysis operations. If a job is associated with a datafeed, you must stop the datafeed before you can close the jobs. If the datafeed has an end date, the job closes automatically on that end date.

You can close a job by using the close job API. For example, the following request closes the job1 job:

POST _xpack/ml/anomaly_detectors/job1/_close

You must have manage_ml, or manage cluster privileges to stop datafeeds. For more information, see Security Privileges.

A job can be opened and closed multiple times throughout its lifecycle.

Closing All Jobs

edit

If you are upgrading your cluster, you can use the following request to close all open jobs on the cluster:

POST _xpack/ml/anomaly_detectors/_all/_close