Siddharth Wagle created HDDS-1572:
-------------------------------------
Summary: Implement a Pipeline scrubber to maintain healthy number
of pipelines in a cluster
Key: HDDS-1572
URL: https://issues.apache.org/jira/browse/HDDS-1572
Project: Hadoop Distributed Data Store
Issue Type: Sub-task
Components: SCM
Reporter: Siddharth Wagle
Assignee: Siddharth Wagle
The design document talks about initial requirements for the pipeline scrubber.
- Maintain a datastructure for datanodes violating the pipeline membership soft
upper bound.
- Scan the pipelines that the nodes are a part of to select candidates for
teardown.
- Scan pipelines that do not have open containers currently in use and
datanodes are in violation.
- Schedule tear down operation if a candidate pipeline is found.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
