Details
-
Improvement
-
Status: Open
-
Minor
-
Resolution: Unresolved
-
None
-
None
-
None
Description
Collecting per-container and per-node resource consumption statistics in a fairly granular manner, and making them available to both infrastructure code (e.g., schedulers) and users (e.g., AMs or directly users via webapps), can facilitate several performance work.
Attachments
Issue Links
- is related to
-
YARN-2928 YARN Timeline Service v.2: alpha 1
- Resolved
-
YARN-3332 [Umbrella] Unified Resource Statistics Collection per node
- Open
-
YARN-1012 Report NM aggregated container resource utilization in heartbeat
- Resolved
- relates to
-
YARN-3033 [Collector wireup] Implement NM starting the standalone timeline collector daemon
- Resolved