|
|
|
SPARK-39200
|
SPARK-20624
Stream is corrupted Exception while fetching the blocks from fallback storage system
|
Frank Yin
|
Rajendra Gujja
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-39024
|
SPARK-20624
Add support for YARN decommissioning when ESS is Enabled
|
Unassigned
|
Abhishek Dixit
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-39018
|
SPARK-20624
Add support for YARN decommissioning when ESS is Disabled
|
Unassigned
|
Abhishek Dixit
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-36614
|
SPARK-20624
Executor loss reason shows "worker lost" rather "Executor decommission"
|
wuyi
|
wuyi
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-36543
|
SPARK-20624
Decommission logs too frequent when waiting migration to finish
|
Apache Spark
|
wuyi
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-35754
|
SPARK-20624
Put blocks only on disk while migrating RDD cached data
|
Unassigned
|
abhishek kumar tiwari
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-35627
|
SPARK-20624
Decommission executors in batches to avoid overloading network by block migrations.
|
Unassigned
|
abhishek kumar tiwari
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-35533
|
SPARK-20624
Do not drop cached RDD blocks to accommodate blocks from decommissioned block manager if enough memory is not available
|
Unassigned
|
abhishek kumar tiwari
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-34088
|
SPARK-20624
Rename all decommission configurations to use the same namespace "spark.decommission.*"
|
Unassigned
|
wuyi
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-34054
|
SPARK-20624
BlockManagerDecommissioner cleanup
|
wuyi
|
wuyi
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32913
|
SPARK-20624
Improve ExecutorDecommissionInfo and ExecutorDecommissionState for different use cases
|
Unassigned
|
wuyi
|
|
In Progress |
Unresolved
|
|
|
|
|
|
|
|
SPARK-32850
|
SPARK-20624
Simply the RPC message flow of decommission
|
wuyi
|
wuyi
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32745
|
SPARK-20624
Add an option to reject block migrations when under disk pressure
|
Unassigned
|
Holden Karau
|
|
Open |
Unresolved
|
|
|
|
|
|
|
|
SPARK-32653
|
SPARK-20624
Decommissioned host/executor should be considered as inactive in TaskSchedulerImpl
|
wuyi
|
wuyi
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32651
|
SPARK-20624
decommission switch configuration should have the highest hierarchy
|
wuyi
|
wuyi
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32643
|
SPARK-20624
[Cleanup] Consolidate state kept in ExecutorDecommissionInfo with TaskSetManager.tidToExecutorKillTimeMapping
|
Devesh Agrawal
|
Devesh Agrawal
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32613
|
SPARK-20624
DecommissionWorkerSuite has started failing sporadically again
|
Devesh Agrawal
|
Devesh Agrawal
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32217
|
SPARK-20624
Track whether the worker is also being decommissioned along with an executor
|
Devesh Agrawal
|
Devesh Agrawal
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32215
|
SPARK-20624
Expose end point on Master so that it can be informed about decommissioned workers out of band
|
Devesh Agrawal
|
Devesh Agrawal
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32199
|
SPARK-20624
Clear shuffle state when decommissioned nodes/executors are finally lost
|
Devesh Agrawal
|
Devesh Agrawal
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-32198
|
SPARK-20624
Don't fail running jobs when decommissioned executors finally go away
|
Devesh Agrawal
|
Devesh Agrawal
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-31946
|
SPARK-20624
Failed to register SIGPWR handler on MacOS
|
wuyi
|
wuyi
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-31555
|
SPARK-20624
Improve cache block migration
|
Unassigned
|
Holden Karau
|
|
Open |
Unresolved
|
|
|
|
|
|
|
|
SPARK-31198
|
SPARK-20624
Use graceful decommissioning as part of dynamic scaling
|
Holden Karau
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-31197
|
SPARK-20624
Exit the executor once all tasks & migrations are finished
|
Holden Karau
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-30836
|
SPARK-20624
Improve the decommissioning K8s integration tests
|
Holden Karau
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-30835
|
SPARK-20624
Add support for YARN decommissioning & pre-emption
|
Abhishek Dixit
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-21040
|
SPARK-20624
On executor/worker decommission consider speculatively re-launching current tasks
|
Prakhar Jain
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-20732
|
SPARK-20624
Copy cache data when node is being shut down
|
Prakhar Jain
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-20629
|
SPARK-20624
Copy shuffle data when nodes are being shut down
|
Holden Karau
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|
|
|
|
SPARK-20628
|
SPARK-20624
Keep track of nodes which are going to be shut down & avoid scheduling new tasks
|
Holden Karau
|
Holden Karau
|
|
Resolved |
Fixed
|
|
|
|
|