THIS IS A TEST INSTANCE. ALL YOUR CHANGES WILL BE LOST!!!!
...
| Page properties | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Document the state by adding a label to the FLIP page with one of "discussion", "accepted", "released", "rejected".
|
Please keep the discussion on the mailing list rather than commenting on the wiki (wiki discussions get unwieldy fast).
Motivation
Currently, the Flink cluster only requests Task Managers (TMs) when there is a resource requirement, and idle TMs are released after a certain period of time. However, in certain scenarios, we need to improve the efficiency of job execution by maintaining a certain number of available resources in the system. For example:
For session clusters running short lived-jobs like OLAP, we should treat session clusters as a long-running service. Having running workers all the time can greatly improve the service stability and reduce the job's cold-start latency;
For application mode, batch job might be scheduled stage by stage. If the next region requires more resources, it might take more time to pull up required resources. If users actually know how many resources are needed when running a single job, initialize all workers when cluster starts can speed up the resource allocation process;
Flink supports FLINK-12122 [Spread out tasks evenly across all available registered TaskManagers], but this requires enough registered TaskManagers. For session cluster, all TaskManagers starting at the beginning can thoroughly solve this problem; for application mode, min required TaskManagers is allocated with best effort which might also help improve the evenly distribution but not guaranteed solve this;
Public Interfaces
| Option name | Default Value |
|---|---|
| slotmanager.number-of-slots.min | 0 |
| slotmanager.min-total-resource.cpu | no default value, it can be derived from slotmanager.number-of-slots.min |
| slotmanager.min-total-resource.memory | no default value, it can be derived from slotmanager.number-of-slots.min |
Notice: Like the maximum resource options, the minimum resource options will also be invalidated in standalone clusters.
Proposed Changes
Minimum required resource check in DefaultResourceAllocationStrategy
The minimum resource limitation will be implemented in the DefaultResourceAllocationStrategy of FineGrainedSlotManager.
...
Notice: The minimum resource limitation will be fulfilled in the best effort manner. The unfulfilled request will be retried in the next resource check but will not block job scheduling.
Resource stability check in SlotManagerConfiguration
After minimum required resource options are introduced, users can configure both minimum and maximum required resources in SlotManager, which might lead to worker resource oscillation. Here is an example:
...
To avoid this oscillation, we need to check the worker number derived from minimum and maximum resource configuration is consistent before starting SlotManager.
Notice: The resource stability check will be disabled when the minimum resource option is 0 which is set as default.
Compatibility, Deprecation, and Migration Plan
- What impact (if any) will there be on existing users? No
Test Plan
UT & Manually verify that the min resource limitation is working as expected.
Rejected Alternatives
If there are alternative ways of accomplishing the same thing, what were they? The purpose of this section is to motivate why the design is the way it is and not some other way.