Details
-
New Feature
-
Status: In Progress
-
Major
-
Resolution: Unresolved
-
None
-
None
-
None
-
None
Description
Currently, there is no Tajo query scheduler. So, all queries launched simultaneously compete cluster resource which is managed by TajoResourceManager.
In this issue, we will investigate, design, and implement a Tajo query scheduler. This is an umbrella issue for that. We will create subtasks for them.
Attachments
Issue Links
- relates to
-
TAJO-550 TajoMaster chooses mostly the same query master
- Resolved
-
TAJO-773 (Umbrella) Integrate with Apache Hadoop YARN as resource allocator
- Open
-
TAJO-855 Refactor TaskRunnerManager/TaskRunner/Task
- Resolved
-
TAJO-703 Sparrow-like scheduler
- Open
-
TAJO-323 Refactor inconsistent class and variable names
- Resolved
- requires
-
TAJO-1397 Resource allocation should be fine grained.
- Resolved
-
TAJO-1255 Remove LazyTaskScheduler and its related things
- Resolved
1.
|
WorkerResourceManager should be broke down into 3 parts | Resolved | Hyunsik Choi | |
2.
|
Move container allocation from SubQuery down to QueryUnitAttempt | Resolved | Hyunsik Choi | |
3.
|
Remove yarn-related code from tajo-core | Resolved | Hyunsik Choi | |
4.
|
Improve worker resource and Add simulator | Resolved | Jinho Kim | |
5.
|
Implement TaskManager | Resolved | Jinho Kim |