Details
-
New Feature
-
Status: Open
-
Major
-
Resolution: Unresolved
-
1.5.3
-
None
-
None
-
None
Description
Implement a Distributed index cache server which can prune and cache block/blocklet datamaps to reduce the memory footprint on the carbon driver application.
Design Document:
https://docs.google.com/document/d/161NXxrKLPucIExkWip5mX00x2iOPH6bvsuQnCzzp47E/edit?ts=5c542ab4#
Attachments
Attachments
1.
|
Implement a DistributableIndexPruneRDD and IndexPruneFileFormat | Resolved | Unassigned |
|
||||||||||
2.
|
Implement a Hadoop RPC framwork for communication | Resolved | Kunal Kapoor |
|
||||||||||
3.
|
Display original query in Indexserver Job | Resolved | Unassigned |
|
||||||||||
4.
|
Large response size Exception is thrown from index server. | Resolved | Kunal Kapoor |
|
||||||||||
5.
|
Make use of LRU mandatory when using IndexServer | Resolved | Kunal Kapoor |
|
||||||||||
6.
|
Implement Show Cache for IndexServer and MV | Closed | Kunal Kapoor |
|
||||||||||
7.
|
Implement Executor ID based task distribution for Index Server | Resolved | Kunal Kapoor |
|
||||||||||
8.
|
Expose a DDL to add index size and data size to tableStatus for legacy segments | Resolved | Kunal Kapoor |
|
||||||||||
9.
|
Optimize the performance of select count(*) for index server | Resolved | Kunal Kapoor |
|
||||||||||
10.
|
Fixed id based distribution for show cache command | Resolved | Kunal Kapoor |
|
||||||||||
11.
|
Add usage and deployment document for index server | Resolved | Kunal Kapoor |
|