Alexey Kudinkin created HUDI-4250:
-------------------------------------
Summary: Optimize Data Skipping to enable in-memory Column Stats
Index
Key: HUDI-4250
URL: https://issues.apache.org/jira/browse/HUDI-4250
Project: Apache Hudi
Issue Type: Bug
Reporter: Alexey Kudinkin
Assignee: Alexey Kudinkin
Fix For: 0.12.0
Executing on Spark has non-trivial amount of overhead, and therefore has to
have a potential of considerable speed-up due to parallelization of the
execution.
In case of Data Skipping seq reading Column Stats Index it only could be
justified for *very large* table (100s of 1000s of files, 100s of columns).
As such, we have to provide an alternative way of fetching Column Stats Index
w/in the reading process to avoid the penalty of scheduling more heavy-weight
execution t/h a Spark engine.
This, along w/ HUDI-4202, will allow to considerably speed up Data Skipping
Currently having overhead of *at least* 1-2s even for tables with a handful of
files.
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
