[
https://issues.apache.org/jira/browse/FLINK-8639?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16370218#comment-16370218
]
ASF GitHub Bot commented on FLINK-8639:
---------------------------------------
Github user sihuazhou commented on a diff in the pull request:
https://github.com/apache/flink/pull/5465#discussion_r169374194
--- Diff:
flink-contrib/flink-statebackend-rocksdb/src/main/java/org/apache/flink/contrib/streaming/state/RocksDBMapState.java
---
@@ -400,7 +410,7 @@ public UV setValue(UV value) {
/** An auxiliary utility to scan all entries under the given key. */
private abstract class RocksDBMapIterator<T> implements Iterator<T> {
- static final int CACHE_SIZE_BASE = 1;
+ static final int CACHE_SIZE_BASE = 32;
--- End diff --
Indeed, I don't think the memory is really a concern (at least when
CACHE_SIZE_LIMIT=128), I almost like to change the CACHE_SIZE to a fixed value
(like 128), What do you think?
> Fix always need to seek multiple times when iterator RocksDBMapState
> --------------------------------------------------------------------
>
> Key: FLINK-8639
> URL: https://issues.apache.org/jira/browse/FLINK-8639
> Project: Flink
> Issue Type: Improvement
> Components: State Backends, Checkpointing
> Affects Versions: 1.4.0
> Reporter: Sihua Zhou
> Assignee: Sihua Zhou
> Priority: Critical
> Fix For: 1.5.0
>
>
> Currently, almost every time we want to iterator a RocksDBMapState we need to
> do seek at least 2 times (Seek is a poor performance action for rocksdb cause
> it can't use the bloomfilter). This is because `RocksDBMapIterator` use a
> `cacheEntries` to cache the seek values every time and the `cacheEntries`'s
> init size is 1.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
