You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Sihua Zhou (JIRA)" <ji...@apache.org> on 2018/03/26 06:32:00 UTC
[jira] [Commented] (FLINK-9070) Improve performance of
RocksDBMapState.clear()
[ https://issues.apache.org/jira/browse/FLINK-9070?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16413431#comment-16413431 ]
Sihua Zhou commented on FLINK-9070:
-----------------------------------
Hi [~kien_truong], this is interesting. I agree with you that the {{RocksDBMapState.clear()}} can be improved, but I don't know how to improve it via {{DeleteRange}} or {{DeleteFilesInRange}} (I only know how to improve this via reduce seek times), do you have a detail suggestion? By the way, AFAIK the bug of {{DeleteRange}} has been fixed since 5.7.3, am I mistake? I ask this because there is another improvement issue will use it. [FLINK-8790|https://issues.apache.org/jira/browse/FLINK-8790].
> Improve performance of RocksDBMapState.clear()
> ----------------------------------------------
>
> Key: FLINK-9070
> URL: https://issues.apache.org/jira/browse/FLINK-9070
> Project: Flink
> Issue Type: Improvement
> Components: State Backends, Checkpointing
> Affects Versions: 1.6.0
> Reporter: Truong Duc Kien
> Priority: Minor
>
> Currently, RocksDBMapState.clear() is implemented by iterating over all the keys and drop them one by one. This iteration can be quite slow with:
> * Large maps
> * High-churn maps with a lot of tombstones
> There are a few methods to speed-up deletion for a range of keys, each with their own caveats:
> * DeleteRange: still experimental, likely buggy
> * DeleteFilesInRange + CompactRange: only good for large ranges
>
> Flink can also keep a list of inserted keys in-memory, then directly delete them without having to iterate over the Rocksdb database again.
>
> Reference:
> * [RocksDB article about range deletion|https://github.com/facebook/rocksdb/wiki/Delete-A-Range-Of-Keys]
> * [Bug in DeleteRange|https://pingcap.com/blog/2017-09-08-rocksdbbug]
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)