[
https://issues.apache.org/jira/browse/FLINK-27155?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17520129#comment-17520129
]
Feifan Wang commented on FLINK-27155:
-------------------------------------
Thanks for reply [~ym] , I've also noticed that local recovery is in the v2
plan before, and I think local recovery and this proposal are on different
levels to reduce DFS pressure.
Local recovery can prevent healthy taskmanagers from downloading state change
files from DFS when fail recovery, while this proposal is aim to avoid the same
new startup taskmanager downloading the same state change file multiple times
regardless of whether to start a job from a retained checkpoint or fail
recovery.
> Reduce multiple reads to the same Changelog file in the same taskmanager
> during restore
> ---------------------------------------------------------------------------------------
>
> Key: FLINK-27155
> URL: https://issues.apache.org/jira/browse/FLINK-27155
> Project: Flink
> Issue Type: Improvement
> Components: Runtime / Checkpointing, Runtime / State Backends
> Reporter: Feifan Wang
> Priority: Major
>
> h3. Background
> In the current implementation, State changes of different operators in the
> same taskmanager may be written to the same changelog file, which effectively
> reduces the number of files and requests to DFS.
> But on the other hand, the current implementation also reads the same
> changelog file multiple times on recovery. More specifically, the number of
> times the same changelog file is accessed is related to the number of
> ChangeSets contained in it. And since each read needs to skip the preceding
> bytes, this network traffic is also wasted.
> The result is a lot of unnecessary request to DFS when there are multiple
> slots and keyed state in the same taskmanager.
> h3. Proposal
> We can reduce multiple reads to the same changelog file in the same
> taskmanager during restore.
> One possible approach is to read the changelog file all at once and cache it
> in memory or local file for a period of time when reading the changelog file.
> I think this could be a subtask of [v2 FLIP-158: Generalized incremental
> checkpoints|https://issues.apache.org/jira/browse/FLINK-25842] .
> Hi [~ym] , [~roman] how do you think about ?
--
This message was sent by Atlassian Jira
(v8.20.1#820001)
