Chesnay Schepler created FLINK-21161:
----------------------------------------
Summary: Investigate Datadog OOM on timeout
Key: FLINK-21161
URL:
https://issues.apache.org/jira/browse/FLINK-21161 Project: Flink
Issue Type: Improvement
Components: Runtime / Metrics
Affects Versions: 1.11.3
Reporter: Chesnay Schepler
Assignee: Chesnay Schepler
The datadog reporter sends reports to datagod via asynchronous calls made with okhttp.
okhttp buffers requests if they cannot be submitted; if any connection issues it might be possible for enough data to be buffered to cause an OOM.
By default the number of concurrent requests is set to 64. We should try to reproduce the problem, and check whether setting this to a lower value would solve it.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)