Xinyu Tan created IOTDB-5828:
--------------------------------
Summary: Optimize the implementation of some metric items in the
metric module to prevent Prometheus pull timeouts
Key: IOTDB-5828
URL: https://issues.apache.org/jira/browse/IOTDB-5828
Project: Apache IoTDB
Issue Type: Improvement
Reporter: Xinyu Tan
Assignee: Liuxuxin
Attachments: image-2023-04-27-17-01-37-144.png,
image-2023-04-27-17-03-29-978.png
!image-2023-04-27-17-03-29-978.png!
!image-2023-04-27-17-01-37-144.png!
Under high write pressure, even without Full GC, the elapsed time of individual
monitor items in the monitoring framework will cause the Prometheus pull
sampling timeout, resulting in missing monitor data, which ultimately affects
performance problem troubleshooting.
The three main time points found by jprofile sampling are the number of file
handles, the number of client concurrency, and the number of threads. The
implementation needs to be optimized
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
