-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Try to replicate InfluxDB sync issue #444
Comments
The device has point-server version A couple of crucial points on this are:
1. InfluxDB server logs:
2. Different frequency stored points are getting gaps at the same time:Screen.Recording.2023-03-10.at.4.23.20.PM.mov |
One more example to test: Screen.Recording.2023-07-24.at.2.19.05.PM.movdata.txt [change it into |
From ChatGPT:In influxdb 1.x, what happens if it gets restarted just after we insert the record successfully? It's not persisting the value.In InfluxDB 1.x, if you insert a record successfully and the server restarts immediately afterward, the inserted data may not be persisted to disk, and therefore it may appear to be lost. This is because InfluxDB follows a write-ahead log (WAL) mechanism for data ingestion. Here's how the process generally works:
To minimize data loss in such scenarios, you can configure the following settings in the influxdb.conf configuration file:
Please note that even with these settings, there is always some level of risk of data loss during a restart or crash scenario. Therefore, it is crucial to have appropriate backup and high availability strategies in place to safeguard against data loss in critical environments. In InfluxDB 2.x, there are improvements and changes in the data storage mechanism, and it is recommended to consider using the latest version if possible. |
https://dash.nube-iiot.com/precise-air/d/PmXrWQDaa/sap-heartbeats?orgId=1&from=1675953722225&to=1676160086990
Screen.Recording.2023-03-08.at.1.42.41.PM.mov
The InfluxDB sync in a certain period of time is blank. But the device and point-server are up from last more than 3 months with generating the history of 15 minutes of intervals.
This could possibly happen when:
But there is also no sign of the device went offline for that time period. Also, it's up from last more than 3 months.
So, try to replicate this case when InfluxDB goes down while writing the values. Or try to find other possible cases.
The text was updated successfully, but these errors were encountered: