Geoffrey Beausire

Multiprocess mode will store metrics files for each PID in a directory then when you will access them it will read everything. Can you be more precise about your current...

You can check https://github.com/criteo/cassandra_exporter#why-not-make-more-use-of-labels-be-more-prometheus-way- The main reason is that Cassandra export its own metric format (that is path based) through JMX and the exporter is trying to do the minimum...

What do you mean by bringing down your Prometheus ? One alternative is to use relabeling in the scrape config to replace `__name__` by `name` (and replace special chars to...

Are you sure your memory issue is not just because the exporter expose a lot of metrics? It's possible to blacklist some high cardinality metrics to save some memory in...

Hello, sorry for the delay. I tried locally the difference between 50 metrics with 1000 series each vs 5000 metrics with 10 series each and didn't notice any particular difference...

If you look on the Cassandra side: - do you have errors? - do you see a drop in write ops when you notice the drops? Inside your container, does...

I actually reproduce on my version with 4 nodes in the same DC.

We had a crash of the whole cluster at the end of a replace operation: Here is the log of a node that crashed (new node is `10.228.191.13`): ``` July...

> First, I want to know if the cluster goes back to normal now? Yes, it went back and the issue didn't reproduce. I set the ring_delay to 300s since....

Hello @asias, with @pgoron we backported your patches (10x + speed up gossip) and we still have long settle time. After investigating deeper it seems to be due to `calculate_effective_replication_map`...