0

I have a 24-node cluster that receives 400k to 600k ops/s at a latency of approximately 15ms-20ms at the 99th percentile.

I haven't found the reason why after restarting the nodes, writes increase to 700k-800k ops/s and write latency decreases to approximately 5ms-15ms for a period of about 24 hours, after which it degrades again.

I would like to have this performance consistently.

I have looked at several metrics like hints, compaction tasks, and Garbage Collection (GC), comparing the day of the restart with the same day of the previous week. I haven't seen anything significant that would indicate a change.

What metrics should I focus on?

Improve this question

1 Answer 1

Reset to default
0

I would start by looking at the Threadpool Metrics to see whats happening inside Cassandra and understand that so you can then see what configuration can be looked at or what area needs more investigating (hopefully).

Improve this answer

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.