Bringing together the Apache Cassandra experts from the community and DataStax.

Want to learn? Have a question? Want to share your expertise? You are in the right place!

Not sure where to begin? Getting Started

 

question

dmngaya avatar image
dmngaya asked ·

How do I calculate the throughput of my cluster?

Hi all,

I have cluster with 30 nodes, how to know throughput of my cluster ?

thanks for your advices ?

performance
10 |1000 characters needed characters left characters exceeded

Up to 8 attachments (including images) can be used with a maximum of 1.0 MiB each and 10.0 MiB total.

1 Answer

Erick Ramirez avatar image
Erick Ramirez answered ·

The throughput of your cluster can't be "calculated" unless you have some reference point. This is because there are lots of moving parts involved and no two clusters are the same.

The factors which contribute to the cluster's capacity include (but not limited to):

  • CPU type/version, number of cores
  • amount of RAM, RAM type
  • disk capacity and IO throughput
  • network capacity, bandwidth, throughput
  • number of nodes
  • data model
  • use case
  • access patterns

If you have not yet deployed your cluster to production, you can benchmark your data model and hardware using tools such as NoSQLBench. It will give you an idea of how many operations-per-second your cluster can sustain and you can extrapolate from that point.

If you have already deployed your cluster, you can collect metrics about the cluster throughput and infer from that. You can use tools such as the open-source DataStax Metrics Collector for Apache Cassandra (MCAC) to collect metrics data and export them to Prometheus/Grafana. Cheers!

Share
10 |1000 characters needed characters left characters exceeded

Up to 8 attachments (including images) can be used with a maximum of 1.0 MiB each and 10.0 MiB total.