Data is smaller and disks are bigger than you'd think.
Reliable Insights
A blog on monitoring, scale and operational Sanity
The quoted storage numbers for Prometheus are usually for the blocks, not including the WAL.
One of the big changes in Prometheus 2.15.0 was reduced memory usage for indexes.
Prometheus 2.10 has a new metric to make finding churn easier.
I previously looked at ingestion memory for 1.x, how about 2.x?
How can you control how much history Prometheus keeps?
The Prometheus TSDB's code base includes a tool to help you find "interesting" metrics in terms of storage performance.
The 2.6.0 release of Prometheus includes WAL loading optimisations to make startup faster.
