Re:Cortex: a multi-tenant, horizontally scalable Prometheus-...
by bboreham on Thursday December 20, 2018 @03:39AM
(#18723352)
Cortex also uses gorilla-inspired compression, using the Prometheus source code.
After compressing timeseries they are stored and indexed using a database-like thing, typically DynamoDB or Bigtable, but soon BoltDB will be an option.
(I am a Cortex maintainer)
It is my understanding that Prometheus's storage engine is LSM based, and uses a compression scheme inspired by gorilla.
Boltdb is basically a btree which causes more write amplification.
Maybe you should try badgerdb.