[voctor]

Citus can parallelize SQL queries across a cluster and across multiple CPU cores. How does it compare with the upcoming 9.6 version of PostgreSQL which will support parallel-able sequential scans, parallel joins and parallel aggregate ?

[lfittl]

AFAIK all the parallel work done in 9.6 refers to parallel operations on a single node (but multiple cores).

This would be complimentary to what Citus does, which is distributing the load across multiple shard instances (each with their own cores, benefiting from the parallel work in 9.6).

[voctor]

Yes, but Citus can also parallelize on multiple cores when used on a single machine ("If you’re running Citus on a single machine, this will scale queries across multiple CPU cores. and create the impression of sharding across databases."). Will this functionality becomes obsolete with the 9.6 ?

[lfittl]

Fair point - I assume this will be merged together in some way (i.e. the Citus stuff building on top of the parallel scan infrastructure), but probably a better question to ask on #citus IRC / open a Github issue.

Some Postgres committers work on Citus as well (e.g. Andres Freud), so I'm sure this has been thought through before.