Description
Currently, queries from the TPC H set are barely within one second on a 3-node cluster with scaleFactor=0.01 (and q2 even hangs).
Let's investigate bottlenecks in sql engine and file corresponding ticked to address these bottlenecks.
For this iteration, let's formulate Definition of Done as "all queries make it within one second on dataset with scaleFactor =0.1"
Attachments
Issue Links
- is blocked by
-
IGNITE-21331 Sql. TPC-H q2 query hangs with sc=0.01
- Resolved
-
IGNITE-21668 Sql. Deadlock in sorted exchange
- Resolved
-
IGNITE-21722 Sql. NPE in correlated nested loop join
- Resolved
- is related to
-
IGNITE-21580 Sql. Unable to optimise query using only two phase aggregates
- Resolved
-
IGNITE-16493 Calcite engine. Decorrelation after subquery rewrite
- Open
-
IGNITE-21809 Sql. Improve intra-query parallelism
- Open
-
IGNITE-21720 Sql. Implement hash join
- Resolved
-
IGNITE-21721 Sql. Adjust cost estimation for index scan
- Resolved