Created 06-23-2017 02:04 AM
We are running kudu 1.3.0 with cdh 5.10(the kudu client version suppose to be 1.2).
When we doing tpc-ds query with impala on kudu(according to https://github.com/cloudera/impala-tpcds-kit), we found that the 'query 3 between predicate' is not push down to kudu, cause kudu scan many rows return to impala.
The following is what we found in impala query profile:
tpc-ds q3.sql snippets:
any reply will be appreciate.
Created 06-23-2017 02:20 AM
Created 06-25-2017 07:12 PM
Created 06-27-2017 02:06 PM
Hi @lewiss, that's correct, currently OR (disjunctive) predicates can't be pushed to Kudu. In theory Impala could rewrite this query to be a union between a bunch of disjoint sub-selects each using a BETWEEN predicate, but I think that optimization is currently missing (it's not something that can be done in general, since the result sets could overlap).