Github user hbdeshmukh commented on a diff in the pull request:
https://github.com/apache/incubator-quickstep/pull/181#discussion_r104573872
--- Diff: query_optimizer/ExecutionGenerator.cpp ---
@@ -679,13 +688,72 @@ void ExecutionGenerator::convertFilterJoin(const
P::FilterJoinPtr &physical_plan
std::piecewise_construct,
std::forward_as_tuple(physical_plan),
std::forward_as_tuple(probe_relation_info->producer_operator_index,
- probe_relation_info->relation));
+ probe_relation_info->relation,
+
probe_relation_info->output_destination_index));
DCHECK(lip_filter_generator_ != nullptr);
lip_filter_generator_->addFilterJoinInfo(physical_plan,
build_filter_operator_index);
}
+namespace {
+
+bool areSamePartitionSchemeHeaders(const PartitionSchemeHeader
&lhs_partition_header,
+ const CatalogRelationSchema &lhs_scheme,
+ const PartitionSchemeHeader
&rhs_partition_header,
+ const CatalogRelationSchema
&rhs_scheme) {
+ if (lhs_partition_header.getPartitionType() !=
rhs_partition_header.getPartitionType()) {
+ return false;
+ }
+
+ if (lhs_partition_header.getNumPartitions() !=
rhs_partition_header.getNumPartitions()) {
+ return false;
+ }
+
+ // Check whether the underlying types in CatalogAttribute are the same.
+ if
(!lhs_scheme.getAttributeById(lhs_partition_header.getPartitionAttributeId())->getType().equals(
+
rhs_scheme.getAttributeById(rhs_partition_header.getPartitionAttributeId())->getType()))
{
+ return false;
+ }
+
+ switch (lhs_partition_header.getPartitionType()) {
+ case PartitionSchemeHeader::PartitionType::kHash:
+ return true;
+ case PartitionSchemeHeader::PartitionType::kRange: {
+ const vector<TypedValue> &lhs_ranges =
+ static_cast<const
RangePartitionSchemeHeader&>(lhs_partition_header).getPartitionRangeBoundaries();
+ const vector<TypedValue> &rhs_ranges =
+ static_cast<const
RangePartitionSchemeHeader&>(rhs_partition_header).getPartitionRangeBoundaries();
+
+ return lhs_ranges == rhs_ranges;
+ }
+ }
+
+ return false;
+}
+
+
+// Note that this method will be deprecated once the partition scheme
header
+// supports multiple partition attributes.
+size_t chooseBestRepartitionAttributeIndex(const CatalogRelationStatistics
&stats,
+ const vector<attribute_id>
&join_attributes) {
+ size_t chose_attr_index = static_cast<size_t>(-1);
+ size_t chose_attr_num_distinct_values = 0;
+
+ for (std::size_t i = 0; i < join_attributes.size(); ++i) {
+ const attribute_id attr = join_attributes[i];
+ if (stats.hasNumDistinctValues(attr) &&
+ stats.getNumDistinctValues(attr) > chose_attr_num_distinct_values)
{
+ chose_attr_index = i;
+ chose_attr_num_distinct_values = stats.getNumDistinctValues(attr);
+ }
+ }
+
+ return (chose_attr_index != static_cast<size_t>(-1)) ? chose_attr_index
: 0;
--- End diff --
I am unable to understand the point of this function. Why do we need to
find the "best repartition attribute"? Assuming a join like ``R.a = S.b``, if
``R`` is partitioned on some other attribute ``c``, we would like to
repartition it based on ``a``, so the only choice for an attribute on which we
should perform the repartitioning is ``a``, isn't it? What's the decision got
do do with the CatalogRelation stats and the number of distinct values of the
attribute?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
