Mailing-List: contact dev-help@quickstep.incubator.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@quickstep.incubator.apache.org
From: hbdeshmukh <git@git.apache.org>
To: dev@quickstep.incubator.apache.org
Reply-To: dev@quickstep.incubator.apache.org
References: <git-pr-181-incubator-quickstep@git.apache.org>
In-Reply-To: <git-pr-181-incubator-quickstep@git.apache.org>
Subject: [GitHub] incubator-quickstep pull request #181: Added limited optimizer support for P...
Content-Type: text/plain
Message-Id: <20170307171648.807C8DFD9E@git1-us-west.apache.org>
Date: Tue,  7 Mar 2017 17:16:48 +0000 (UTC)
archived-at: Tue, 07 Mar 2017 17:16:55 -0000

Github user hbdeshmukh commented on a diff in the pull request:

    https://github.com/apache/incubator-quickstep/pull/181#discussion_r104724405
  
    --- Diff: query_optimizer/ExecutionGenerator.cpp ---
    @@ -740,6 +805,202 @@ void ExecutionGenerator::convertHashJoin(const P::HashJoinPtr &physical_plan) {
         key_types.push_back(&left_attribute_type);
       }
     
    +  const CatalogRelationInfo *build_relation_info =
    +      findRelationInfoOutputByPhysical(build_physical);
    +  const CatalogRelationInfo *probe_operator_info =
    +      findRelationInfoOutputByPhysical(probe_physical);
    +
    +  const CatalogRelation *build_relation = build_relation_info->relation;
    +  const CatalogRelation *probe_relation = probe_operator_info->relation;
    +
    +  // FIXME(quickstep-team): Add support for self-join.
    +  if (build_relation == probe_relation) {
    +    THROW_SQL_ERROR() << "Self-join is not supported";
    +  }
    +
    +  const PartitionScheme *build_partition_scheme = build_relation->getPartitionScheme();
    +  const PartitionScheme *probe_partition_scheme = probe_relation->getPartitionScheme();
    +
    +  bool build_needs_repartition = false;
    +  bool probe_needs_repartition = false;
    +  bool needs_swap = false;
    +  if (build_partition_scheme && probe_partition_scheme) {
    +    const PartitionSchemeHeader &build_partition_scheme_header = build_partition_scheme->getPartitionSchemeHeader();
    +    const PartitionSchemeHeader &probe_partition_scheme_header = probe_partition_scheme->getPartitionSchemeHeader();
    +
    +    switch (build_partition_scheme_header.getPartitionType()) {
    +      case PartitionSchemeHeader::PartitionType::kRange:
    +        build_needs_repartition = true;
    +
    +        switch (probe_partition_scheme_header.getPartitionType()) {
    +          case PartitionSchemeHeader::PartitionType::kRange:
    +            probe_needs_repartition = true;
    +            break;
    +          case PartitionSchemeHeader::PartitionType::kHash: {
    +            const attribute_id probe_partition_attr = probe_partition_scheme_header.getPartitionAttributeId();
    +            if (find(probe_attribute_ids.begin(), probe_attribute_ids.end(), probe_partition_attr) !=
    +                    probe_attribute_ids.end()) {
    +              needs_swap = true;
    +            } else {
    +              probe_needs_repartition = true;
    +            }
    +            break;
    +          }
    +        }
    +        break;
    +      case PartitionSchemeHeader::PartitionType::kHash: {
    +        const attribute_id build_partition_attr = build_partition_scheme_header.getPartitionAttributeId();
    +        if (find(build_attribute_ids.begin(), build_attribute_ids.end(), build_partition_attr) !=
    +                build_attribute_ids.end()) {
    +          // BuildRelation has a useful partition.
    +          switch (probe_partition_scheme_header.getPartitionType()) {
    +            case PartitionSchemeHeader::PartitionType::kRange:
    +              probe_needs_repartition = true;
    +              break;
    +            case PartitionSchemeHeader::PartitionType::kHash: {
    +              if (areSamePartitionSchemeHeaders(build_partition_scheme_header, *build_relation,
    +                                                probe_partition_scheme_header, *probe_relation)) {
    +                if (cost_model_for_hash_join_->estimateCardinality(build_physical) >
    +                        cost_model_for_hash_join_->estimateCardinality(probe_physical)) {
    +                  needs_swap = true;
    +                }
    +              } else {
    +                probe_needs_repartition = true;
    +              }
    +              break;
    +            }
    +          }
    +        } else {
    +          build_needs_repartition = true;
    +
    +          switch (probe_partition_scheme_header.getPartitionType()) {
    +            case PartitionSchemeHeader::PartitionType::kRange:
    +              probe_needs_repartition = true;
    +              break;
    +            case PartitionSchemeHeader::PartitionType::kHash: {
    +              const attribute_id probe_partition_attr = probe_partition_scheme_header.getPartitionAttributeId();
    +              if (find(probe_attribute_ids.begin(), probe_attribute_ids.end(), probe_partition_attr) !=
    +                      probe_attribute_ids.end()) {
    +                needs_swap = true;
    +              } else {
    +                probe_needs_repartition = true;
    +              }
    +              break;
    +            }
    +          }
    +        }
    +        break;
    +      }
    +    }
    +  } else if (probe_partition_scheme) {
    +    needs_swap = true;
    +
    +    const PartitionSchemeHeader &probe_partition_scheme_header = probe_partition_scheme->getPartitionSchemeHeader();
    +    switch (probe_partition_scheme_header.getPartitionType()) {
    +      case PartitionSchemeHeader::PartitionType::kRange:
    +        probe_needs_repartition = true;
    +        break;
    +      case PartitionSchemeHeader::PartitionType::kHash: {
    +        const attribute_id probe_partition_attr = probe_partition_scheme_header.getPartitionAttributeId();
    +
    +        probe_needs_repartition =
    +            (find(probe_attribute_ids.begin(), probe_attribute_ids.end(), probe_partition_attr) ==
    +                probe_attribute_ids.end());
    +        break;
    +      }
    +    }
    +  } else if (build_partition_scheme) {
    +    const PartitionSchemeHeader &build_partition_scheme_header = build_partition_scheme->getPartitionSchemeHeader();
    +    switch (build_partition_scheme_header.getPartitionType()) {
    +      case PartitionSchemeHeader::PartitionType::kRange:
    +        build_needs_repartition = true;
    +        break;
    +      case PartitionSchemeHeader::PartitionType::kHash: {
    +        const attribute_id build_partition_attr = build_partition_scheme_header.getPartitionAttributeId();
    +        build_needs_repartition =
    +            (find(build_attribute_ids.begin(), build_attribute_ids.end(), build_partition_attr) ==
    +                build_attribute_ids.end());
    +        break;
    +      }
    +    }
    +  }
    +
    +  if (needs_swap) {
    +    swap(probe_physical, build_physical);
    +    swap(probe_attribute_ids, build_attribute_ids);
    +    swap(any_probe_attributes_nullable, any_build_attributes_nullable);
    +    swap(left_join_attributes, right_join_attributes);
    +    swap(probe_operator_info, build_relation_info);
    +    swap(probe_relation, build_relation);
    +    swap(probe_partition_scheme, build_partition_scheme);
    +    swap(probe_needs_repartition, build_needs_repartition);
    +  }
    +
    +  unique_ptr<PartitionScheme> probe_repartition_scheme;
    +  if (build_needs_repartition) {
    +    const size_t repartition_attr_index =
    +        chooseBestRepartitionAttributeIndex(build_relation->getStatistics(), build_attribute_ids);
    +    auto build_repartition_scheme_header =
    +        make_unique<HashPartitionSchemeHeader>(FLAGS_num_repartitions,
    +                                               build_attribute_ids[repartition_attr_index]);
    +    auto build_repartition_scheme = make_unique<PartitionScheme>(build_repartition_scheme_header.release());
    +
    +    build_partition_scheme = build_repartition_scheme.get();
    +
    +    if (build_relation_info->isStoredRelation()) {
    +      THROW_SQL_ERROR() << "Re-partition for the base build table is not supported";
    +    } else {
    +      S::InsertDestination *build_insert_destination_proto =
    +          query_context_proto_->mutable_insert_destinations(build_relation_info->output_destination_index);
    +
    +      build_insert_destination_proto->set_insert_destination_type(S::InsertDestinationType::PARTITION_AWARE);
    +      build_insert_destination_proto->MutableExtension(S::PartitionAwareInsertDestination::partition_scheme)
    +        ->MergeFrom(build_repartition_scheme->getProto());
    +
    +      CatalogRelation *mutable_build_relation =
    +          catalog_database_->getRelationByIdMutable(build_relation->getID());
    +      mutable_build_relation->setPartitionScheme(build_repartition_scheme.release());
    --- End diff --
    
    May be I missed some of your older PRs, but can you explain how we will physically repartition the relations?


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---