mike-tr-adamson commented on code in PR #2673: URL: https://github.com/apache/cassandra/pull/2673#discussion_r1371825799
########## src/java/org/apache/cassandra/index/sai/plan/VectorTopKProcessor.java: ########## @@ -0,0 +1,198 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.cassandra.index.sai.plan; + +import java.nio.ByteBuffer; +import java.util.Comparator; +import java.util.Optional; +import java.util.PriorityQueue; +import java.util.TreeMap; +import java.util.TreeSet; +import javax.annotation.Nullable; + +import com.google.common.base.Preconditions; +import org.apache.commons.lang3.tuple.Triple; + +import org.apache.cassandra.cql3.Operator; +import org.apache.cassandra.db.ColumnFamilyStore; +import org.apache.cassandra.db.DecoratedKey; +import org.apache.cassandra.db.Keyspace; +import org.apache.cassandra.db.ReadCommand; +import org.apache.cassandra.db.filter.RowFilter; +import org.apache.cassandra.db.partitions.BasePartitionIterator; +import org.apache.cassandra.db.partitions.PartitionIterator; +import org.apache.cassandra.db.partitions.UnfilteredPartitionIterator; +import org.apache.cassandra.db.rows.BaseRowIterator; +import org.apache.cassandra.db.rows.Row; +import org.apache.cassandra.db.rows.Unfiltered; +import org.apache.cassandra.index.Index; +import org.apache.cassandra.index.SecondaryIndexManager; +import org.apache.cassandra.index.sai.IndexContext; +import org.apache.cassandra.index.sai.StorageAttachedIndex; +import org.apache.cassandra.index.sai.utils.InMemoryPartitionIterator; +import org.apache.cassandra.index.sai.utils.InMemoryUnfilteredPartitionIterator; +import org.apache.cassandra.index.sai.utils.PartitionInfo; +import org.apache.cassandra.index.sai.utils.TypeUtil; +import org.apache.cassandra.schema.ColumnMetadata; +import org.apache.cassandra.utils.FBUtilities; +import org.apache.cassandra.utils.Pair; + +/** + * Processor that scans all rows from given partitions and selects rows with top-k scores based on vector indexes. + * <p> + * This processor performs the following steps: + * - collect rows with score into PriorityQueue that sorts rows based on score. If there are multiple vector indexes, + * the final score is the sum of all vector index scores. + * - remove rows with the lowest scores from PQ if PQ size exceeds limit + * - return rows from PQ in primary key order to client + * <p> + * Note that recall will be lower with paging, because: + * - page size is used as limit + * - for the first query, coordinator returns global top page-size rows within entire ring + * - for the subsequent queries, coordinators returns global top page-size rows withom range from last-returned-row to max token Review Comment: Yes, I have removed that whole section on paging. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
