godfreyhe commented on a change in pull request #9203: [FLINK-13375][table-api] Improve config names in ExecutionConfigOptions and OptimizerConfigOptions URL: https://github.com/apache/flink/pull/9203#discussion_r307095535
########## File path: flink-table/flink-table-api-java/src/main/java/org/apache/flink/table/api/config/OptimizerConfigOptions.java ########## @@ -0,0 +1,88 @@ +/* + * 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.flink.table.api.config; + +import org.apache.flink.configuration.ConfigOption; + +import static org.apache.flink.configuration.ConfigOptions.key; + +/** + * This class holds configuration constants used by Flink's table planner module. + */ +public class OptimizerConfigOptions { + + // ------------------------------------------------------------------------ + // Optimizer Options + // ------------------------------------------------------------------------ + public static final ConfigOption<String> TABLE_OPTIMIZER_AGG_PHASE_STRATEGY = + key("table.optimizer.agg-phase-strategy") + .defaultValue("AUTO") + .withDescription("Strategy for aggregate phase. Only AUTO, TWO_PHASE or ONE_PHASE can be set.\n" + + "AUTO: No special enforcer for aggregate stage. Whether to choose two stage aggregate or one" + + " stage aggregate depends on cost. \n" + + "TWO_PHASE: Enforce to use two stage aggregate which has localAggregate and globalAggregate. " + + "Note that if aggregate call does not support optimize into two phase, we will still use one stage aggregate.\n" + + "ONE_PHASE: Enforce to use one stage aggregate which only has CompleteGlobalAggregate."); + + public static final ConfigOption<Long> TABLE_OPTIMIZER_BROADCAST_JOIN_THRESHOLD = + key("table.optimizer.join.broadcast-threshold") + .defaultValue(1024 * 1024L) + .withDescription("Configures the maximum size in bytes for a table that will be broadcast to all worker " + + "nodes when performing a join. By setting this value to -1 to disable broadcasting."); + + public static final ConfigOption<Boolean> TABLE_OPTIMIZER_DISTINCT_AGG_SPLIT_ENABLED = + key("table.optimizer.distinct-agg.split.enabled") + .defaultValue(false) + .withDescription("Tells the optimizer whether to split distinct aggregation " + + "(e.g. COUNT(DISTINCT col), SUM(DISTINCT col)) into two level. " + + "The first aggregation is shuffled by an additional key which is calculated using " + + "the hashcode of distinct_key and number of buckets. This optimization is very useful " + + "when there is data skew in distinct aggregation and gives the ability to scale-up the job. " + + "Default is false."); + + public static final ConfigOption<Integer> TABLE_OPTIMIZER_DISTINCT_AGG_SPLIT_BUCKET_NUM = + key("table.optimizer.distinct-agg.split.bucket-num") + .defaultValue(1024) + .withDescription("Configure the number of buckets when splitting distinct aggregation. " + + "The number is used in the first level aggregation to calculate a bucket key " + + "'hash_code(distinct_key) % BUCKET_NUM' which is used as an additional group key after splitting."); + + public static final ConfigOption<Boolean> TABLE_OPTIMIZER_REUSE_SUB_PLAN_ENABLED = + key("table.optimizer.reuse-sub-plan-enabled") + .defaultValue(true) + .withDescription("When it is true, optimizer will try to find out duplicated " + + "sub-plan and reuse them."); + + public static final ConfigOption<Boolean> TABLE_OPTIMIZER_REUSE_SOURCE_ENABLED = + key("table.optimizer.reuse-source-enabled") + .defaultValue(true) + .withDescription("When it is true, optimizer will try to find out duplicated table source and " + + "reuse them. This works only when " + TABLE_OPTIMIZER_REUSE_SUB_PLAN_ENABLED.key() + " is true."); + + public static final ConfigOption<Boolean> TABLE_OPTIMIZER_SOURCE_PREDICATE_PUSHDOWN_ENABLED = + key("table.optimizer.source.predicate-pushdown-enabled") + .defaultValue(true) + .withDescription("If it is true, the optimizer will push down predicates to the FilterableTableSource. " + Review comment: When it is true, the optimizer will push down predicates into the FilterableTableSource. ... ? ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
