dongjoon-hyun commented on a change in pull request #31476: URL: https://github.com/apache/spark/pull/31476#discussion_r570572005
########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/CustomMetric.java ########## @@ -0,0 +1,38 @@ +/* + * 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.spark.sql.connector; + +import org.apache.spark.annotation.Evolving; + +/** + * A general custom metric. Review comment: Shall we remove `general`? ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/Scan.java ########## @@ -102,4 +102,13 @@ default MicroBatchStream toMicroBatchStream(String checkpointLocation) { default ContinuousStream toContinuousStream(String checkpointLocation) { throw new UnsupportedOperationException(description() + ": Continuous scan are not supported"); } + + /** + * Returns an array of supported custom metrics with name and description. + * By default it returns empty array. + */ + default CustomMetric[] supportedCustomMetrics() { Review comment: I also thought like @sunchao . +1 for a new trait. ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/PartitionReader.java ########## @@ -48,4 +49,12 @@ * Return the current record. This method should return same value until `next` is called. */ T get(); + + /** + * Returns an array of custom metrics. By default it returns empty array. + */ + default CustomMetric[] getCustomMetrics() { Review comment: Also, can we split this as a trait, too? ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/SupportsReportMetrics.java ########## @@ -0,0 +1,39 @@ +/* + * 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.spark.sql.connector; + +import org.apache.spark.annotation.Evolving; + +/** + * Data sources can implement this interface to + * report supported custom metrics to Spark in read/write path. + * + * @since 3.2.0 + */ +@Evolving +public interface SupportsReportMetrics { + + /** + * Returns an array of supported custom metrics with name and description. + * By default it returns empty array. + */ + default CustomMetric[] supportedCustomMetrics() { Review comment: 2-space Indentation? ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/PartitionReaderWithMetrics.java ########## @@ -0,0 +1,39 @@ +/* + * 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.spark.sql.connector.read; + +import org.apache.spark.annotation.Evolving; +import org.apache.spark.sql.connector.CustomMetric; + +/** + * A mix in interface for {@link PartitionReader}. Partition reader can this interface to + * report custom metrics to Spark. + * + * @since 3.2.0 + */ +@Evolving +public interface PartitionReaderWithMetrics<T> extends PartitionReader<T> { + + /** + * Returns an array of custom metrics. By default it returns empty array. + */ + default CustomMetric[] getCustomMetrics() { Review comment: 2-space Indentation? ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/PartitionReaderWithMetrics.java ########## @@ -0,0 +1,39 @@ +/* + * 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.spark.sql.connector.read; + +import org.apache.spark.annotation.Evolving; +import org.apache.spark.sql.connector.CustomMetric; + +/** + * A mix in interface for {@link PartitionReader}. Partition reader can this interface to Review comment: `can this` -> `can implement this` ########## File path: sql/catalyst/src/main/java/org/apache/spark/sql/connector/read/Scan.java ########## @@ -102,4 +102,13 @@ default MicroBatchStream toMicroBatchStream(String checkpointLocation) { default ContinuousStream toContinuousStream(String checkpointLocation) { throw new UnsupportedOperationException(description() + ": Continuous scan are not supported"); } + + /** + * Returns an array of supported custom metrics with name and description. + * By default it returns empty array. + */ + default CustomMetric[] supportedCustomMetrics() { Review comment: Encourage is different from enforcing. > We want to encourage sources to provide metrics. In addition, if we tightly couple this together, we are unable to split it permanently without a breaking change. That's a design risk to me. > There's also just more cost with having a lot of interfaces for very specific things. Given that, I'd recommend to put orthogonal concept separately. Since this is a design issue, cc @cloud-fan , @gatorsmile , @gengliangwang , too. ---------------------------------------------------------------- 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: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
