Github user thunterdb commented on a diff in the pull request: https://github.com/apache/spark/pull/12331#discussion_r59557153 --- Diff: mllib/src/main/scala/org/apache/spark/ml/util/Instrumentation.scala --- @@ -0,0 +1,109 @@ +/* + * 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.ml.util + +import java.util.concurrent.atomic.AtomicLong + +import org.apache.spark.internal.Logging +import org.apache.spark.ml.{Estimator, Model} +import org.apache.spark.ml.param.Param +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.Dataset + +/** + * A small wrapper that defines a training session for an estimator, and some methods to log + * useful information during this session. + * + * A new class is expected to be created within fit(). + * + * @param estimator the estimator that is being fit + * @param dataset the training dataset + * @tparam E the type of the estimator + */ +private[ml] class Instrumentation[E <: Estimator[_]] private ( + estimator: E, dataset: RDD[_]) extends Logging { + private val id = Instrumentation.counter.incrementAndGet() + init() + + private def init(): Unit = { + log(s"training: numPartitions=${dataset.partitions.length}" + + s" storageLevel=${dataset.getStorageLevel}") + } + + /** + * Logs a message with a prefix that uniquely identifies the prefix session. + */ + def log(msg: String): Unit = { + val className = estimator.getClass.getSimpleName + logInfo(s"Instrumentation($className-${estimator.uid}-${dataset.hashCode()}-$id): $msg") --- End diff -- done
--- 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. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org