jcamachor commented on a change in pull request #787: HIVE-22239 URL: https://github.com/apache/hive/pull/787#discussion_r332994124
########## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/columnstats/aggr/TimestampColumnStatsAggregator.java ########## @@ -0,0 +1,358 @@ +/* + * 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.hadoop.hive.metastore.columnstats.aggr; + +import java.util.Collections; +import java.util.Comparator; +import java.util.HashMap; +import java.util.LinkedList; +import java.util.List; +import java.util.Map; +import org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator; +import org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimatorFactory; +import org.apache.hadoop.hive.metastore.api.ColumnStatisticsData; +import org.apache.hadoop.hive.metastore.api.ColumnStatisticsObj; +import org.apache.hadoop.hive.metastore.api.Timestamp; +import org.apache.hadoop.hive.metastore.api.TimestampColumnStatsData; +import org.apache.hadoop.hive.metastore.api.MetaException; +import org.apache.hadoop.hive.metastore.columnstats.cache.TimestampColumnStatsDataInspector; +import org.apache.hadoop.hive.metastore.utils.MetaStoreServerUtils.ColStatsObjWithSourceInfo; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static org.apache.hadoop.hive.metastore.columnstats.ColumnsStatsUtils.timestampInspectorFromStats; + +public class TimestampColumnStatsAggregator extends ColumnStatsAggregator implements + IExtrapolatePartStatus { + + private static final Logger LOG = LoggerFactory.getLogger(TimestampColumnStatsAggregator.class); + + @Override + public ColumnStatisticsObj aggregate(List<ColStatsObjWithSourceInfo> colStatsWithSourceInfo, + List<String> partNames, boolean areAllPartsFound) throws MetaException { + ColumnStatisticsObj statsObj = null; + String colType = null; + String colName = null; + // check if all the ColumnStatisticsObjs contain stats and all the ndv are + // bitvectors + boolean doAllPartitionContainStats = partNames.size() == colStatsWithSourceInfo.size(); + NumDistinctValueEstimator ndvEstimator = null; + for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) { + ColumnStatisticsObj cso = csp.getColStatsObj(); + if (statsObj == null) { + colName = cso.getColName(); + colType = cso.getColType(); + statsObj = ColumnStatsAggregatorFactory.newColumnStaticsObj(colName, colType, + cso.getStatsData().getSetField()); + LOG.trace("doAllPartitionContainStats for column: {} is: {}", colName, doAllPartitionContainStats); + } + TimestampColumnStatsDataInspector timestampColumnStats = timestampInspectorFromStats(cso); + + if (timestampColumnStats.getNdvEstimator() == null) { + ndvEstimator = null; + break; + } else { + // check if all of the bit vectors can merge + NumDistinctValueEstimator estimator = timestampColumnStats.getNdvEstimator(); + if (ndvEstimator == null) { + ndvEstimator = estimator; + } else { + if (ndvEstimator.canMerge(estimator)) { + continue; + } else { + ndvEstimator = null; + break; + } + } + } + } + if (ndvEstimator != null) { + ndvEstimator = NumDistinctValueEstimatorFactory + .getEmptyNumDistinctValueEstimator(ndvEstimator); + } + LOG.debug("all of the bit vectors can merge for " + colName + " is " + (ndvEstimator != null)); + ColumnStatisticsData columnStatisticsData = new ColumnStatisticsData(); + if (doAllPartitionContainStats || colStatsWithSourceInfo.size() < 2) { + TimestampColumnStatsDataInspector aggregateData = null; + long lowerBound = 0; + long higherBound = 0; + double densityAvgSum = 0.0; + for (ColStatsObjWithSourceInfo csp : colStatsWithSourceInfo) { + ColumnStatisticsObj cso = csp.getColStatsObj(); + TimestampColumnStatsDataInspector newData = timestampInspectorFromStats(cso); + higherBound += newData.getNumDVs(); + densityAvgSum += (diff(newData.getHighValue(), newData.getLowValue())) + / newData.getNumDVs(); + if (ndvEstimator != null) { + ndvEstimator.mergeEstimators(newData.getNdvEstimator()); + } + if (aggregateData == null) { + aggregateData = newData.deepCopy(); + } else { + aggregateData.setLowValue(min(aggregateData.getLowValue(), newData.getLowValue())); + aggregateData + .setHighValue(max(aggregateData.getHighValue(), newData.getHighValue())); + aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls()); + aggregateData.setNumDVs(Math.max(aggregateData.getNumDVs(), newData.getNumDVs())); + } + } + if (ndvEstimator != null) { + // if all the ColumnStatisticsObjs contain bitvectors, we do not need to + // use uniform distribution assumption because we can merge bitvectors + // to get a good estimation. + aggregateData.setNumDVs(ndvEstimator.estimateNumDistinctValues()); + } else { + long estimation; + if (useDensityFunctionForNDVEstimation) { + // We have estimation, lowerbound and higherbound. We use estimation + // if it is between lowerbound and higherbound. + double densityAvg = densityAvgSum / partNames.size(); + estimation = (long) (diff(aggregateData.getHighValue(), aggregateData.getLowValue()) / densityAvg); Review comment: I agree with you... Much of this logic could be simplified. There is an abstract class `ColumnStatsAggregator` but it is basically empty. We should move some of the common logic there or to a utility class. I have created another JIRA: https://issues.apache.org/jira/browse/HIVE-22310. ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
