Examples with Output org.apache.hadoop.hive.serde2.ByteStream.Output used on opensource projects

Example 16 with Output

use of org.apache.hadoop.hive.serde2.ByteStream.Output in project hive by apache.

the class GenMRSkewJoinProcessor method processSkewJoin.

/**
 * Create tasks for processing skew joins. The idea is (HIVE-964) to use
 * separated jobs and map-joins to handle skew joins.
 * <p>
 * <ul>
 * <li>
 * Number of mr jobs to handle skew keys is the number of table minus 1 (we
 * can stream the last table, so big keys in the last table will not be a
 * problem).
 * <li>
 * At runtime in Join, we output big keys in one table into one corresponding
 * directories, and all same keys in other tables into different dirs(one for
 * each table). The directories will look like:
 * <ul>
 * <li>
 * dir-T1-bigkeys(containing big keys in T1), dir-T2-keys(containing keys
 * which is big in T1),dir-T3-keys(containing keys which is big in T1), ...
 * <li>
 * dir-T1-keys(containing keys which is big in T2), dir-T2-bigkeys(containing
 * big keys in T2),dir-T3-keys(containing keys which is big in T2), ...
 * <li>
 * dir-T1-keys(containing keys which is big in T3), dir-T2-keys(containing big
 * keys in T3),dir-T3-bigkeys(containing keys which is big in T3), ... .....
 * </ul>
 * </ul>
 * For each table, we launch one mapjoin job, taking the directory containing
 * big keys in this table and corresponding dirs in other tables as input.
 * (Actally one job for one row in the above.)
 *
 * <p>
 * For more discussions, please check
 * https://issues.apache.org/jira/browse/HIVE-964.
 */
@SuppressWarnings("unchecked")
public static void processSkewJoin(JoinOperator joinOp, Task<? extends Serializable> currTask, ParseContext parseCtx) throws SemanticException {
    // now does not work with outer joins
    if (!GenMRSkewJoinProcessor.skewJoinEnabled(parseCtx.getConf(), joinOp)) {
        return;
    }
    List<Task<? extends Serializable>> children = currTask.getChildTasks();
    Path baseTmpDir = parseCtx.getContext().getMRTmpPath();
    JoinDesc joinDescriptor = joinOp.getConf();
    Map<Byte, List<ExprNodeDesc>> joinValues = joinDescriptor.getExprs();
    int numAliases = joinValues.size();
    Map<Byte, Path> bigKeysDirMap = new HashMap<Byte, Path>();
    Map<Byte, Map<Byte, Path>> smallKeysDirMap = new HashMap<Byte, Map<Byte, Path>>();
    Map<Byte, Path> skewJoinJobResultsDir = new HashMap<Byte, Path>();
    Byte[] tags = joinDescriptor.getTagOrder();
    for (int i = 0; i < numAliases; i++) {
        Byte alias = tags[i];
        bigKeysDirMap.put(alias, getBigKeysDir(baseTmpDir, alias));
        Map<Byte, Path> smallKeysMap = new HashMap<Byte, Path>();
        smallKeysDirMap.put(alias, smallKeysMap);
        for (Byte src2 : tags) {
            if (!src2.equals(alias)) {
                smallKeysMap.put(src2, getSmallKeysDir(baseTmpDir, alias, src2));
            }
        }
        skewJoinJobResultsDir.put(alias, getBigKeysSkewJoinResultDir(baseTmpDir, alias));
    }
    joinDescriptor.setHandleSkewJoin(true);
    joinDescriptor.setBigKeysDirMap(bigKeysDirMap);
    joinDescriptor.setSmallKeysDirMap(smallKeysDirMap);
    joinDescriptor.setSkewKeyDefinition(HiveConf.getIntVar(parseCtx.getConf(), HiveConf.ConfVars.HIVESKEWJOINKEY));
    HashMap<Path, Task<? extends Serializable>> bigKeysDirToTaskMap = new HashMap<Path, Task<? extends Serializable>>();
    List<Serializable> listWorks = new ArrayList<Serializable>();
    List<Task<? extends Serializable>> listTasks = new ArrayList<Task<? extends Serializable>>();
    MapredWork currPlan = (MapredWork) currTask.getWork();
    TableDesc keyTblDesc = (TableDesc) currPlan.getReduceWork().getKeyDesc().clone();
    List<String> joinKeys = Utilities.getColumnNames(keyTblDesc.getProperties());
    List<String> joinKeyTypes = Utilities.getColumnTypes(keyTblDesc.getProperties());
    Map<Byte, TableDesc> tableDescList = new HashMap<Byte, TableDesc>();
    Map<Byte, RowSchema> rowSchemaList = new HashMap<Byte, RowSchema>();
    Map<Byte, List<ExprNodeDesc>> newJoinValues = new HashMap<Byte, List<ExprNodeDesc>>();
    Map<Byte, List<ExprNodeDesc>> newJoinKeys = new HashMap<Byte, List<ExprNodeDesc>>();
    // used for create mapJoinDesc, should be in order
    List<TableDesc> newJoinValueTblDesc = new ArrayList<TableDesc>();
    for (Byte tag : tags) {
        newJoinValueTblDesc.add(null);
    }
    for (int i = 0; i < numAliases; i++) {
        Byte alias = tags[i];
        List<ExprNodeDesc> valueCols = joinValues.get(alias);
        String colNames = "";
        String colTypes = "";
        int columnSize = valueCols.size();
        List<ExprNodeDesc> newValueExpr = new ArrayList<ExprNodeDesc>();
        List<ExprNodeDesc> newKeyExpr = new ArrayList<ExprNodeDesc>();
        ArrayList<ColumnInfo> columnInfos = new ArrayList<ColumnInfo>();
        boolean first = true;
        for (int k = 0; k < columnSize; k++) {
            TypeInfo type = valueCols.get(k).getTypeInfo();
            // any name, it does not matter.
            String newColName = i + "_VALUE_" + k;
            ColumnInfo columnInfo = new ColumnInfo(newColName, type, alias.toString(), false);
            columnInfos.add(columnInfo);
            newValueExpr.add(new ExprNodeColumnDesc(columnInfo));
            if (!first) {
                colNames = colNames + ",";
                colTypes = colTypes + ",";
            }
            first = false;
            colNames = colNames + newColName;
            colTypes = colTypes + valueCols.get(k).getTypeString();
        }
        // we are putting join keys at last part of the spilled table
        for (int k = 0; k < joinKeys.size(); k++) {
            if (!first) {
                colNames = colNames + ",";
                colTypes = colTypes + ",";
            }
            first = false;
            colNames = colNames + joinKeys.get(k);
            colTypes = colTypes + joinKeyTypes.get(k);
            ColumnInfo columnInfo = new ColumnInfo(joinKeys.get(k), TypeInfoFactory.getPrimitiveTypeInfo(joinKeyTypes.get(k)), alias.toString(), false);
            columnInfos.add(columnInfo);
            newKeyExpr.add(new ExprNodeColumnDesc(columnInfo));
        }
        newJoinValues.put(alias, newValueExpr);
        newJoinKeys.put(alias, newKeyExpr);
        tableDescList.put(alias, Utilities.getTableDesc(colNames, colTypes));
        rowSchemaList.put(alias, new RowSchema(columnInfos));
        // construct value table Desc
        String valueColNames = "";
        String valueColTypes = "";
        first = true;
        for (int k = 0; k < columnSize; k++) {
            // any name, it does not matter.
            String newColName = i + "_VALUE_" + k;
            if (!first) {
                valueColNames = valueColNames + ",";
                valueColTypes = valueColTypes + ",";
            }
            valueColNames = valueColNames + newColName;
            valueColTypes = valueColTypes + valueCols.get(k).getTypeString();
            first = false;
        }
        newJoinValueTblDesc.set(Byte.valueOf((byte) i), Utilities.getTableDesc(valueColNames, valueColTypes));
    }
    joinDescriptor.setSkewKeysValuesTables(tableDescList);
    joinDescriptor.setKeyTableDesc(keyTblDesc);
    for (int i = 0; i < numAliases - 1; i++) {
        Byte src = tags[i];
        MapWork newPlan = PlanUtils.getMapRedWork().getMapWork();
        // This code has been only added for testing
        boolean mapperCannotSpanPartns = parseCtx.getConf().getBoolVar(HiveConf.ConfVars.HIVE_MAPPER_CANNOT_SPAN_MULTIPLE_PARTITIONS);
        newPlan.setMapperCannotSpanPartns(mapperCannotSpanPartns);
        MapredWork clonePlan = SerializationUtilities.clonePlan(currPlan);
        Operator<? extends OperatorDesc>[] parentOps = new TableScanOperator[tags.length];
        for (int k = 0; k < tags.length; k++) {
            Operator<? extends OperatorDesc> ts = GenMapRedUtils.createTemporaryTableScanOperator(joinOp.getCompilationOpContext(), rowSchemaList.get((byte) k));
            ((TableScanOperator) ts).setTableDescSkewJoin(tableDescList.get((byte) k));
            parentOps[k] = ts;
        }
        Operator<? extends OperatorDesc> tblScan_op = parentOps[i];
        ArrayList<String> aliases = new ArrayList<String>();
        String alias = src.toString().intern();
        aliases.add(alias);
        Path bigKeyDirPath = bigKeysDirMap.get(src);
        newPlan.addPathToAlias(bigKeyDirPath, aliases);
        newPlan.getAliasToWork().put(alias, tblScan_op);
        PartitionDesc part = new PartitionDesc(tableDescList.get(src), null);
        newPlan.addPathToPartitionInfo(bigKeyDirPath, part);
        newPlan.getAliasToPartnInfo().put(alias, part);
        Operator<? extends OperatorDesc> reducer = clonePlan.getReduceWork().getReducer();
        assert reducer instanceof JoinOperator;
        JoinOperator cloneJoinOp = (JoinOperator) reducer;
        String dumpFilePrefix = "mapfile" + PlanUtils.getCountForMapJoinDumpFilePrefix();
        MapJoinDesc mapJoinDescriptor = new MapJoinDesc(newJoinKeys, keyTblDesc, newJoinValues, newJoinValueTblDesc, newJoinValueTblDesc, joinDescriptor.getOutputColumnNames(), i, joinDescriptor.getConds(), joinDescriptor.getFilters(), joinDescriptor.getNoOuterJoin(), dumpFilePrefix, joinDescriptor.getMemoryMonitorInfo(), joinDescriptor.getInMemoryDataSize());
        mapJoinDescriptor.setTagOrder(tags);
        mapJoinDescriptor.setHandleSkewJoin(false);
        mapJoinDescriptor.setNullSafes(joinDescriptor.getNullSafes());
        mapJoinDescriptor.setColumnExprMap(joinDescriptor.getColumnExprMap());
        MapredLocalWork localPlan = new MapredLocalWork(new LinkedHashMap<String, Operator<? extends OperatorDesc>>(), new LinkedHashMap<String, FetchWork>());
        Map<Byte, Path> smallTblDirs = smallKeysDirMap.get(src);
        for (int j = 0; j < numAliases; j++) {
            if (j == i) {
                continue;
            }
            Byte small_alias = tags[j];
            Operator<? extends OperatorDesc> tblScan_op2 = parentOps[j];
            localPlan.getAliasToWork().put(small_alias.toString(), tblScan_op2);
            Path tblDir = smallTblDirs.get(small_alias);
            localPlan.getAliasToFetchWork().put(small_alias.toString(), new FetchWork(tblDir, tableDescList.get(small_alias)));
        }
        newPlan.setMapRedLocalWork(localPlan);
        // construct a map join and set it as the child operator of tblScan_op
        MapJoinOperator mapJoinOp = (MapJoinOperator) OperatorFactory.getAndMakeChild(joinOp.getCompilationOpContext(), mapJoinDescriptor, (RowSchema) null, parentOps);
        // change the children of the original join operator to point to the map
        // join operator
        List<Operator<? extends OperatorDesc>> childOps = cloneJoinOp.getChildOperators();
        for (Operator<? extends OperatorDesc> childOp : childOps) {
            childOp.replaceParent(cloneJoinOp, mapJoinOp);
        }
        mapJoinOp.setChildOperators(childOps);
        HiveConf jc = new HiveConf(parseCtx.getConf(), GenMRSkewJoinProcessor.class);
        newPlan.setNumMapTasks(HiveConf.getIntVar(jc, HiveConf.ConfVars.HIVESKEWJOINMAPJOINNUMMAPTASK));
        newPlan.setMinSplitSize(HiveConf.getLongVar(jc, HiveConf.ConfVars.HIVESKEWJOINMAPJOINMINSPLIT));
        newPlan.setInputformat(HiveInputFormat.class.getName());
        MapredWork w = new MapredWork();
        w.setMapWork(newPlan);
        Task<? extends Serializable> skewJoinMapJoinTask = TaskFactory.get(w);
        skewJoinMapJoinTask.setFetchSource(currTask.isFetchSource());
        bigKeysDirToTaskMap.put(bigKeyDirPath, skewJoinMapJoinTask);
        listWorks.add(skewJoinMapJoinTask.getWork());
        listTasks.add(skewJoinMapJoinTask);
    }
    if (children != null) {
        for (Task<? extends Serializable> tsk : listTasks) {
            for (Task<? extends Serializable> oldChild : children) {
                tsk.addDependentTask(oldChild);
            }
        }
        currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
        for (Task<? extends Serializable> oldChild : children) {
            oldChild.getParentTasks().remove(currTask);
        }
        listTasks.addAll(children);
    }
    ConditionalResolverSkewJoinCtx context = new ConditionalResolverSkewJoinCtx(bigKeysDirToTaskMap, children);
    ConditionalWork cndWork = new ConditionalWork(listWorks);
    ConditionalTask cndTsk = (ConditionalTask) TaskFactory.get(cndWork);
    cndTsk.setListTasks(listTasks);
    cndTsk.setResolver(new ConditionalResolverSkewJoin());
    cndTsk.setResolverCtx(context);
    currTask.setChildTasks(new ArrayList<Task<? extends Serializable>>());
    currTask.addDependentTask(cndTsk);
    return;
}

Example 17 with Output

use of org.apache.hadoop.hive.serde2.ByteStream.Output in project hive by apache.

the class VectorMapJoinInnerBigOnlyMultiKeyOperator method process.

// ---------------------------------------------------------------------------
// Process Multi-Key Inner Big-Only Join on a vectorized row batch.
// 
@Override
public void process(Object row, int tag) throws HiveException {
    try {
        VectorizedRowBatch batch = (VectorizedRowBatch) row;
        alias = (byte) tag;
        if (needCommonSetup) {
            // Our one time process method initialization.
            commonSetup(batch);
            /*
         * Initialize Multi-Key members for this specialized class.
         */
            keyVectorSerializeWrite = new VectorSerializeRow(new BinarySortableSerializeWrite(bigTableKeyColumnMap.length));
            keyVectorSerializeWrite.init(bigTableKeyTypeInfos, bigTableKeyColumnMap);
            currentKeyOutput = new Output();
            saveKeyOutput = new Output();
            needCommonSetup = false;
        }
        if (needHashTableSetup) {
            // Setup our hash table specialization.  It will be the first time the process
            // method is called, or after a Hybrid Grace reload.
            /*
         * Get our Multi-Key hash multi-set information for this specialized class.
         */
            hashMultiSet = (VectorMapJoinBytesHashMultiSet) vectorMapJoinHashTable;
            needHashTableSetup = false;
        }
        batchCounter++;
        // For inner joins, we may apply the filter(s) now.
        for (VectorExpression ve : bigTableFilterExpressions) {
            ve.evaluate(batch);
        }
        final int inputLogicalSize = batch.size;
        if (inputLogicalSize == 0) {
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
            }
            return;
        }
        // Perform any key expressions.  Results will go into scratch columns.
        if (bigTableKeyExpressions != null) {
            for (VectorExpression ve : bigTableKeyExpressions) {
                ve.evaluate(batch);
            }
        }
        /*
       * Multi-Key specific declarations.
       */
        // None.
        /*
       * Multi-Key check for repeating.
       */
        // If all BigTable input columns to key expressions are isRepeating, then
        // calculate key once; lookup once.
        boolean allKeyInputColumnsRepeating;
        if (bigTableKeyColumnMap.length == 0) {
            allKeyInputColumnsRepeating = false;
        } else {
            allKeyInputColumnsRepeating = true;
            for (int i = 0; i < bigTableKeyColumnMap.length; i++) {
                if (!batch.cols[bigTableKeyColumnMap[i]].isRepeating) {
                    allKeyInputColumnsRepeating = false;
                    break;
                }
            }
        }
        if (allKeyInputColumnsRepeating) {
            /*
         * Repeating.
         */
            // All key input columns are repeating.  Generate key once.  Lookup once.
            // Since the key is repeated, we must use entry 0 regardless of selectedInUse.
            /*
         * Multi-Key specific repeated lookup.
         */
            keyVectorSerializeWrite.setOutput(currentKeyOutput);
            keyVectorSerializeWrite.serializeWrite(batch, 0);
            JoinUtil.JoinResult joinResult;
            if (keyVectorSerializeWrite.getHasAnyNulls()) {
                joinResult = JoinUtil.JoinResult.NOMATCH;
            } else {
                byte[] keyBytes = currentKeyOutput.getData();
                int keyLength = currentKeyOutput.getLength();
                joinResult = hashMultiSet.contains(keyBytes, 0, keyLength, hashMultiSetResults[0]);
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
            }
            finishInnerBigOnlyRepeated(batch, joinResult, hashMultiSetResults[0]);
        } else {
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
            }
            // We remember any matching rows in matchs / matchSize.  At the end of the loop,
            // selected / batch.size will represent both matching and non-matching rows for outer join.
            // Only deferred rows will have been removed from selected.
            int[] selected = batch.selected;
            boolean selectedInUse = batch.selectedInUse;
            int hashMultiSetResultCount = 0;
            int allMatchCount = 0;
            int equalKeySeriesCount = 0;
            int spillCount = 0;
            /*
         * Multi-Key specific variables.
         */
            Output temp;
            // We optimize performance by only looking up the first key in a series of equal keys.
            boolean haveSaveKey = false;
            JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH;
            // Logical loop over the rows in the batch since the batch may have selected in use.
            for (int logical = 0; logical < inputLogicalSize; logical++) {
                int batchIndex = (selectedInUse ? selected[logical] : logical);
                /*
           * Multi-Key get key.
           */
                // Generate binary sortable key for current row in vectorized row batch.
                keyVectorSerializeWrite.setOutput(currentKeyOutput);
                keyVectorSerializeWrite.serializeWrite(batch, batchIndex);
                boolean isAnyNulls = keyVectorSerializeWrite.getHasAnyNulls();
                if (isAnyNulls || !haveSaveKey || !saveKeyOutput.arraysEquals(currentKeyOutput)) {
                    if (haveSaveKey) {
                        // Move on with our counts.
                        switch(saveJoinResult) {
                            case MATCH:
                                // We have extracted the count from the hash multi-set result, so we don't keep it.
                                equalKeySeriesCount++;
                                break;
                            case SPILL:
                                // We keep the hash multi-set result for its spill information.
                                hashMultiSetResultCount++;
                                break;
                            case NOMATCH:
                                break;
                        }
                    }
                    if (isAnyNulls) {
                        saveJoinResult = JoinUtil.JoinResult.NOMATCH;
                        haveSaveKey = false;
                    } else {
                        // Regardless of our matching result, we keep that information to make multiple use
                        // of it for a possible series of equal keys.
                        haveSaveKey = true;
                        /*
               * Multi-Key specific save key.
               */
                        temp = saveKeyOutput;
                        saveKeyOutput = currentKeyOutput;
                        currentKeyOutput = temp;
                        /*
               * Single-Column Long specific lookup key.
               */
                        byte[] keyBytes = saveKeyOutput.getData();
                        int keyLength = saveKeyOutput.getLength();
                        saveJoinResult = hashMultiSet.contains(keyBytes, 0, keyLength, hashMultiSetResults[hashMultiSetResultCount]);
                    }
                    switch(saveJoinResult) {
                        case MATCH:
                            equalKeySeriesValueCounts[equalKeySeriesCount] = hashMultiSetResults[hashMultiSetResultCount].count();
                            equalKeySeriesAllMatchIndices[equalKeySeriesCount] = allMatchCount;
                            equalKeySeriesDuplicateCounts[equalKeySeriesCount] = 1;
                            allMatchs[allMatchCount++] = batchIndex;
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH isSingleValue " + equalKeySeriesIsSingleValue[equalKeySeriesCount] + " currentKey " + currentKey);
                            break;
                        case SPILL:
                            spills[spillCount] = batchIndex;
                            spillHashMapResultIndices[spillCount] = hashMultiSetResultCount;
                            spillCount++;
                            break;
                        case NOMATCH:
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH" + " currentKey " + currentKey);
                            break;
                    }
                } else {
                    switch(saveJoinResult) {
                        case MATCH:
                            equalKeySeriesDuplicateCounts[equalKeySeriesCount]++;
                            allMatchs[allMatchCount++] = batchIndex;
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH duplicate");
                            break;
                        case SPILL:
                            spills[spillCount] = batchIndex;
                            spillHashMapResultIndices[spillCount] = hashMultiSetResultCount;
                            spillCount++;
                            break;
                        case NOMATCH:
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH duplicate");
                            break;
                    }
                }
            }
            if (haveSaveKey) {
                // Update our counts for the last key.
                switch(saveJoinResult) {
                    case MATCH:
                        // We have extracted the count from the hash multi-set result, so we don't keep it.
                        equalKeySeriesCount++;
                        break;
                    case SPILL:
                        // We keep the hash multi-set result for its spill information.
                        hashMultiSetResultCount++;
                        break;
                    case NOMATCH:
                        break;
                }
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " allMatchs " + intArrayToRangesString(allMatchs, allMatchCount) + " equalKeySeriesValueCounts " + longArrayToRangesString(equalKeySeriesValueCounts, equalKeySeriesCount) + " equalKeySeriesAllMatchIndices " + intArrayToRangesString(equalKeySeriesAllMatchIndices, equalKeySeriesCount) + " equalKeySeriesDuplicateCounts " + intArrayToRangesString(equalKeySeriesDuplicateCounts, equalKeySeriesCount) + " spills " + intArrayToRangesString(spills, spillCount) + " spillHashMapResultIndices " + intArrayToRangesString(spillHashMapResultIndices, spillCount) + " hashMapResults " + Arrays.toString(Arrays.copyOfRange(hashMultiSetResults, 0, hashMultiSetResultCount)));
            }
            finishInnerBigOnly(batch, allMatchCount, equalKeySeriesCount, spillCount, (VectorMapJoinHashTableResult[]) hashMultiSetResults, hashMultiSetResultCount);
        }
        if (batch.size > 0) {
            // Forward any remaining selected rows.
            forwardBigTableBatch(batch);
        }
    } catch (IOException e) {
        throw new HiveException(e);
    } catch (Exception e) {
        throw new HiveException(e);
    }
}

Example 18 with Output

use of org.apache.hadoop.hive.serde2.ByteStream.Output in project hive by apache.

the class VectorMapJoinInnerMultiKeyOperator method process.

// ---------------------------------------------------------------------------
// Process Multi-Key Inner Join on a vectorized row batch.
// 
@Override
public void process(Object row, int tag) throws HiveException {
    try {
        VectorizedRowBatch batch = (VectorizedRowBatch) row;
        alias = (byte) tag;
        if (needCommonSetup) {
            // Our one time process method initialization.
            commonSetup(batch);
            /*
         * Initialize Multi-Key members for this specialized class.
         */
            keyVectorSerializeWrite = new VectorSerializeRow(new BinarySortableSerializeWrite(bigTableKeyColumnMap.length));
            keyVectorSerializeWrite.init(bigTableKeyTypeInfos, bigTableKeyColumnMap);
            currentKeyOutput = new Output();
            saveKeyOutput = new Output();
            needCommonSetup = false;
        }
        if (needHashTableSetup) {
            // Setup our hash table specialization.  It will be the first time the process
            // method is called, or after a Hybrid Grace reload.
            /*
         * Get our Multi-Key hash map information for this specialized class.
         */
            hashMap = (VectorMapJoinBytesHashMap) vectorMapJoinHashTable;
            needHashTableSetup = false;
        }
        batchCounter++;
        // Do the per-batch setup for an inner join.
        innerPerBatchSetup(batch);
        // For inner joins, we may apply the filter(s) now.
        for (VectorExpression ve : bigTableFilterExpressions) {
            ve.evaluate(batch);
        }
        final int inputLogicalSize = batch.size;
        if (inputLogicalSize == 0) {
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
            }
            return;
        }
        // Perform any key expressions.  Results will go into scratch columns.
        if (bigTableKeyExpressions != null) {
            for (VectorExpression ve : bigTableKeyExpressions) {
                ve.evaluate(batch);
            }
        }
        /*
       * Multi-Key specific declarations.
       */
        // None.
        /*
       * Multi-Key check for repeating.
       */
        // If all BigTable input columns to key expressions are isRepeating, then
        // calculate key once; lookup once.
        boolean allKeyInputColumnsRepeating;
        if (bigTableKeyColumnMap.length == 0) {
            allKeyInputColumnsRepeating = false;
        } else {
            allKeyInputColumnsRepeating = true;
            for (int i = 0; i < bigTableKeyColumnMap.length; i++) {
                if (!batch.cols[bigTableKeyColumnMap[i]].isRepeating) {
                    allKeyInputColumnsRepeating = false;
                    break;
                }
            }
        }
        if (allKeyInputColumnsRepeating) {
            /*
         * Repeating.
         */
            // All key input columns are repeating.  Generate key once.  Lookup once.
            // Since the key is repeated, we must use entry 0 regardless of selectedInUse.
            /*
         * Multi-Key specific repeated lookup.
         */
            keyVectorSerializeWrite.setOutput(currentKeyOutput);
            keyVectorSerializeWrite.serializeWrite(batch, 0);
            JoinUtil.JoinResult joinResult;
            if (keyVectorSerializeWrite.getHasAnyNulls()) {
                joinResult = JoinUtil.JoinResult.NOMATCH;
            } else {
                byte[] keyBytes = currentKeyOutput.getData();
                int keyLength = currentKeyOutput.getLength();
                joinResult = hashMap.lookup(keyBytes, 0, keyLength, hashMapResults[0]);
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
            }
            finishInnerRepeated(batch, joinResult, hashMapResults[0]);
        } else {
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
            }
            // We remember any matching rows in matchs / matchSize.  At the end of the loop,
            // selected / batch.size will represent both matching and non-matching rows for outer join.
            // Only deferred rows will have been removed from selected.
            int[] selected = batch.selected;
            boolean selectedInUse = batch.selectedInUse;
            int hashMapResultCount = 0;
            int allMatchCount = 0;
            int equalKeySeriesCount = 0;
            int spillCount = 0;
            /*
         * Multi-Key specific variables.
         */
            Output temp;
            // We optimize performance by only looking up the first key in a series of equal keys.
            boolean haveSaveKey = false;
            JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH;
            // Logical loop over the rows in the batch since the batch may have selected in use.
            for (int logical = 0; logical < inputLogicalSize; logical++) {
                int batchIndex = (selectedInUse ? selected[logical] : logical);
                /*
           * Multi-Key get key.
           */
                // Generate binary sortable key for current row in vectorized row batch.
                keyVectorSerializeWrite.setOutput(currentKeyOutput);
                keyVectorSerializeWrite.serializeWrite(batch, batchIndex);
                boolean isAnyNull = keyVectorSerializeWrite.getHasAnyNulls();
                if (isAnyNull || !haveSaveKey || !saveKeyOutput.arraysEquals(currentKeyOutput)) {
                    if (haveSaveKey) {
                        // Move on with our counts.
                        switch(saveJoinResult) {
                            case MATCH:
                                hashMapResultCount++;
                                equalKeySeriesCount++;
                                break;
                            case SPILL:
                                hashMapResultCount++;
                                break;
                            case NOMATCH:
                                break;
                        }
                    }
                    if (isAnyNull) {
                        saveJoinResult = JoinUtil.JoinResult.NOMATCH;
                        haveSaveKey = false;
                    } else {
                        // Regardless of our matching result, we keep that information to make multiple use
                        // of it for a possible series of equal keys.
                        haveSaveKey = true;
                        /*
               * Multi-Key specific save key.
               */
                        temp = saveKeyOutput;
                        saveKeyOutput = currentKeyOutput;
                        currentKeyOutput = temp;
                        /*
               * Multi-Key specific lookup key.
               */
                        byte[] keyBytes = saveKeyOutput.getData();
                        int keyLength = saveKeyOutput.getLength();
                        saveJoinResult = hashMap.lookup(keyBytes, 0, keyLength, hashMapResults[hashMapResultCount]);
                    }
                    switch(saveJoinResult) {
                        case MATCH:
                            equalKeySeriesHashMapResultIndices[equalKeySeriesCount] = hashMapResultCount;
                            equalKeySeriesAllMatchIndices[equalKeySeriesCount] = allMatchCount;
                            equalKeySeriesIsSingleValue[equalKeySeriesCount] = hashMapResults[hashMapResultCount].isSingleRow();
                            equalKeySeriesDuplicateCounts[equalKeySeriesCount] = 1;
                            allMatchs[allMatchCount++] = batchIndex;
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH isSingleValue " + equalKeySeriesIsSingleValue[equalKeySeriesCount] + " currentKey " + currentKey);
                            break;
                        case SPILL:
                            spills[spillCount] = batchIndex;
                            spillHashMapResultIndices[spillCount] = hashMapResultCount;
                            spillCount++;
                            break;
                        case NOMATCH:
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH" + " currentKey " + currentKey);
                            break;
                    }
                } else {
                    switch(saveJoinResult) {
                        case MATCH:
                            equalKeySeriesDuplicateCounts[equalKeySeriesCount]++;
                            allMatchs[allMatchCount++] = batchIndex;
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH duplicate");
                            break;
                        case SPILL:
                            spills[spillCount] = batchIndex;
                            spillHashMapResultIndices[spillCount] = hashMapResultCount;
                            spillCount++;
                            break;
                        case NOMATCH:
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH duplicate");
                            break;
                    }
                }
            }
            if (haveSaveKey) {
                // Update our counts for the last key.
                switch(saveJoinResult) {
                    case MATCH:
                        hashMapResultCount++;
                        equalKeySeriesCount++;
                        break;
                    case SPILL:
                        hashMapResultCount++;
                        break;
                    case NOMATCH:
                        break;
                }
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " allMatchs " + intArrayToRangesString(allMatchs, allMatchCount) + " equalKeySeriesHashMapResultIndices " + intArrayToRangesString(equalKeySeriesHashMapResultIndices, equalKeySeriesCount) + " equalKeySeriesAllMatchIndices " + intArrayToRangesString(equalKeySeriesAllMatchIndices, equalKeySeriesCount) + " equalKeySeriesIsSingleValue " + Arrays.toString(Arrays.copyOfRange(equalKeySeriesIsSingleValue, 0, equalKeySeriesCount)) + " equalKeySeriesDuplicateCounts " + Arrays.toString(Arrays.copyOfRange(equalKeySeriesDuplicateCounts, 0, equalKeySeriesCount)) + " spills " + intArrayToRangesString(spills, spillCount) + " spillHashMapResultIndices " + intArrayToRangesString(spillHashMapResultIndices, spillCount) + " hashMapResults " + Arrays.toString(Arrays.copyOfRange(hashMapResults, 0, hashMapResultCount)));
            }
            finishInner(batch, allMatchCount, equalKeySeriesCount, spillCount, hashMapResultCount);
        }
        if (batch.size > 0) {
            // Forward any remaining selected rows.
            forwardBigTableBatch(batch);
        }
    } catch (IOException e) {
        throw new HiveException(e);
    } catch (Exception e) {
        throw new HiveException(e);
    }
}

Example 19 with Output

use of org.apache.hadoop.hive.serde2.ByteStream.Output in project hive by apache.

the class VectorMapJoinLeftSemiMultiKeyOperator method process.

// ---------------------------------------------------------------------------
// Process Multi-Key Left-Semi Join on a vectorized row batch.
// 
@Override
public void process(Object row, int tag) throws HiveException {
    try {
        VectorizedRowBatch batch = (VectorizedRowBatch) row;
        alias = (byte) tag;
        if (needCommonSetup) {
            // Our one time process method initialization.
            commonSetup(batch);
            /*
         * Initialize Multi-Key members for this specialized class.
         */
            keyVectorSerializeWrite = new VectorSerializeRow(new BinarySortableSerializeWrite(bigTableKeyColumnMap.length));
            keyVectorSerializeWrite.init(bigTableKeyTypeInfos, bigTableKeyColumnMap);
            currentKeyOutput = new Output();
            saveKeyOutput = new Output();
            needCommonSetup = false;
        }
        if (needHashTableSetup) {
            // Setup our hash table specialization.  It will be the first time the process
            // method is called, or after a Hybrid Grace reload.
            /*
         * Get our Multi-Key hash set information for this specialized class.
         */
            hashSet = (VectorMapJoinBytesHashSet) vectorMapJoinHashTable;
            needHashTableSetup = false;
        }
        batchCounter++;
        // For left semi joins, we may apply the filter(s) now.
        for (VectorExpression ve : bigTableFilterExpressions) {
            ve.evaluate(batch);
        }
        final int inputLogicalSize = batch.size;
        if (inputLogicalSize == 0) {
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
            }
            return;
        }
        // Perform any key expressions.  Results will go into scratch columns.
        if (bigTableKeyExpressions != null) {
            for (VectorExpression ve : bigTableKeyExpressions) {
                ve.evaluate(batch);
            }
        }
        /*
       * Multi-Key specific declarations.
       */
        // None.
        /*
       * Multi-Key Long check for repeating.
       */
        // If all BigTable input columns to key expressions are isRepeating, then
        // calculate key once; lookup once.
        boolean allKeyInputColumnsRepeating;
        if (bigTableKeyColumnMap.length == 0) {
            allKeyInputColumnsRepeating = false;
        } else {
            allKeyInputColumnsRepeating = true;
            for (int i = 0; i < bigTableKeyColumnMap.length; i++) {
                if (!batch.cols[bigTableKeyColumnMap[i]].isRepeating) {
                    allKeyInputColumnsRepeating = false;
                    break;
                }
            }
        }
        if (allKeyInputColumnsRepeating) {
            /*
         * Repeating.
         */
            // All key input columns are repeating.  Generate key once.  Lookup once.
            // Since the key is repeated, we must use entry 0 regardless of selectedInUse.
            /*
         * Multi-Key specific repeated lookup.
         */
            keyVectorSerializeWrite.setOutput(currentKeyOutput);
            keyVectorSerializeWrite.serializeWrite(batch, 0);
            JoinUtil.JoinResult joinResult;
            if (keyVectorSerializeWrite.getHasAnyNulls()) {
                joinResult = JoinUtil.JoinResult.NOMATCH;
            } else {
                byte[] keyBytes = currentKeyOutput.getData();
                int keyLength = currentKeyOutput.getLength();
                // LOG.debug(CLASS_NAME + " processOp all " + displayBytes(keyBytes, 0, keyLength));
                joinResult = hashSet.contains(keyBytes, 0, keyLength, hashSetResults[0]);
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
            }
            finishLeftSemiRepeated(batch, joinResult, hashSetResults[0]);
        } else {
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
            }
            // We remember any matching rows in matchs / matchSize.  At the end of the loop,
            // selected / batch.size will represent both matching and non-matching rows for outer join.
            // Only deferred rows will have been removed from selected.
            int[] selected = batch.selected;
            boolean selectedInUse = batch.selectedInUse;
            int hashSetResultCount = 0;
            int allMatchCount = 0;
            int spillCount = 0;
            /*
         * Multi-Key specific variables.
         */
            Output temp;
            // We optimize performance by only looking up the first key in a series of equal keys.
            boolean haveSaveKey = false;
            JoinUtil.JoinResult saveJoinResult = JoinUtil.JoinResult.NOMATCH;
            // Logical loop over the rows in the batch since the batch may have selected in use.
            for (int logical = 0; logical < inputLogicalSize; logical++) {
                int batchIndex = (selectedInUse ? selected[logical] : logical);
                /*
           * Multi-Key get key.
           */
                // Generate binary sortable key for current row in vectorized row batch.
                keyVectorSerializeWrite.setOutput(currentKeyOutput);
                keyVectorSerializeWrite.serializeWrite(batch, batchIndex);
                boolean isAnyNull = keyVectorSerializeWrite.getHasAnyNulls();
                if (isAnyNull || !haveSaveKey || !saveKeyOutput.arraysEquals(currentKeyOutput)) {
                    if (haveSaveKey) {
                        // Move on with our counts.
                        switch(saveJoinResult) {
                            case MATCH:
                                // We have extracted the existence from the hash set result, so we don't keep it.
                                break;
                            case SPILL:
                                // We keep the hash set result for its spill information.
                                hashSetResultCount++;
                                break;
                            case NOMATCH:
                                break;
                        }
                    }
                    if (isAnyNull) {
                        saveJoinResult = JoinUtil.JoinResult.NOMATCH;
                        haveSaveKey = false;
                    } else {
                        // Regardless of our matching result, we keep that information to make multiple use
                        // of it for a possible series of equal keys.
                        haveSaveKey = true;
                        /*
               * Multi-Key specific save key and lookup.
               */
                        temp = saveKeyOutput;
                        saveKeyOutput = currentKeyOutput;
                        currentKeyOutput = temp;
                        /*
               * Multi-key specific lookup key.
               */
                        byte[] keyBytes = saveKeyOutput.getData();
                        int keyLength = saveKeyOutput.getLength();
                        saveJoinResult = hashSet.contains(keyBytes, 0, keyLength, hashSetResults[hashSetResultCount]);
                    }
                    switch(saveJoinResult) {
                        case MATCH:
                            allMatchs[allMatchCount++] = batchIndex;
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH isSingleValue " + equalKeySeriesIsSingleValue[equalKeySeriesCount] + " currentKey " + currentKey);
                            break;
                        case SPILL:
                            spills[spillCount] = batchIndex;
                            spillHashMapResultIndices[spillCount] = hashSetResultCount;
                            spillCount++;
                            break;
                        case NOMATCH:
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH" + " currentKey " + currentKey);
                            break;
                    }
                } else {
                    switch(saveJoinResult) {
                        case MATCH:
                            allMatchs[allMatchCount++] = batchIndex;
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " MATCH duplicate");
                            break;
                        case SPILL:
                            spills[spillCount] = batchIndex;
                            spillHashMapResultIndices[spillCount] = hashSetResultCount;
                            spillCount++;
                            break;
                        case NOMATCH:
                            // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, CLASS_NAME + " NOMATCH duplicate");
                            break;
                    }
                }
            }
            if (haveSaveKey) {
                // Update our counts for the last key.
                switch(saveJoinResult) {
                    case MATCH:
                        // We have extracted the existence from the hash set result, so we don't keep it.
                        break;
                    case SPILL:
                        // We keep the hash set result for its spill information.
                        hashSetResultCount++;
                        break;
                    case NOMATCH:
                        break;
                }
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug(CLASS_NAME + " allMatchs " + intArrayToRangesString(allMatchs, allMatchCount) + " spills " + intArrayToRangesString(spills, spillCount) + " spillHashMapResultIndices " + intArrayToRangesString(spillHashMapResultIndices, spillCount) + " hashMapResults " + Arrays.toString(Arrays.copyOfRange(hashSetResults, 0, hashSetResultCount)));
            }
            finishLeftSemi(batch, allMatchCount, spillCount, (VectorMapJoinHashTableResult[]) hashSetResults);
        }
        if (batch.size > 0) {
            // Forward any remaining selected rows.
            forwardBigTableBatch(batch);
        }
    } catch (IOException e) {
        throw new HiveException(e);
    } catch (Exception e) {
        throw new HiveException(e);
    }
}

Example 20 with Output

use of org.apache.hadoop.hive.serde2.ByteStream.Output in project flink by apache.

the class HiveParserCalcitePlanner method genSelectForWindowing.

private RelNode genSelectForWindowing(HiveParserQB qb, RelNode srcRel, HashSet<ColumnInfo> newColumns) throws SemanticException {
    HiveParserWindowingSpec wSpec = !qb.getAllWindowingSpecs().isEmpty() ? qb.getAllWindowingSpecs().values().iterator().next() : null;
    if (wSpec == null) {
        return null;
    }
    // 1. Get valid Window Function Spec
    wSpec.validateAndMakeEffective();
    List<HiveParserWindowingSpec.WindowExpressionSpec> windowExpressions = wSpec.getWindowExpressions();
    if (windowExpressions == null || windowExpressions.isEmpty()) {
        return null;
    }
    HiveParserRowResolver inputRR = relToRowResolver.get(srcRel);
    // 2. Get RexNodes for original Projections from below
    List<RexNode> projsForWindowSelOp = new ArrayList<>(HiveParserUtils.getProjsFromBelowAsInputRef(srcRel));
    // 3. Construct new Row Resolver with everything from below.
    HiveParserRowResolver outRR = new HiveParserRowResolver();
    if (!HiveParserRowResolver.add(outRR, inputRR)) {
        LOG.warn("Duplicates detected when adding columns to RR: see previous message");
    }
    // 4. Walk through Window Expressions & Construct RexNodes for those. Update out_rwsch
    final HiveParserQBParseInfo qbp = qb.getParseInfo();
    final String selClauseName = qbp.getClauseNames().iterator().next();
    final boolean cubeRollupGrpSetPresent = (!qbp.getDestRollups().isEmpty() || !qbp.getDestGroupingSets().isEmpty() || !qbp.getDestCubes().isEmpty());
    for (HiveParserWindowingSpec.WindowExpressionSpec winExprSpec : windowExpressions) {
        if (!qbp.getDestToGroupBy().isEmpty()) {
            // Special handling of grouping function
            winExprSpec.setExpression(rewriteGroupingFunctionAST(getGroupByForClause(qbp, selClauseName), winExprSpec.getExpression(), !cubeRollupGrpSetPresent));
        }
        if (outRR.getExpression(winExprSpec.getExpression()) == null) {
            Pair<RexNode, TypeInfo> rexAndType = getWindowRexAndType(winExprSpec, srcRel);
            projsForWindowSelOp.add(rexAndType.getKey());
            // 6.2.2 Update Output Row Schema
            ColumnInfo oColInfo = new ColumnInfo(getColumnInternalName(projsForWindowSelOp.size()), rexAndType.getValue(), null, false);
            outRR.putExpression(winExprSpec.getExpression(), oColInfo);
            newColumns.add(oColInfo);
        }
    }
    return genSelectRelNode(projsForWindowSelOp, outRR, srcRel, windowExpressions);
}