Examples with JoinDesc org.apache.hadoop.hive.ql.plan.JoinDesc used on opensource projects

Example 1 with JoinDesc

use of org.apache.hadoop.hive.ql.plan.JoinDesc 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 2 with JoinDesc

use of org.apache.hadoop.hive.ql.plan.JoinDesc in project hive by apache.

the class ConvertJoinMapJoin method checkAndConvertSMBJoin.

@SuppressWarnings("unchecked")
private Object checkAndConvertSMBJoin(OptimizeTezProcContext context, JoinOperator joinOp, TezBucketJoinProcCtx tezBucketJoinProcCtx, final long maxSize) throws SemanticException {
    // map join either based on the size. Check if we can convert to SMB join.
    if (!(HiveConf.getBoolVar(context.conf, ConfVars.HIVE_AUTO_SORTMERGE_JOIN)) || ((!HiveConf.getBoolVar(context.conf, ConfVars.HIVE_AUTO_SORTMERGE_JOIN_REDUCE)) && joinOp.getOpTraits().getNumReduceSinks() >= 2)) {
        fallbackToReduceSideJoin(joinOp, context, maxSize);
        return null;
    }
    Class<? extends BigTableSelectorForAutoSMJ> bigTableMatcherClass = null;
    try {
        String selector = HiveConf.getVar(context.parseContext.getConf(), HiveConf.ConfVars.HIVE_AUTO_SORTMERGE_JOIN_BIGTABLE_SELECTOR);
        bigTableMatcherClass = JavaUtils.loadClass(selector);
    } catch (ClassNotFoundException e) {
        throw new SemanticException(e.getMessage());
    }
    BigTableSelectorForAutoSMJ bigTableMatcher = ReflectionUtils.newInstance(bigTableMatcherClass, null);
    JoinDesc joinDesc = joinOp.getConf();
    JoinCondDesc[] joinCondns = joinDesc.getConds();
    Set<Integer> joinCandidates = MapJoinProcessor.getBigTableCandidates(joinCondns);
    if (joinCandidates.isEmpty()) {
        // of any type. So return false.
        return false;
    }
    int mapJoinConversionPos = bigTableMatcher.getBigTablePosition(context.parseContext, joinOp, joinCandidates);
    if (mapJoinConversionPos < 0) {
        // contains aliases from sub-query
        // we are just converting to a common merge join operator. The shuffle
        // join in map-reduce case.
        fallbackToReduceSideJoin(joinOp, context, maxSize);
        return null;
    }
    if (checkConvertJoinSMBJoin(joinOp, context, mapJoinConversionPos, tezBucketJoinProcCtx)) {
        convertJoinSMBJoin(joinOp, context, mapJoinConversionPos, tezBucketJoinProcCtx.getNumBuckets(), true);
    } else {
        // we are just converting to a common merge join operator. The shuffle
        // join in map-reduce case.
        fallbackToReduceSideJoin(joinOp, context, maxSize);
    }
    return null;
}

Example 3 with JoinDesc

use of org.apache.hadoop.hive.ql.plan.JoinDesc in project hive by apache.

the class SkewJoinHandler method initiliaze.

public void initiliaze(Configuration hconf) {
    this.hconf = hconf;
    JoinDesc desc = joinOp.getConf();
    skewKeyDefinition = desc.getSkewKeyDefinition();
    skewKeysTableObjectInspector = new HashMap<Byte, StructObjectInspector>(numAliases);
    tblDesc = desc.getSkewKeysValuesTables();
    tblSerializers = new HashMap<Byte, AbstractSerDe>(numAliases);
    bigKeysExistingMap = new HashMap<Byte, Boolean>(numAliases);
    taskId = Utilities.getTaskId(hconf);
    int[][] filterMap = desc.getFilterMap();
    for (int i = 0; i < numAliases; i++) {
        Byte alias = conf.getTagOrder()[i];
        List<ObjectInspector> skewTableKeyInspectors = new ArrayList<ObjectInspector>();
        StructObjectInspector soi = (StructObjectInspector) joinOp.inputObjInspectors[alias];
        StructField sf = soi.getStructFieldRef(Utilities.ReduceField.KEY.toString());
        List<? extends StructField> keyFields = ((StructObjectInspector) sf.getFieldObjectInspector()).getAllStructFieldRefs();
        int keyFieldSize = keyFields.size();
        for (int k = 0; k < keyFieldSize; k++) {
            skewTableKeyInspectors.add(keyFields.get(k).getFieldObjectInspector());
        }
        TableDesc joinKeyDesc = desc.getKeyTableDesc();
        List<String> keyColNames = Utilities.getColumnNames(joinKeyDesc.getProperties());
        StructObjectInspector structTblKeyInpector = ObjectInspectorFactory.getStandardStructObjectInspector(keyColNames, skewTableKeyInspectors);
        try {
            AbstractSerDe serializer = (AbstractSerDe) ReflectionUtils.newInstance(tblDesc.get(alias).getSerDeClass(), null);
            serializer.initialize(null, tblDesc.get(alias).getProperties(), null);
            tblSerializers.put((byte) i, serializer);
        } catch (SerDeException e) {
            LOG.error("Skewjoin will be disabled due to " + e.getMessage(), e);
            joinOp.handleSkewJoin = false;
            break;
        }
        boolean hasFilter = filterMap != null && filterMap[i] != null;
        TableDesc valTblDesc = JoinUtil.getSpillTableDesc(alias, joinOp.spillTableDesc, conf, !hasFilter);
        List<String> valColNames = new ArrayList<String>();
        if (valTblDesc != null) {
            valColNames = Utilities.getColumnNames(valTblDesc.getProperties());
        }
        StructObjectInspector structTblValInpector = ObjectInspectorFactory.getStandardStructObjectInspector(valColNames, joinOp.joinValuesStandardObjectInspectors[i]);
        StructObjectInspector structTblInpector = ObjectInspectorFactory.getUnionStructObjectInspector(Arrays.asList(structTblValInpector, structTblKeyInpector));
        skewKeysTableObjectInspector.put((byte) i, structTblInpector);
    }
    // reset rowcontainer's serde, objectinspector, and tableDesc.
    for (int i = 0; i < numAliases; i++) {
        Byte alias = conf.getTagOrder()[i];
        RowContainer<ArrayList<Object>> rc = (RowContainer) joinOp.storage[i];
        if (rc != null) {
            rc.setSerDe(tblSerializers.get((byte) i), skewKeysTableObjectInspector.get((byte) i));
            rc.setTableDesc(tblDesc.get(alias));
        }
    }
}

Example 4 with JoinDesc

use of org.apache.hadoop.hive.ql.plan.JoinDesc in project hive by apache.

the class MapJoinProcessor method checkFullOuterMapJoinCompatible.

private static boolean checkFullOuterMapJoinCompatible(HiveConf hiveConf, JoinOperator joinOp) throws SemanticException {
    JoinDesc joinDesc = joinOp.getConf();
    // Make sure all key and value expressions are columns.
    for (Entry<Byte, List<ExprNodeDesc>> mapEntry : joinDesc.getExprs().entrySet()) {
        List<ExprNodeDesc> exprList = mapEntry.getValue();
        for (ExprNodeDesc expr : exprList) {
            if (!(expr instanceof ExprNodeColumnDesc)) {
                LOG.debug("FULL OUTER MapJoin: only column expressions are supported " + expr.toString());
                return false;
            }
        }
    }
    // Check for supported key data types.
    Byte[] order = joinDesc.getTagOrder();
    ExprNodeDesc[][] joinKeysArray = joinDesc.getJoinKeys();
    for (int i = 0; i < order.length; i++) {
        byte pos = order[i];
        ExprNodeDesc[] keyExprs = joinKeysArray[pos];
        for (ExprNodeDesc keyExpr : keyExprs) {
            TypeInfo typeInfo = keyExpr.getTypeInfo();
            // the same check used in Tez HashTableLoader.
            if (!MapJoinKey.isSupportedField(typeInfo)) {
                LOG.debug("FULL OUTER MapJoin not enabled: key type {} not supported", typeInfo);
                return false;
            }
        }
    }
    if (onExpressionHasNullSafes(joinDesc)) {
        LOG.debug("FULL OUTER MapJoin not enabled: nullsafe not supported");
        return false;
    }
    boolean isVectorizationMapJoinNativeEnabled = HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVE_VECTORIZATION_MAPJOIN_NATIVE_ENABLED);
    boolean isHybridHashJoin = HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEUSEHYBRIDGRACEHASHJOIN);
    if (isVectorizationMapJoinNativeEnabled && isHybridHashJoin) {
        LOG.debug("FULL OUTER MapJoin not enabled: Native Vector MapJoin and Hybrid Grace not supported");
        return false;
    }
    if (joinDesc.getResidualFilterExprs() != null && joinDesc.getResidualFilterExprs().size() != 0) {
        LOG.debug("FULL OUTER MapJoin not enabled: non-equi joins not supported");
        return false;
    }
    return true;
}

Example 5 with JoinDesc

use of org.apache.hadoop.hive.ql.plan.JoinDesc in project hive by apache.

the class TopNKeyPushdownProcessor method pushDownThroughJoin.

// Only push down through Left Outer Join is supported.
// Right and Full Outer Join support will be added in a follow up patch.
private void pushDownThroughJoin(TopNKeyOperator topNKey) throws SemanticException {
    CommonJoinOperator<? extends JoinDesc> parent = (CommonJoinOperator<? extends JoinDesc>) topNKey.getParentOperators().get(0);
    JoinDesc joinDesc = parent.getConf();
    JoinCondDesc[] joinConds = joinDesc.getConds();
    JoinCondDesc firstJoinCond = joinConds[0];
    for (JoinCondDesc joinCond : joinConds) {
        if (!firstJoinCond.equals(joinCond)) {
            return;
        }
    }
    if (firstJoinCond.getType() == JoinDesc.LEFT_OUTER_JOIN) {
        pushdownThroughLeftOuterJoin(topNKey);
    } else if (firstJoinCond.getType() == JoinDesc.INNER_JOIN && joinDesc.isPkFkJoin()) {
        pushdownInnerJoin(topNKey, joinDesc.getFkJoinTableIndex(), joinDesc.isNonFkSideIsFiltered());
    }
}