Examples with CompositeProcessor org.apache.hadoop.hive.ql.lib.CompositeProcessor used on opensource projects

Example 1 with CompositeProcessor

use of org.apache.hadoop.hive.ql.lib.CompositeProcessor in project hive by apache.

the class TezCompiler method generateTaskTree.

@Override
protected void generateTaskTree(List<Task<? extends Serializable>> rootTasks, ParseContext pCtx, List<Task<MoveWork>> mvTask, Set<ReadEntity> inputs, Set<WriteEntity> outputs) throws SemanticException {
    PerfLogger perfLogger = SessionState.getPerfLogger();
    perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.TEZ_COMPILER);
    ParseContext tempParseContext = getParseContext(pCtx, rootTasks);
    GenTezUtils utils = new GenTezUtils();
    GenTezWork genTezWork = new GenTezWork(utils);
    GenTezProcContext procCtx = new GenTezProcContext(conf, tempParseContext, mvTask, rootTasks, inputs, outputs);
    // create a walker which walks the tree in a DFS manner while maintaining
    // the operator stack.
    // The dispatcher generates the plan from the operator tree
    Map<Rule, NodeProcessor> opRules = new LinkedHashMap<Rule, NodeProcessor>();
    opRules.put(new RuleRegExp("Split Work - ReduceSink", ReduceSinkOperator.getOperatorName() + "%"), genTezWork);
    opRules.put(new RuleRegExp("No more walking on ReduceSink-MapJoin", MapJoinOperator.getOperatorName() + "%"), new ReduceSinkMapJoinProc());
    opRules.put(new RuleRegExp("Recognize a Sorted Merge Join operator to setup the right edge and" + " stop traversing the DummyStore-MapJoin", CommonMergeJoinOperator.getOperatorName() + "%"), new MergeJoinProc());
    opRules.put(new RuleRegExp("Split Work + Move/Merge - FileSink", FileSinkOperator.getOperatorName() + "%"), new CompositeProcessor(new FileSinkProcessor(), genTezWork));
    opRules.put(new RuleRegExp("Split work - DummyStore", DummyStoreOperator.getOperatorName() + "%"), genTezWork);
    opRules.put(new RuleRegExp("Handle Potential Analyze Command", TableScanOperator.getOperatorName() + "%"), new ProcessAnalyzeTable(utils));
    opRules.put(new RuleRegExp("Remember union", UnionOperator.getOperatorName() + "%"), new UnionProcessor());
    opRules.put(new RuleRegExp("AppMasterEventOperator", AppMasterEventOperator.getOperatorName() + "%"), new AppMasterEventProcessor());
    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    Dispatcher disp = new DefaultRuleDispatcher(null, opRules, procCtx);
    List<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(pCtx.getTopOps().values());
    GraphWalker ogw = new GenTezWorkWalker(disp, procCtx);
    ogw.startWalking(topNodes, null);
    // we need to specify the reserved memory for each work that contains Map Join
    for (List<BaseWork> baseWorkList : procCtx.mapJoinWorkMap.values()) {
        for (BaseWork w : baseWorkList) {
            // work should be the smallest unit for memory allocation
            w.setReservedMemoryMB((int) (conf.getLongVar(ConfVars.HIVECONVERTJOINNOCONDITIONALTASKTHRESHOLD) / (1024 * 1024)));
        }
    }
    // we need to clone some operator plans and remove union operators still
    int indexForTezUnion = 0;
    for (BaseWork w : procCtx.workWithUnionOperators) {
        GenTezUtils.removeUnionOperators(procCtx, w, indexForTezUnion++);
    }
    // then we make sure the file sink operators are set up right
    for (FileSinkOperator fileSink : procCtx.fileSinkSet) {
        GenTezUtils.processFileSink(procCtx, fileSink);
    }
    // Connect any edges required for min/max pushdown
    if (pCtx.getRsToRuntimeValuesInfoMap().size() > 0) {
        for (ReduceSinkOperator rs : pCtx.getRsToRuntimeValuesInfoMap().keySet()) {
            // Process min/max
            GenTezUtils.processDynamicSemiJoinPushDownOperator(procCtx, pCtx.getRsToRuntimeValuesInfoMap().get(rs), rs);
        }
    }
    // and finally we hook up any events that need to be sent to the tez AM
    LOG.debug("There are " + procCtx.eventOperatorSet.size() + " app master events.");
    for (AppMasterEventOperator event : procCtx.eventOperatorSet) {
        LOG.debug("Handling AppMasterEventOperator: " + event);
        GenTezUtils.processAppMasterEvent(procCtx, event);
    }
    perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.TEZ_COMPILER, "generateTaskTree");
}

Example 2 with CompositeProcessor

use of org.apache.hadoop.hive.ql.lib.CompositeProcessor in project hive by apache.

the class SparkCompiler method generateTaskTreeHelper.

private void generateTaskTreeHelper(GenSparkProcContext procCtx, List<Node> topNodes) throws SemanticException {
    // create a walker which walks the tree in a DFS manner while maintaining
    // the operator stack. The dispatcher generates the plan from the operator tree
    Map<SemanticRule, SemanticNodeProcessor> opRules = new LinkedHashMap<SemanticRule, SemanticNodeProcessor>();
    GenSparkWork genSparkWork = new GenSparkWork(GenSparkUtils.getUtils());
    opRules.put(new RuleRegExp("Split Work - ReduceSink", ReduceSinkOperator.getOperatorName() + "%"), genSparkWork);
    opRules.put(new RuleRegExp("Split Work - SparkPartitionPruningSink", SparkPartitionPruningSinkOperator.getOperatorName() + "%"), genSparkWork);
    opRules.put(new TypeRule(MapJoinOperator.class), new SparkReduceSinkMapJoinProc());
    opRules.put(new RuleRegExp("Split Work + Move/Merge - FileSink", FileSinkOperator.getOperatorName() + "%"), new CompositeProcessor(new SparkFileSinkProcessor(), genSparkWork));
    opRules.put(new RuleRegExp("Handle Analyze Command", TableScanOperator.getOperatorName() + "%"), new SparkProcessAnalyzeTable(GenSparkUtils.getUtils()));
    opRules.put(new RuleRegExp("Remember union", UnionOperator.getOperatorName() + "%"), new SemanticNodeProcessor() {

        @Override
        public Object process(Node n, Stack<Node> s, NodeProcessorCtx procCtx, Object... os) throws SemanticException {
            GenSparkProcContext context = (GenSparkProcContext) procCtx;
            UnionOperator union = (UnionOperator) n;
            // simply need to remember that we've seen a union.
            context.currentUnionOperators.add(union);
            return null;
        }
    });
    /**
     *  SMB join case:   (Big)   (Small)  (Small)
     *                     TS       TS       TS
     *                      \       |       /
     *                       \      DS     DS
     *                         \   |    /
     *                         SMBJoinOP
     *
     * Some of the other processors are expecting only one traversal beyond SMBJoinOp.
     * We need to traverse from the big-table path only, and stop traversing on the
     * small-table path once we reach SMBJoinOp.
     * Also add some SMB join information to the context, so we can properly annotate
     * the MapWork later on.
     */
    opRules.put(new TypeRule(SMBMapJoinOperator.class), new SemanticNodeProcessor() {

        @Override
        public Object process(Node currNode, Stack<Node> stack, NodeProcessorCtx procCtx, Object... os) throws SemanticException {
            GenSparkProcContext context = (GenSparkProcContext) procCtx;
            SMBMapJoinOperator currSmbNode = (SMBMapJoinOperator) currNode;
            SparkSMBMapJoinInfo smbMapJoinCtx = context.smbMapJoinCtxMap.get(currSmbNode);
            if (smbMapJoinCtx == null) {
                smbMapJoinCtx = new SparkSMBMapJoinInfo();
                context.smbMapJoinCtxMap.put(currSmbNode, smbMapJoinCtx);
            }
            for (Node stackNode : stack) {
                if (stackNode instanceof DummyStoreOperator) {
                    // If coming from small-table side, do some book-keeping, and skip traversal.
                    smbMapJoinCtx.smallTableRootOps.add(context.currentRootOperator);
                    return true;
                }
            }
            // If coming from big-table side, do some book-keeping, and continue traversal
            smbMapJoinCtx.bigTableRootOp = context.currentRootOperator;
            return false;
        }
    });
    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    SemanticDispatcher disp = new DefaultRuleDispatcher(null, opRules, procCtx);
    SemanticGraphWalker ogw = new GenSparkWorkWalker(disp, procCtx);
    ogw.startWalking(topNodes, null);
}

Example 3 with CompositeProcessor

use of org.apache.hadoop.hive.ql.lib.CompositeProcessor in project hive by apache.

the class TezCompiler method generateTaskTree.

@Override
protected void generateTaskTree(List<Task<?>> rootTasks, ParseContext pCtx, List<Task<MoveWork>> mvTask, Set<ReadEntity> inputs, Set<WriteEntity> outputs) throws SemanticException {
    PerfLogger perfLogger = SessionState.getPerfLogger();
    perfLogger.perfLogBegin(this.getClass().getName(), PerfLogger.TEZ_COMPILER);
    ParseContext tempParseContext = getParseContext(pCtx, rootTasks);
    GenTezUtils utils = new GenTezUtils();
    GenTezWork genTezWork = new GenTezWork(utils);
    GenTezProcContext procCtx = new GenTezProcContext(conf, tempParseContext, mvTask, rootTasks, inputs, outputs);
    // create a walker which walks the tree in a DFS manner while maintaining
    // the operator stack.
    // The dispatcher generates the plan from the operator tree
    Map<SemanticRule, SemanticNodeProcessor> opRules = new LinkedHashMap<SemanticRule, SemanticNodeProcessor>();
    opRules.put(new RuleRegExp("Split Work - ReduceSink", ReduceSinkOperator.getOperatorName() + "%"), genTezWork);
    opRules.put(new RuleRegExp("No more walking on ReduceSink-MapJoin", MapJoinOperator.getOperatorName() + "%"), new ReduceSinkMapJoinProc());
    opRules.put(new RuleRegExp("Recognize a Sorted Merge Join operator to setup the right edge and" + " stop traversing the DummyStore-MapJoin", CommonMergeJoinOperator.getOperatorName() + "%"), new MergeJoinProc());
    opRules.put(new RuleRegExp("Split Work + Move/Merge - FileSink", FileSinkOperator.getOperatorName() + "%"), new CompositeProcessor(new FileSinkProcessor(), genTezWork));
    opRules.put(new RuleRegExp("Split work - DummyStore", DummyStoreOperator.getOperatorName() + "%"), genTezWork);
    opRules.put(new RuleRegExp("Handle Potential Analyze Command", TableScanOperator.getOperatorName() + "%"), new ProcessAnalyzeTable(utils));
    opRules.put(new RuleRegExp("Remember union", UnionOperator.getOperatorName() + "%"), new UnionProcessor());
    opRules.put(new RuleRegExp("AppMasterEventOperator", AppMasterEventOperator.getOperatorName() + "%"), new AppMasterEventProcessor());
    // The dispatcher fires the processor corresponding to the closest matching
    // rule and passes the context along
    SemanticDispatcher disp = new DefaultRuleDispatcher(null, opRules, procCtx);
    List<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(pCtx.getTopOps().values());
    SemanticGraphWalker ogw = new GenTezWorkWalker(disp, procCtx);
    ogw.startWalking(topNodes, null);
    // we need to specify the reserved memory for each work that contains Map Join
    for (List<BaseWork> baseWorkList : procCtx.mapJoinWorkMap.values()) {
        for (BaseWork w : baseWorkList) {
            // work should be the smallest unit for memory allocation
            w.setReservedMemoryMB((int) (conf.getLongVar(ConfVars.HIVECONVERTJOINNOCONDITIONALTASKTHRESHOLD) / (1024 * 1024)));
        }
    }
    // we need to clone some operator plans and remove union operators still
    int indexForTezUnion = 0;
    for (BaseWork w : procCtx.workWithUnionOperators) {
        GenTezUtils.removeUnionOperators(procCtx, w, indexForTezUnion++);
    }
    // then we make sure the file sink operators are set up right
    for (FileSinkOperator fileSink : procCtx.fileSinkSet) {
        GenTezUtils.processFileSink(procCtx, fileSink);
    }
    // Connect any edges required for min/max pushdown
    if (pCtx.getRsToRuntimeValuesInfoMap().size() > 0) {
        for (ReduceSinkOperator rs : pCtx.getRsToRuntimeValuesInfoMap().keySet()) {
            // Process min/max
            GenTezUtils.processDynamicSemiJoinPushDownOperator(procCtx, pCtx.getRsToRuntimeValuesInfoMap().get(rs), rs);
        }
    }
    // and finally we hook up any events that need to be sent to the tez AM
    LOG.debug("There are " + procCtx.eventOperatorSet.size() + " app master events.");
    for (AppMasterEventOperator event : procCtx.eventOperatorSet) {
        LOG.debug("Handling AppMasterEventOperator: " + event);
        GenTezUtils.processAppMasterEvent(procCtx, event);
    }
    perfLogger.perfLogEnd(this.getClass().getName(), PerfLogger.TEZ_COMPILER, "generateTaskTree");
}