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

Example 66 with SemanticGraphWalker

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

the class TezCompiler method runTopNKeyOptimization.

private static void runTopNKeyOptimization(OptimizeTezProcContext procCtx) throws SemanticException {
    if (!procCtx.conf.getBoolVar(ConfVars.HIVE_OPTIMIZE_TOPNKEY)) {
        return;
    }
    Map<SemanticRule, SemanticNodeProcessor> opRules = new LinkedHashMap<SemanticRule, SemanticNodeProcessor>();
    opRules.put(new RuleRegExp("Top n key optimization", ReduceSinkOperator.getOperatorName() + "%"), new TopNKeyProcessor(HiveConf.getIntVar(procCtx.conf, HiveConf.ConfVars.HIVE_MAX_TOPN_ALLOWED), HiveConf.getFloatVar(procCtx.conf, ConfVars.HIVE_TOPN_EFFICIENCY_THRESHOLD), HiveConf.getIntVar(procCtx.conf, ConfVars.HIVE_TOPN_EFFICIENCY_CHECK_BATCHES), HiveConf.getIntVar(procCtx.conf, ConfVars.HIVE_TOPN_MAX_NUMBER_OF_PARTITIONS)));
    opRules.put(new RuleRegExp("Top n key pushdown", TopNKeyOperator.getOperatorName() + "%"), new TopNKeyPushdownProcessor());
    // 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(procCtx.parseContext.getTopOps().values());
    SemanticGraphWalker ogw = new DefaultGraphWalker(disp);
    ogw.startWalking(topNodes, null);
}

Example 67 with SemanticGraphWalker

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

the class TezCompiler method runStatsDependentOptimizations.

private void runStatsDependentOptimizations(OptimizeTezProcContext procCtx) throws SemanticException {
    // Sequence of TableScan operators to be walked
    Deque<Operator<?>> deque = new LinkedList<Operator<?>>();
    deque.addAll(procCtx.parseContext.getTopOps().values());
    // create a walker which walks the tree in a DFS manner while maintaining
    // the operator stack.
    Map<SemanticRule, SemanticNodeProcessor> opRules = new LinkedHashMap<SemanticRule, SemanticNodeProcessor>();
    opRules.put(new RuleRegExp("Set parallelism - ReduceSink", ReduceSinkOperator.getOperatorName() + "%"), new SetReducerParallelism());
    opRules.put(new RuleRegExp("Convert Join to Map-join", JoinOperator.getOperatorName() + "%"), new ConvertJoinMapJoin());
    if (procCtx.conf.getBoolVar(ConfVars.HIVEMAPAGGRHASHMINREDUCTIONSTATSADJUST)) {
        opRules.put(new RuleRegExp("Set min reduction - GBy (Hash)", GroupByOperator.getOperatorName() + "%"), new SetHashGroupByMinReduction());
    }
    // 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(procCtx.parseContext.getTopOps().values());
    SemanticGraphWalker ogw = new ForwardWalker(disp);
    ogw.startWalking(topNodes, null);
}

Example 68 with SemanticGraphWalker

use of org.apache.hadoop.hive.ql.lib.SemanticGraphWalker 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");
}

Example 69 with SemanticGraphWalker

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

the class TezCompiler method removeSemiJoinIfNoStats.

private void removeSemiJoinIfNoStats(OptimizeTezProcContext procCtx) throws SemanticException {
    Map<SemanticRule, SemanticNodeProcessor> opRules = new LinkedHashMap<SemanticRule, SemanticNodeProcessor>();
    opRules.put(new RuleRegExp("R1", GroupByOperator.getOperatorName() + "%" + ReduceSinkOperator.getOperatorName() + "%" + GroupByOperator.getOperatorName() + "%" + ReduceSinkOperator.getOperatorName() + "%"), new SemiJoinRemovalProc(true, false));
    SemiJoinRemovalContext ctx = new SemiJoinRemovalContext(procCtx.parseContext);
    SemanticDispatcher disp = new DefaultRuleDispatcher(null, opRules, ctx);
    List<Node> topNodes = new ArrayList<Node>();
    topNodes.addAll(procCtx.parseContext.getTopOps().values());
    SemanticGraphWalker ogw = new PreOrderOnceWalker(disp);
    ogw.startWalking(topNodes, null);
}

Example 70 with SemanticGraphWalker

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

the class TezCompiler method runDynamicPartitionPruning.

private void runDynamicPartitionPruning(OptimizeTezProcContext procCtx) throws SemanticException {
    if (!procCtx.conf.getBoolVar(ConfVars.TEZ_DYNAMIC_PARTITION_PRUNING)) {
        return;
    }
    // Sequence of TableScan operators to be walked
    Deque<Operator<?>> deque = new LinkedList<Operator<?>>();
    deque.addAll(procCtx.parseContext.getTopOps().values());
    Map<SemanticRule, SemanticNodeProcessor> opRules = new LinkedHashMap<SemanticRule, SemanticNodeProcessor>();
    opRules.put(new RuleRegExp(new String("Dynamic Partition Pruning"), FilterOperator.getOperatorName() + "%"), new DynamicPartitionPruningOptimization());
    // 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(procCtx.parseContext.getTopOps().values());
    SemanticGraphWalker ogw = new ForwardWalker(disp);
    ogw.startWalking(topNodes, null);
}