Examples with SortBucketJoinProcCtx org.apache.hadoop.hive.ql.optimizer.SortBucketJoinProcCtx used on opensource projects

Example 1 with SortBucketJoinProcCtx

use of org.apache.hadoop.hive.ql.optimizer.SortBucketJoinProcCtx in project hive by apache.

the class SparkSMBJoinHintOptimizer method process.

@Override
public Object process(Node nd, Stack<Node> stack, NodeProcessorCtx procCtx, Object... nodeOutputs) throws SemanticException {
    MapJoinOperator mapJoinOp = (MapJoinOperator) nd;
    SortBucketJoinProcCtx smbJoinContext = (SortBucketJoinProcCtx) procCtx;
    boolean convert = canConvertBucketMapJoinToSMBJoin(mapJoinOp, stack, smbJoinContext, nodeOutputs);
    // and sort merge bucketed mapjoin cannot be performed
    if (!convert && pGraphContext.getConf().getBoolVar(HiveConf.ConfVars.HIVEENFORCESORTMERGEBUCKETMAPJOIN)) {
        throw new SemanticException(ErrorMsg.SORTMERGE_MAPJOIN_FAILED.getMsg());
    }
    if (convert) {
        removeSmallTableReduceSink(mapJoinOp);
        convertBucketMapJoinToSMBJoin(mapJoinOp, smbJoinContext);
    }
    return null;
}

Example 2 with SortBucketJoinProcCtx

use of org.apache.hadoop.hive.ql.optimizer.SortBucketJoinProcCtx in project hive by apache.

the class SparkJoinHintOptimizer method process.

@Override
public Object process(Node nd, Stack<Node> stack, NodeProcessorCtx procCtx, Object... nodeOutputs) throws SemanticException {
    OptimizeSparkProcContext context = (OptimizeSparkProcContext) procCtx;
    HiveConf hiveConf = context.getParseContext().getConf();
    // Convert from mapjoin to bucket map join if enabled.
    if (hiveConf.getBoolVar(HiveConf.ConfVars.HIVEOPTBUCKETMAPJOIN) || hiveConf.getBoolVar(HiveConf.ConfVars.HIVEOPTSORTMERGEBUCKETMAPJOIN)) {
        BucketJoinProcCtx bjProcCtx = new BucketJoinProcCtx(hiveConf);
        bucketMapJoinOptimizer.process(nd, stack, bjProcCtx, nodeOutputs);
    }
    // Convert from bucket map join to sort merge bucket map join if enabled.
    if (hiveConf.getBoolVar(HiveConf.ConfVars.HIVEOPTSORTMERGEBUCKETMAPJOIN)) {
        SortBucketJoinProcCtx smbJoinCtx = new SortBucketJoinProcCtx(hiveConf);
        smbMapJoinOptimizer.process(nd, stack, smbJoinCtx, nodeOutputs);
    }
    return null;
}

Example 3 with SortBucketJoinProcCtx

use of org.apache.hadoop.hive.ql.optimizer.SortBucketJoinProcCtx in project hive by apache.

the class SparkSortMergeJoinOptimizer method process.

@Override
public Object process(Node nd, Stack<Node> stack, NodeProcessorCtx procCtx, Object... nodeOutputs) throws SemanticException {
    JoinOperator joinOp = (JoinOperator) nd;
    HiveConf conf = ((OptimizeSparkProcContext) procCtx).getParseContext().getConf();
    if (!conf.getBoolVar(HiveConf.ConfVars.HIVE_AUTO_SORTMERGE_JOIN)) {
        return null;
    }
    SortBucketJoinProcCtx smbJoinContext = new SortBucketJoinProcCtx(conf);
    boolean convert = canConvertJoinToSMBJoin(joinOp, smbJoinContext, pGraphContext, stack);
    if (convert) {
        return convertJoinToSMBJoinAndReturn(joinOp, smbJoinContext);
    }
    return null;
}