Search in sources :

Example 31 with ColumnVector

use of org.apache.hadoop.hive.ql.exec.vector.ColumnVector in project hive by apache.

the class VectorMapJoinInnerGenerateResultOperator method innerPerBatchSetup.

/*
   * Inner join (hash map).
   */
/**
   * Do the per-batch setup for an inner join.
   */
protected void innerPerBatchSetup(VectorizedRowBatch batch) {
    for (int column : smallTableOutputVectorColumns) {
        ColumnVector smallTableColumn = batch.cols[column];
        smallTableColumn.reset();
    }
}
Also used : ColumnVector(org.apache.hadoop.hive.ql.exec.vector.ColumnVector)

Example 32 with ColumnVector

use of org.apache.hadoop.hive.ql.exec.vector.ColumnVector in project hive by apache.

the class VectorMapJoinOuterGenerateResultOperator method generateOuterNullsRepeatedAll.

/**
   * Generate the non-match outer join output results for the whole repeating vectorized
   * row batch.
   *
   * Each row will get nulls for all small table values.
   *
   * @param batch
   *          The big table batch.
   */
protected void generateOuterNullsRepeatedAll(VectorizedRowBatch batch) throws HiveException {
    for (int column : smallTableOutputVectorColumns) {
        ColumnVector colVector = batch.cols[column];
        colVector.noNulls = false;
        colVector.isNull[0] = true;
        colVector.isRepeating = true;
    }
    // as null, too.
    for (int column : bigTableOuterKeyOutputVectorColumns) {
        ColumnVector colVector = batch.cols[column];
        colVector.noNulls = false;
        colVector.isNull[0] = true;
        colVector.isRepeating = true;
    }
}
Also used : ColumnVector(org.apache.hadoop.hive.ql.exec.vector.ColumnVector)

Example 33 with ColumnVector

use of org.apache.hadoop.hive.ql.exec.vector.ColumnVector in project hive by apache.

the class VectorMapJoinOuterGenerateResultOperator method generateOuterNulls.

/**
    * Generate the non matching outer join output results for one vectorized row batch.
    *
    * For each non matching row specified by parameter, generate nulls for the small table results.
    *
    * @param batch
    *          The big table batch with any matching and any non matching rows both as
    *          selected in use.
    * @param noMatchs
    *          A subset of the rows of the batch that are non matches.
    * @param noMatchSize
    *          Number of non matches in noMatchs.
    */
protected void generateOuterNulls(VectorizedRowBatch batch, int[] noMatchs, int noMatchSize) throws IOException, HiveException {
    for (int i = 0; i < noMatchSize; i++) {
        int batchIndex = noMatchs[i];
        // key as null, too.
        for (int column : bigTableOuterKeyOutputVectorColumns) {
            ColumnVector colVector = batch.cols[column];
            colVector.noNulls = false;
            colVector.isNull[batchIndex] = true;
        }
        // Small table values are set to null.
        for (int column : smallTableOutputVectorColumns) {
            ColumnVector colVector = batch.cols[column];
            colVector.noNulls = false;
            colVector.isNull[batchIndex] = true;
        }
    }
}
Also used : ColumnVector(org.apache.hadoop.hive.ql.exec.vector.ColumnVector)

Example 34 with ColumnVector

use of org.apache.hadoop.hive.ql.exec.vector.ColumnVector in project hive by apache.

the class VectorMapJoinOuterMultiKeyOperator method process.

//---------------------------------------------------------------------------
// Process Multi-Key Outer 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++;
        final int inputLogicalSize = batch.size;
        if (inputLogicalSize == 0) {
            if (isLogDebugEnabled) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " empty");
            }
            return;
        }
        // Do the per-batch setup for an outer join.
        outerPerBatchSetup(batch);
        // For outer join, remember our input rows before ON expression filtering or before
        // hash table matching so we can generate results for all rows (matching and non matching)
        // later.
        boolean inputSelectedInUse = batch.selectedInUse;
        if (inputSelectedInUse) {
            // if (!verifyMonotonicallyIncreasing(batch.selected, batch.size)) {
            //   throw new HiveException("batch.selected is not in sort order and unique");
            // }
            System.arraycopy(batch.selected, 0, inputSelected, 0, inputLogicalSize);
        }
        // Filtering for outer join just removes rows available for hash table matching.
        boolean someRowsFilteredOut = false;
        if (bigTableFilterExpressions.length > 0) {
            // Since the input
            for (VectorExpression ve : bigTableFilterExpressions) {
                ve.evaluate(batch);
            }
            someRowsFilteredOut = (batch.size != inputLogicalSize);
            if (isLogDebugEnabled) {
                if (batch.selectedInUse) {
                    if (inputSelectedInUse) {
                        LOG.debug(CLASS_NAME + " inputSelected " + intArrayToRangesString(inputSelected, inputLogicalSize) + " filtered batch.selected " + intArrayToRangesString(batch.selected, batch.size));
                    } else {
                        LOG.debug(CLASS_NAME + " inputLogicalSize " + inputLogicalSize + " filtered batch.selected " + intArrayToRangesString(batch.selected, batch.size));
                    }
                }
            }
        }
        // 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.
        // Also determine if any nulls are present since for a join that means no match.
        boolean allKeyInputColumnsRepeating;
        // Only valid if allKeyInputColumnsRepeating is true.
        boolean someKeyInputColumnIsNull = false;
        if (bigTableKeyColumnMap.length == 0) {
            allKeyInputColumnsRepeating = false;
        } else {
            allKeyInputColumnsRepeating = true;
            for (int i = 0; i < bigTableKeyColumnMap.length; i++) {
                ColumnVector colVector = batch.cols[bigTableKeyColumnMap[i]];
                if (!colVector.isRepeating) {
                    allKeyInputColumnsRepeating = false;
                    break;
                }
                if (!colVector.noNulls && colVector.isNull[0]) {
                    someKeyInputColumnIsNull = true;
                }
            }
        }
        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.
         */
            JoinUtil.JoinResult joinResult;
            if (batch.size == 0) {
                // Whole repeated key batch was filtered out.
                joinResult = JoinUtil.JoinResult.NOMATCH;
            } else if (someKeyInputColumnIsNull) {
                // Any (repeated) null key column is no match for whole batch.
                joinResult = JoinUtil.JoinResult.NOMATCH;
            } else {
                // All key input columns are repeating.  Generate key once.  Lookup once.
                keyVectorSerializeWrite.setOutput(currentKeyOutput);
                keyVectorSerializeWrite.serializeWrite(batch, 0);
                byte[] keyBytes = currentKeyOutput.getData();
                int keyLength = currentKeyOutput.getLength();
                joinResult = hashMap.lookup(keyBytes, 0, keyLength, hashMapResults[0]);
            }
            if (isLogDebugEnabled) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " repeated joinResult " + joinResult.name());
            }
            finishOuterRepeated(batch, joinResult, hashMapResults[0], someRowsFilteredOut, inputSelectedInUse, inputLogicalSize);
        } else {
            if (isLogDebugEnabled) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " non-repeated");
            }
            int[] selected = batch.selected;
            boolean selectedInUse = batch.selectedInUse;
            int hashMapResultCount = 0;
            int allMatchCount = 0;
            int equalKeySeriesCount = 0;
            int spillCount = 0;
            boolean atLeastOneNonMatch = someRowsFilteredOut;
            /*
         * 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 < batch.size; logical++) {
                int batchIndex = (selectedInUse ? selected[logical] : logical);
                // VectorizedBatchUtil.debugDisplayOneRow(batch, batchIndex, taskName + ", " + getOperatorId() + " candidate " + CLASS_NAME + " batch");
                /*
           * Multi-Key outer null detection.
           */
                // Generate binary sortable key for current row in vectorized row batch.
                keyVectorSerializeWrite.setOutput(currentKeyOutput);
                keyVectorSerializeWrite.serializeWrite(batch, batchIndex);
                if (keyVectorSerializeWrite.getHasAnyNulls()) {
                    // Have that the NULL does not interfere with the current equal key series, if there
                    // is one. We do not set saveJoinResult.
                    //
                    //    Let a current MATCH equal key series keep going, or
                    //    Let a current SPILL equal key series keep going, or
                    //    Let a current NOMATCH keep not matching.
                    atLeastOneNonMatch = true;
                // LOG.debug(CLASS_NAME + " logical " + logical + " batchIndex " + batchIndex + " NULL");
                } else {
                    if (!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;
                            }
                        }
                        // 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:
                                atLeastOneNonMatch = true;
                                // 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 (!verifyMonotonicallyIncreasing(allMatchs, allMatchCount)) {
                //   throw new HiveException("allMatchs is not in sort order and unique");
                // }
                }
            }
            if (haveSaveKey) {
                // Update our counts for the last key.
                switch(saveJoinResult) {
                    case MATCH:
                        hashMapResultCount++;
                        equalKeySeriesCount++;
                        break;
                    case SPILL:
                        hashMapResultCount++;
                        break;
                    case NOMATCH:
                        break;
                }
            }
            if (isLogDebugEnabled) {
                LOG.debug(CLASS_NAME + " batch #" + batchCounter + " 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)) + " atLeastOneNonMatch " + atLeastOneNonMatch + " inputSelectedInUse " + inputSelectedInUse + " inputLogicalSize " + inputLogicalSize + " spills " + intArrayToRangesString(spills, spillCount) + " spillHashMapResultIndices " + intArrayToRangesString(spillHashMapResultIndices, spillCount) + " hashMapResults " + Arrays.toString(Arrays.copyOfRange(hashMapResults, 0, hashMapResultCount)));
            }
            // We will generate results for all matching and non-matching rows.
            finishOuter(batch, allMatchCount, equalKeySeriesCount, atLeastOneNonMatch, inputSelectedInUse, inputLogicalSize, 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);
    }
}
Also used : JoinUtil(org.apache.hadoop.hive.ql.exec.JoinUtil) VectorSerializeRow(org.apache.hadoop.hive.ql.exec.vector.VectorSerializeRow) HiveException(org.apache.hadoop.hive.ql.metadata.HiveException) BinarySortableSerializeWrite(org.apache.hadoop.hive.serde2.binarysortable.fast.BinarySortableSerializeWrite) IOException(java.io.IOException) IOException(java.io.IOException) HiveException(org.apache.hadoop.hive.ql.metadata.HiveException) ColumnVector(org.apache.hadoop.hive.ql.exec.vector.ColumnVector) VectorizedRowBatch(org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch) Output(org.apache.hadoop.hive.serde2.ByteStream.Output) VectorExpression(org.apache.hadoop.hive.ql.exec.vector.expressions.VectorExpression)

Example 35 with ColumnVector

use of org.apache.hadoop.hive.ql.exec.vector.ColumnVector in project hive by apache.

the class VectorUDFArgDesc method getDeferredJavaObject.

public DeferredObject getDeferredJavaObject(int row, VectorizedRowBatch b, int argPosition, VectorExpressionWriter[] writers) {
    if (isConstant()) {
        return this.constObjVal;
    } else {
        // get column
        ColumnVector cv = b.cols[columnNum];
        // write value to object that can be inspected
        Object o;
        try {
            o = writers[argPosition].writeValue(cv, row);
            return new GenericUDF.DeferredJavaObject(o);
        } catch (HiveException e) {
            throw new RuntimeException("Unable to get Java object from VectorizedRowBatch", e);
        }
    }
}
Also used : HiveException(org.apache.hadoop.hive.ql.metadata.HiveException) DeferredObject(org.apache.hadoop.hive.ql.udf.generic.GenericUDF.DeferredObject) ColumnVector(org.apache.hadoop.hive.ql.exec.vector.ColumnVector)

Aggregations

ColumnVector (org.apache.hadoop.hive.ql.exec.vector.ColumnVector)43 LongColumnVector (org.apache.hadoop.hive.ql.exec.vector.LongColumnVector)24 BytesColumnVector (org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector)19 TimestampColumnVector (org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector)14 DoubleColumnVector (org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector)11 VectorizedRowBatch (org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch)9 DecimalColumnVector (org.apache.hadoop.hive.ql.exec.vector.DecimalColumnVector)8 HiveException (org.apache.hadoop.hive.ql.metadata.HiveException)4 TestVectorizedRowBatch (org.apache.hadoop.hive.ql.exec.vector.TestVectorizedRowBatch)3 Output (org.apache.hadoop.hive.serde2.ByteStream.Output)3 BinarySortableSerializeWrite (org.apache.hadoop.hive.serde2.binarysortable.fast.BinarySortableSerializeWrite)3 Test (org.junit.Test)3 ParseException (java.text.ParseException)2 IOException (java.io.IOException)1 Timestamp (java.sql.Timestamp)1 ArrayList (java.util.ArrayList)1 ColumnStreamData (org.apache.hadoop.hive.common.io.encoded.EncodedColumnBatch.ColumnStreamData)1 LlapDataBuffer (org.apache.hadoop.hive.llap.cache.LlapDataBuffer)1 SerDeStripeMetadata (org.apache.hadoop.hive.llap.io.decode.GenericColumnVectorProducer.SerDeStripeMetadata)1 JoinUtil (org.apache.hadoop.hive.ql.exec.JoinUtil)1