Examples with QueryRunner org.apache.druid.query.QueryRunner used on opensource projects

Example 56 with QueryRunner

use of org.apache.druid.query.QueryRunner in project druid by druid-io.

the class TimeCompareBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
    executorService = Execs.multiThreaded(numSegments, "TopNThreadPool");
    setupQueries();
    String schemaName = "basic";
    schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schemaName);
    segmentIntervals = new Interval[numSegments];
    long startMillis = schemaInfo.getDataInterval().getStartMillis();
    long endMillis = schemaInfo.getDataInterval().getEndMillis();
    long partialIntervalMillis = (endMillis - startMillis) / numSegments;
    for (int i = 0; i < numSegments; i++) {
        long partialEndMillis = startMillis + partialIntervalMillis;
        segmentIntervals[i] = Intervals.utc(startMillis, partialEndMillis);
        log.info("Segment [%d] with interval [%s]", i, segmentIntervals[i]);
        startMillis = partialEndMillis;
    }
    incIndexes = new ArrayList<>();
    for (int i = 0; i < numSegments; i++) {
        log.info("Generating rows for segment " + i);
        DataGenerator gen = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED + i, segmentIntervals[i], rowsPerSegment);
        IncrementalIndex incIndex = makeIncIndex();
        for (int j = 0; j < rowsPerSegment; j++) {
            InputRow row = gen.nextRow();
            if (j % 10000 == 0) {
                log.info(j + " rows generated.");
            }
            incIndex.add(row);
        }
        incIndexes.add(incIndex);
    }
    tmpDir = FileUtils.createTempDir();
    log.info("Using temp dir: " + tmpDir.getAbsolutePath());
    qIndexes = new ArrayList<>();
    for (int i = 0; i < numSegments; i++) {
        File indexFile = INDEX_MERGER_V9.persist(incIndexes.get(i), tmpDir, new IndexSpec(), null);
        QueryableIndex qIndex = INDEX_IO.loadIndex(indexFile);
        qIndexes.add(qIndex);
    }
    List<QueryRunner<Result<TopNResultValue>>> singleSegmentRunners = new ArrayList<>();
    QueryToolChest toolChest = topNFactory.getToolchest();
    for (int i = 0; i < numSegments; i++) {
        SegmentId segmentId = SegmentId.dummy("qIndex " + i);
        QueryRunner<Result<TopNResultValue>> runner = QueryBenchmarkUtil.makeQueryRunner(topNFactory, segmentId, new QueryableIndexSegment(qIndexes.get(i), segmentId));
        singleSegmentRunners.add(new PerSegmentOptimizingQueryRunner<>(toolChest.preMergeQueryDecoration(runner), new PerSegmentQueryOptimizationContext(new SegmentDescriptor(segmentIntervals[i], "1", 0))));
    }
    topNRunner = toolChest.postMergeQueryDecoration(new FinalizeResultsQueryRunner<>(toolChest.mergeResults(topNFactory.mergeRunners(executorService, singleSegmentRunners)), toolChest));
    List<QueryRunner<Result<TimeseriesResultValue>>> singleSegmentRunnersT = new ArrayList<>();
    QueryToolChest toolChestT = timeseriesFactory.getToolchest();
    for (int i = 0; i < numSegments; i++) {
        SegmentId segmentId = SegmentId.dummy("qIndex " + i);
        QueryRunner<Result<TimeseriesResultValue>> runner = QueryBenchmarkUtil.makeQueryRunner(timeseriesFactory, segmentId, new QueryableIndexSegment(qIndexes.get(i), segmentId));
        singleSegmentRunnersT.add(new PerSegmentOptimizingQueryRunner<>(toolChestT.preMergeQueryDecoration(runner), new PerSegmentQueryOptimizationContext(new SegmentDescriptor(segmentIntervals[i], "1", 0))));
    }
    timeseriesRunner = toolChestT.postMergeQueryDecoration(new FinalizeResultsQueryRunner<>(toolChestT.mergeResults(timeseriesFactory.mergeRunners(executorService, singleSegmentRunnersT)), toolChestT));
}

Example 57 with QueryRunner

use of org.apache.druid.query.QueryRunner in project druid by druid-io.

the class SearchBenchmark method queryMultiQueryableIndex.

@Benchmark
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.MICROSECONDS)
public void queryMultiQueryableIndex(Blackhole blackhole, QueryableIndexState state) {
    List<QueryRunner<Row>> singleSegmentRunners = new ArrayList<>();
    QueryToolChest toolChest = factory.getToolchest();
    for (int i = 0; i < state.numSegments; i++) {
        String segmentName = "qIndex " + i;
        final QueryRunner<Result<SearchResultValue>> runner = QueryBenchmarkUtil.makeQueryRunner(factory, SegmentId.dummy(segmentName), new QueryableIndexSegment(state.qIndexes.get(i), SegmentId.dummy(segmentName)));
        singleSegmentRunners.add(toolChest.preMergeQueryDecoration(runner));
    }
    QueryRunner theRunner = toolChest.postMergeQueryDecoration(new FinalizeResultsQueryRunner<>(toolChest.mergeResults(factory.mergeRunners(state.executorService, singleSegmentRunners)), toolChest));
    Sequence<Result<SearchResultValue>> queryResult = theRunner.run(QueryPlus.wrap(query), ResponseContext.createEmpty());
    List<Result<SearchResultValue>> results = queryResult.toList();
    blackhole.consume(results);
}

Example 58 with QueryRunner

use of org.apache.druid.query.QueryRunner in project druid by druid-io.

the class GroupByStrategyV2 method mergeResults.

@Override
public Sequence<ResultRow> mergeResults(final QueryRunner<ResultRow> baseRunner, final GroupByQuery query, final ResponseContext responseContext) {
    // Merge streams using ResultMergeQueryRunner, then apply postaggregators, then apply limit (which may
    // involve materialization)
    final ResultMergeQueryRunner<ResultRow> mergingQueryRunner = new ResultMergeQueryRunner<>(baseRunner, this::createResultComparator, this::createMergeFn);
    // Set up downstream context.
    final ImmutableMap.Builder<String, Object> context = ImmutableMap.builder();
    context.put("finalize", false);
    context.put(GroupByQueryConfig.CTX_KEY_STRATEGY, GroupByStrategySelector.STRATEGY_V2);
    context.put(CTX_KEY_OUTERMOST, false);
    Granularity granularity = query.getGranularity();
    List<DimensionSpec> dimensionSpecs = query.getDimensions();
    // the CTX_TIMESTAMP_RESULT_FIELD is set in DruidQuery.java
    final String timestampResultField = query.getContextValue(GroupByQuery.CTX_TIMESTAMP_RESULT_FIELD);
    final boolean hasTimestampResultField = (timestampResultField != null && !timestampResultField.isEmpty()) && query.getContextBoolean(CTX_KEY_OUTERMOST, true) && !query.isApplyLimitPushDown();
    int timestampResultFieldIndex = 0;
    if (hasTimestampResultField) {
        // sql like "group by city_id,time_floor(__time to day)",
        // the original translated query is granularity=all and dimensions:[d0, d1]
        // the better plan is granularity=day and dimensions:[d0]
        // but the ResultRow structure is changed from [d0, d1] to [__time, d0]
        // this structure should be fixed as [d0, d1] (actually it is [d0, __time]) before postAggs are called.
        // 
        // the above is the general idea of this optimization.
        // but from coding perspective, the granularity=all and "d0" dimension are referenced by many places,
        // eg: subtotals, having, grouping set, post agg,
        // there would be many many places need to be fixed if "d0" dimension is removed from query.dimensions
        // and the same to the granularity change.
        // so from easier coding perspective, this optimization is coded as groupby engine-level inner process change.
        // the most part of codes are in GroupByStrategyV2 about the process change between broker and compute node.
        // the basic logic like nested queries and subtotals are kept unchanged,
        // they will still see the granularity=all and the "d0" dimension.
        // 
        // the tradeoff is that GroupByStrategyV2 behaviors differently according to the query contexts set in DruidQuery
        // in another word,
        // the query generated by "explain plan for select ..." doesn't match to the native query ACTUALLY being executed,
        // the granularity and dimensions are slightly different.
        // now, part of the query plan logic is handled in GroupByStrategyV2, not only in DruidQuery.toGroupByQuery()
        final Granularity timestampResultFieldGranularity = query.getContextValue(GroupByQuery.CTX_TIMESTAMP_RESULT_FIELD_GRANULARITY);
        dimensionSpecs = query.getDimensions().stream().filter(dimensionSpec -> !dimensionSpec.getOutputName().equals(timestampResultField)).collect(Collectors.toList());
        granularity = timestampResultFieldGranularity;
        // when timestampResultField is the last dimension, should set sortByDimsFirst=true,
        // otherwise the downstream is sorted by row's timestamp first which makes the final ordering not as expected
        timestampResultFieldIndex = query.getContextValue(GroupByQuery.CTX_TIMESTAMP_RESULT_FIELD_INDEX);
        if (!query.getContextSortByDimsFirst() && timestampResultFieldIndex == query.getDimensions().size() - 1) {
            context.put(GroupByQuery.CTX_KEY_SORT_BY_DIMS_FIRST, true);
        }
        // it is actually equals to sortByDimsFirst=false
        if (query.getContextSortByDimsFirst() && timestampResultFieldIndex == 0) {
            context.put(GroupByQuery.CTX_KEY_SORT_BY_DIMS_FIRST, false);
        }
    // when hasTimestampResultField=true and timestampResultField is neither first nor last dimension,
    // the DefaultLimitSpec will always do the reordering
    }
    final int timestampResultFieldIndexInOriginalDimensions = timestampResultFieldIndex;
    if (query.getUniversalTimestamp() != null && !hasTimestampResultField) {
        // universalTimestamp works only when granularity is all
        // hasTimestampResultField works only when granularity is all
        // fudgeTimestamp should not be used when hasTimestampResultField=true due to the row's actual timestamp is used
        context.put(CTX_KEY_FUDGE_TIMESTAMP, String.valueOf(query.getUniversalTimestamp().getMillis()));
    }
    // The having spec shouldn't be passed down, so we need to convey the existing limit push down status
    context.put(GroupByQueryConfig.CTX_KEY_APPLY_LIMIT_PUSH_DOWN, query.isApplyLimitPushDown());
    // Always request array result rows when passing the query downstream.
    context.put(GroupByQueryConfig.CTX_KEY_ARRAY_RESULT_ROWS, true);
    final GroupByQuery newQuery = new GroupByQuery(query.getDataSource(), query.getQuerySegmentSpec(), query.getVirtualColumns(), query.getDimFilter(), granularity, dimensionSpecs, query.getAggregatorSpecs(), // Don't apply postaggregators on compute nodes
    ImmutableList.of(), // Don't do "having" clause until the end of this method.
    null, // higher-up).
    query.isApplyLimitPushDown() ? ((DefaultLimitSpec) query.getLimitSpec()).withOffsetToLimit() : null, query.getSubtotalsSpec(), query.getContext()).withOverriddenContext(context.build());
    final Sequence<ResultRow> mergedResults = mergingQueryRunner.run(QueryPlus.wrap(newQuery), responseContext);
    if (!query.getContextBoolean(CTX_KEY_OUTERMOST, true) || query.getContextBoolean(GroupByQueryConfig.CTX_KEY_EXECUTING_NESTED_QUERY, false)) {
        return mergedResults;
    } else if (query.getPostAggregatorSpecs().isEmpty()) {
        if (!hasTimestampResultField) {
            return mergedResults;
        }
        return Sequences.map(mergedResults, row -> {
            final ResultRow resultRow = ResultRow.create(query.getResultRowSizeWithoutPostAggregators());
            moveOrReplicateTimestampInRow(query, timestampResultFieldIndexInOriginalDimensions, row, resultRow);
            return resultRow;
        });
    } else {
        return Sequences.map(mergedResults, row -> {
            // This function's purpose is to apply PostAggregators.
            final ResultRow rowWithPostAggregations = ResultRow.create(query.getResultRowSizeWithPostAggregators());
            // Copy everything that comes before the postaggregations.
            if (hasTimestampResultField) {
                moveOrReplicateTimestampInRow(query, timestampResultFieldIndexInOriginalDimensions, row, rowWithPostAggregations);
            } else {
                for (int i = 0; i < query.getResultRowPostAggregatorStart(); i++) {
                    rowWithPostAggregations.set(i, row.get(i));
                }
            }
            // Compute postaggregations. We need to do this with a result-row map because PostAggregator.compute
            // expects a map. Some further design adjustment may eliminate the need for it, and speed up this function.
            final Map<String, Object> mapForPostAggregationComputation = rowWithPostAggregations.toMap(query);
            for (int i = 0; i < query.getPostAggregatorSpecs().size(); i++) {
                final PostAggregator postAggregator = query.getPostAggregatorSpecs().get(i);
                final Object value = postAggregator.compute(mapForPostAggregationComputation);
                rowWithPostAggregations.set(query.getResultRowPostAggregatorStart() + i, value);
                mapForPostAggregationComputation.put(postAggregator.getName(), value);
            }
            return rowWithPostAggregations;
        });
    }
}

Example 59 with QueryRunner

use of org.apache.druid.query.QueryRunner in project druid by druid-io.

the class SegmentMetadataQueryRunnerFactory method createRunner.

@Override
public QueryRunner<SegmentAnalysis> createRunner(final Segment segment) {
    return new QueryRunner<SegmentAnalysis>() {

        @Override
        public Sequence<SegmentAnalysis> run(QueryPlus<SegmentAnalysis> inQ, ResponseContext responseContext) {
            SegmentMetadataQuery updatedQuery = ((SegmentMetadataQuery) inQ.getQuery()).withFinalizedAnalysisTypes(toolChest.getConfig());
            final SegmentAnalyzer analyzer = new SegmentAnalyzer(updatedQuery.getAnalysisTypes());
            final Map<String, ColumnAnalysis> analyzedColumns = analyzer.analyze(segment);
            final long numRows = analyzer.numRows(segment);
            long totalSize = 0;
            if (analyzer.analyzingSize()) {
                // Initialize with the size of the whitespace, 1 byte per
                totalSize = analyzedColumns.size() * numRows;
            }
            Map<String, ColumnAnalysis> columns = new TreeMap<>();
            ColumnIncluderator includerator = updatedQuery.getToInclude();
            for (Map.Entry<String, ColumnAnalysis> entry : analyzedColumns.entrySet()) {
                final String columnName = entry.getKey();
                final ColumnAnalysis column = entry.getValue();
                if (!column.isError()) {
                    totalSize += column.getSize();
                }
                if (includerator.include(columnName)) {
                    columns.put(columnName, column);
                }
            }
            List<Interval> retIntervals = updatedQuery.analyzingInterval() ? Collections.singletonList(segment.getDataInterval()) : null;
            final Map<String, AggregatorFactory> aggregators;
            Metadata metadata = null;
            if (updatedQuery.hasAggregators()) {
                metadata = segment.asStorageAdapter().getMetadata();
                if (metadata != null && metadata.getAggregators() != null) {
                    aggregators = new HashMap<>();
                    for (AggregatorFactory aggregator : metadata.getAggregators()) {
                        aggregators.put(aggregator.getName(), aggregator);
                    }
                } else {
                    aggregators = null;
                }
            } else {
                aggregators = null;
            }
            final TimestampSpec timestampSpec;
            if (updatedQuery.hasTimestampSpec()) {
                if (metadata == null) {
                    metadata = segment.asStorageAdapter().getMetadata();
                }
                timestampSpec = metadata != null ? metadata.getTimestampSpec() : null;
            } else {
                timestampSpec = null;
            }
            final Granularity queryGranularity;
            if (updatedQuery.hasQueryGranularity()) {
                if (metadata == null) {
                    metadata = segment.asStorageAdapter().getMetadata();
                }
                queryGranularity = metadata != null ? metadata.getQueryGranularity() : null;
            } else {
                queryGranularity = null;
            }
            Boolean rollup = null;
            if (updatedQuery.hasRollup()) {
                if (metadata == null) {
                    metadata = segment.asStorageAdapter().getMetadata();
                }
                rollup = metadata != null ? metadata.isRollup() : null;
                if (rollup == null) {
                    // in this case, this segment is built before no-rollup function is coded,
                    // thus it is built with rollup
                    rollup = Boolean.TRUE;
                }
            }
            return Sequences.simple(Collections.singletonList(new SegmentAnalysis(segment.getId().toString(), retIntervals, columns, totalSize, numRows, aggregators, timestampSpec, queryGranularity, rollup)));
        }
    };
}

Example 60 with QueryRunner

use of org.apache.druid.query.QueryRunner in project druid by druid-io.

the class SegmentMetadataQueryRunnerFactory method mergeRunners.

@Override
public QueryRunner<SegmentAnalysis> mergeRunners(QueryProcessingPool queryProcessingPool, Iterable<QueryRunner<SegmentAnalysis>> queryRunners) {
    return new ConcatQueryRunner<SegmentAnalysis>(Sequences.map(Sequences.simple(queryRunners), new Function<QueryRunner<SegmentAnalysis>, QueryRunner<SegmentAnalysis>>() {

        @Override
        public QueryRunner<SegmentAnalysis> apply(final QueryRunner<SegmentAnalysis> input) {
            return new QueryRunner<SegmentAnalysis>() {

                @Override
                public Sequence<SegmentAnalysis> run(final QueryPlus<SegmentAnalysis> queryPlus, final ResponseContext responseContext) {
                    final Query<SegmentAnalysis> query = queryPlus.getQuery();
                    final int priority = QueryContexts.getPriority(query);
                    final QueryPlus<SegmentAnalysis> threadSafeQueryPlus = queryPlus.withoutThreadUnsafeState();
                    ListenableFuture<Sequence<SegmentAnalysis>> future = queryProcessingPool.submitRunnerTask(new AbstractPrioritizedQueryRunnerCallable<Sequence<SegmentAnalysis>, SegmentAnalysis>(priority, input) {

                        @Override
                        public Sequence<SegmentAnalysis> call() {
                            return Sequences.simple(input.run(threadSafeQueryPlus, responseContext).toList());
                        }
                    });
                    try {
                        queryWatcher.registerQueryFuture(query, future);
                        if (QueryContexts.hasTimeout(query)) {
                            return future.get(QueryContexts.getTimeout(query), TimeUnit.MILLISECONDS);
                        } else {
                            return future.get();
                        }
                    } catch (InterruptedException e) {
                        log.warn(e, "Query interrupted, cancelling pending results, query id [%s]", query.getId());
                        future.cancel(true);
                        throw new QueryInterruptedException(e);
                    } catch (CancellationException e) {
                        throw new QueryInterruptedException(e);
                    } catch (TimeoutException e) {
                        log.info("Query timeout, cancelling pending results for query id [%s]", query.getId());
                        future.cancel(true);
                        throw new QueryTimeoutException(StringUtils.nonStrictFormat("Query [%s] timed out", query.getId()));
                    } catch (ExecutionException e) {
                        throw new RuntimeException(e);
                    }
                }
            };
        }
    }));
}