Examples with FactTable io.cdap.cdap.data2.dataset2.lib.timeseries.FactTable used on opensource projects

Example 6 with FactTable

use of io.cdap.cdap.data2.dataset2.lib.timeseries.FactTable in project cdap by caskdata.

the class DefaultCube method query.

@Override
public Collection<TimeSeries> query(CubeQuery query) {
    /*
      CubeQuery example: "dataset read ops for app per dataset". Or:

      SELECT count('read.ops')                                           << measure name and type
      FROM aggregation1.1min_resolution                                  << aggregation and resolution
      GROUP BY dataset,                                                  << groupByDimensions
      WHERE namespace='ns1' AND app='myApp' AND program='myFlow' AND     << dimensionValues
            ts>=1423370200 AND ts{@literal<}1423398198                   << startTs and endTs
      LIMIT 100                                                          << limit

      Execution:

      1) (optional, if aggregation to query in is not provided) find aggregation to supply results

      Here, we need aggregation that has following dimensions: 'namespace', 'app', 'program', 'dataset'.

      Ideally (to reduce the scan range), 'dataset' should be in the end, other dimensions as close to the beginning
      as possible, and minimal number of other "unspecified" dimensions.

      Let's say we found aggregation: 'namespace', 'app', 'program', 'instance', 'dataset'

      2) build a scan in the aggregation

      For scan we set "any" into the dimension values that aggregation has but query doesn't define value for:

      'namespace'='ns1', 'app'='myApp', 'program'='myFlow', 'instance'=*, 'dataset'=*

      Plus specified measure & aggregation?:

      'measureName'='read.ops'
      'measureType'='COUNTER'

      3) While scanning build a table: dimension values -> time -> value. Use measureType as values aggregate
         function if needed.
    */
    incrementMetric("cube.query.request.count", 1);
    if (!resolutionToFactTable.containsKey(query.getResolution())) {
        incrementMetric("cube.query.request.failure.count", 1);
        throw new IllegalArgumentException("There's no data aggregated for specified resolution to satisfy the query: " + query.toString());
    }
    // 1) find aggregation to query
    Aggregation agg;
    String aggName;
    if (query.getAggregation() != null) {
        aggName = query.getAggregation();
        agg = aggregations.get(query.getAggregation());
        if (agg == null) {
            incrementMetric("cube.query.request.failure.count", 1);
            throw new IllegalArgumentException(String.format("Specified aggregation %s is not found in cube aggregations: %s", query.getAggregation(), aggregations.keySet().toString()));
        }
    } else {
        ImmutablePair<String, Aggregation> aggregation = findAggregation(query);
        if (aggregation == null) {
            incrementMetric("cube.query.request.failure.count", 1);
            throw new IllegalArgumentException("There's no data aggregated for specified dimensions " + "to satisfy the query: " + query.toString());
        }
        agg = aggregation.getSecond();
        aggName = aggregation.getFirst();
    }
    // tell how many queries end up querying specific pre-aggregated views and resolutions
    incrementMetric("cube.query.agg." + aggName + ".count", 1);
    incrementMetric("cube.query.res." + query.getResolution() + ".count", 1);
    // 2) build a scan for a query
    List<DimensionValue> dimensionValues = Lists.newArrayList();
    for (String dimensionName : agg.getDimensionNames()) {
        // if not defined in query, will be set as null, which means "any"
        dimensionValues.add(new DimensionValue(dimensionName, query.getDimensionValues().get(dimensionName)));
    }
    FactScan scan = new FactScan(query.getStartTs(), query.getEndTs(), query.getMeasurements().keySet(), dimensionValues);
    // 3) execute scan query
    FactTable table = resolutionToFactTable.get(query.getResolution());
    FactScanner scanner = table.scan(scan);
    Table<Map<String, String>, String, Map<Long, Long>> resultMap = getTimeSeries(query, scanner);
    incrementMetric("cube.query.request.success.count", 1);
    incrementMetric("cube.query.result.size", resultMap.size());
    Collection<TimeSeries> timeSeries = convertToQueryResult(query, resultMap);
    incrementMetric("cube.query.result.timeseries.count", timeSeries.size());
    return timeSeries;
}

Example 7 with FactTable

use of io.cdap.cdap.data2.dataset2.lib.timeseries.FactTable in project cdap by caskdata.

the class FactTableTest method testMaxResolution.

@Test
public void testMaxResolution() throws Exception {
    // we use Integer.MAX_VALUE as resolution to compute all-time total values
    InMemoryTableService.create("TotalsEntityTable");
    InMemoryTableService.create("TotalsDataTable");
    int resolution = Integer.MAX_VALUE;
    // should not matter when resolution is max
    int rollTimebaseInterval = 3600;
    FactTable table = new FactTable(new InMemoryMetricsTable("TotalsDataTable"), new EntityTable(new InMemoryMetricsTable("TotalsEntityTable")), resolution, rollTimebaseInterval);
    // ts is expected in seconds
    long ts = System.currentTimeMillis() / 1000;
    int count = 1000;
    for (int i = 0; i < count; i++) {
        for (int k = 0; k < 10; k++) {
            // shift one day
            writeInc(table, "metric" + k, ts + i * 60 * 60 * 24, i * k, "dim" + k, "value" + k);
        }
    }
    for (int k = 0; k < 10; k++) {
        // 0, 0 should match timestamp of all data points
        FactScan scan = new FactScan(0, 0, "metric" + k, dimValues("dim" + k, "value" + k));
        Table<String, List<DimensionValue>, List<TimeValue>> expected = HashBasedTable.create();
        expected.put("metric" + k, dimValues("dim" + k, "value" + k), ImmutableList.of(new TimeValue(0, k * count * (count - 1) / 2)));
        assertScan(table, expected, scan);
    }
}

Example 8 with FactTable

use of io.cdap.cdap.data2.dataset2.lib.timeseries.FactTable in project cdap by caskdata.

the class FactTableTest method testCache.

@Test
public void testCache() throws Exception {
    String tableName = "testCacheTable";
    String entityTableName = "testCacheEntityTable";
    InMemoryTableService.create(tableName);
    InMemoryTableService.create(entityTableName);
    int resolution = 5;
    InMemoryMetricsTable metricsTable = new InMemoryMetricsTable(tableName);
    FactTable table = new FactTable(metricsTable, new EntityTable(new InMemoryMetricsTable(entityTableName)), resolution, 2);
    // set the metrics collector for the table
    FactTableMetricsCollector metricsCollector = new FactTableMetricsCollector(resolution);
    table.setMetricsCollector(metricsCollector);
    // Initially the cache should be empty
    Assert.assertEquals(0, table.getFactCounterCache().size());
    // add some value with current ts
    long timestampNow = TimeUnit.MILLISECONDS.toSeconds(System.currentTimeMillis()) / resolution * resolution;
    List<DimensionValue> dims = dimValues("dim1", "dim2");
    List<Fact> metrics = new ArrayList<>();
    for (int i = 0; i < 10; i++) {
        metrics.add(new Fact(timestampNow, dims, new Measurement("metric" + i, MeasureType.COUNTER, 1)));
    }
    table.add(metrics);
    // Since no previous add to the metric store, these increment should still be considered as COUNTER, and the
    // cache should be updated.
    Assert.assertEquals(10, metricsCollector.getLastIncrementSize());
    Assert.assertEquals(0, metricsCollector.getLastGaugeSize());
    Assert.assertEquals(10, table.getFactCounterCache().size());
    for (long value : table.getFactCounterCache().asMap().values()) {
        Assert.assertEquals(timestampNow, value);
    }
    // Add metrics older than the current timestamp, these increment should still be considered as COUNTER, and the
    // cache should NOT be updated.
    metrics = new ArrayList<>();
    for (int i = 0; i < 10; i++) {
        metrics.add(new Fact(timestampNow - 5, dims, new Measurement("metric" + i, MeasureType.COUNTER, 1)));
    }
    table.add(metrics);
    Assert.assertEquals(10, metricsCollector.getLastIncrementSize());
    Assert.assertEquals(0, metricsCollector.getLastGaugeSize());
    Assert.assertEquals(10, table.getFactCounterCache().size());
    for (long value : table.getFactCounterCache().asMap().values()) {
        Assert.assertEquals(timestampNow, value);
    }
    // Now insert metrics newer than the current timestamp, the increment should be considered as GAUGE, and the cache
    // should be updated
    metrics = new ArrayList<>();
    for (int i = 0; i < 10; i++) {
        metrics.add(new Fact(timestampNow + 5, dims, new Measurement("metric" + i, MeasureType.COUNTER, 1)));
    }
    table.add(metrics);
    Assert.assertEquals(0, metricsCollector.getLastIncrementSize());
    Assert.assertEquals(10, metricsCollector.getLastGaugeSize());
    Assert.assertEquals(10, table.getFactCounterCache().size());
    for (long value : table.getFactCounterCache().asMap().values()) {
        Assert.assertEquals(timestampNow + 5, value);
    }
}

Example 9 with FactTable

use of io.cdap.cdap.data2.dataset2.lib.timeseries.FactTable in project cdap by caskdata.

the class FactTableTest method testQuery.

@Test
public void testQuery() throws Exception {
    InMemoryTableService.create("QueryEntityTable");
    InMemoryTableService.create("QueryDataTable");
    int resolution = 10;
    int rollTimebaseInterval = 2;
    FactTable table = new FactTable(new InMemoryMetricsTable("QueryDataTable"), new EntityTable(new InMemoryMetricsTable("QueryEntityTable")), resolution, rollTimebaseInterval);
    // aligned to start of resolution bucket
    // "/1000" because time is expected to be in seconds
    long ts = ((System.currentTimeMillis() / 1000) / resolution) * resolution;
    for (int i = 0; i < 3; i++) {
        for (int k = 1; k < 3; k++) {
            // note: "+i" to ts here and below doesn't affect results, just to confirm
            // that data points are rounded to the resolution
            writeInc(table, "metric" + k, ts + i * resolution + i, k + i, "dim1", "value1", "dim2", "value2");
            writeInc(table, "metric" + k, ts + i * resolution + i, 2 * k + i, "dim1", "value2", "dim2", "value2");
            writeInc(table, "metric" + k, ts + i * resolution + i, 3 * k + i, "dim1", "value2", "dim2", "value1");
            writeInc(table, "metric" + k, ts + i * resolution + i, 4 * k + i, "dim1", "value1", "dim2", "value3");
            // null value in dim matches only fuzzy ("any")
            writeInc(table, "metric" + k, ts + i * resolution + i, 5 * k + i, "dim1", null, "dim2", "value3");
        }
    }
    Table<String, List<DimensionValue>, List<TimeValue>> expected;
    FactScan scan;
    for (int i = 1; i < 3; i++) {
        // all time points
        scan = new FactScan(ts - resolution, ts + 3 * resolution, "metric" + i, dimValues("dim1", "value1", "dim2", "value2"));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts, resolution, i, i + 1, i + 2));
        assertScan(table, expected, scan);
        // time points since second interval
        scan = new FactScan(ts + resolution, ts + 3 * resolution, "metric" + i, dimValues("dim1", "value1", "dim2", "value2"));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts + resolution, resolution, i + 1, i + 2));
        assertScan(table, expected, scan);
        // time points before third interval
        scan = new FactScan(ts - resolution, ts + resolution, "metric" + i, dimValues("dim1", "value1", "dim2", "value2"));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts, resolution, i, i + 1));
        assertScan(table, expected, scan);
        // time points for fuzzy dim2 since second interval
        scan = new FactScan(ts + resolution, ts + 3 * resolution, // null stands for any
        "metric" + i, dimValues("dim1", "value1", "dim2", null));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts + resolution, resolution, i + 1, i + 2));
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value3"), timeValues(ts + resolution, resolution, 4 * i + 1, 4 * i + 2));
        assertScan(table, expected, scan);
        // time points for fuzzy dim1 before third interval
        scan = new FactScan(ts - resolution, ts + resolution, // null stands for any
        "metric" + i, dimValues("dim1", null, "dim2", "value3"));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value3"), timeValues(ts, resolution, 4 * i, 4 * i + 1));
        expected.put("metric" + i, dimValues("dim1", null, "dim2", "value3"), timeValues(ts, resolution, 5 * i, 5 * i + 1));
        assertScan(table, expected, scan);
        // time points for both fuzzy dims before third interval
        scan = new FactScan(ts - resolution, ts + resolution, // null stands for any
        "metric" + i, dimValues("dim1", null, "dim2", null));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts, resolution, i, i + 1));
        expected.put("metric" + i, dimValues("dim1", "value2", "dim2", "value1"), timeValues(ts, resolution, 3 * i, 3 * i + 1));
        expected.put("metric" + i, dimValues("dim1", "value2", "dim2", "value2"), timeValues(ts, resolution, 2 * i, 2 * i + 1));
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value3"), timeValues(ts, resolution, 4 * i, 4 * i + 1));
        expected.put("metric" + i, dimValues("dim1", null, "dim2", "value3"), timeValues(ts, resolution, 5 * i, 5 * i + 1));
        assertScan(table, expected, scan);
        // time points for both fuzzy dims since third interval
        scan = new FactScan(ts + resolution, ts + 3 * resolution, // null stands for any
        "metric" + i, dimValues("dim1", null, "dim2", null));
        expected = HashBasedTable.create();
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts + resolution, resolution, i + 1, i + 2));
        expected.put("metric" + i, dimValues("dim1", "value2", "dim2", "value1"), timeValues(ts + resolution, resolution, 3 * i + 1, 3 * i + 2));
        expected.put("metric" + i, dimValues("dim1", "value2", "dim2", "value2"), timeValues(ts + resolution, resolution, 2 * i + 1, 2 * i + 2));
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value3"), timeValues(ts + resolution, resolution, 4 * i + 1, 4 * i + 2));
        expected.put("metric" + i, dimValues("dim1", null, "dim2", "value3"), timeValues(ts + resolution, resolution, 5 * i + 1, 5 * i + 2));
        assertScan(table, expected, scan);
    }
    // all time points
    scan = new FactScan(ts - resolution, ts + 3 * resolution, dimValues("dim1", "value1", "dim2", "value2"));
    expected = HashBasedTable.create();
    for (int i = 1; i < 3; i++) {
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts, resolution, i, i + 1, i + 2));
    }
    assertScan(table, expected, scan);
    // time points since second interval
    scan = new FactScan(ts + resolution, ts + 3 * resolution, dimValues("dim1", "value1", "dim2", "value2"));
    expected = HashBasedTable.create();
    for (int i = 1; i < 3; i++) {
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts + resolution, resolution, i + 1, i + 2));
    }
    assertScan(table, expected, scan);
    // time points before third interval
    scan = new FactScan(ts - resolution, ts + resolution, dimValues("dim1", "value1", "dim2", "value2"));
    expected = HashBasedTable.create();
    for (int i = 1; i < 3; i++) {
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts, resolution, i, i + 1));
    }
    assertScan(table, expected, scan);
    // time points for fuzzy dim2 since second interval
    scan = new FactScan(ts + resolution, ts + 3 * resolution, dimValues("dim1", "value1", "dim2", null));
    expected = HashBasedTable.create();
    for (int i = 1; i < 3; i++) {
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value2"), timeValues(ts + resolution, resolution, i + 1, i + 2));
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value3"), timeValues(ts + resolution, resolution, 4 * i + 1, 4 * i + 2));
    }
    assertScan(table, expected, scan);
    // time points for fuzzy dim1 before third interval (very important case - caught some bugs)
    scan = new FactScan(ts - resolution, ts + resolution, dimValues("dim1", null, "dim2", "value3"));
    expected = HashBasedTable.create();
    for (int i = 1; i < 3; i++) {
        expected.put("metric" + i, dimValues("dim1", "value1", "dim2", "value3"), timeValues(ts, resolution, 4 * i, 4 * i + 1));
        expected.put("metric" + i, dimValues("dim1", null, "dim2", "value3"), timeValues(ts, resolution, 5 * i, 5 * i + 1));
    }
    assertScan(table, expected, scan);
}

Example 10 with FactTable

use of io.cdap.cdap.data2.dataset2.lib.timeseries.FactTable in project cdap by caskdata.

the class FactTableTest method testSearch.

@Test
public void testSearch() throws Exception {
    InMemoryTableService.create("SearchEntityTable");
    InMemoryTableService.create("SearchDataTable");
    int resolution = Integer.MAX_VALUE;
    int rollTimebaseInterval = 2;
    FactTable table = new FactTable(new InMemoryMetricsTable("SearchDataTable"), new EntityTable(new InMemoryMetricsTable("SearchEntityTable")), resolution, rollTimebaseInterval);
    // aligned to start of resolution bucket
    // "/1000" because time is expected to be in seconds
    long ts = ((System.currentTimeMillis() / 1000) / resolution) * resolution;
    List<String> aggregationList = ImmutableList.of("dim1", "dim2", "dim3", "dim4");
    for (int i = 0; i < 2; i++) {
        writeInc(table, "metric-a" + i, ts + i, i, "dim1", "value1", "dim2", "value2", "dim3", "value3", "dim4", "value4");
        writeInc(table, "metric-b" + i, ts + i, i, "dim1", "value2", "dim2", "value2", "dim3", "x3", "dim4", "x4");
        writeInc(table, "metric-c" + i, ts + i, i, "dim1", "value2", "dim2", "value2", "dim3", null, "dim4", "y4");
        writeInc(table, "metric-d" + i, ts + i, i, "dim1", "value1", "dim2", "value3", "dim3", "y3", "dim4", null);
    }
    Map<String, String> slice = Maps.newHashMap();
    slice.put("dim1", "value2");
    slice.put("dim2", "value2");
    slice.put("dim3", null);
    // verify search dims
    testTagSearch(table, aggregationList, ImmutableMap.of("dim2", "value2"), ImmutableSet.of(new DimensionValue("dim1", "value1"), new DimensionValue("dim1", "value2")));
    testTagSearch(table, aggregationList, ImmutableMap.of("dim1", "value1"), ImmutableSet.of(new DimensionValue("dim2", "value2"), new DimensionValue("dim2", "value3")));
    testTagSearch(table, aggregationList, ImmutableMap.<String, String>of(), ImmutableSet.of(new DimensionValue("dim1", "value1"), new DimensionValue("dim1", "value2")));
    testTagSearch(table, aggregationList, ImmutableMap.of("dim1", "value2", "dim2", "value2"), ImmutableSet.of(new DimensionValue("dim3", "x3"), new DimensionValue("dim4", "y4")));
    testTagSearch(table, aggregationList, slice, ImmutableSet.of(new DimensionValue("dim4", "x4"), new DimensionValue("dim4", "y4")));
    testTagSearch(table, aggregationList, ImmutableMap.of("dim1", "value2", "dim2", "value3", "dim3", "y3"), ImmutableSet.<DimensionValue>of());
    // verify search metrics
    testMetricNamesSearch(table, aggregationList, ImmutableMap.of("dim1", "value1", "dim2", "value2", "dim3", "value3"), ImmutableSet.<String>of("metric-a0", "metric-a1"));
    testMetricNamesSearch(table, aggregationList, ImmutableMap.of("dim2", "value2"), ImmutableSet.<String>of("metric-a0", "metric-a1", "metric-b0", "metric-b1", "metric-c0", "metric-c1"));
    testMetricNamesSearch(table, aggregationList, slice, ImmutableSet.of("metric-b0", "metric-b1", "metric-c0", "metric-c1"));
}