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

Example 16 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"));
}

Example 17 with FactTable

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

the class FactTableTest method testPreSplits.

@Test
public void testPreSplits() throws Exception {
    InMemoryTableService.create("presplitEntityTable");
    InMemoryTableService.create("presplitDataTable");
    int resolution = 10;
    int rollTimebaseInterval = 2;
    InMemoryMetricsTable metricsTable = new InMemoryMetricsTable("presplitDataTable");
    FactTable table = new FactTable(metricsTable, new EntityTable(new InMemoryMetricsTable("presplitEntityTable")), resolution, rollTimebaseInterval);
    byte[][] splits = FactTable.getSplits(3);
    long ts = System.currentTimeMillis() / 1000;
    DimensionValue dimVal1 = new DimensionValue("dim1", "value1");
    DimensionValue dimVal2 = new DimensionValue("dim2", "value2");
    DimensionValue dimVal3 = new DimensionValue("dim3", "value3");
    // first agg view: dim1
    table.add(ImmutableList.of(new Fact(ts, ImmutableList.of(dimVal1), new Measurement("metric1", MeasureType.COUNTER, 1))));
    // second agg view: dim1 & dim2
    table.add(ImmutableList.of(new Fact(ts, ImmutableList.of(dimVal1, dimVal2), new Measurement("metric1", MeasureType.COUNTER, 1))));
    // third agg view: dim3
    table.add(ImmutableList.of(new Fact(ts, ImmutableList.of(dimVal3), new Measurement("metric1", MeasureType.COUNTER, 1))));
    // Verify all written records are spread across splits
    Scanner scanner = metricsTable.scan(null, null, null);
    Row row;
    Set<Integer> splitsWithRows = Sets.newHashSet();
    while ((row = scanner.next()) != null) {
        boolean added = false;
        for (int i = 0; i < splits.length; i++) {
            if (Bytes.compareTo(row.getRow(), splits[i]) < 0) {
                splitsWithRows.add(i);
                added = true;
                break;
            }
        }
        if (!added) {
            // falls into last split
            splitsWithRows.add(splits.length);
        }
    }
    Assert.assertEquals(3, splitsWithRows.size());
}

Example 18 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 19 with FactTable

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

the class FactTableTest method testBasics.

@Test
public void testBasics() throws Exception {
    InMemoryTableService.create("EntityTable");
    InMemoryTableService.create("DataTable");
    int resolution = 10;
    int rollTimebaseInterval = 2;
    FactTable table = new FactTable(new InMemoryMetricsTable("DataTable"), new EntityTable(new InMemoryMetricsTable("EntityTable")), resolution, rollTimebaseInterval);
    // aligned to start of resolution bucket
    // "/1000" because time is expected to be in seconds
    long ts = ((System.currentTimeMillis() / 1000) / resolution) * resolution;
    // testing encoding with multiple dims
    List<DimensionValue> dimensionValues = ImmutableList.of(new DimensionValue("dim1", "value1"), new DimensionValue("dim2", "value2"), new DimensionValue("dim3", "value3"));
    // trying adding one by one, in same (first) time resolution bucket
    for (int i = 0; i < 5; i++) {
        for (int k = 1; k < 4; k++) {
            // note: "+i" here and below doesn't affect results, just to confirm
            // that data points are rounded to the resolution
            table.add(ImmutableList.of(new Fact(ts + i, dimensionValues, new Measurement("metric" + k, MeasureType.COUNTER, k))));
        }
    }
    // trying adding one by one, in different time resolution buckets
    for (int i = 0; i < 3; i++) {
        for (int k = 1; k < 4; k++) {
            table.add(ImmutableList.of(new Fact(ts + resolution * i + i, dimensionValues, new Measurement("metric" + k, MeasureType.COUNTER, 2 * k))));
        }
    }
    // trying adding as list
    // first incs in same (second) time resolution bucket
    List<Fact> aggs = Lists.newArrayList();
    for (int i = 0; i < 7; i++) {
        for (int k = 1; k < 4; k++) {
            aggs.add(new Fact(ts + resolution, dimensionValues, new Measurement("metric" + k, MeasureType.COUNTER, 3 * k)));
        }
    }
    // then incs in different time resolution buckets
    for (int i = 0; i < 3; i++) {
        for (int k = 1; k < 4; k++) {
            aggs.add(new Fact(ts + resolution * i, dimensionValues, new Measurement("metric" + k, MeasureType.COUNTER, 4 * k)));
        }
    }
    table.add(aggs);
    // verify each metric
    for (int k = 1; k < 4; k++) {
        FactScan scan = new FactScan(ts - 2 * resolution, ts + 3 * resolution, "metric" + k, dimensionValues);
        Table<String, List<DimensionValue>, List<TimeValue>> expected = HashBasedTable.create();
        expected.put("metric" + k, dimensionValues, ImmutableList.of(new TimeValue(ts, 11 * k), new TimeValue(ts + resolution, 27 * k), new TimeValue(ts + 2 * resolution, 6 * k)));
        assertScan(table, expected, scan);
    }
    // verify each metric within a single timeBase
    for (int k = 1; k < 4; k++) {
        FactScan scan = new FactScan(ts, ts + resolution - 1, "metric" + k, dimensionValues);
        Table<String, List<DimensionValue>, List<TimeValue>> expected = HashBasedTable.create();
        expected.put("metric" + k, dimensionValues, ImmutableList.of(new TimeValue(ts, 11 * k)));
        assertScan(table, expected, scan);
    }
    // verify all metrics with fuzzy metric in scan
    Table<String, List<DimensionValue>, List<TimeValue>> expected = HashBasedTable.create();
    for (int k = 1; k < 4; k++) {
        expected.put("metric" + k, dimensionValues, ImmutableList.of(new TimeValue(ts, 11 * k), new TimeValue(ts + resolution, 27 * k), new TimeValue(ts + 2 * resolution, 6 * k)));
    }
    // metric = null means "all"
    FactScan scan = new FactScan(ts - 2 * resolution, ts + 3 * resolution, dimensionValues);
    assertScan(table, expected, scan);
    // delete metric test
    expected.clear();
    // delete the metrics data at (timestamp + 20) resolution
    scan = new FactScan(ts + resolution * 2, ts + resolution * 3, dimensionValues);
    table.delete(scan);
    for (int k = 1; k < 4; k++) {
        expected.put("metric" + k, dimensionValues, ImmutableList.of(new TimeValue(ts, 11 * k), new TimeValue(ts + resolution, 27 * k)));
    }
    // verify deletion
    scan = new FactScan(ts - 2 * resolution, ts + 3 * resolution, dimensionValues);
    assertScan(table, expected, scan);
    // delete metrics for "metric1" at ts0 and verify deletion
    scan = new FactScan(ts, ts + 1, "metric1", dimensionValues);
    table.delete(scan);
    expected.clear();
    expected.put("metric1", dimensionValues, ImmutableList.of(new TimeValue(ts + resolution, 27)));
    scan = new FactScan(ts - 2 * resolution, ts + 3 * resolution, "metric1", dimensionValues);
    assertScan(table, expected, scan);
    // verify the next dims search
    Collection<DimensionValue> nextTags = table.findSingleDimensionValue(ImmutableList.of("dim1", "dim2", "dim3"), ImmutableMap.of("dim1", "value1"), ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of(new DimensionValue("dim2", "value2")), nextTags);
    Map<String, String> slice = Maps.newHashMap();
    slice.put("dim1", null);
    nextTags = table.findSingleDimensionValue(ImmutableList.of("dim1", "dim2", "dim3"), slice, ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of(new DimensionValue("dim2", "value2")), nextTags);
    nextTags = table.findSingleDimensionValue(ImmutableList.of("dim1", "dim2", "dim3"), ImmutableMap.of("dim1", "value1", "dim2", "value2"), ts, ts + 3);
    Assert.assertEquals(ImmutableSet.of(new DimensionValue("dim3", "value3")), nextTags);
    // add new dim values
    dimensionValues = ImmutableList.of(new DimensionValue("dim1", "value1"), new DimensionValue("dim2", "value5"), new DimensionValue("dim3", null));
    table.add(ImmutableList.of(new Fact(ts, dimensionValues, new Measurement("metric", MeasureType.COUNTER, 10))));
    dimensionValues = ImmutableList.of(new DimensionValue("dim1", "value1"), new DimensionValue("dim2", null), new DimensionValue("dim3", "value3"));
    table.add(ImmutableList.of(new Fact(ts, dimensionValues, new Measurement("metric", MeasureType.COUNTER, 10))));
    nextTags = table.findSingleDimensionValue(ImmutableList.of("dim1", "dim2", "dim3"), ImmutableMap.of("dim1", "value1"), ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of(new DimensionValue("dim2", "value2"), new DimensionValue("dim2", "value5"), new DimensionValue("dim3", "value3")), nextTags);
    // search for metric names given dims list and verify
    Collection<String> metricNames = table.findMeasureNames(ImmutableList.of("dim1", "dim2", "dim3"), ImmutableMap.of("dim1", "value1", "dim2", "value2", "dim3", "value3"), ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of("metric2", "metric3"), metricNames);
    metricNames = table.findMeasureNames(ImmutableList.of("dim1", "dim2", "dim3"), ImmutableMap.of("dim1", "value1"), ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of("metric", "metric2", "metric3"), metricNames);
    metricNames = table.findMeasureNames(ImmutableList.of("dim1", "dim2", "dim3"), ImmutableMap.of("dim2", "value2"), ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of("metric2", "metric3"), metricNames);
    metricNames = table.findMeasureNames(ImmutableList.of("dim1", "dim2", "dim3"), slice, ts, ts + 1);
    Assert.assertEquals(ImmutableSet.of("metric", "metric2", "metric3"), metricNames);
}

Example 20 with FactTable

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

the class DefaultMetricDatasetFactory method getOrCreateFactTable.

// todo: figure out roll time based on resolution from config? See DefaultMetricsTableFactory for example
@Override
public FactTable getOrCreateFactTable(int resolution) {
    String tableName = cConf.get(Constants.Metrics.METRICS_TABLE_PREFIX, Constants.Metrics.DEFAULT_METRIC_TABLE_PREFIX) + ".ts." + resolution;
    TableProperties.Builder props = TableProperties.builder();
    // don't add TTL for MAX_RESOLUTION table. CDAP-1626
    if (resolution != Integer.MAX_VALUE) {
        int ttl = resolution < 60 ? cConf.getInt(Constants.Metrics.MINIMUM_RESOLUTION_RETENTION_SECONDS) : cConf.getInt(Constants.Metrics.RETENTION_SECONDS + resolution + Constants.Metrics.RETENTION_SECONDS_SUFFIX);
        if (ttl > 0) {
            props.setTTL(ttl);
        }
    }
    MetricsTable table = getOrCreateMetricsTable(tableName, props.build());
    return new FactTable(table, entityTable.get(), resolution, getRollTime(resolution));
}