Search in sources :

Example 6 with ComponentMetricsHelper

use of com.twitter.heron.healthmgr.common.ComponentMetricsHelper in project incubator-heron by apache.

the class DataSkewDiagnoser method diagnose.

@Override
public Diagnosis diagnose(List<Symptom> symptoms) {
    List<Symptom> bpSymptoms = getBackPressureSymptoms(symptoms);
    Map<String, ComponentMetrics> processingRateSkewComponents = getProcessingRateSkewComponents(symptoms);
    Map<String, ComponentMetrics> waitQDisparityComponents = getWaitQDisparityComponents(symptoms);
    if (bpSymptoms.isEmpty() || processingRateSkewComponents.isEmpty() || waitQDisparityComponents.isEmpty()) {
        // Since there is no back pressure or disparate execute count, no action is needed
        return null;
    } else if (bpSymptoms.size() > 1) {
        // TODO handle cases where multiple detectors create back pressure symptom
        throw new IllegalStateException("Multiple back-pressure symptoms case");
    }
    ComponentMetrics bpMetrics = bpSymptoms.iterator().next().getComponent();
    // verify data skew, larger queue size and back pressure for the same component exists
    ComponentMetrics exeCountMetrics = processingRateSkewComponents.get(bpMetrics.getName());
    ComponentMetrics pendingBufferMetrics = waitQDisparityComponents.get(bpMetrics.getName());
    if (exeCountMetrics == null || pendingBufferMetrics == null) {
        // for the component with back pressure. This is not a data skew case
        return null;
    }
    ComponentMetrics mergedData = ComponentMetrics.merge(bpMetrics, ComponentMetrics.merge(exeCountMetrics, pendingBufferMetrics));
    ComponentMetricsHelper compStats = new ComponentMetricsHelper(mergedData);
    compStats.computeBpStats();
    MetricsStats exeStats = compStats.computeMinMaxStats(METRIC_EXE_COUNT);
    MetricsStats bufferStats = compStats.computeMinMaxStats(METRIC_BUFFER_SIZE);
    Symptom resultSymptom = null;
    for (InstanceMetrics boltMetrics : compStats.getBoltsWithBackpressure()) {
        double exeCount = boltMetrics.getMetricValueSum(METRIC_EXE_COUNT.text());
        double bufferSize = boltMetrics.getMetricValueSum(METRIC_BUFFER_SIZE.text());
        double bpValue = boltMetrics.getMetricValueSum(METRIC_BACK_PRESSURE.text());
        if (exeStats.getMetricMax() < 1.10 * exeCount && bufferStats.getMetricMax() < 2 * bufferSize) {
            LOG.info(String.format("DataSkew: %s back-pressure(%s), high execution count: %s and " + "high buffer size %s", boltMetrics.getName(), bpValue, exeCount, bufferSize));
            resultSymptom = new Symptom(SYMPTOM_DATA_SKEW.text(), mergedData);
        }
    }
    return resultSymptom != null ? new Diagnosis(DIAGNOSIS_DATA_SKEW.text(), resultSymptom) : null;
}
Also used : InstanceMetrics(com.microsoft.dhalion.metrics.InstanceMetrics) ComponentMetricsHelper(com.twitter.heron.healthmgr.common.ComponentMetricsHelper) Diagnosis(com.microsoft.dhalion.diagnoser.Diagnosis) Symptom(com.microsoft.dhalion.detector.Symptom) ComponentMetrics(com.microsoft.dhalion.metrics.ComponentMetrics) MetricsStats(com.twitter.heron.healthmgr.common.MetricsStats)

Example 7 with ComponentMetricsHelper

use of com.twitter.heron.healthmgr.common.ComponentMetricsHelper in project incubator-heron by apache.

the class UnderProvisioningDiagnoser method diagnose.

@Override
public Diagnosis diagnose(List<Symptom> symptoms) {
    List<Symptom> bpSymptoms = getBackPressureSymptoms(symptoms);
    Map<String, ComponentMetrics> processingRateSkewComponents = getProcessingRateSkewComponents(symptoms);
    Map<String, ComponentMetrics> waitQDisparityComponents = getWaitQDisparityComponents(symptoms);
    if (bpSymptoms.isEmpty() || !processingRateSkewComponents.isEmpty() || !waitQDisparityComponents.isEmpty()) {
        // and buffer sizes, no action is needed
        return null;
    } else if (bpSymptoms.size() > 1) {
        // TODO handle cases where multiple detectors create back pressure symptom
        throw new IllegalStateException("Multiple back-pressure symptoms case");
    }
    ComponentMetrics bpMetrics = bpSymptoms.iterator().next().getComponent();
    ComponentMetricsHelper compStats = new ComponentMetricsHelper(bpMetrics);
    compStats.computeBpStats();
    LOG.info(String.format("UNDER_PROVISIONING: %s back-pressure(%s) and similar processing rates " + "and buffer sizes", bpMetrics.getName(), compStats.getTotalBackpressure()));
    Symptom resultSymptom = new Symptom(SYMPTOM_UNDER_PROVISIONING.text(), bpMetrics);
    return new Diagnosis(DIAGNOSIS_UNDER_PROVISIONING.text(), resultSymptom);
}
Also used : ComponentMetricsHelper(com.twitter.heron.healthmgr.common.ComponentMetricsHelper) Diagnosis(com.microsoft.dhalion.diagnoser.Diagnosis) Symptom(com.microsoft.dhalion.detector.Symptom) ComponentMetrics(com.microsoft.dhalion.metrics.ComponentMetrics)

Aggregations

Symptom (com.microsoft.dhalion.detector.Symptom)7 ComponentMetrics (com.microsoft.dhalion.metrics.ComponentMetrics)7 ComponentMetricsHelper (com.twitter.heron.healthmgr.common.ComponentMetricsHelper)7 MetricsStats (com.twitter.heron.healthmgr.common.MetricsStats)4 ArrayList (java.util.ArrayList)4 Diagnosis (com.microsoft.dhalion.diagnoser.Diagnosis)3 InstanceMetrics (com.microsoft.dhalion.metrics.InstanceMetrics)2