[
https://issues.apache.org/jira/browse/BEAM-11425?focusedWorklogId=522196&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-522196
]
ASF GitHub Bot logged work on BEAM-11425:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 09/Dec/20 11:45
Start Date: 09/Dec/20 11:45
Worklog Time Spent: 10m
Work Description: kamilwu commented on a change in pull request #13505:
URL: https://github.com/apache/beam/pull/13505#discussion_r539238569
##########
File path: sdks/go/pkg/beam/runners/dataflow/dataflowlib/metrics.go
##########
@@ -0,0 +1,125 @@
+// Licensed to the Apache Software Foundation (ASF) under one or more
+// contributor license agreements. See the NOTICE file distributed with
+// this work for additional information regarding copyright ownership.
+// The ASF licenses this file to You under the Apache License, Version 2.0
+// (the "License"); you may not use this file except in compliance with
+// the License. You may obtain a copy of the License at
+//
+// http://www.apache.org/licenses/LICENSE-2.0
+//
+// Unless required by applicable law or agreed to in writing, software
+// distributed under the License is distributed on an "AS IS" BASIS,
+// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+// See the License for the specific language governing permissions and
+// limitations under the License.
+
+// Package dataflowlib translates a Beam pipeline model to the
+// Dataflow API job model, for submission to Google Cloud Dataflow.
+
+package dataflowlib
+
+import (
+ "encoding/json"
+ "fmt"
+
+ "github.com/apache/beam/sdks/go/pkg/beam/core/metrics"
+ df "google.golang.org/api/dataflow/v1b3"
+)
+
+// FromMetricUpdates extracts metrics from a slice of MetricUpdate objects and
+// groups them into counters, distributions and gauges.
+//
+// Dataflow currently only reports Counter and Distribution metrics to Cloud
+// Monitoring. Gauge metrics are not supported. The output metrics.Results will
+// not contain any gauges.
+func FromMetricUpdates(allMetrics []*df.MetricUpdate, job *df.Job)
*metrics.Results {
+ ac, ad := groupByType(allMetrics, job, true)
+ cc, cd := groupByType(allMetrics, job, false)
+
+ return metrics.NewResults(metrics.MergeCounters(ac, cc),
metrics.MergeDistributions(ad, cd), make([]metrics.GaugeResult, 0))
+}
+
+func groupByType(allMetrics []*df.MetricUpdate, job *df.Job, tentative bool) (
+ map[metrics.StepKey]int64,
+ map[metrics.StepKey]metrics.DistributionValue) {
+ counters := make(map[metrics.StepKey]int64)
+ distributions := make(map[metrics.StepKey]metrics.DistributionValue)
+
+ for _, metric := range allMetrics {
+ isTentative := metric.Name.Context["tentative"] == "true"
+ // Returns true when variables differ (exclusive or)
+ if (isTentative || tentative) && (!isTentative || !tentative) {
+ continue
+ }
+
+ key, err := extractKey(metric, job)
+ if err != nil {
+ continue
+ }
+
+ if metric.Scalar != nil {
+ v, err := extractCounterValue(metric.Scalar)
+ if err != nil {
+ continue
+ }
+ counters[key] = v
+ } else if metric.Distribution != nil {
+ v, err := extractDistributionValue(metric.Distribution)
+ if err != nil {
+ continue
+ }
+ distributions[key] = v
+ }
+ }
+ return counters, distributions
+}
+
+func extractKey(metric *df.MetricUpdate, job *df.Job) (metrics.StepKey, error)
{
+ stepName, ok := metric.Name.Context["step"]
+ if !ok {
+ return metrics.StepKey{}, fmt.Errorf("could not find the
internal step name")
+ }
+ userStepName := ""
+
+ for _, step := range job.Steps {
+ if step.Name == stepName {
+ properties := make(map[string]string)
+ json.Unmarshal(step.Properties, &properties)
+ userStepName = properties["user_name"]
+ break
+ }
+ }
+ if userStepName == "" {
+ return metrics.StepKey{}, fmt.Errorf("could not translate the
internal step name %v", stepName)
+ }
+
+ namespace := metric.Name.Context["namespace"]
+ if namespace == "" {
+ namespace = "dataflow/v1b3"
+ }
+
+ return metrics.StepKey{Step: userStepName, Name: metric.Name.Name,
Namespace: namespace}, nil
+}
+
+func extractCounterValue(obj interface{}) (int64, error) {
+ v, ok := obj.(float64)
+ if !ok {
+ return -1, fmt.Errorf("expected float64, got data of type %T
instead", obj)
+ }
+ return int64(v), nil
+}
+
+func extractDistributionValue(obj interface{}) (metrics.DistributionValue,
error) {
+ m := obj.(map[string]interface{})
+ propertiesToVisit := []string{"count", "sum", "min", "max"}
+ values := make([]int64, 4)
+
+ for i, p := range propertiesToVisit {
+ v, ok := m[p].(float64)
+ if !ok {
+ return metrics.DistributionValue{},
fmt.Errorf("expected float64, got data of type %T instead", m[p])
+ }
+ values[i] = int64(v)
+ }
+ return metrics.DistributionValue{Count: values[0], Sum: values[1], Min:
values[2], Max: values[3]}, nil
+}
Review comment:
Good to hear that!
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 522196)
Time Spent: 1h (was: 50m)
> [Go SDK] Support metrics querying (Dataflow)
> --------------------------------------------
>
> Key: BEAM-11425
> URL: https://issues.apache.org/jira/browse/BEAM-11425
> Project: Beam
> Issue Type: Sub-task
> Components: sdk-go
> Reporter: Kamil Wasilewski
> Assignee: Kamil Wasilewski
> Priority: P2
> Time Spent: 1h
> Remaining Estimate: 0h
>
> The idea of querying metrics described in the parent ticket doesn't apply to
> Dataflow runner. Instead, we can get metrics from Monitoring API (this is how
> it works in Python SDK:
> https://github.com/apache/beam/blob/master/sdks/python/apache_beam/runners/dataflow/dataflow_metrics.py)
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
