[receiver/statsdreceiver] add support for distribution type metrics

.chloggen/anup_statsd_receiver_distribution_support.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: receiver/statsdreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Add support for distribution type metrics in the statsdreceiver."
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [24768]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: [user]

receiver/statsdreceiver/README.md

@@ -38,7 +38,7 @@ The Following settings are optional:
 - `timer_histogram_mapping:`(default value is below): Specify what OTLP type to convert received timing/histogram data to.
 
 
-`"statsd_type"` specifies received Statsd data type. Possible values for this setting are `"timing"`, `"timer"` and `"histogram"`.
+`"statsd_type"` specifies received Statsd data type. Possible values for this setting are `"timing"`, `"timer"`, `"histogram"` and `"distribution"`.
 
 `"observer_type"` specifies OTLP data type to convert to. We support `"gauge"`, `"summary"`, and `"histogram"`. For `"gauge"`, it does not perform any aggregation.
 For `"summary`, the statsD receiver will aggregate to one OTLP summary metric for one metric description (the same metric name with the same tags). It will send percentile 0, 10, 50, 90, 95, 100 to the downstream.  The `"histogram"` setting selects an [auto-scaling exponential histogram configured with only a maximum size](https://github.com/lightstep/go-expohisto#readme), as shown in the example below.
@@ -61,6 +61,10 @@ receivers:
         observer_type: "histogram"
         histogram: 
           max_size: 100
+      - statsd_type: "distribution"
+        observer_type: "histogram"
+        histogram: 
+          max_size: 50    
 ```
 
 The full list of settings exposed for this receiver are documented [here](./config.go)
@@ -138,6 +142,10 @@ receivers:
         observer_type: "histogram"
         histogram:
           max_size: 50
+      - statsd_type: "distribution"
+        observer_type: "histogram"
+        histogram: 
+          max_size: 50    
       - statsd_type: "timing"
         observer_type: "summary"
 

receiver/statsdreceiver/config.go

@@ -39,7 +39,7 @@ func (c *Config) Validate() error {
 		}
 
 		switch eachMap.StatsdType {
-		case protocol.TimingTypeName, protocol.TimingAltTypeName, protocol.HistogramTypeName:
+		case protocol.TimingTypeName, protocol.TimingAltTypeName, protocol.HistogramTypeName, protocol.DistributionTypeName:
 			// do nothing
 		case protocol.CounterTypeName, protocol.GaugeTypeName:
 			fallthrough

receiver/statsdreceiver/config_test.go

@@ -54,6 +54,13 @@ func TestLoadConfig(t *testing.T) {
 							MaxSize: 170,
 						},
 					},
+					{
+						StatsdType:   "distribution",
+						ObserverType: "histogram",
+						Histogram: protocol.HistogramConfig{
+							MaxSize: 170,
+						},
+					},
 				},
 			},
 		},

receiver/statsdreceiver/factory.go

@@ -25,7 +25,7 @@ const (
 )
 
 var (
-	defaultTimerHistogramMapping = []protocol.TimerHistogramMapping{{StatsdType: "timer", ObserverType: "gauge"}, {StatsdType: "histogram", ObserverType: "gauge"}}
+	defaultTimerHistogramMapping = []protocol.TimerHistogramMapping{{StatsdType: "timer", ObserverType: "gauge"}, {StatsdType: "histogram", ObserverType: "gauge"}, {StatsdType: "distribution", ObserverType: "gauge"}}
 )
 
 // NewFactory creates a factory for the StatsD receiver.

receiver/statsdreceiver/internal/protocol/statsd_parser.go

@@ -33,16 +33,18 @@ type (
 const (
 	tagMetricType = "metric_type"
 
-	CounterType   MetricType = "c"
-	GaugeType     MetricType = "g"
-	HistogramType MetricType = "h"
-	TimingType    MetricType = "ms"
-
-	CounterTypeName   TypeName = "counter"
-	GaugeTypeName     TypeName = "gauge"
-	HistogramTypeName TypeName = "histogram"
-	TimingTypeName    TypeName = "timing"
-	TimingAltTypeName TypeName = "timer"
+	CounterType      MetricType = "c"
+	GaugeType        MetricType = "g"
+	HistogramType    MetricType = "h"
+	TimingType       MetricType = "ms"
+	DistributionType MetricType = "d"
+
+	CounterTypeName      TypeName = "counter"
+	GaugeTypeName        TypeName = "gauge"
+	HistogramTypeName    TypeName = "histogram"
+	TimingTypeName       TypeName = "timing"
+	TimingAltTypeName    TypeName = "timer"
+	DistributionTypeName TypeName = "distribution"
 
 	GaugeObserver     ObserverType = "gauge"
 	SummaryObserver   ObserverType = "summary"
@@ -143,6 +145,8 @@ func (t MetricType) FullName() TypeName {
 		return TimingTypeName
 	case HistogramType:
 		return HistogramTypeName
+	case DistributionType:
+		return DistributionTypeName
 	}
 	return TypeName(fmt.Sprintf("unknown(%s)", t))
 }
@@ -162,7 +166,7 @@ func (p *StatsDParser) Initialize(enableMetricType bool, isMonotonicCounter bool
 	// Note: validation occurs in ("../".Config).validate()
 	for _, eachMap := range sendTimerHistogram {
 		switch eachMap.StatsdType {
-		case HistogramTypeName:
+		case HistogramTypeName, DistributionTypeName:
 			p.histogramEvents.method = eachMap.ObserverType
 			p.histogramEvents.histogramConfig = expoHistogramConfig(eachMap.Histogram)
 		case TimingTypeName, TimingAltTypeName:
@@ -255,7 +259,7 @@ var timeNowFunc = time.Now
 
 func (p *StatsDParser) observerCategoryFor(t MetricType) ObserverCategory {
 	switch t {
-	case HistogramType:
+	case HistogramType, DistributionType:
 		return p.histogramEvents
 	case TimingType:
 		return p.timerEvents
@@ -301,7 +305,7 @@ func (p *StatsDParser) Aggregate(line string, addr net.Addr) error {
 			point.SetIntValue(point.IntValue() + parsedMetric.counterValue())
 		}
 
-	case TimingType, HistogramType:
+	case TimingType, HistogramType, DistributionType:
 		category := p.observerCategoryFor(parsedMetric.description.metricType)
 		switch category.method {
 		case GaugeObserver:
@@ -372,7 +376,7 @@ func parseMessageToMetric(line string, enableMetricType bool) (statsDMetric, err
 
 	inType := MetricType(parts[1])
 	switch inType {
-	case CounterType, GaugeType, HistogramType, TimingType:
+	case CounterType, GaugeType, HistogramType, TimingType, DistributionType:
 		result.description.metricType = inType
 	default:
 		return result, fmt.Errorf("unsupported metric type: %s", inType)

receiver/statsdreceiver/internal/protocol/statsd_parser_test.go

@@ -409,6 +409,17 @@ func Test_ParseMessageToMetricWithMetricType(t *testing.T) {
 				[]string{"metric_type"},
 				[]string{"histogram"}),
 		},
+		{
+			name:  "int distribution",
+			input: "test.metric:42|d",
+			wantMetric: testStatsDMetric(
+				"test.metric",
+				42,
+				false,
+				"d", 0,
+				[]string{"metric_type"},
+				[]string{"distribution"}),
+		},
 	}
 
 	for _, tt := range tests {
@@ -632,12 +643,14 @@ func TestStatsDParser_Aggregate(t *testing.T) {
 			},
 		},
 		{
-			name: "counter and gauge: 2 timings and 2 histograms",
+			name: "counter and gauge: 2 timings and 2 histograms and 2 distribution",
 			input: []string{
 				"statsdTestMetric1:500|ms|#mykey:myvalue",
 				"statsdTestMetric1:400|h|#mykey:myvalue",
 				"statsdTestMetric1:300|ms|#mykey:myvalue",
 				"statsdTestMetric1:10|h|@0.1|#mykey:myvalue",
+				"statsdTestMetric1:100|d|#mykey:myvalue",
+				"statsdTestMetric1:200|d|#mykey:myvalue",
 			},
 			expectedGauges:   map[statsDMetricDescription]pmetric.ScopeMetrics{},
 			expectedCounters: map[statsDMetricDescription]pmetric.ScopeMetrics{},
@@ -646,6 +659,8 @@ func TestStatsDParser_Aggregate(t *testing.T) {
 				buildGaugeMetric(testStatsDMetric("statsdTestMetric1", 400, false, "h", 0, []string{"mykey"}, []string{"myvalue"}), time.Unix(711, 0)),
 				buildGaugeMetric(testStatsDMetric("statsdTestMetric1", 300, false, "ms", 0, []string{"mykey"}, []string{"myvalue"}), time.Unix(711, 0)),
 				buildGaugeMetric(testStatsDMetric("statsdTestMetric1", 10, false, "h", 0, []string{"mykey"}, []string{"myvalue"}), time.Unix(711, 0)),
+				buildGaugeMetric(testStatsDMetric("statsdTestMetric1", 100, false, "d", 0, []string{"mykey"}, []string{"myvalue"}), time.Unix(711, 0)),
+				buildGaugeMetric(testStatsDMetric("statsdTestMetric1", 200, false, "d", 0, []string{"mykey"}, []string{"myvalue"}), time.Unix(711, 0)),
 			},
 		},
 	}
@@ -933,6 +948,30 @@ func TestStatsDParser_AggregateTimerWithSummary(t *testing.T) {
 				},
 			},
 		},
+		{
+			name: "distribution",
+			input: []string{
+				"statsdTestMetric1:1|d|#mykey:myvalue",
+				"statsdTestMetric2:2|d|#mykey:myvalue",
+				"statsdTestMetric1:1|d|#mykey:myvalue",
+				"statsdTestMetric1:10|d|#mykey:myvalue",
+				"statsdTestMetric1:20|d|#mykey:myvalue",
+				"statsdTestMetric2:5|d|#mykey:myvalue",
+				"statsdTestMetric2:10|d|#mykey:myvalue",
+			},
+			expectedSummaries: map[statsDMetricDescription]summaryMetric{
+				testDescription("statsdTestMetric1", "d",
+					[]string{"mykey"}, []string{"myvalue"}): {
+					points:  []float64{1, 1, 10, 20},
+					weights: []float64{1, 1, 1, 1},
+				},
+				testDescription("statsdTestMetric2", "d",
+					[]string{"mykey"}, []string{"myvalue"}): {
+					points:  []float64{2, 5, 10},
+					weights: []float64{1, 1, 1},
+				},
+			},
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -1319,6 +1358,33 @@ func TestStatsDParser_AggregateTimerWithHistogram(t *testing.T) {
 			}(),
 			mapping: normalMapping,
 		},
+		{
+			name: "one_each_distribution",
+			input: []string{
+				"expohisto:1|d|#mykey:myvalue",
+				"expohisto:0|d|#mykey:myvalue",
+				"expohisto:-1|d|#mykey:myvalue",
+			},
+			expected: func() pmetric.Metrics {
+				data, dp := newPoint()
+				dp.SetCount(3)
+				dp.SetSum(0)
+				dp.SetMin(-1)
+				dp.SetMax(1)
+				dp.SetZeroCount(1)
+				dp.SetScale(logarithm.MaxScale)
+				dp.Positive().SetOffset(-1)
+				dp.Negative().SetOffset(-1)
+				dp.Positive().BucketCounts().FromRaw([]uint64{
+					1,
+				})
+				dp.Negative().BucketCounts().FromRaw([]uint64{
+					1,
+				})
+				return data
+			}(),
+			mapping: normalMapping,
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {

receiver/statsdreceiver/testdata/config.yaml

@@ -11,3 +11,7 @@ statsd/receiver_settings:
       observer_type: "histogram"
       histogram:
         max_size: 170
+    - statsd_type: "distribution"
+      observer_type: "histogram"
+      histogram:
+        max_size: 170