feat(scaler): add observability (metrics + tracing) to the external scaler #1634
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,81 @@ | ||
| package metrics | ||
|
Member
There was a problem hiding this comment. We should probably also add a test like the prometheus_test.go the interceptor has right now? |
||
|
|
||
| import ( | ||
| "context" | ||
| "fmt" | ||
| "time" | ||
|
|
||
| "go.opentelemetry.io/otel/attribute" | ||
| api "go.opentelemetry.io/otel/metric" | ||
| sdkmetric "go.opentelemetry.io/otel/sdk/metric" | ||
| ) | ||
|
|
||
| const ( | ||
| meterName = "keda-external-scaler" | ||
|
|
||
| // ServiceName is the OTEL service.name used for both metrics and tracing. | ||
| ServiceName = "keda-http-external-scaler" | ||
|
Member
There was a problem hiding this comment. We should probably also align the service name of the interceptor to use this naming scheme |
||
|
|
||
| MetricPingerFetchDuration = "scaler.pinger.fetch.duration" | ||
| MetricPingerFetchErrors = "scaler.pinger.fetch.errors" | ||
| MetricPingerEndpoints = "scaler.pinger.endpoints" | ||
|
|
||
| AttrNamespace = "namespace" | ||
| AttrService = "service" | ||
|
Comment on lines
+23
to
+24
|
||
| ) | ||
|
|
||
| // Instruments holds all metric instruments for the external scaler. | ||
| type Instruments struct { | ||
| pingerFetchDuration api.Float64Histogram | ||
| pingerFetchErrors api.Int64Counter | ||
| pingerEndpoints api.Int64Gauge | ||
| } | ||
|
|
||
| // NewInstruments creates metric instruments from a MeterProvider. | ||
| func NewInstruments(provider *sdkmetric.MeterProvider) (*Instruments, error) { | ||
| meter := provider.Meter(meterName) | ||
|
|
||
| pingerFetchDuration, err := meter.Float64Histogram( | ||
| MetricPingerFetchDuration, | ||
| api.WithDescription("Duration of a queue pinger fetch cycle across all interceptor pods"), | ||
| api.WithUnit("s"), | ||
| api.WithExplicitBucketBoundaries( | ||
| 0.005, 0.01, 0.025, 0.05, 0.075, 0.1, 0.25, 0.5, 0.75, 1, 2.5, 5, | ||
| ), | ||
| ) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("creating pinger fetch duration histogram: %w", err) | ||
| } | ||
|
|
||
| pingerFetchErrors, err := meter.Int64Counter( | ||
| MetricPingerFetchErrors, | ||
| api.WithDescription("Total failed queue pinger fetch cycles"), | ||
| ) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("creating pinger fetch errors counter: %w", err) | ||
| } | ||
|
|
||
| pingerEndpoints, err := meter.Int64Gauge( | ||
| MetricPingerEndpoints, | ||
| api.WithDescription("Number of interceptor endpoints the scaler is polling"), | ||
| ) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("creating pinger endpoints gauge: %w", err) | ||
| } | ||
|
|
||
| return &Instruments{ | ||
| pingerFetchDuration: pingerFetchDuration, | ||
| pingerFetchErrors: pingerFetchErrors, | ||
| pingerEndpoints: pingerEndpoints, | ||
| }, nil | ||
| } | ||
|
|
||
| // RecordFetch records a completed pinger fetch cycle. | ||
| func (i *Instruments) RecordFetch(duration time.Duration, endpointCount int, fetchErr error) { | ||
| attrs := api.WithAttributeSet(attribute.NewSet()) | ||
|
Member
There was a problem hiding this comment. Can be removed as there are no attributes |
||
| i.pingerFetchDuration.Record(context.Background(), duration.Seconds(), attrs) | ||
| i.pingerEndpoints.Record(context.Background(), int64(endpointCount), attrs) | ||
| if fetchErr != nil { | ||
| i.pingerFetchErrors.Add(context.Background(), 1, attrs) | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,51 @@ | ||
| package metrics | ||
|
Member
There was a problem hiding this comment. This looks like a copy of interceptor/provider/metrics.go, we should deduplicate this code. |
||
|
|
||
| import ( | ||
| "context" | ||
| "fmt" | ||
|
|
||
| "go.opentelemetry.io/otel/attribute" | ||
| "go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetrichttp" | ||
| "go.opentelemetry.io/otel/exporters/prometheus" | ||
| sdkmetric "go.opentelemetry.io/otel/sdk/metric" | ||
| "go.opentelemetry.io/otel/sdk/resource" | ||
|
|
||
| "github.com/kedacore/http-add-on/pkg/build" | ||
| ) | ||
|
|
||
| // NewMeterProvider creates a MeterProvider with Prometheus and/or OTLP readers. | ||
| // Without readers, all instrument operations become no-ops. | ||
| func NewMeterProvider(promEnabled, otlpEnabled bool, opts ...sdkmetric.Option) (*sdkmetric.MeterProvider, error) { | ||
| var options []sdkmetric.Option | ||
|
|
||
| if promEnabled { | ||
| promExporter, err := prometheus.New( | ||
| prometheus.WithoutScopeInfo(), | ||
| ) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("creating prometheus exporter: %w", err) | ||
| } | ||
| options = append(options, sdkmetric.WithReader(promExporter)) | ||
| } | ||
|
|
||
| if otlpEnabled { | ||
| otlpExporter, err := otlpmetrichttp.New(context.Background()) | ||
| if err != nil { | ||
| return nil, fmt.Errorf("creating OTLP exporter: %w", err) | ||
| } | ||
| options = append(options, sdkmetric.WithReader( | ||
| sdkmetric.NewPeriodicReader(otlpExporter), | ||
| )) | ||
| } | ||
|
|
||
| options = append(options, sdkmetric.WithResource( | ||
| resource.NewSchemaless( | ||
| attribute.String("service.name", ServiceName), | ||
| attribute.String("service.version", build.Version()), | ||
| ), | ||
| )) | ||
|
Fedosin marked this conversation as resolved.
|
||
|
|
||
| options = append(options, opts...) | ||
|
|
||
| return sdkmetric.NewMeterProvider(options...), nil | ||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I guess we could also deduplicate the config to ensure it is consistent across components?