feat: add otel tracing support for Refinery internal operations

.gitignore

@@ -23,3 +23,6 @@ dockerize*
 .idea/
 
 .DS_Store
+
+# redis dump file
+*.rdb

cmd/refinery/main.go

@@ -11,6 +11,8 @@ import (
 	"syscall"
 	"time"
 
+	"go.opentelemetry.io/otel/trace"
+	"go.opentelemetry.io/otel/trace/noop"
 	_ "go.uber.org/automaxprocs"
 	"golang.org/x/exp/slices"
 
@@ -23,6 +25,7 @@ import (
 	"github.com/honeycombio/refinery/app"
 	"github.com/honeycombio/refinery/collect"
 	"github.com/honeycombio/refinery/config"
+	"github.com/honeycombio/refinery/internal/otelutil"
 	"github.com/honeycombio/refinery/internal/peer"
 	"github.com/honeycombio/refinery/logger"
 	"github.com/honeycombio/refinery/metrics"
@@ -198,6 +201,18 @@ func main() {
 		oTelMetrics = &metrics.OTelMetrics{}
 	}
 
+	resourceLib := "refinery"
+	resourceVer := version
+	tracer := trace.Tracer(noop.Tracer{})
+	shutdown := func() {}
+
+	if c.GetOTelTracingConfig().Enabled {
+		// let's set up some OTel tracing
+		tracer, shutdown = otelutil.SetupTracing(c.GetOTelTracingConfig(), resourceLib, resourceVer)
+	}
+
+	defer shutdown()
+
 	// we need to include all the metrics types so we can inject them in case they're needed
 	var g inject.Graph
 	if opts.Debug {
@@ -216,6 +231,8 @@ func main() {
 		{Value: legacyMetrics, Name: "legacyMetrics"},
 		{Value: promMetrics, Name: "promMetrics"},
 		{Value: oTelMetrics, Name: "otelMetrics"},
+		{Value: tracer, Name: "tracer"},
+
 		{Value: metricsSingleton, Name: "metrics"},
 		{Value: genericMetricsRecorder, Name: "genericMetrics"},
 		{Value: upstreamMetricsRecorder, Name: "upstreamMetrics"},

config/cmdenv.go

@@ -40,6 +40,7 @@ type CmdEnv struct {
 	HoneycombLoggerAPIKey string     `long:"logger-api-key" env:"REFINERY_HONEYCOMB_LOGGER_API_KEY" description:"Honeycomb logger API key"`
 	LegacyMetricsAPIKey   string     `long:"legacy-metrics-api-key" env:"REFINERY_HONEYCOMB_METRICS_API_KEY" description:"API key for legacy Honeycomb metrics"`
 	OTelMetricsAPIKey     string     `long:"otel-metrics-api-key" env:"REFINERY_OTEL_METRICS_API_KEY" description:"API key for OTel metrics if being sent to Honeycomb"`
+	OTelTracesAPIKey      string     `long:"otel-traces-api-key" env:"REFINERY_OTEL_TRACES_API_KEY" description:"API key for OTel metrics if being sent to Honeycomb"`
 	QueryAuthToken        string     `long:"query-auth-token" env:"REFINERY_QUERY_AUTH_TOKEN" description:"Token for debug/management queries"`
 	AvailableMemory       MemorySize `long:"available-memory" env:"REFINERY_AVAILABLE_MEMORY" description:"The maximum memory available for Refinery to use (ex: 4GiB)."`
 	Debug                 bool       `short:"d" long:"debug" description:"Runs debug service (on the first open port between localhost:6060 and :6069 by default)"`

config/config.go

@@ -146,6 +146,8 @@ type Config interface {
 
 	GetIdentifierInterfaceName() (string, error)
 
+	GetOTelTracingConfig() OTelTracingConfig
+
 	GetUseIPV6Identifier() (bool, error)
 
 	GetRedisIdentifier() (string, error)

config/configLoadHelpers.go

@@ -167,6 +167,10 @@ func validateConfig(opts *CmdEnv) ([]string, error) {
 		config.OTelMetrics.APIKey = "InvalidHoneycombAPIKey"
 	}
 
+	if config.OTelTracing.APIKey == "" {
+		config.OTelTracing.APIKey = "InvalidHoneycombAPIKey"
+	}
+
 	// write it out to a YAML buffer
 	buf := new(bytes.Buffer)
 	encoder := yaml.NewEncoder(buf)

config/file_config.go

@@ -59,6 +59,7 @@ type configContents struct {
 	PrometheusMetrics    PrometheusMetricsConfig   `yaml:"PrometheusMetrics"`
 	LegacyMetrics        LegacyMetricsConfig       `yaml:"LegacyMetrics"`
 	OTelMetrics          OTelMetricsConfig         `yaml:"OTelMetrics"`
+	OTelTracing          OTelTracingConfig         `yaml:"OTelTracing"`
 	PeerManagement       PeerManagementConfig      `yaml:"PeerManagement"`
 	RedisPeerManagement  RedisPeerManagementConfig `yaml:"RedisPeerManagement"`
 	Collection           CollectionConfig          `yaml:"Collection"`
@@ -183,6 +184,14 @@ type OTelMetricsConfig struct {
 	ReportingInterval Duration `yaml:"ReportingInterval" default:"30s"`
 }
 
+type OTelTracingConfig struct {
+	Enabled    bool   `yaml:"Enabled" default:"false"`
+	APIHost    string `yaml:"APIHost" default:"https://api.honeycomb.io"`
+	APIKey     string `yaml:"APIKey" cmdenv:"OTelTracesAPIKey,HoneycombAPIKey"`
+	Dataset    string `yaml:"Dataset" default:"Refinery Traces"`
+	SampleRate uint64 `yaml:"SampleRate" default:"100"`
+}
+
 type PeerManagementConfig struct {
 	Type                    string   `yaml:"Type" default:"file"`
 	Identifier              string   `yaml:"Identifier"`
@@ -832,6 +841,13 @@ func (f *fileConfig) GetEnvironmentCacheTTL() time.Duration {
 	return time.Duration(f.mainConfig.Specialized.EnvironmentCacheTTL)
 }
 
+func (f *fileConfig) GetOTelTracingConfig() OTelTracingConfig {
+	f.mux.RLock()
+	defer f.mux.RUnlock()
+
+	return f.mainConfig.OTelTracing
+}
+
 func (f *fileConfig) GetDatasetPrefix() string {
 	f.mux.RLock()
 	defer f.mux.RUnlock()

config/metadata/configMeta.yaml

@@ -740,6 +740,78 @@ groups:
           compression costs may outweigh the benefits, in which case `none`
           may be used.
 
+  - name: OTelTracing
+    title: "OpenTelemetry Tracing"
+    description: contains configuration for Refinery's own tracing.
+    fields:
+      - name: Enabled
+        type: bool
+        valuetype: nondefault
+        default: false
+        reload: false
+        firstversion: v2.6
+        summary: controls whether to send Refinery's own otel traces.
+        description: >
+          The setting specifies if Refinery sends traces.
+
+      - name: APIHost
+        type: url
+        valuetype: nondefault
+        default: "https://api.honeycomb.io"
+        reload: false
+        firstversion: v2.6
+        summary: is the URL of the OpenTelemetry API to which traces will be sent.
+        description: >
+          Refinery's internal traces will be sent to the `/v1/traces`
+          endpoint on this host.
+
+      - name: APIKey
+        type: string
+        pattern: apikey
+        valuetype: nondefault
+        default: ""
+        example: "SetThisToAHoneycombKey"
+        reload: false
+        firstversion: v2.6
+        envvar: REFINERY_HONEYCOMB_TRACES_API_KEY, REFINERY_HONEYCOMB_API_KEY
+        commandline: otel-traces-api-key
+        validations:
+          - type: format
+            arg: apikey
+        summary: is the API key used to send Refinery's traces to Honeycomb.
+        description: >
+          It is recommended that you create a separate team and key for
+          Refinery telemetry.
+          If this is blank, then Refinery will not set the Honeycomb-specific
+          headers for OpenTelemetry, and your `APIHost` must be set to a
+          valid OpenTelemetry endpoint.
+
+      - name: Dataset
+        type: string
+        valuetype: nondefault
+        default: "Refinery Traces"
+        reload: false
+        validations:
+          - type: notempty
+        firstversion: v2.6
+        summary: is the Honeycomb dataset to which Refinery sends its OpenTelemetry metrics.
+        description: >
+          Only used if `APIKey` is specified.
+
+      - name: SampleRate
+        type: int
+        valuetype: nondefault
+        default: 100
+        validations:
+          - type: minimum
+            arg: 1
+        reload: true
+        summary: is the rate at which Refinery samples its own traces.
+        description: >
+          This is the Honeycomb sample rate used to sample traces sent by Refinery. Since each
+          incoming span generates multiple outgoing spans, a sample rate of at least 100 is
+          strongly advised.
+
   - name: PeerManagement
     title: "Peer Management"
     description: controls how the Refinery cluster communicates between peers.

config/mock.go

@@ -58,6 +58,7 @@ type MockConfig struct {
 	GetLegacyMetricsConfigVal        LegacyMetricsConfig
 	GetPrometheusMetricsConfigVal    PrometheusMetricsConfig
 	GetOTelMetricsConfigVal          OTelMetricsConfig
+	GetOTelTracingConfigVal          OTelTracingConfig
 	GetSendDelayErr                  error
 	GetSendDelayVal                  time.Duration
 	GetBatchTimeoutVal               time.Duration
@@ -295,6 +296,13 @@ func (m *MockConfig) GetOTelMetricsConfig() OTelMetricsConfig {
 	return m.GetOTelMetricsConfigVal
 }
 
+func (m *MockConfig) GetOTelTracingConfig() OTelTracingConfig {
+	m.Mux.RLock()
+	defer m.Mux.RUnlock()
+
+	return m.GetOTelTracingConfigVal
+}
+
 func (m *MockConfig) GetSendDelay() (time.Duration, error) {
 	m.Mux.RLock()
 	defer m.Mux.RUnlock()

go.mod

@@ -18,6 +18,7 @@ require (
 	github.com/honeycombio/dynsampler-go v0.6.0
 	github.com/honeycombio/husky v0.30.0
 	github.com/honeycombio/libhoney-go v1.23.1
+	github.com/honeycombio/otel-config-go v1.16.0
 	github.com/jessevdk/go-flags v1.5.0
 	github.com/jonboulle/clockwork v0.4.0
 	github.com/json-iterator/go v1.1.12
@@ -38,7 +39,8 @@ require (
 	go.opentelemetry.io/otel/metric v1.27.0
 	go.opentelemetry.io/otel/sdk v1.27.0
 	go.opentelemetry.io/otel/sdk/metric v1.27.0
-	go.opentelemetry.io/proto/otlp v1.2.0
+	go.opentelemetry.io/otel/trace v1.27.0
+	go.opentelemetry.io/proto/otlp v1.3.1
 	go.uber.org/automaxprocs v1.5.3
 	golang.org/x/exp v0.0.0-20231127185646-65229373498e
 	google.golang.org/grpc v1.64.0
@@ -57,28 +59,43 @@ require (
 	github.com/facebookgo/limitgroup v0.0.0-20150612190941-6abd8d71ec01 // indirect
 	github.com/facebookgo/muster v0.0.0-20150708232844-fd3d7953fd52 // indirect
 	github.com/facebookgo/structtag v0.0.0-20150214074306-217e25fb9691 // indirect
-	github.com/go-logr/logr v1.4.1 // indirect
+	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-ole/go-ole v1.3.0 // indirect
 	github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 // indirect
+	github.com/lufia/plan9stats v0.0.0-20240513124658-fba389f38bae // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
 	github.com/prometheus/client_model v0.5.0 // indirect
 	github.com/prometheus/common v0.48.0 // indirect
 	github.com/prometheus/procfs v0.12.0 // indirect
+	github.com/sethvargo/go-envconfig v1.0.3 // indirect
+	github.com/shirou/gopsutil/v3 v3.24.5 // indirect
+	github.com/shoenig/go-m1cpu v0.1.6 // indirect
 	github.com/tidwall/match v1.1.1 // indirect
 	github.com/tidwall/pretty v1.2.0 // indirect
+	github.com/tklauser/go-sysconf v0.3.14 // indirect
+	github.com/tklauser/numcpus v0.8.0 // indirect
 	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
-	go.opentelemetry.io/otel/trace v1.27.0 // indirect
-	go.uber.org/atomic v1.7.0 // indirect
-	go.uber.org/multierr v1.9.0 // indirect
-	golang.org/x/net v0.25.0 // indirect
-	golang.org/x/sys v0.20.0 // indirect
-	golang.org/x/text v0.15.0 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20240520151616-dc85e6b867a5 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20240515191416-fc5f0ca64291 // indirect
+	github.com/yusufpapurcu/wmi v1.2.4 // indirect
+	go.opentelemetry.io/contrib/instrumentation/host v0.52.0 // indirect
+	go.opentelemetry.io/contrib/instrumentation/runtime v0.52.0 // indirect
+	go.opentelemetry.io/contrib/propagators/b3 v1.27.0 // indirect
+	go.opentelemetry.io/contrib/propagators/ot v1.27.0 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.27.0 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.27.0 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.27.0 // indirect
+	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.27.0 // indirect
+	go.uber.org/multierr v1.11.0 // indirect
+	golang.org/x/net v0.26.0 // indirect
+	golang.org/x/sys v0.21.0 // indirect
+	golang.org/x/text v0.16.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240617180043-68d350f18fd4 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240617180043-68d350f18fd4 // indirect
 )
 
-replace go.opentelemetry.io/proto/otlp => github.com/honeycombio/opentelemetry-proto-go/otlp v0.19.0-compat
+replace go.opentelemetry.io/proto/otlp => github.com/honeycombio/opentelemetry-proto-go/otlp v1.3.1-compat
 
 replace github.com/panmari/cuckoofilter => github.com/honeycombio/cuckoofilter v0.0.0-20230630225016-cf48793fb7c1