feat(OpenTelemetry): Integrate OpenTelemetry into agent (#90)

* feat(OpenTelemetry): Integrate OpenTelemetry into agent

- integrate OpenTelemetry logging with zap logger for better observability
- add OpenTelemetry gRPC middleware for enhanced tracing capabilities
- document new OTLP exporter endpoint for better configuration guidance

* docs: document OTEL env var

---------

Co-authored-by: Cedric Kienzler <cedric@specht-labs.de>
This commit is contained in:
Cedric Kienzler
2025-06-06 22:43:37 +02:00
committed by GitHub
parent ca5e9258fa
commit 7ec49ce05c
16 changed files with 192 additions and 83 deletions

View File

@@ -89,6 +89,7 @@ BLADE_LISTEN_METRICS=":1234"
| `BLADE_FAN_SPEED_PERCENT=80` | Set static fan speed |
| `BLADE_CRITICAL_TEMPERATURE_THRESHOLD=60` | Set critical temp threshold (°C) |
| `BLADE_HAL_RPM_REPORTING_STANDARD_FAN_UNIT=false` | Disable RPM monitoring for lower CPU use |
| `OTEL_EXPORTER_OTLP_ENDPOINT` | Endpoint for the OTLP exporter |
## Exposing the gRPC API for Remote Access

View File

@@ -17,6 +17,8 @@ import (
"github.com/compute-blade-community/compute-blade-agent/internal/api"
"github.com/compute-blade-community/compute-blade-agent/pkg/log"
"github.com/prometheus/client_golang/prometheus/promhttp"
"github.com/spechtlabs/go-otel-utils/otelprovider"
"github.com/spechtlabs/go-otel-utils/otelzap"
"github.com/spf13/pflag"
"github.com/spf13/viper"
"go.uber.org/zap"
@@ -25,7 +27,6 @@ import (
var (
Version string
Commit string
Date string
)
var debug = pflag.BoolP("debug", "v", false, "enable verbose logging")
@@ -55,13 +56,68 @@ func main() {
baseLogger = zap.Must(zap.NewProduction())
}
zapLogger := baseLogger.With(zap.String("app", "compute-blade-agent"))
zapLogger := baseLogger.With(
zap.String("app", "compute-blade-agent"),
zap.String("version", Version),
zap.String("commit", Commit),
)
defer func() {
_ = zapLogger.Sync()
}()
_ = zap.ReplaceGlobals(zapLogger.With(zap.String("scope", "global")))
baseCtx := log.IntoContext(context.Background(), zapLogger)
// Replace zap global
undoZapGlobals := zap.ReplaceGlobals(zapLogger)
// Redirect stdlib log to zap
undoStdLogRedirect := zap.RedirectStdLog(zapLogger)
// Create OpenTelemetry Log and Trace provider
logProvider := otelprovider.NewLogger(
otelprovider.WithLogAutomaticEnv(),
)
traceProvider := otelprovider.NewTracer(
otelprovider.WithTraceAutomaticEnv(),
)
// Create otelLogger
otelZapLogger := otelzap.New(zapLogger,
otelzap.WithCaller(true),
otelzap.WithMinLevel(zap.InfoLevel),
otelzap.WithAnnotateLevel(zap.WarnLevel),
otelzap.WithErrorStatusLevel(zap.ErrorLevel),
otelzap.WithStackTrace(false),
otelzap.WithLoggerProvider(logProvider),
)
// Replace global otelZap logger
undoOtelZapGlobals := otelzap.ReplaceGlobals(otelZapLogger)
defer undoOtelZapGlobals()
// Cleanup Logging and Tracing
defer func() {
if err := traceProvider.ForceFlush(context.Background()); err != nil {
otelzap.L().Warn("failed to flush traces")
}
if err := logProvider.ForceFlush(context.Background()); err != nil {
otelzap.L().Warn("failed to flush logs")
}
if err := traceProvider.Shutdown(context.Background()); err != nil {
panic(err)
}
if err := logProvider.Shutdown(context.Background()); err != nil {
panic(err)
}
undoStdLogRedirect()
undoZapGlobals()
}()
// Setup context
baseCtx := log.IntoContext(context.Background(), otelZapLogger)
ctx, cancelCtx := context.WithCancelCause(baseCtx)
defer cancelCtx(context.Canceled)
@@ -69,7 +125,7 @@ func main() {
var cbAgentConfig agent.ComputeBladeAgentConfig
if err := viper.Unmarshal(&cbAgentConfig); err != nil {
cancelCtx(err)
log.FromContext(ctx).Fatal("Failed to load configuration", zap.Error(err))
log.FromContext(ctx).WithError(err).Fatal("Failed to load configuration")
}
// setup stop signal handlers
@@ -97,11 +153,11 @@ func main() {
}
}()
log.FromContext(ctx).Info("Bootstrapping compute-blade-agent", zap.String("version", Version), zap.String("commit", Commit), zap.String("date", Date))
log.FromContext(ctx).Info("Bootstrapping compute-blade-agent")
computebladeAgent, err := agent.NewComputeBladeAgent(ctx, cbAgentConfig)
if err != nil {
cancelCtx(err)
log.FromContext(ctx).Fatal("Failed to create agent", zap.Error(err))
log.FromContext(ctx).WithError(err).Fatal("Failed to create agent")
}
// Run agent
@@ -124,13 +180,17 @@ func main() {
// Wait for done
<-ctx.Done()
// Since ctx is now done, we can no longer use it to get `log.FromContext(ctx)`
// but we must use otelzap.L() to get a logger
// Shut down gRPC and Prom Servers async
var wg sync.WaitGroup
// Shut-Down GRPC Server
wg.Add(1)
go func() {
defer wg.Done()
log.FromContext(ctx).Info("Shutting down grpc server")
otelzap.L().Info("Shutting down grpc server")
grpcServer.GracefulStop()
}()
@@ -142,18 +202,19 @@ func main() {
shutdownCtx, shutdownCtxCancel := context.WithTimeout(context.Background(), 5*time.Second)
defer shutdownCtxCancel()
otelzap.L().Info("Shutting down prometheus/pprof server")
if err := promServer.Shutdown(shutdownCtx); err != nil {
log.FromContext(ctx).Error("Failed to shutdown prometheus/pprof server", zap.Error(err))
otelzap.L().WithError(err).Error("Failed to shutdown prometheus/pprof server")
}
}()
wg.Wait()
// Wait for context cancel
// Terminate accordingly
if err := ctx.Err(); !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Fatal("Exiting", zap.Error(err))
otelzap.L().WithError(err).Fatal("Exiting")
} else {
log.FromContext(ctx).Info("Exiting")
otelzap.L().Info("Exiting")
}
}
@@ -172,7 +233,7 @@ func runPrometheusEndpoint(ctx context.Context, cancel context.CancelCauseFunc,
go func() {
err := server.ListenAndServe()
if err != nil && !errors.Is(err, http.ErrServerClosed) {
log.FromContext(ctx).Error("Failed to start prometheus/pprof server", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to start prometheus/pprof server")
cancel(err)
}
}()

View File

@@ -2,6 +2,7 @@ package main
import (
"errors"
bladeapiv1alpha1 "github.com/compute-blade-community/compute-blade-agent/api/bladeapi/v1alpha1"
"github.com/sierrasoftworks/humane-errors-go"
"github.com/spf13/cobra"

View File

@@ -6,7 +6,7 @@ import (
"path/filepath"
"github.com/sierrasoftworks/humane-errors-go"
"go.uber.org/zap"
"github.com/spechtlabs/go-otel-utils/otelzap"
)
type BladectlConfig struct {
@@ -58,7 +58,7 @@ func NewAuthenticatedBladectlConfig(server string, caPEM []byte, clientCertDER [
func NewBladectlConfig(server string) *BladectlConfig {
hostname, err := os.Hostname()
if err != nil {
zap.L().Fatal("Failed to extract hostname", zap.Error(err))
otelzap.L().WithError(err).Fatal("Failed to extract hostname")
}
return &BladectlConfig{

25
go.mod
View File

@@ -6,12 +6,15 @@ require (
github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.3.2
github.com/prometheus/client_golang v1.22.0
github.com/sierrasoftworks/humane-errors-go v0.0.0-20250507223502-4bb667dc1e16
github.com/spechtlabs/go-otel-utils/otelprovider v0.0.10
github.com/spechtlabs/go-otel-utils/otelzap v0.0.10
github.com/spf13/cobra v1.9.1
github.com/spf13/pflag v1.0.6
github.com/spf13/viper v1.20.1
github.com/stretchr/testify v1.10.0
github.com/warthog618/gpiod v0.9.1
go.bug.st/serial v1.6.4
go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0
go.uber.org/zap v1.27.0
golang.org/x/sync v0.15.0
google.golang.org/grpc v1.73.0
@@ -21,13 +24,19 @@ require (
)
require (
github.com/aws/smithy-go v1.22.3 // indirect
github.com/beorn7/perks v1.0.1 // indirect
github.com/cenkalti/backoff/v4 v4.3.0 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/creack/goselect v0.1.3 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/fsnotify/fsnotify v1.9.0 // indirect
github.com/go-logr/logr v1.4.2 // indirect
github.com/go-logr/stdr v1.2.2 // indirect
github.com/go-viper/mapstructure/v2 v2.2.1 // indirect
github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
github.com/google/uuid v1.6.0 // indirect
github.com/grpc-ecosystem/grpc-gateway/v2 v2.26.1 // indirect
github.com/inconshreveable/mousetrap v1.1.0 // indirect
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
github.com/pelletier/go-toml/v2 v2.2.4 // indirect
@@ -41,9 +50,23 @@ require (
github.com/spf13/cast v1.8.0 // indirect
github.com/stretchr/objx v0.5.2 // indirect
github.com/subosito/gotenv v1.6.0 // indirect
go.opentelemetry.io/auto/sdk v1.1.0 // indirect
go.opentelemetry.io/otel v1.36.0 // indirect
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploggrpc v0.11.0 // indirect
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp v0.11.0 // indirect
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.35.0 // indirect
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.35.0 // indirect
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.35.0 // indirect
go.opentelemetry.io/otel/log v0.11.0 // indirect
go.opentelemetry.io/otel/metric v1.36.0 // indirect
go.opentelemetry.io/otel/sdk v1.36.0 // indirect
go.opentelemetry.io/otel/sdk/log v0.11.0 // indirect
go.opentelemetry.io/otel/trace v1.36.0 // indirect
go.opentelemetry.io/proto/otlp v1.5.0 // indirect
go.uber.org/multierr v1.11.0 // indirect
golang.org/x/net v0.40.0 // indirect
golang.org/x/sys v0.33.0 // indirect
golang.org/x/text v0.25.0 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20250512202823-5a2f75b736a9 // indirect
google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20250519155744-55703ea1f237 // indirect
)

63
go.sum
View File

@@ -1,5 +1,9 @@
github.com/aws/smithy-go v1.22.3 h1:Z//5NuZCSW6R4PhQ93hShNbyBbn8BWCmCVCt+Q8Io5k=
github.com/aws/smithy-go v1.22.3/go.mod h1:t1ufH5HMublsJYulve2RKmHDC15xu1f26kHCp/HgceI=
github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK343L8=
github.com/cenkalti/backoff/v4 v4.3.0/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
@@ -11,6 +15,7 @@ github.com/frankban/quicktest v1.14.6 h1:7Xjx+VpznH+oBnejlPUj8oUpdxnVs4f8XU8WnHk
github.com/frankban/quicktest v1.14.6/go.mod h1:4ptaffx2x8+WTWXmUCuVU6aPUX1/Mz7zb5vbUoiM6w0=
github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
@@ -27,6 +32,8 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.3.2 h1:sGm2vDRFUrQJO/Veii4h4zG2vvqG6uWNkBHSTqXOZk0=
github.com/grpc-ecosystem/go-grpc-middleware/v2 v2.3.2/go.mod h1:wd1YpapPLivG6nQgbf7ZkG1hhSOXDhhn4MLTknx2aAc=
github.com/grpc-ecosystem/grpc-gateway/v2 v2.26.1 h1:e9Rjr40Z98/clHv5Yg79Is0NtosR5LXRvdr7o/6NwbA=
github.com/grpc-ecosystem/grpc-gateway/v2 v2.26.1/go.mod h1:tIxuGz/9mpox++sgp9fJjHO0+q1X9/UOWd798aAm22M=
github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
github.com/klauspost/compress v1.18.0 h1:c/Cqfb0r+Yi+JtIEq73FWXVkRonBlf0CRNYc8Zttxdo=
@@ -53,8 +60,8 @@ github.com/prometheus/common v0.63.0 h1:YR/EIY1o3mEFP/kZCD7iDMnLPlGyuU2Gb3HIcXnA
github.com/prometheus/common v0.63.0/go.mod h1:VVFF/fBIoToEnWRVkYoXEkq3R3paCoxG9PXP74SnV18=
github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
github.com/rogpeppe/go-internal v1.13.1 h1:KvO1DLK/DRN07sQ1LQKScxyZJuNnedQ5/wKSR38lUII=
github.com/rogpeppe/go-internal v1.13.1/go.mod h1:uMEvuHeurkdAXX61udpOXGD/AzZDWNMNyH2VO9fmH0o=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/sagikazarmark/locafero v0.9.0 h1:GbgQGNtTrEmddYDSAH9QLRyfAHY12md+8YFTqyMTC9k=
github.com/sagikazarmark/locafero v0.9.0/go.mod h1:UBUyz37V+EdMS3hDF3QWIiVr/2dPrx49OMO0Bn0hJqk=
@@ -62,6 +69,10 @@ github.com/sierrasoftworks/humane-errors-go v0.0.0-20250507223502-4bb667dc1e16 h
github.com/sierrasoftworks/humane-errors-go v0.0.0-20250507223502-4bb667dc1e16/go.mod h1:CbJLj9L1qHdzLg4YRh2Lzr0noe9pR6QrVEqfLbITRKw=
github.com/sourcegraph/conc v0.3.0 h1:OQTbbt6P72L20UqAkXXuLOj79LfEanQ+YQFNpLA9ySo=
github.com/sourcegraph/conc v0.3.0/go.mod h1:Sdozi7LEKbFPqYX2/J+iBAM6HpqSLTASQIKqDmF7Mt0=
github.com/spechtlabs/go-otel-utils/otelprovider v0.0.10 h1:Q5p+5KGA587GfzR6FdXGje4XBfxhi1u4NSu6lSnWCGA=
github.com/spechtlabs/go-otel-utils/otelprovider v0.0.10/go.mod h1:sFuJXEBbNq/pQx9pP5OnVtx9yGJnH4fXi7x3qihW0ak=
github.com/spechtlabs/go-otel-utils/otelzap v0.0.10 h1:RR/WS4b+ABxNL7xzlK4FTvnuXRbGk3yyggvvLnQ+FeM=
github.com/spechtlabs/go-otel-utils/otelzap v0.0.10/go.mod h1:IhsBuW+sZwLxX1Ww5LmTlIonBP8GiyhsiZkIRq+ySE0=
github.com/spf13/afero v1.14.0 h1:9tH6MapGnn/j0eb0yIXiLjERO8RB6xIVZRDCX7PtqWA=
github.com/spf13/afero v1.14.0/go.mod h1:acJQ8t0ohCGuMN3O+Pv0V0hgMxNYDlvdk+VTfyZmbYo=
github.com/spf13/cast v1.8.0 h1:gEN9K4b8Xws4EX0+a0reLmhq8moKn7ntRlQYgjPeCDk=
@@ -84,16 +95,34 @@ go.bug.st/serial v1.6.4 h1:7FmqNPgVp3pu2Jz5PoPtbZ9jJO5gnEnZIvnI1lzve8A=
go.bug.st/serial v1.6.4/go.mod h1:nofMJxTeNVny/m6+KaafC6vJGj3miwQZ6vW4BZUGJPI=
go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
go.opentelemetry.io/otel v1.34.0 h1:zRLXxLCgL1WyKsPVrgbSdMN4c0FMkDAskSTQP+0hdUY=
go.opentelemetry.io/otel v1.34.0/go.mod h1:OWFPOQ+h4G8xpyjgqo4SxJYdDQ/qmRH+wivy7zzx9oI=
go.opentelemetry.io/otel/metric v1.34.0 h1:+eTR3U0MyfWjRDhmFMxe2SsW64QrZ84AOhvqS7Y+PoQ=
go.opentelemetry.io/otel/metric v1.34.0/go.mod h1:CEDrp0fy2D0MvkXE+dPV7cMi8tWZwX3dmaIhwPOaqHE=
go.opentelemetry.io/otel/sdk v1.34.0 h1:95zS4k/2GOy069d321O8jWgYsW3MzVV+KuSPKp7Wr1A=
go.opentelemetry.io/otel/sdk v1.34.0/go.mod h1:0e/pNiaMAqaykJGKbi+tSjWfNNHMTxoC9qANsCzbyxU=
go.opentelemetry.io/otel/sdk/metric v1.34.0 h1:5CeK9ujjbFVL5c1PhLuStg1wxA7vQv7ce1EK0Gyvahk=
go.opentelemetry.io/otel/sdk/metric v1.34.0/go.mod h1:jQ/r8Ze28zRKoNRdkjCZxfs6YvBTG1+YIqyFVFYec5w=
go.opentelemetry.io/otel/trace v1.34.0 h1:+ouXS2V8Rd4hp4580a8q23bg0azF2nI8cqLYnC8mh/k=
go.opentelemetry.io/otel/trace v1.34.0/go.mod h1:Svm7lSjQD7kG7KJ/MUHPVXSDGz2OX4h0M2jHBhmSfRE=
go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0 h1:q4XOmH/0opmeuJtPsbFNivyl7bCt7yRBbeEm2sC/XtQ=
go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0/go.mod h1:snMWehoOh2wsEwnvvwtDyFCxVeDAODenXHtn5vzrKjo=
go.opentelemetry.io/otel v1.36.0 h1:UumtzIklRBY6cI/lllNZlALOF5nNIzJVb16APdvgTXg=
go.opentelemetry.io/otel v1.36.0/go.mod h1:/TcFMXYjyRNh8khOAO9ybYkqaDBb/70aVwkNML4pP8E=
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploggrpc v0.11.0 h1:HMUytBT3uGhPKYY/u/G5MR9itrlSO2SMOsSD3Tk3k7A=
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploggrpc v0.11.0/go.mod h1:hdDXsiNLmdW/9BF2jQpnHHlhFajpWCEYfM6e5m2OAZg=
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp v0.11.0 h1:C/Wi2F8wEmbxJ9Kuzw/nhP+Z9XaHYMkyDmXy6yR2cjw=
go.opentelemetry.io/otel/exporters/otlp/otlplog/otlploghttp v0.11.0/go.mod h1:0Lr9vmGKzadCTgsiBydxr6GEZ8SsZ7Ks53LzjWG5Ar4=
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.35.0 h1:1fTNlAIJZGWLP5FVu0fikVry1IsiUnXjf7QFvoNN3Xw=
go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.35.0/go.mod h1:zjPK58DtkqQFn+YUMbx0M2XV3QgKU0gS9LeGohREyK4=
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.35.0 h1:m639+BofXTvcY1q8CGs4ItwQarYtJPOWmVobfM1HpVI=
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.35.0/go.mod h1:LjReUci/F4BUyv+y4dwnq3h/26iNOeC3wAIqgvTIZVo=
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.35.0 h1:xJ2qHD0C1BeYVTLLR9sX12+Qb95kfeD/byKj6Ky1pXg=
go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.35.0/go.mod h1:u5BF1xyjstDowA1R5QAO9JHzqK+ublenEW/dyqTjBVk=
go.opentelemetry.io/otel/log v0.11.0 h1:c24Hrlk5WJ8JWcwbQxdBqxZdOK7PcP/LFtOtwpDTe3Y=
go.opentelemetry.io/otel/log v0.11.0/go.mod h1:U/sxQ83FPmT29trrifhQg+Zj2lo1/IPN1PF6RTFqdwc=
go.opentelemetry.io/otel/metric v1.36.0 h1:MoWPKVhQvJ+eeXWHFBOPoBOi20jh6Iq2CcCREuTYufE=
go.opentelemetry.io/otel/metric v1.36.0/go.mod h1:zC7Ks+yeyJt4xig9DEw9kuUFe5C3zLbVjV2PzT6qzbs=
go.opentelemetry.io/otel/sdk v1.36.0 h1:b6SYIuLRs88ztox4EyrvRti80uXIFy+Sqzoh9kFULbs=
go.opentelemetry.io/otel/sdk v1.36.0/go.mod h1:+lC+mTgD+MUWfjJubi2vvXWcVxyr9rmlshZni72pXeY=
go.opentelemetry.io/otel/sdk/log v0.11.0 h1:7bAOpjpGglWhdEzP8z0VXc4jObOiDEwr3IYbhBnjk2c=
go.opentelemetry.io/otel/sdk/log v0.11.0/go.mod h1:dndLTxZbwBstZoqsJB3kGsRPkpAgaJrWfQg3lhlHFFY=
go.opentelemetry.io/otel/sdk/metric v1.35.0 h1:1RriWBmCKgkeHEhM7a2uMjMUfP7MsOF5JpUCaEqEI9o=
go.opentelemetry.io/otel/sdk/metric v1.35.0/go.mod h1:is6XYCUMpcKi+ZsOvfluY5YstFnhW0BidkR+gL+qN+w=
go.opentelemetry.io/otel/trace v1.36.0 h1:ahxWNuqZjpdiFAyrIoQ4GIiAIhxAunQR6MUoKrsNd4w=
go.opentelemetry.io/otel/trace v1.36.0/go.mod h1:gQ+OnDZzrybY4k4seLzPAWNwVBBVlF2szhehOBB/tGA=
go.opentelemetry.io/proto/otlp v1.5.0 h1:xJvq7gMzB31/d406fB8U5CBdyQGw4P399D1aQWU/3i4=
go.opentelemetry.io/proto/otlp v1.5.0/go.mod h1:keN8WnHxOy8PG0rQZjJJ5A2ebUoafqWp0eVQ4yIXvJ4=
go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
@@ -102,18 +131,16 @@ go.uber.org/zap v1.27.0 h1:aJMhYGrd5QSmlpLMr2MftRKl7t8J8PTZPA732ud/XR8=
go.uber.org/zap v1.27.0/go.mod h1:GB2qFLM7cTU87MWRP2mPIjqfIDnGu+VIO4V/SdhGo2E=
golang.org/x/net v0.40.0 h1:79Xs7wF06Gbdcg4kdCCIQArK11Z1hr5POQ6+fIYHNuY=
golang.org/x/net v0.40.0/go.mod h1:y0hY0exeL2Pku80/zKK7tpntoX23cqL3Oa6njdgRtds=
golang.org/x/sync v0.14.0 h1:woo0S4Yywslg6hp4eUFjTVOyKt0RookbpAHG4c1HmhQ=
golang.org/x/sync v0.14.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
golang.org/x/sync v0.15.0 h1:KWH3jNZsfyT6xfAfKiz6MRNmd46ByHDYaZ7KSkCtdW8=
golang.org/x/sync v0.15.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
golang.org/x/sys v0.33.0 h1:q3i8TbbEz+JRD9ywIRlyRAQbM0qF7hu24q3teo2hbuw=
golang.org/x/sys v0.33.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
golang.org/x/text v0.25.0 h1:qVyWApTSYLk/drJRO5mDlNYskwQznZmkpV2c8q9zls4=
golang.org/x/text v0.25.0/go.mod h1:WEdwpYrmk1qmdHvhkSTNPm3app7v4rsT8F2UD6+VHIA=
google.golang.org/genproto/googleapis/rpc v0.0.0-20250512202823-5a2f75b736a9 h1:IkAfh6J/yllPtpYFU0zZN1hUPYdT0ogkBT/9hMxHjvg=
google.golang.org/genproto/googleapis/rpc v0.0.0-20250512202823-5a2f75b736a9/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
google.golang.org/grpc v1.72.0 h1:S7UkcVa60b5AAQTaO6ZKamFp1zMZSU0fGDK2WZLbBnM=
google.golang.org/grpc v1.72.0/go.mod h1:wH5Aktxcg25y1I3w7H69nHfXdOG3UiadoBtjh3izSDM=
google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463 h1:hE3bRWtU6uceqlh4fhrSnUyjKHMKB9KrTLLG+bc0ddM=
google.golang.org/genproto/googleapis/api v0.0.0-20250324211829-b45e905df463/go.mod h1:U90ffi8eUL9MwPcrJylN5+Mk2v3vuPDptd5yyNUiRR8=
google.golang.org/genproto/googleapis/rpc v0.0.0-20250519155744-55703ea1f237 h1:cJfm9zPbe1e873mHJzmQ1nwVEeRDU/T1wXDK2kUSU34=
google.golang.org/genproto/googleapis/rpc v0.0.0-20250519155744-55703ea1f237/go.mod h1:qQ0YXyHHx3XkvlzUtpXDkS29lDSafHMZBAZDc03LQ3A=
google.golang.org/grpc v1.73.0 h1:VIWSmpI2MegBtTuFt5/JWy2oXxtjJ/e89Z70ImfD2ok=
google.golang.org/grpc v1.73.0/go.mod h1:50sbHOUqWoCQGI8V2HQLJM0B+LMlIUjNSZmow7EVBQc=
google.golang.org/protobuf v1.36.6 h1:z1NpPI8ku2WgiWnf+t9wTPsn6eP1L7ksHUlkfLvd9xY=

View File

@@ -89,7 +89,7 @@ func (a *computeBladeAgentImpl) RunAsync(ctx context.Context, cancel context.Can
log.FromContext(ctx).Info("Starting agent")
err := a.Run(ctx)
if err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("Failed to run agent", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to run agent")
cancel(err)
}
}()
@@ -117,7 +117,7 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
defer wg.Done()
log.FromContext(ctx).Info("Starting HAL")
if err := a.blade.Run(ctx); err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("HAL failed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("HAL failed")
cancelCtx(err)
}
}()
@@ -130,7 +130,7 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
for {
err := a.blade.WaitForEdgeButtonPress(ctx)
if err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("Edge button event handler failed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Edge button event handler failed")
cancelCtx(err)
} else if err != nil {
return
@@ -151,7 +151,7 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
log.FromContext(ctx).Info("Starting top LED engine")
err := a.runTopLedEngine(ctx)
if err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("Top LED engine failed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Top LED engine failed")
cancelCtx(err)
}
}()
@@ -163,7 +163,7 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
log.FromContext(ctx).Info("Starting edge LED engine")
err := a.runEdgeLedEngine(ctx)
if err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("Edge LED engine failed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Edge LED engine failed")
cancelCtx(err)
}
}()
@@ -175,7 +175,7 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
log.FromContext(ctx).Info("Starting fan controller")
err := a.runFanController(ctx)
if err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("Fan Controller Failed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Fan Controller Failed")
cancelCtx(err)
}
}()
@@ -192,7 +192,7 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
case event := <-a.eventChan:
err := a.handleEvent(ctx, event)
if err != nil && !errors.Is(err, context.Canceled) {
log.FromContext(ctx).Error("Event handler failed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Event handler failed")
cancelCtx(err)
}
}
@@ -207,16 +207,16 @@ func (a *computeBladeAgentImpl) Run(origCtx context.Context) error {
func (a *computeBladeAgentImpl) cleanup(ctx context.Context) {
log.FromContext(ctx).Info("Exiting, restoring safe settings")
if err := a.blade.SetFanSpeed(100); err != nil {
log.FromContext(ctx).Error("Failed to set fan speed to 100%", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to set fan speed to 100%")
}
if err := a.blade.SetLed(hal.LedEdge, led.Color{}); err != nil {
log.FromContext(ctx).Error("Failed to set edge LED to off", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to set edge LED to off")
}
if err := a.blade.SetLed(hal.LedTop, led.Color{}); err != nil {
log.FromContext(ctx).Error("Failed to set edge LED to off", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to set edge LED to off")
}
if err := a.Close(); err != nil {
log.FromContext(ctx).Error("Failed to close blade", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to close blade")
}
}
@@ -377,14 +377,14 @@ func (a *computeBladeAgentImpl) runFanController(ctx context.Context) error {
// Get temperature
temp, err := a.blade.GetTemperature()
if err != nil {
log.FromContext(ctx).Error("Failed to get temperature", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to get temperature")
temp = 100 // set to a high value to trigger the maximum speed defined by the fan curve
}
// Derive fan speed from temperature
speed := a.fanController.GetFanSpeed(temp)
// Set fan speed
if err := a.blade.SetFanSpeed(speed); err != nil {
log.FromContext(ctx).Error("Failed to set fan speed", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to set fan speed")
}
}
}

View File

@@ -12,6 +12,7 @@ import (
"github.com/compute-blade-community/compute-blade-agent/pkg/log"
grpczap "github.com/grpc-ecosystem/go-grpc-middleware/v2/interceptors/logging"
"github.com/sierrasoftworks/humane-errors-go"
"go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc"
"go.uber.org/zap"
"google.golang.org/grpc"
"google.golang.org/grpc/codes"
@@ -72,10 +73,7 @@ func NewGrpcApiServer(ctx context.Context, options ...GrpcApiServiceOption) *Age
// Load server's certificate and private key
cert, certPool, err := EnsureServerCertificate(ctx)
if err != nil {
log.FromContext(ctx).Fatal("failed to load server key pair",
zap.Error(err),
zap.Strings("advice", err.Advice()),
)
log.FromContext(ctx).WithError(err).Fatal("failed to load server key pair")
}
// Create the TLS config that enforces mTLS for client authentication
@@ -90,24 +88,19 @@ func NewGrpcApiServer(ctx context.Context, options ...GrpcApiServiceOption) *Age
// Make sure we have a local bladectl config with authentication enabled
if err := EnsureAuthenticatedBladectlConfig(ctx, service.listenAddr, service.listenMode); err != nil {
log.FromContext(ctx).Fatal("failed to ensure proper local bladectl config",
zap.Error(err),
zap.Strings("advice", err.Advice()),
)
log.FromContext(ctx).WithError(err).Fatal("failed to ensure proper local bladectl config")
}
} else {
// Make sure we have a local bladectl config with no authentication enabled
if err := EnsureUnauthenticatedBladectlConfig(ctx, service.listenAddr, service.listenMode); err != nil {
log.FromContext(ctx).Fatal("failed to ensure proper local bladectl config",
zap.Error(err),
zap.Strings("advice", err.Advice()),
)
log.FromContext(ctx).WithError(err).Fatal("failed to ensure proper local bladectl config")
}
}
// Add Logging Middleware
grpcOpts = append(grpcOpts, grpc.ChainUnaryInterceptor(grpczap.UnaryServerInterceptor(log.InterceptorLogger(zap.L()))))
grpcOpts = append(grpcOpts, grpc.ChainStreamInterceptor(grpczap.StreamServerInterceptor(log.InterceptorLogger(zap.L()))))
grpcOpts = append(grpcOpts, grpc.ChainUnaryInterceptor(grpczap.UnaryServerInterceptor(log.InterceptorLogger(log.FromContext(ctx)))))
grpcOpts = append(grpcOpts, grpc.ChainStreamInterceptor(grpczap.StreamServerInterceptor(log.InterceptorLogger(log.FromContext(ctx)))))
grpcOpts = append(grpcOpts, grpc.StatsHandler(otelgrpc.NewServerHandler()))
// Make server
service.server = grpc.NewServer(grpcOpts...)
@@ -121,11 +114,7 @@ func (s *AgentGrpcService) ServeAsync(ctx context.Context, cancel context.Cancel
go func() {
err := s.Serve(ctx)
if err != nil {
log.FromContext(ctx).Error("Failed to start grpc server",
zap.Error(err),
zap.String("cause", err.Cause().Error()),
zap.Strings("advice", err.Advice()),
)
log.FromContext(ctx).WithError(err).Error("Failed to start grpc server")
cancel(err.Cause())
}

View File

@@ -2,6 +2,7 @@ package api
import (
"github.com/compute-blade-community/compute-blade-agent/pkg/agent"
"github.com/spechtlabs/go-otel-utils/otelzap"
"go.uber.org/zap"
)
@@ -34,7 +35,7 @@ func WithListenMode(mode string) GrpcApiServiceOption {
return func(service *AgentGrpcService) {
lMode, err := ListenModeFromString(mode)
if err != nil {
zap.L().Fatal(err.Error(),
otelzap.L().Fatal(err.Error(),
zap.String("mode", mode),
zap.Strings("advice", err.Advice()),
)

View File

@@ -7,6 +7,7 @@ import (
"github.com/compute-blade-community/compute-blade-agent/pkg/events"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promauto"
"github.com/spechtlabs/go-otel-utils/otelzap"
"go.uber.org/zap"
)
@@ -63,7 +64,7 @@ func (s *computebladeStateImpl) RegisterEvent(event events.Event) {
s.criticalConfirmChan = make(chan struct{})
default:
zap.L().Warn("Unknown event", zap.String("event", event.String()))
otelzap.L().Warn("Unknown event", zap.String("event", event.String()))
}
// Set identify state metric

View File

@@ -199,7 +199,7 @@ func (bcm *bcm2711) setup(ctx context.Context) error {
return err
}
} else {
log.FromContext(ctx).Info("no smart fan unit detected, assuming standard fan unit", zap.Error(err))
log.FromContext(ctx).WithError(err).Info("no smart fan unit detected, assuming standard fan unit")
// FAN PWM output for standard fan unit (GPIO 12)
// -> bcm2711RegGpfsel1 8:6, alt0
bcm.gpioMem[bcm2711RegGpfsel1] = (bcm.gpioMem[bcm2711RegGpfsel1] &^ (0b111 << 6)) | (0b100 << 6)
@@ -258,7 +258,7 @@ func (bcm *bcm2711) WaitForEdgeButtonPress(parentCtx context.Context) error {
go func() {
err := bcm.fanUnit.WaitForButtonPress(ctx)
if err != nil && err != context.Canceled {
log.FromContext(ctx).Error("failed to wait for button press", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("failed to wait for button press")
} else {
close(fanUnitChan)
}

View File

@@ -7,6 +7,7 @@ import (
"time"
"github.com/compute-blade-community/compute-blade-agent/pkg/hal/led"
"github.com/spechtlabs/go-otel-utils/otelzap"
"go.uber.org/zap"
)
@@ -19,7 +20,7 @@ type SimulatedHal struct {
}
func NewCm4Hal(_ context.Context, _ ComputeBladeHalOpts) (ComputeBladeHal, error) {
logger := zap.L().Named("hal").Named("simulated-cm4")
logger := otelzap.L().Named("hal").Named("simulated-cm4")
logger.Warn("Using simulated hal")
computeModule.WithLabelValues("simulated").Set(1)

View File

@@ -4,9 +4,10 @@ package hal
import (
"context"
"math"
"github.com/compute-blade-community/compute-blade-agent/pkg/log"
"go.uber.org/zap"
"math"
"github.com/compute-blade-community/compute-blade-agent/pkg/hal/led"
"github.com/warthog618/gpiod"

View File

@@ -14,7 +14,6 @@ import (
"github.com/compute-blade-community/compute-blade-agent/pkg/smartfanunit"
"github.com/compute-blade-community/compute-blade-agent/pkg/smartfanunit/proto"
"go.bug.st/serial"
"go.uber.org/zap"
"golang.org/x/sync/errgroup"
)
@@ -32,7 +31,7 @@ func SmartFanUnitPresent(ctx context.Context, portName string) (bool, error) {
defer func(rwc serial.Port) {
err := rwc.Close()
if err != nil {
log.FromContext(ctx).Warn("Error while closing serial port", zap.Error(err))
log.FromContext(ctx).WithError(err).Warn("Error while closing serial port")
}
}(rwc)
@@ -42,7 +41,7 @@ func SmartFanUnitPresent(ctx context.Context, portName string) (bool, error) {
log.FromContext(ctx).Warn("Closing serial port")
err := rwc.Close()
if err != nil {
log.FromContext(ctx).Warn("Error while closing serial port", zap.Error(err))
log.FromContext(ctx).WithError(err).Warn("Error while closing serial port")
}
}()
@@ -117,7 +116,7 @@ func (fuc *smartFanUnit) Run(parentCtx context.Context) error {
pkt, err := proto.ReadPacket(ctx, fuc.rwc)
if err != nil {
log.FromContext(ctx).Error("Failed to read packet from serial port", zap.Error(err))
log.FromContext(ctx).WithError(err).Error("Failed to read packet from serial port")
continue
}
fuc.eb.Publish(inboundTopic, pkt)

View File

@@ -4,12 +4,13 @@ import (
"context"
"github.com/grpc-ecosystem/go-grpc-middleware/v2/interceptors/logging"
"github.com/spechtlabs/go-otel-utils/otelzap"
"go.uber.org/zap"
)
// InterceptorLogger adapts zap logger to interceptor logger.
// This code is simple enough to be copied and not imported.
func InterceptorLogger(l *zap.Logger) logging.Logger {
func InterceptorLogger(l *otelzap.Logger) logging.Logger {
return logging.LoggerFunc(func(ctx context.Context, lvl logging.Level, msg string, fields ...any) {
f := make([]zap.Field, 0, len(fields)/2)
@@ -24,12 +25,14 @@ func InterceptorLogger(l *zap.Logger) logging.Logger {
f = append(f, zap.Int(key.(string), v))
case bool:
f = append(f, zap.Bool(key.(string), v))
case zap.Field:
f = append(f, v)
default:
f = append(f, zap.Any(key.(string), v))
}
}
logger := zap.L().WithOptions(zap.AddCallerSkip(4)).With(f...)
logger := l.WithOptions(zap.AddCallerSkip(4)).With(f...)
switch lvl {
case logging.LevelDebug:

View File

@@ -3,21 +3,22 @@ package log
import (
"context"
"github.com/spechtlabs/go-otel-utils/otelzap"
"go.uber.org/zap"
)
type logCtxKey int
func IntoContext(ctx context.Context, logger *zap.Logger) context.Context {
func IntoContext(ctx context.Context, logger *otelzap.Logger) context.Context {
return context.WithValue(ctx, logCtxKey(0), logger)
}
func FromContext(ctx context.Context) *zap.Logger {
func FromContext(ctx context.Context) *otelzap.Logger {
val := ctx.Value(logCtxKey(0))
if val != nil {
return val.(*zap.Logger)
return val.(*otelzap.Logger)
}
zap.L().WithOptions(zap.AddCallerSkip(1)).Warn("No logger in context, passing default")
return zap.L()
otelzap.L().WithOptions(zap.AddCallerSkip(1)).Warn("No logger in context, passing default")
return otelzap.L()
}