Merge branch 'main' into rename-tpbase-libc

Author: dalehamel

.github/workflows/push-docker-image.yml

@@ -23,7 +23,7 @@ jobs:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@29109295f81e9208d7d86ff1c6c12d2833863392 # v3.6.0
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
       - name: Set current timestamp tag

Cargo.lock

@@ -11,6 +11,7 @@ import (
 
 	"github.com/peterbourgon/ff/v3"
 
+	"go.opentelemetry.io/ebpf-profiler/collector/config"
 	"go.opentelemetry.io/ebpf-profiler/internal/controller"
 	"go.opentelemetry.io/ebpf-profiler/tracer"
 )
@@ -42,7 +43,7 @@ var (
 	mapScaleFactorHelp = fmt.Sprintf("Scaling factor for eBPF map sizes. "+
 		"Every increase by 1 doubles the map size. Increase if you see eBPF map size errors. "+
 		"Default is %d corresponding to 4GB of executable address space, max is %d.",
-		defaultArgMapScaleFactor, controller.MaxArgMapScaleFactor)
+		defaultArgMapScaleFactor, config.MaxArgMapScaleFactor)
 	disableTLSHelp             = "Disable encryption for data in transit."
 	bpfVerifierLogLevelHelp    = "Log level of the eBPF verifier output (0,1,2). Default is 0."
 	versionHelp                = "Show version."
@@ -63,6 +64,7 @@ var (
 		"If zero, monotonic-realtime clock sync will be performed once, " +
 		"on agent startup, but not periodically."
 	sendErrorFramesHelp = "Send error frames (devfiler only, breaks Kibana)"
+	sendIdleFramesHelp  = "Unwind and report idle states of the Linux kernel."
 	offCPUThresholdHelp = fmt.Sprintf("The probability for an off-cpu event being recorded. "+
 		"Valid values are in the range [0..1]. 0 disables off-cpu profiling. "+
 		"Default is %d.",
@@ -118,6 +120,7 @@ func parseArgs() (*controller.Config, error) {
 
 	fs.BoolVar(&args.SendErrorFrames, "send-error-frames", defaultArgSendErrorFrames,
 		sendErrorFramesHelp)
+	fs.BoolVar(&args.SendIdleFrames, "send-idle-frames", false, sendIdleFramesHelp)
 
 	fs.StringVar(&args.Tracers, "t", "all", "Shorthand for -tracers.")
 	fs.StringVar(&args.Tracers, "tracers", "all", tracersHelp)

cli_flags.go

@@ -3,7 +3,19 @@
 
 package config // import "go.opentelemetry.io/ebpf-profiler/collector/config"
 
-import "time"
+import (
+	"errors"
+	"fmt"
+	"runtime"
+	"time"
+
+	"go.opentelemetry.io/ebpf-profiler/tracer"
+)
+
+const (
+	// 1TB of executable address space
+	MaxArgMapScaleFactor = 8
+)
 
 // Config is the configuration for the collector.
 type Config struct {
@@ -15,6 +27,7 @@ type Config struct {
 	Tracers                string        `mapstructure:"tracers"`
 	ClockSyncInterval      time.Duration `mapstructure:"clock_sync_interval"`
 	SendErrorFrames        bool          `mapstructure:"send_error_frames"`
+	SendIdleFrames         bool          `mapstructure:"send_idle_frames"`
 	VerboseMode            bool          `mapstructure:"verbose_mode"`
 	OffCPUThreshold        float64       `mapstructure:"off_cpu_threshold"`
 	IncludeEnvVars         string        `mapstructure:"include_env_vars"`
@@ -26,3 +39,70 @@ type Config struct {
 	MaxGRPCRetries         uint32        `mapstructure:"max_grpc_retries"`
 	MaxRPCMsgSize          int           `mapstructure:"max_rpc_msg_size"`
 }
+
+// Validate validates the config.
+// This is automatically called by the config parser as it implements the xconfmap.Validator interface.
+func (cfg *Config) Validate() error {
+	if cfg.SamplesPerSecond < 1 {
+		return fmt.Errorf("invalid sampling frequency: %d", cfg.SamplesPerSecond)
+	}
+
+	if cfg.MapScaleFactor > MaxArgMapScaleFactor {
+		return fmt.Errorf(
+			"eBPF map scaling factor %d exceeds limit (max: %d)",
+			cfg.MapScaleFactor, MaxArgMapScaleFactor,
+		)
+	}
+
+	if cfg.BPFVerifierLogLevel > 2 {
+		return fmt.Errorf("invalid eBPF verifier log level: %d", cfg.BPFVerifierLogLevel)
+	}
+
+	if cfg.ProbabilisticInterval < 1*time.Minute || cfg.ProbabilisticInterval > 5*time.Minute {
+		return errors.New(
+			"invalid argument for probabilistic-interval: use " +
+				"a duration between 1 and 5 minutes",
+		)
+	}
+
+	if cfg.ProbabilisticThreshold < 1 ||
+		cfg.ProbabilisticThreshold > tracer.ProbabilisticThresholdMax {
+		return fmt.Errorf(
+			"invalid argument for probabilistic-threshold. Value "+
+				"should be between 1 and %d",
+			tracer.ProbabilisticThresholdMax,
+		)
+	}
+
+	if cfg.OffCPUThreshold < 0.0 || cfg.OffCPUThreshold > 1.0 {
+		return errors.New(
+			"invalid argument for off-cpu-threshold. The value " +
+				"should be in the range [0..1]. 0 disables off-cpu profiling")
+	}
+
+	if !cfg.NoKernelVersionCheck {
+		major, minor, patch, err := tracer.GetCurrentKernelVersion()
+		if err != nil {
+			return fmt.Errorf("failed to get kernel version: %v", err)
+		}
+
+		var minMajor, minMinor uint32
+		switch runtime.GOARCH {
+		case "amd64":
+			minMajor, minMinor = 5, 2
+		case "arm64":
+			// Older ARM64 kernel versions have broken bpf_probe_read.
+			// https://github.com/torvalds/linux/commit/6ae08ae3dea2cfa03dd3665a3c8475c2d429ef47
+			minMajor, minMinor = 5, 5
+		default:
+			return fmt.Errorf("unsupported architecture: %s", runtime.GOARCH)
+		}
+
+		if major < minMajor || (major == minMajor && minor < minMinor) {
+			return fmt.Errorf("host Agent requires kernel version "+
+				"%d.%d or newer but got %d.%d.%d", minMajor, minMinor, major, minor, patch)
+		}
+	}
+
+	return nil
+}

collector/config/config.go

@@ -0,0 +1,20 @@
+// Copyright The OpenTelemetry Authors
+// SPDX-License-Identifier: Apache-2.0
+
+package config // import "go.opentelemetry.io/ebpf-profiler/collector/config"
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+	"go.opentelemetry.io/collector/confmap/xconfmap"
+)
+
+func TestValidate(t *testing.T) {
+	cfg := &Config{
+		SamplesPerSecond: 0,
+	}
+	err := xconfmap.Validate(cfg)
+	require.Error(t, err)
+	require.Equal(t, "invalid sampling frequency: 0", err.Error())
+}

collector/config/config_test.go

@@ -11,9 +11,9 @@ module go.opentelemetry.io/ebpf-profiler
 go 1.24.0
 
 require (
-	github.com/aws/aws-sdk-go-v2 v1.39.5
-	github.com/aws/aws-sdk-go-v2/config v1.31.16
-	github.com/aws/aws-sdk-go-v2/service/s3 v1.89.1
+	github.com/aws/aws-sdk-go-v2 v1.39.6
+	github.com/aws/aws-sdk-go-v2/config v1.31.17
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.90.0
 	github.com/cilium/ebpf v0.20.0
 	github.com/elastic/go-freelru v0.16.0
 	github.com/elastic/go-perf v0.0.0-20241029065020-30bec95324b8
@@ -25,6 +25,7 @@ require (
 	github.com/stretchr/testify v1.11.1
 	github.com/zeebo/xxh3 v1.0.2
 	go.opentelemetry.io/collector/component v1.45.0
+	go.opentelemetry.io/collector/confmap/xconfmap v0.138.0
 	go.opentelemetry.io/collector/consumer/consumertest v0.139.0
 	go.opentelemetry.io/collector/consumer/xconsumer v0.139.0
 	go.opentelemetry.io/collector/pdata v1.45.0
@@ -44,37 +45,45 @@ require (
 )
 
 require (
-	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.2 // indirect
-	github.com/aws/aws-sdk-go-v2/credentials v1.18.20 // indirect
-	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.12 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.12 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.12 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.3 // indirect
+	github.com/aws/aws-sdk-go-v2/credentials v1.18.21 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.13 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.13 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.13 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 // indirect
-	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.12 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.2 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.3 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.12 // indirect
-	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.12 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sso v1.30.0 // indirect
-	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.4 // indirect
-	github.com/aws/aws-sdk-go-v2/service/sts v1.39.0 // indirect
-	github.com/aws/smithy-go v1.23.1 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.3 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.4 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.13 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.1 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.5 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.39.1 // indirect
+	github.com/aws/smithy-go v1.23.2 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
+	github.com/gobwas/glob v0.2.3 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
 	github.com/hashicorp/go-version v1.7.0 // indirect
 	github.com/josharian/native v1.1.0 // indirect
 	github.com/jsimonetti/rtnetlink/v2 v2.0.3 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.8 // indirect
+	github.com/knadh/koanf/maps v0.1.2 // indirect
+	github.com/knadh/koanf/providers/confmap v1.0.0 // indirect
+	github.com/knadh/koanf/v2 v2.3.0 // indirect
 	github.com/mdlayher/netlink v1.7.2 // indirect
 	github.com/mdlayher/socket v0.4.1 // indirect
+	github.com/mitchellh/copystructure v1.2.0 // indirect
+	github.com/mitchellh/reflectwalk v1.0.2 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/collector/component/componenttest v0.139.0 // indirect
+	go.opentelemetry.io/collector/confmap v1.44.0 // indirect
 	go.opentelemetry.io/collector/consumer v1.45.0 // indirect
 	go.opentelemetry.io/collector/consumer/consumererror v0.139.0 // indirect
 	go.opentelemetry.io/collector/featuregate v1.45.0 // indirect
@@ -84,6 +93,7 @@ require (
 	go.opentelemetry.io/otel/trace v1.38.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.uber.org/zap v1.27.0 // indirect
+	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/net v0.46.0 // indirect
 	golang.org/x/text v0.30.0 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20250804133106-a7a43d27e69b // indirect