feat: 增强 OpenTelemetry 提供者配置,添加连接安全、采样器和批处理选项
This commit is contained in:
121
templates/project/providers/otel/README.md.raw
Normal file
121
templates/project/providers/otel/README.md.raw
Normal file
@@ -0,0 +1,121 @@
|
||||
OpenTelemetry Provider (OTLP Traces + Metrics)
|
||||
|
||||
该 Provider 基于 OpenTelemetry Go SDK,初始化全局 Tracer 与 Meter,支持 OTLP(gRPC/HTTP) 导出,并收集运行时指标。
|
||||
|
||||
配置(config.toml)
|
||||
|
||||
```
|
||||
[OTEL]
|
||||
ServiceName = "my-service"
|
||||
Version = "1.0.0"
|
||||
Env = "dev"
|
||||
|
||||
# 导出端点(二选一)
|
||||
EndpointGRPC = "otel-collector:4317"
|
||||
EndpointHTTP = "otel-collector:4318"
|
||||
|
||||
# 认证(可选)
|
||||
Token = "Bearer <your-token>" # 也可只填纯 token,Provider 会自动补齐 Bearer 前缀
|
||||
|
||||
# 安全(可选)
|
||||
InsecureGRPC = true # gRPC 导出是否使用 insecure
|
||||
InsecureHTTP = true # HTTP 导出是否使用 insecure
|
||||
|
||||
# 采样(可选)
|
||||
Sampler = "always" # always|ratio
|
||||
SamplerRatio = 0.1 # Sampler=ratio 时生效,0..1
|
||||
|
||||
# 批处理(可选,毫秒)
|
||||
BatchTimeoutMs = 5000
|
||||
ExportTimeoutMs = 10000
|
||||
MaxQueueSize = 2048
|
||||
MaxExportBatchSize = 512
|
||||
|
||||
# 指标(可选,毫秒)
|
||||
MetricReaderIntervalMs = 10000 # 指标导出周期
|
||||
RuntimeReadMemStatsIntervalMs = 5000 # 运行时指标读取周期
|
||||
```
|
||||
|
||||
启用
|
||||
|
||||
```
|
||||
import "test/providers/otel"
|
||||
|
||||
func providers() container.Providers {
|
||||
return container.Providers{
|
||||
otel.DefaultProvider(),
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
使用
|
||||
|
||||
- Traces: 通过 `go.opentelemetry.io/otel` 获取全局 Tracer,或使用仓库提供的 `providers/otel/funcs.go` 包装。
|
||||
|
||||
```
|
||||
ctx, span := otel.Tracer("my-service").Start(ctx, "my-op")
|
||||
// ...
|
||||
span.End()
|
||||
```
|
||||
|
||||
- Metrics: 通过 `otel.Meter("my-service")` 创建仪表,或使用 `providers/otel/funcs.go` 的便捷函数。
|
||||
|
||||
与 Tracing Provider 的区别与场景建议
|
||||
|
||||
- Tracing Provider(Jaeger + OpenTracing)只做链路,适合已有 OpenTracing 项目;
|
||||
- OTEL Provider(OpenTelemetry)统一 Traces+Metrics,对接 OTLP 生态,适合新项目或希望统一可观测性;
|
||||
- 可先混用:保留 Jaeger 链路,同时启用 OTEL 运行时指标,逐步迁移。
|
||||
|
||||
快速启动(本地 Collector)
|
||||
|
||||
最小化 docker-compose:
|
||||
|
||||
```
|
||||
services:
|
||||
otel-collector:
|
||||
image: otel/opentelemetry-collector:0.104.0
|
||||
command: ["--config=/etc/otelcol-config.yml"]
|
||||
volumes:
|
||||
- ./otelcol-config.yml:/etc/otelcol-config.yml:ro
|
||||
ports:
|
||||
- "4317:4317" # OTLP gRPC
|
||||
- "4318:4318" # OTLP HTTP
|
||||
```
|
||||
|
||||
示例 otelcol-config.yml:
|
||||
|
||||
```
|
||||
receivers:
|
||||
otlp:
|
||||
protocols:
|
||||
grpc:
|
||||
http:
|
||||
exporters:
|
||||
debug:
|
||||
verbosity: detailed
|
||||
processors:
|
||||
batch:
|
||||
service:
|
||||
pipelines:
|
||||
traces:
|
||||
receivers: [otlp]
|
||||
processors: [batch]
|
||||
exporters: [debug]
|
||||
metrics:
|
||||
receivers: [otlp]
|
||||
processors: [batch]
|
||||
exporters: [debug]
|
||||
```
|
||||
|
||||
应用端:
|
||||
|
||||
```
|
||||
[OTEL]
|
||||
EndpointGRPC = "127.0.0.1:4317"
|
||||
InsecureGRPC = true
|
||||
```
|
||||
|
||||
故障与降级
|
||||
|
||||
- Collector/网络异常:OTEL SDK 异步批处理,不阻塞业务;可能丢点/丢指标;
|
||||
- 启动失败:初始化报错会阻止启动;如需“不可达也不影响启动”,可加开关降级为 no-op(可按需补充)。
|
||||
@@ -21,13 +21,32 @@ func DefaultProvider() container.ProviderContainer {
|
||||
}
|
||||
|
||||
type Config struct {
|
||||
ServiceName string
|
||||
Version string
|
||||
Env string
|
||||
ServiceName string
|
||||
Version string
|
||||
Env string
|
||||
|
||||
EndpointGRPC string
|
||||
EndpointHTTP string
|
||||
Token string
|
||||
EndpointGRPC string
|
||||
EndpointHTTP string
|
||||
Token string
|
||||
|
||||
// Connection security
|
||||
InsecureGRPC bool // if true, use grpc insecure for OTLP gRPC
|
||||
InsecureHTTP bool // if true, use http insecure for OTLP HTTP
|
||||
|
||||
// Tracing sampler
|
||||
// Sampler: "always" (default) or "ratio"
|
||||
Sampler string
|
||||
SamplerRatio float64 // used when Sampler == "ratio"; 0..1
|
||||
|
||||
// Tracing batcher options (milliseconds)
|
||||
BatchTimeoutMs uint
|
||||
ExportTimeoutMs uint
|
||||
MaxQueueSize int
|
||||
MaxExportBatchSize int
|
||||
|
||||
// Metrics options (milliseconds)
|
||||
MetricReaderIntervalMs uint // export interval for PeriodicReader
|
||||
RuntimeReadMemStatsIntervalMs uint // runtime metrics min read interval
|
||||
}
|
||||
|
||||
func (c *Config) format() {
|
||||
|
||||
@@ -26,6 +26,17 @@ import (
|
||||
"google.golang.org/grpc/encoding/gzip"
|
||||
)
|
||||
|
||||
// formatAuth formats token into an Authorization header value.
|
||||
func formatAuth(token string) string {
|
||||
if token == "" {
|
||||
return ""
|
||||
}
|
||||
if len(token) > 7 && (token[:7] == "Bearer " || token[:7] == "bearer ") {
|
||||
return token
|
||||
}
|
||||
return "Bearer " + token
|
||||
}
|
||||
|
||||
func Provide(opts ...opt.Option) error {
|
||||
o := opt.New(opts...)
|
||||
var config Config
|
||||
@@ -82,7 +93,7 @@ func (o *builder) initResource(ctx context.Context) (err error) {
|
||||
semconv.HostNameKey.String(hostName), // 主机名
|
||||
),
|
||||
)
|
||||
return
|
||||
return err
|
||||
}
|
||||
|
||||
func (o *builder) initMeterProvider(ctx context.Context) (err error) {
|
||||
@@ -92,34 +103,35 @@ func (o *builder) initMeterProvider(ctx context.Context) (err error) {
|
||||
otlpmetricgrpc.WithCompressor(gzip.Name),
|
||||
}
|
||||
|
||||
if o.config.Token != "" {
|
||||
headers := map[string]string{"Authentication": o.config.Token}
|
||||
opts = append(opts, otlpmetricgrpc.WithHeaders(headers))
|
||||
if h := formatAuth(o.config.Token); h != "" {
|
||||
opts = append(opts, otlpmetricgrpc.WithHeaders(map[string]string{"Authorization": h}))
|
||||
}
|
||||
|
||||
exporter, err := otlpmetricgrpc.New(ctx, opts...)
|
||||
exporter, err := otlpmetricgrpc.New(ctx, opts...)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return exporter, nil
|
||||
}
|
||||
|
||||
exporterHttpFunc := func(ctx context.Context) (sdkmetric.Exporter, error) {
|
||||
opts := []otlpmetrichttp.Option{
|
||||
otlpmetrichttp.WithEndpoint(o.config.EndpointHTTP),
|
||||
otlpmetrichttp.WithCompression(1),
|
||||
}
|
||||
exporterHttpFunc := func(ctx context.Context) (sdkmetric.Exporter, error) {
|
||||
opts := []otlpmetrichttp.Option{
|
||||
otlpmetrichttp.WithEndpoint(o.config.EndpointHTTP),
|
||||
otlpmetrichttp.WithCompression(1),
|
||||
}
|
||||
if o.config.InsecureHTTP {
|
||||
opts = append(opts, otlpmetrichttp.WithInsecure())
|
||||
}
|
||||
if h := formatAuth(o.config.Token); h != "" {
|
||||
opts = append(opts, otlpmetrichttp.WithHeaders(map[string]string{"Authorization": h}))
|
||||
}
|
||||
|
||||
if o.config.Token != "" {
|
||||
opts = append(opts, otlpmetrichttp.WithURLPath(o.config.Token))
|
||||
}
|
||||
|
||||
exporter, err := otlpmetrichttp.New(ctx, opts...)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return exporter, nil
|
||||
}
|
||||
exporter, err := otlpmetrichttp.New(ctx, opts...)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return exporter, nil
|
||||
}
|
||||
|
||||
var exporter sdkmetric.Exporter
|
||||
if o.config.EndpointHTTP != "" {
|
||||
@@ -129,18 +141,27 @@ func (o *builder) initMeterProvider(ctx context.Context) (err error) {
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
return
|
||||
return err
|
||||
}
|
||||
|
||||
meterProvider := sdkmetric.NewMeterProvider(
|
||||
sdkmetric.WithReader(
|
||||
sdkmetric.NewPeriodicReader(exporter),
|
||||
),
|
||||
sdkmetric.WithResource(o.resource),
|
||||
)
|
||||
// periodic reader with optional custom interval
|
||||
var readerOpts []sdkmetric.PeriodicReaderOption
|
||||
if o.config.MetricReaderIntervalMs > 0 {
|
||||
readerOpts = append(readerOpts, sdkmetric.WithInterval(time.Duration(o.config.MetricReaderIntervalMs)*time.Millisecond))
|
||||
}
|
||||
meterProvider := sdkmetric.NewMeterProvider(
|
||||
sdkmetric.WithReader(
|
||||
sdkmetric.NewPeriodicReader(exporter, readerOpts...),
|
||||
),
|
||||
sdkmetric.WithResource(o.resource),
|
||||
)
|
||||
otel.SetMeterProvider(meterProvider)
|
||||
|
||||
err = runtime.Start(runtime.WithMinimumReadMemStatsInterval(time.Second * 5))
|
||||
interval := 5 * time.Second
|
||||
if o.config.RuntimeReadMemStatsIntervalMs > 0 {
|
||||
interval = time.Duration(o.config.RuntimeReadMemStatsIntervalMs) * time.Millisecond
|
||||
}
|
||||
err = runtime.Start(runtime.WithMinimumReadMemStatsInterval(interval))
|
||||
if err != nil {
|
||||
return errors.Wrapf(err, "Failed to start runtime metrics")
|
||||
}
|
||||
@@ -151,23 +172,21 @@ func (o *builder) initMeterProvider(ctx context.Context) (err error) {
|
||||
}
|
||||
})
|
||||
|
||||
return
|
||||
return err
|
||||
}
|
||||
|
||||
func (o *builder) initTracerProvider(ctx context.Context) error {
|
||||
exporterGrpcFunc := func(ctx context.Context) (*otlptrace.Exporter, error) {
|
||||
opts := []otlptracegrpc.Option{
|
||||
otlptracegrpc.WithCompressor(gzip.Name),
|
||||
otlptracegrpc.WithEndpoint(o.config.EndpointGRPC),
|
||||
otlptracegrpc.WithInsecure(), // 添加不安全连接选项
|
||||
}
|
||||
opts := []otlptracegrpc.Option{
|
||||
otlptracegrpc.WithCompressor(gzip.Name),
|
||||
otlptracegrpc.WithEndpoint(o.config.EndpointGRPC),
|
||||
}
|
||||
if o.config.InsecureGRPC {
|
||||
opts = append(opts, otlptracegrpc.WithInsecure())
|
||||
}
|
||||
|
||||
if o.config.Token != "" {
|
||||
headers := map[string]string{
|
||||
"Authentication": o.config.Token,
|
||||
"authorization": o.config.Token, // 添加标准认证头
|
||||
}
|
||||
opts = append(opts, otlptracegrpc.WithHeaders(headers))
|
||||
if h := formatAuth(o.config.Token); h != "" {
|
||||
opts = append(opts, otlptracegrpc.WithHeaders(map[string]string{"Authorization": h}))
|
||||
}
|
||||
|
||||
log.Debugf("Creating GRPC trace exporter with endpoint: %s", o.config.EndpointGRPC)
|
||||
@@ -188,18 +207,16 @@ func (o *builder) initTracerProvider(ctx context.Context) error {
|
||||
}
|
||||
|
||||
exporterHttpFunc := func(ctx context.Context) (*otlptrace.Exporter, error) {
|
||||
opts := []otlptracehttp.Option{
|
||||
otlptracehttp.WithInsecure(),
|
||||
otlptracehttp.WithCompression(1),
|
||||
otlptracehttp.WithEndpoint(o.config.EndpointHTTP),
|
||||
}
|
||||
opts := []otlptracehttp.Option{
|
||||
otlptracehttp.WithCompression(1),
|
||||
otlptracehttp.WithEndpoint(o.config.EndpointHTTP),
|
||||
}
|
||||
if o.config.InsecureHTTP {
|
||||
opts = append(opts, otlptracehttp.WithInsecure())
|
||||
}
|
||||
|
||||
if o.config.Token != "" {
|
||||
opts = append(opts,
|
||||
otlptracehttp.WithHeaders(map[string]string{
|
||||
"Authentication": o.config.Token,
|
||||
}),
|
||||
)
|
||||
if h := formatAuth(o.config.Token); h != "" {
|
||||
opts = append(opts, otlptracehttp.WithHeaders(map[string]string{"Authorization": h}))
|
||||
}
|
||||
|
||||
log.Debugf("Creating HTTP trace exporter with endpoint: %s", o.config.EndpointHTTP)
|
||||
@@ -225,11 +242,39 @@ func (o *builder) initTracerProvider(ctx context.Context) error {
|
||||
return err
|
||||
}
|
||||
|
||||
traceProvider := sdktrace.NewTracerProvider(
|
||||
sdktrace.WithSampler(sdktrace.AlwaysSample()),
|
||||
sdktrace.WithResource(o.resource),
|
||||
sdktrace.WithBatcher(exporter),
|
||||
)
|
||||
// Sampler
|
||||
sampler := sdktrace.AlwaysSample()
|
||||
if o.config.Sampler == "ratio" {
|
||||
ratio := o.config.SamplerRatio
|
||||
if ratio <= 0 {
|
||||
ratio = 0
|
||||
}
|
||||
if ratio > 1 {
|
||||
ratio = 1
|
||||
}
|
||||
sampler = sdktrace.ParentBased(sdktrace.TraceIDRatioBased(ratio))
|
||||
}
|
||||
|
||||
// Batcher options
|
||||
var batchOpts []sdktrace.BatchSpanProcessorOption
|
||||
if o.config.BatchTimeoutMs > 0 {
|
||||
batchOpts = append(batchOpts, sdktrace.WithBatchTimeout(time.Duration(o.config.BatchTimeoutMs)*time.Millisecond))
|
||||
}
|
||||
if o.config.ExportTimeoutMs > 0 {
|
||||
batchOpts = append(batchOpts, sdktrace.WithExportTimeout(time.Duration(o.config.ExportTimeoutMs)*time.Millisecond))
|
||||
}
|
||||
if o.config.MaxQueueSize > 0 {
|
||||
batchOpts = append(batchOpts, sdktrace.WithMaxQueueSize(o.config.MaxQueueSize))
|
||||
}
|
||||
if o.config.MaxExportBatchSize > 0 {
|
||||
batchOpts = append(batchOpts, sdktrace.WithMaxExportBatchSize(o.config.MaxExportBatchSize))
|
||||
}
|
||||
|
||||
traceProvider := sdktrace.NewTracerProvider(
|
||||
sdktrace.WithSampler(sampler),
|
||||
sdktrace.WithResource(o.resource),
|
||||
sdktrace.WithBatcher(exporter, batchOpts...),
|
||||
)
|
||||
container.AddCloseAble(func() {
|
||||
log.Error("shut down")
|
||||
if err := traceProvider.Shutdown(ctx); err != nil {
|
||||
|
||||
Reference in New Issue
Block a user