47 lines
1.3 KiB
Go
Raw Normal View History

fix(OTEL): reduce high cardinality in traces and metrics (#9286) # Which Problems Are Solved There were multiple issues in the OpenTelemetry (OTEL) implementation and usage for tracing and metrics, which lead to high cardinality and potential memory leaks: - wrongly initiated tracing interceptors - high cardinality in traces: - HTTP/1.1 endpoints containing host names - HTTP/1.1 endpoints containing object IDs like userID (e.g. `/management/v1/users/2352839823/`) - high amount of traces from internal processes (spooler) - high cardinality in metrics endpoint: - GRPC entries containing host names - notification metrics containing instanceIDs and error messages # How the Problems Are Solved - Properly initialize the interceptors once and update them to use the grpc stats handler (unary interceptors were deprecated). - Remove host names from HTTP/1.1 span names and use path as default. - Set / overwrite the uri for spans on the grpc-gateway with the uri pattern (`/management/v1/users/{user_id}`). This is used for spans in traces and metric entries. - Created a new sampler which will only sample spans in the following cases: - remote was already sampled - remote was not sampled, root span is of kind `Server` and based on fraction set in the runtime configuration - This will prevent having a lot of spans from the spooler back ground jobs if they were not started by a client call querying an object (e.g. UserByID). - Filter out host names and alike from OTEL generated metrics (using a `view`). - Removed instance and error messages from notification metrics. # Additional Changes Fixed the middleware handling for serving Console. Telemetry and instance selection are only used for the environment.json, but not on statically served files. # Additional Context - closes #8096 - relates to #9074 - back ports to at least 2.66.x, 2.67.x and 2.68.x
2025-02-04 09:55:26 +01:00
package tracing
import (
"fmt"
"slices"
sdk_trace "go.opentelemetry.io/otel/sdk/trace"
"go.opentelemetry.io/otel/trace"
)
type spanKindSampler struct {
sampler sdk_trace.Sampler
kinds []trace.SpanKind
}
// ShouldSample implements the [sdk_trace.Sampler] interface.
// It will not sample any spans which do not match the configured span kinds.
// For spans which do match, the decorated sampler is used to make the sampling decision.
func (sk spanKindSampler) ShouldSample(p sdk_trace.SamplingParameters) sdk_trace.SamplingResult {
psc := trace.SpanContextFromContext(p.ParentContext)
if !slices.Contains(sk.kinds, p.Kind) {
return sdk_trace.SamplingResult{
Decision: sdk_trace.Drop,
Tracestate: psc.TraceState(),
}
}
s := sk.sampler.ShouldSample(p)
return s
}
func (sk spanKindSampler) Description() string {
return fmt.Sprintf("SpanKindBased{sampler:%s,kinds:%v}",
sk.sampler.Description(),
sk.kinds,
)
}
// SpanKindBased returns a sampler decorator which behaves differently, based on the kind of the span.
// If the span kind does not match one of the configured kinds, it will not be sampled.
// If the span kind matches, the decorated sampler is used to make sampling decision.
func SpanKindBased(sampler sdk_trace.Sampler, kinds ...trace.SpanKind) sdk_trace.Sampler {
return spanKindSampler{
sampler: sampler,
kinds: kinds,
}
}