mirror of
https://github.com/zitadel/zitadel.git
synced 2025-03-01 05:07:24 +00:00
990e1982c7
# 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
81 lines
1.7 KiB
Go
81 lines
1.7 KiB
Go
package tracing
|
|
|
|
import (
|
|
"context"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
sdk_trace "go.opentelemetry.io/otel/sdk/trace"
|
|
"go.opentelemetry.io/otel/trace"
|
|
)
|
|
|
|
func TestSpanKindBased(t *testing.T) {
|
|
type args struct {
|
|
sampler sdk_trace.Sampler
|
|
kinds []trace.SpanKind
|
|
}
|
|
type want struct {
|
|
description string
|
|
sampled int
|
|
}
|
|
tests := []struct {
|
|
name string
|
|
args args
|
|
want want
|
|
}{
|
|
{
|
|
"never sample, no sample",
|
|
args{
|
|
sampler: sdk_trace.NeverSample(),
|
|
kinds: []trace.SpanKind{trace.SpanKindServer},
|
|
},
|
|
want{
|
|
description: "SpanKindBased{sampler:AlwaysOffSampler,kinds:[server]}",
|
|
sampled: 0,
|
|
},
|
|
},
|
|
{
|
|
"always sample, no kind, no sample",
|
|
args{
|
|
sampler: sdk_trace.AlwaysSample(),
|
|
kinds: nil,
|
|
},
|
|
want{
|
|
description: "SpanKindBased{sampler:AlwaysOnSampler,kinds:[]}",
|
|
sampled: 0,
|
|
},
|
|
},
|
|
{
|
|
"always sample, 2 kinds, 2 samples",
|
|
args{
|
|
sampler: sdk_trace.AlwaysSample(),
|
|
kinds: []trace.SpanKind{trace.SpanKindServer, trace.SpanKindClient},
|
|
},
|
|
want{
|
|
description: "SpanKindBased{sampler:AlwaysOnSampler,kinds:[server client]}",
|
|
sampled: 2,
|
|
},
|
|
},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
sampler := SpanKindBased(tt.args.sampler, tt.args.kinds...)
|
|
assert.Equal(t, tt.want.description, sampler.Description())
|
|
|
|
p := sdk_trace.NewTracerProvider(sdk_trace.WithSampler(sampler))
|
|
tr := p.Tracer("test")
|
|
|
|
var sampled int
|
|
for i := trace.SpanKindUnspecified; i <= trace.SpanKindConsumer; i++ {
|
|
ctx := context.Background()
|
|
_, span := tr.Start(ctx, "test", trace.WithSpanKind(i))
|
|
if span.SpanContext().IsSampled() {
|
|
sampled++
|
|
}
|
|
}
|
|
|
|
assert.Equal(t, tt.want.sampled, sampled)
|
|
})
|
|
}
|
|
}
|