Files
Tim MöhlmannandGitHub eb22b58756 feat(telemetry): improved instrumentation for observability (#11159)
# Which Problems Are Solved

Zitadel did not provide easy correlation between errors, logs, traces
and metrics. The configuration for those instrumentations was also not
consistent, with some supporting different exporters then others.
Implementation and parsing of config was also spaghettified over
multiple packages, with awkward parsing and inconsistent naming of
options.

# How the Problems Are Solved

All telemetry is now merged under the name "instrumentation". Why?
1. We thought it was a good idea in the past to call the milestone
exporter `Telemtry` in the runtime config. Calling this `TelemetryV2`
looks weird.
2. Not everything is a meter and not everything is sent (tele...). 
3. It's also
[defined](https://opentelemetry.io/docs/concepts/instrumentation/) as
such by the OTEL documentation.

## New features

- Adds structured, context based logging with trace-ID awareness
- Static log fields are added to the context, such as service and
request path
- Static log fields are injected in each logline emitted by the
application
- Structured logs can also be send to an otel exporter
- Structured logs can be printed to StdErr in text and JSON format
- Error sinks make sure every error is logged at the correct level:
- Warnings for client side errors (HTTP 400 range, Invalid request etc)
  - Error for server side errors (Internal server errors)
- Metrics can now also be send to a OTEL collector. (previously they
could only be scraped from `/debug/metrics` with prometheus)

## Exporters

This change adds all the exporters supported by OTEL upstream and some
google specific exporters for our cloud deployment.

- StdOut / StdErr: all instrumentations
- OTEL gRPC / HTTP: all instrumentations
- Google: all instrumentations except logging
- Prometheus (pull-based): only metrics

The exception is profiling, which only supports the google exporting due
to lack of support by OTEL upstream.

## Configuration and structure 

- All instrumentation is moved into the new `backend/v3/instrumentation`
package. It reuses configuration types, so both code and runtime
configuration are easier to understand.
- The `internal/telemetry` packages are removed.
- Instrumentation is started with a single function and a proper
shutdown function is now provided.
- Legacy configuration is still parsed from the runtime config, as long
as the new configuration is disabled. This allows backporting this
feature to v4 without breaking existing configurations.

# Additional Changes

- Devcontainer: set `$PATH` variable so installed go binaries can be run
individually, without NX.
- NX: install GCI tool to fix imports

# Additional Context

- Closes https://github.com/zitadel/zitadel/issues/8408
- Closes https://github.com/zitadel/zitadel/issues/6664
- Backport to v4
2026-01-12 05:51:39 +00:00

207 lines
5.7 KiB
Go

package serrors
import (
"context"
"encoding/json"
"errors"
"fmt"
"net/http"
"strconv"
"github.com/zitadel/logging"
http_util "github.com/zitadel/zitadel/internal/api/http"
zhttp_middleware "github.com/zitadel/zitadel/internal/api/http/middleware"
"github.com/zitadel/zitadel/internal/api/scim/schemas"
"github.com/zitadel/zitadel/internal/i18n"
"github.com/zitadel/zitadel/internal/zerrors"
)
type scimErrorType string
type wrappedScimError struct {
Parent error
ScimType scimErrorType
Status int
}
type ScimError struct {
Schemas []schemas.ScimSchemaType `json:"schemas"`
ScimType scimErrorType `json:"scimType,omitempty"`
Detail string `json:"detail,omitempty"`
StatusCode int `json:"-"`
Status string `json:"status"`
ZitadelDetail *ErrorDetail `json:"urn:ietf:params:scim:api:zitadel:messages:2.0:ErrorDetail,omitempty"`
}
type ErrorDetail struct {
ID string `json:"id"`
Message string `json:"message"`
}
const (
// ScimTypeInvalidValue A required value was missing,
// or the value specified was not compatible with the operation,
// or attribute type (see Section 2.2 of RFC7643),
// or resource schema (see Section 4 of RFC7643).
ScimTypeInvalidValue scimErrorType = "invalidValue"
// ScimTypeInvalidSyntax The request body message structure was invalid or did
// not conform to the request schema.
ScimTypeInvalidSyntax scimErrorType = "invalidSyntax"
// ScimTypeInvalidFilter The specified filter syntax as invalid, or the
// specified attribute and filter comparison combination is not supported.
ScimTypeInvalidFilter scimErrorType = "invalidFilter"
// ScimTypeInvalidPath The "path" attribute was invalid or malformed.
ScimTypeInvalidPath scimErrorType = "invalidPath"
// ScimTypeNoTarget The specified "path" did not
// yield an attribute or attribute value that could be operated on.
// This occurs when the specified "path" value contains a filter that yields no match.
ScimTypeNoTarget scimErrorType = "noTarget"
// ScimTypeUniqueness One or more of the attribute values are already in use or are reserved.
ScimTypeUniqueness scimErrorType = "uniqueness"
)
func ErrorHandler(translator *i18n.Translator) func(next zhttp_middleware.HandlerFuncWithError) http.Handler {
return func(next zhttp_middleware.HandlerFuncWithError) http.Handler {
var err error
return http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if err = next(w, r); err == nil {
return
}
scimErr := MapToScimError(r.Context(), translator, err)
w.WriteHeader(scimErr.StatusCode)
jsonErr := json.NewEncoder(w).Encode(scimErr)
logging.OnError(jsonErr).Warn("Failed to marshal scim error response")
})
}
}
func ThrowInvalidValue(parent error) error {
return &wrappedScimError{
Parent: parent,
ScimType: ScimTypeInvalidValue,
}
}
func ThrowInvalidSyntax(parent error) error {
return &wrappedScimError{
Parent: parent,
ScimType: ScimTypeInvalidSyntax,
}
}
func ThrowInvalidFilter(parent error) error {
return &wrappedScimError{
Parent: parent,
ScimType: ScimTypeInvalidFilter,
}
}
func ThrowInvalidPath(parent error) error {
return &wrappedScimError{
Parent: parent,
ScimType: ScimTypeInvalidPath,
}
}
func ThrowNoTarget(parent error) error {
return &wrappedScimError{
Parent: parent,
ScimType: ScimTypeNoTarget,
}
}
func ThrowPayloadTooLarge(parent error) error {
return &wrappedScimError{
Parent: parent,
Status: http.StatusRequestEntityTooLarge,
}
}
func IsScimOrZitadelError(err error) bool {
_, zok := zerrors.AsZitadelError(err)
return IsScimError(err) || zok
}
func IsScimError(err error) bool {
var scimErr *wrappedScimError
return errors.As(err, &scimErr)
}
func (err *ScimError) Error() string {
return fmt.Sprintf("SCIM Error: %s: %s", err.ScimType, err.Detail)
}
func (err *wrappedScimError) Error() string {
return fmt.Sprintf("SCIM Error: %s: %s", err.ScimType, err.Parent.Error())
}
func MapToScimError(ctx context.Context, translator *i18n.Translator, err error) *ScimError {
scimError := new(ScimError)
if ok := errors.As(err, &scimError); ok {
return scimError
}
scimWrappedError := new(wrappedScimError)
if ok := errors.As(err, &scimWrappedError); ok {
mappedErr := MapToScimError(ctx, translator, scimWrappedError.Parent)
if scimWrappedError.ScimType != "" {
mappedErr.ScimType = scimWrappedError.ScimType
}
if scimWrappedError.Status != 0 {
mappedErr.Status = strconv.Itoa(scimWrappedError.Status)
mappedErr.StatusCode = scimWrappedError.Status
}
return mappedErr
}
zitadelErr := new(zerrors.ZitadelError)
if ok := errors.As(err, &zitadelErr); !ok {
return &ScimError{
Schemas: []schemas.ScimSchemaType{schemas.IdError},
Detail: "Unknown internal server error",
Status: strconv.Itoa(http.StatusInternalServerError),
StatusCode: http.StatusInternalServerError,
}
}
statusCode, ok := http_util.ZitadelErrorToHTTPStatusCode(ctx, err)
if !ok {
statusCode = http.StatusInternalServerError
}
localizedMsg := translator.LocalizeFromCtx(ctx, zitadelErr.GetMessage(), nil)
return &ScimError{
Schemas: []schemas.ScimSchemaType{schemas.IdError, schemas.IdZitadelErrorDetail},
ScimType: mapErrorToScimErrorType(err),
Detail: localizedMsg,
StatusCode: statusCode,
Status: strconv.Itoa(statusCode),
ZitadelDetail: &ErrorDetail{
ID: zitadelErr.GetID(),
Message: zitadelErr.GetMessage(),
},
}
}
func mapErrorToScimErrorType(err error) scimErrorType {
switch {
case zerrors.IsErrorInvalidArgument(err):
return ScimTypeInvalidValue
case zerrors.IsErrorAlreadyExists(err):
return ScimTypeUniqueness
default:
return ""
}
}