Files
zitadel/cmd/start/config.go
T
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

159 lines
5.6 KiB
Go

package start
import (
"context"
"errors"
"fmt"
"time"
"github.com/mitchellh/mapstructure"
"github.com/spf13/viper"
"github.com/zitadel/logging"
"github.com/zitadel/zitadel/backend/v3/instrumentation"
"github.com/zitadel/zitadel/cmd/encryption"
"github.com/zitadel/zitadel/cmd/hooks"
"github.com/zitadel/zitadel/internal/actions"
admin_es "github.com/zitadel/zitadel/internal/admin/repository/eventsourcing"
"github.com/zitadel/zitadel/internal/api/authz"
"github.com/zitadel/zitadel/internal/api/http/middleware"
"github.com/zitadel/zitadel/internal/api/oidc"
"github.com/zitadel/zitadel/internal/api/saml"
scim_config "github.com/zitadel/zitadel/internal/api/scim/config"
"github.com/zitadel/zitadel/internal/api/ui/console"
"github.com/zitadel/zitadel/internal/api/ui/login"
auth_es "github.com/zitadel/zitadel/internal/auth/repository/eventsourcing"
"github.com/zitadel/zitadel/internal/cache/connector"
"github.com/zitadel/zitadel/internal/command"
"github.com/zitadel/zitadel/internal/config/hook"
"github.com/zitadel/zitadel/internal/config/network"
"github.com/zitadel/zitadel/internal/config/systemdefaults"
"github.com/zitadel/zitadel/internal/database"
"github.com/zitadel/zitadel/internal/domain"
"github.com/zitadel/zitadel/internal/eventstore"
"github.com/zitadel/zitadel/internal/execution"
"github.com/zitadel/zitadel/internal/id"
"github.com/zitadel/zitadel/internal/logstore"
"github.com/zitadel/zitadel/internal/notification/handlers"
"github.com/zitadel/zitadel/internal/query/projection"
"github.com/zitadel/zitadel/internal/serviceping"
static_config "github.com/zitadel/zitadel/internal/static/config"
)
type Config struct {
Instrumentation instrumentation.Config
Log *logging.Config
Port uint16
ExternalPort uint16
ExternalDomain string
ExternalSecure bool
TLS network.TLS
InstanceHostHeaders []string
PublicHostHeaders []string
HTTP2HostHeader string
HTTP1HostHeader string
WebAuthNName string
Database database.Config
Caches *connector.CachesConfig
Tracing *instrumentation.LegacyTraceConfig
Metrics *instrumentation.LegacyMetricConfig
Profiler *instrumentation.LegacyProfileConfig
Projections projection.Config
Notifications handlers.WorkerConfig
Executions execution.WorkerConfig
Auth auth_es.Config
Admin admin_es.Config
UserAgentCookie *middleware.UserAgentCookieConfig
OIDC oidc.Config
SAML saml.Config
SCIM scim_config.Config
Login login.Config
Console console.Config
AssetStorage static_config.AssetStorageConfig
InternalAuthZ authz.Config
SystemAuthZ authz.Config
SystemDefaults systemdefaults.SystemDefaults
EncryptionKeys *encryption.EncryptionKeyConfig
DefaultInstance command.InstanceSetup
AuditLogRetention time.Duration
SystemAPIUsers map[string]*authz.SystemAPIUser
CustomerPortal string
Machine *id.Config
Actions *actions.Config
Eventstore *eventstore.Config
LogStore *logstore.Configs
Quotas *QuotasConfig
Telemetry *handlers.TelemetryPusherConfig
ServicePing *serviceping.Config
}
type QuotasConfig struct {
Access struct {
logstore.EmitterConfig `mapstructure:",squash"`
middleware.AccessConfig `mapstructure:",squash"`
}
Execution *logstore.EmitterConfig
}
func NewConfig(ctx context.Context, v *viper.Viper) (*Config, instrumentation.ShutdownFunc, error) {
config, err := readConfig(v)
if err != nil {
return nil, nil, fmt.Errorf("unable to read config: %w", err)
}
config.Instrumentation.Trace.SetLegacyConfig(config.Tracing)
config.Instrumentation.Metric.SetLegacyConfig(config.Metrics)
config.Instrumentation.Profile.SetLegacyConfig(config.Profiler)
shutdown, err := instrumentation.Start(ctx, config.Instrumentation)
if err != nil {
return nil, nil, fmt.Errorf("unable to start instrumentation: %w", err)
}
// Legacy logger
err = config.Log.SetLogger()
if err != nil {
err = errors.Join(err, shutdown(ctx))
return nil, nil, fmt.Errorf("unable to set logger: %w", err)
}
id.Configure(config.Machine)
if config.Actions != nil {
actions.SetHTTPConfig(&config.Actions.HTTP)
}
err = config.SystemDefaults.Validate()
if err != nil {
err = errors.Join(err, shutdown(ctx))
return nil, nil, fmt.Errorf("system defaults config invalid: %w", err)
}
// Copy the global role permissions mappings to the instance until we allow instance-level configuration over the API.
config.DefaultInstance.RolePermissionMappings = config.InternalAuthZ.RolePermissionMappings
return config, shutdown, nil
}
func readConfig(v *viper.Viper) (*Config, error) {
config := new(Config)
err := v.Unmarshal(config,
viper.DecodeHook(mapstructure.ComposeDecodeHookFunc(
hooks.SliceTypeStringDecode[*domain.CustomMessageText],
hooks.SliceTypeStringDecode[authz.RoleMapping],
hooks.MapTypeStringDecode[string, *authz.SystemAPIUser],
hooks.MapHTTPHeaderStringDecode,
database.DecodeHook(false),
actions.HTTPConfigDecodeHook,
hook.EnumHookFunc(authz.MemberTypeString),
hooks.MapTypeStringDecode[domain.Feature, any],
hooks.SliceTypeStringDecode[*command.SetQuota],
hook.Base64ToBytesHookFunc(),
hook.TagToLanguageHookFunc(),
mapstructure.StringToTimeDurationHookFunc(),
mapstructure.StringToTimeHookFunc(time.RFC3339),
mapstructure.StringToSliceHookFunc(","),
mapstructure.TextUnmarshallerHookFunc(),
)),
)
return config, err
}