Files
zitadel/internal/eventstore/handler/v2/failed_event.go
T
11dbb1b277 feat(logging): add streams (#11435)
# Which Problems Are Solved

Streams allow differentiating logs produced by different components of
Zitadel.

# How the Problems Are Solved

The `backend/v3/instrumentation/logging` package now exposes convenience
function for setting and getting a logger from the context. As well as
high-level functions to emit log records at various levels. When
constructing a new logger a "stream" needs to be specified:

- **runtime**: General runtime logs, such as startup and shutdown
messages. Default for logs that do not belong to the other categories.
- **request**: Logs for incoming API and HTTP requests.
- **event_handler**: Logs for event handling in projections.
- **queue**: Logs for the job queue processing.
- **event_pusher**: Logs for event pushing to the database. Disabled by
default, contains sensitive information.

Each line from the returned logger contains a `stream` field as well as
a `version` field with the current Zitadel version.

## Runtime config

Streams can be enabled by passing an array of stream names in the
runtime config. Because some log streams may contain sensitive data
(especially events), it is now also possible to mask values by their
key.

# Additional Changes

- Wrap `slogctx` in the `logging` package. (Except API error converter
packages, because of import cycle)
- Add some docs to `logging` package so other devs understand how to add
logging to Zitadel
- Add `logging.OnError` and `logging.WithError` helper functions with
`Panic()` and `Fatal()` methods, to preserve current calls in the `cmd`
packages.
- Add instance context extractor.
- Only output request details in the request info log. Request ID
remains propagated through context.
- Moved middleware functionality into protocol specific packages. 
- Removed setting of URI to context in metric middleware. There were ony
setters and no getters. (Unused value)
- Reuse a single statusWriter in the middleware package for middlewares
that need to know the response status.

# Additional Context

- Closes #11333
- Closes #11331 
- Partly #11330

---------

Co-authored-by: Silvan <[email protected]>
2026-02-04 11:51:43 +01:00

108 lines
2.6 KiB
Go

package handler
import (
"context"
"database/sql"
_ "embed"
"log/slog"
"time"
"github.com/zitadel/zitadel/backend/v3/instrumentation/logging"
"github.com/zitadel/zitadel/internal/eventstore"
"github.com/zitadel/zitadel/internal/zerrors"
)
var (
//go:embed failed_event_set.sql
setFailedEventStmt string
//go:embed failed_event_get_count.sql
failureCountStmt string
)
type failure struct {
sequence uint64
instance string
aggregateID string
aggregateType eventstore.AggregateType
eventDate time.Time
err error
}
func (f *failure) LogValue() slog.Value {
return slog.GroupValue(
slog.Uint64("sequence", f.sequence),
slog.String("instance", f.instance),
slog.String("aggregate_id", f.aggregateID),
)
}
func failureFromEvent(event eventstore.Event, err error) *failure {
return &failure{
sequence: event.Sequence(),
instance: event.Aggregate().InstanceID,
aggregateID: event.Aggregate().ID,
aggregateType: event.Aggregate().Type,
eventDate: event.CreatedAt(),
err: err,
}
}
func failureFromStatement(statement *Statement, err error) *failure {
return &failure{
sequence: statement.Sequence,
instance: statement.Aggregate.InstanceID,
aggregateID: statement.Aggregate.ID,
aggregateType: statement.Aggregate.Type,
eventDate: statement.CreationDate,
err: err,
}
}
func (h *Handler) handleFailedStmt(ctx context.Context, tx *sql.Tx, f *failure) (shouldContinue bool) {
ctx = logging.With(ctx, "failure", f)
failureCount, err := h.failureCount(tx, f)
if err != nil {
logging.Warn(ctx, "unable to get failure count", "err", err)
return false
}
failureCount += 1
err = h.setFailureCount(tx, failureCount, f)
logging.OnError(ctx, err).Warn("unable to update failure count")
return failureCount >= h.maxFailureCount
}
func (h *Handler) failureCount(tx *sql.Tx, f *failure) (count uint8, err error) {
row := tx.QueryRow(failureCountStmt,
h.projection.Name(),
f.instance,
f.aggregateType,
f.aggregateID,
f.sequence,
)
if err = row.Err(); err != nil {
return 0, zerrors.ThrowInternal(err, "CRDB-Unnex", "unable to update failure count")
}
if err = row.Scan(&count); err != nil {
return 0, zerrors.ThrowInternal(err, "CRDB-RwSMV", "unable to scan count")
}
return count, nil
}
func (h *Handler) setFailureCount(tx *sql.Tx, count uint8, f *failure) error {
_, err := tx.Exec(setFailedEventStmt,
h.projection.Name(),
f.instance,
f.aggregateType,
f.aggregateID,
f.eventDate,
f.sequence,
count,
f.err.Error(),
)
if err != nil {
return zerrors.ThrowInternal(err, "CRDB-4Ht4x", "set failure count failed")
}
return nil
}