Add structured daemon lifecycle logs
VM start, image build, and network/setup failures were hard to diagnose because bangerd emitted almost no lifecycle logs and the Firecracker SDK logger was discarded. This adds a daemon-wide JSON logger with configurable log level so failures leave breadcrumbs instead of only side effects. Log the main daemon and VM lifecycle stages, preserve raw Firecracker and image-build helper output in dedicated files, and include those log paths in daemon status and returned errors. Bridge SDK logrus output into the daemon logger at debug level so low-level Firecracker diagnostics are available without making normal info logs unreadable. Validation: go test ./... and make build. Left unrelated worktree changes out of this commit, including internal/api/types.go, the deleted shell scripts, and my-rootfs.ext4.
This commit is contained in:
parent
5018bc6170
commit
644e60d739
13 changed files with 746 additions and 31 deletions
129
internal/daemon/logger.go
Normal file
129
internal/daemon/logger.go
Normal file
|
|
@ -0,0 +1,129 @@
|
|||
package daemon
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"log/slog"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"banger/internal/model"
|
||||
)
|
||||
|
||||
func newDaemonLogger(w io.Writer, rawLevel string) (*slog.Logger, string, error) {
|
||||
level, normalized, err := parseLogLevel(rawLevel)
|
||||
if err != nil {
|
||||
return nil, "", err
|
||||
}
|
||||
logger := slog.New(slog.NewJSONHandler(w, &slog.HandlerOptions{Level: level}))
|
||||
return logger, normalized, nil
|
||||
}
|
||||
|
||||
func parseLogLevel(raw string) (slog.Level, string, error) {
|
||||
switch strings.ToLower(strings.TrimSpace(raw)) {
|
||||
case "", "info":
|
||||
return slog.LevelInfo, "info", nil
|
||||
case "debug":
|
||||
return slog.LevelDebug, "debug", nil
|
||||
case "warn", "warning":
|
||||
return slog.LevelWarn, "warn", nil
|
||||
case "error":
|
||||
return slog.LevelError, "error", nil
|
||||
default:
|
||||
return 0, "", fmt.Errorf("unsupported log_level %q (use debug, info, warn, or error)", raw)
|
||||
}
|
||||
}
|
||||
|
||||
func (d *Daemon) beginOperation(name string, attrs ...any) operationLog {
|
||||
if d.logger != nil {
|
||||
d.logger.Info("operation started", append([]any{"operation", name}, attrs...)...)
|
||||
}
|
||||
return operationLog{
|
||||
logger: d.logger,
|
||||
name: name,
|
||||
started: time.Now(),
|
||||
attrs: append([]any(nil), attrs...),
|
||||
}
|
||||
}
|
||||
|
||||
type operationLog struct {
|
||||
logger *slog.Logger
|
||||
name string
|
||||
started time.Time
|
||||
attrs []any
|
||||
}
|
||||
|
||||
func (o operationLog) stage(stage string, attrs ...any) {
|
||||
o.log(slog.LevelInfo, "operation stage", append([]any{"stage", stage}, attrs...)...)
|
||||
}
|
||||
|
||||
func (o operationLog) debugStage(stage string, attrs ...any) {
|
||||
o.log(slog.LevelDebug, "operation stage", append([]any{"stage", stage}, attrs...)...)
|
||||
}
|
||||
|
||||
func (o operationLog) done(attrs ...any) {
|
||||
o.log(slog.LevelInfo, "operation completed", append([]any{"duration_ms", time.Since(o.started).Milliseconds()}, attrs...)...)
|
||||
}
|
||||
|
||||
func (o operationLog) fail(err error, attrs ...any) error {
|
||||
if err == nil {
|
||||
return nil
|
||||
}
|
||||
o.log(slog.LevelError, "operation failed", append([]any{"duration_ms", time.Since(o.started).Milliseconds(), "error", err.Error()}, attrs...)...)
|
||||
return err
|
||||
}
|
||||
|
||||
func (o operationLog) log(level slog.Level, msg string, attrs ...any) {
|
||||
if o.logger == nil {
|
||||
return
|
||||
}
|
||||
base := append([]any{"operation", o.name}, o.attrs...)
|
||||
base = append(base, attrs...)
|
||||
o.logger.Log(context.Background(), level, msg, base...)
|
||||
}
|
||||
|
||||
func vmLogAttrs(vm model.VMRecord) []any {
|
||||
attrs := []any{
|
||||
"vm_id", vm.ID,
|
||||
"vm_name", vm.Name,
|
||||
"image_id", vm.ImageID,
|
||||
}
|
||||
if vm.Runtime.GuestIP != "" {
|
||||
attrs = append(attrs, "guest_ip", vm.Runtime.GuestIP)
|
||||
}
|
||||
if vm.Runtime.TapDevice != "" {
|
||||
attrs = append(attrs, "tap_device", vm.Runtime.TapDevice)
|
||||
}
|
||||
if vm.Runtime.APISockPath != "" {
|
||||
attrs = append(attrs, "api_socket", vm.Runtime.APISockPath)
|
||||
}
|
||||
if vm.Runtime.PID > 0 {
|
||||
attrs = append(attrs, "pid", vm.Runtime.PID)
|
||||
}
|
||||
if vm.Runtime.LogPath != "" {
|
||||
attrs = append(attrs, "log_path", vm.Runtime.LogPath)
|
||||
}
|
||||
return attrs
|
||||
}
|
||||
|
||||
func imageLogAttrs(image model.Image) []any {
|
||||
attrs := []any{
|
||||
"image_id", image.ID,
|
||||
"image_name", image.Name,
|
||||
}
|
||||
if image.ArtifactDir != "" {
|
||||
attrs = append(attrs, "artifact_dir", image.ArtifactDir)
|
||||
}
|
||||
if image.RootfsPath != "" {
|
||||
attrs = append(attrs, "rootfs_path", image.RootfsPath)
|
||||
}
|
||||
return attrs
|
||||
}
|
||||
|
||||
func annotateLogPath(err error, path string) error {
|
||||
if err == nil || strings.TrimSpace(path) == "" {
|
||||
return err
|
||||
}
|
||||
return fmt.Errorf("%w; inspect %s", err, path)
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue