thaloco/banger
1
Fork 0
Code Pull requests Releases Packages Activity Actions

daemon: thread per-RPC op_id end-to-end

Browse source 
Today there's no way to correlate a CLI failure with a daemon log
line. operationLog records relative timing but no id, two concurrent
vm.start calls log indistinguishably, and the async
vmCreateOperationState.ID is user-facing yet never reaches the
journal. The root helper logs plain text to stderr while bangerd
logs JSON, so a merged journalctl is hard to grep across the
trust-boundary split.

Mint a per-RPC op id at dispatch entry, store it on context, and
include it as an "op_id" attr on every operationLog record. The
id is stamped onto every error response (including the early
short-circuit paths bad_version and unknown_method). rpc.Call
forwards the context op id on requests so a daemon RPC and the
helper RPCs it triggers all share one id. The helper now logs
JSON to match bangerd, adopts the inbound id, and emits a single
"helper rpc completed" / "helper rpc failed" line per call so
operators can see at a glance how long each privileged op took.

vmCreateOperationState.ID is now the same id dispatch generated
for vm.create.begin — one identifier between client status polls,
daemon logs, and helper logs.

The wire format gains two optional fields: rpc.Request.OpID and
rpc.ErrorResponse.OpID, both omitempty so older peers (and the
opposite direction) ignore them. ErrorResponse.Error() now appends
"(op-XXXXXX)" to its string form when set; existing callers that
just print err.Error() get the id for free.

Tests cover: dispatch stamps op_id on unknown_method, bad_version,
and handler-returned errors; rpc.Call exposes the typed
*ErrorResponse via errors.As so the CLI can read code/op_id; ctx
op_id is forwarded to the server in the request envelope.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Thales Maciel 2026-04-26 22:13:44 -03:00
parent b8c48765fb
commit e47b8146dc
No known key found for this signature in database
GPG key ID: 33112E6833C34679
16 changed files with 333 additions and 44 deletions
Download patch file Download diff file Expand all files Collapse all files

10
internal/daemon/vm_lifecycle.go
View file

@ -30,7 +30,7 @@ func (s *VMService) StartVM(ctx context.Context, idOrName string) (model.VMRecor
}
func (s *VMService) startVMLocked(ctx context.Context, vm model.VMRecord, image model.Image) (_ model.VMRecord, err error) {
op := s.beginOperation("vm.start", append(vmLogAttrs(vm), imageLogAttrs(image)...)...)
op := s.beginOperation(ctx, "vm.start", append(vmLogAttrs(vm), imageLogAttrs(image)...)...)
defer func() {
if err != nil {
err = annotateLogPath(err, vm.Runtime.LogPath)
@ -97,7 +97,7 @@ func (s *VMService) StopVM(ctx context.Context, idOrName string) (model.VMRecord
func (s *VMService) stopVMLocked(ctx context.Context, current model.VMRecord) (vm model.VMRecord, err error) {
vm = current
op := s.beginOperation("vm.stop", "vm_ref", vm.ID)
op := s.beginOperation(ctx, "vm.stop", "vm_ref", vm.ID)
defer func() {
if err != nil {
op.fail(err, vmLogAttrs(vm)...)
@ -154,7 +154,7 @@ func (s *VMService) KillVM(ctx context.Context, params api.VMKillParams) (model.
func (s *VMService) killVMLocked(ctx context.Context, current model.VMRecord, signalValue string) (vm model.VMRecord, err error) {
vm = current
op := s.beginOperation("vm.kill", "vm_ref", vm.ID, "signal", signalValue)
op := s.beginOperation(ctx, "vm.kill", "vm_ref", vm.ID, "signal", signalValue)
defer func() {
if err != nil {
op.fail(err, vmLogAttrs(vm)...)
@ -209,7 +209,7 @@ func (s *VMService) killVMLocked(ctx context.Context, current model.VMRecord, si
}
func (s *VMService) RestartVM(ctx context.Context, idOrName string) (vm model.VMRecord, err error) {
op := s.beginOperation("vm.restart", "vm_ref", idOrName)
op := s.beginOperation(ctx, "vm.restart", "vm_ref", idOrName)
defer func() {
if err != nil {
op.fail(err, vmLogAttrs(vm)...)
@ -244,7 +244,7 @@ func (s *VMService) DeleteVM(ctx context.Context, idOrName string) (model.VMReco
func (s *VMService) deleteVMLocked(ctx context.Context, current model.VMRecord) (vm model.VMRecord, err error) {
vm = current
op := s.beginOperation("vm.delete", "vm_ref", vm.ID)
op := s.beginOperation(ctx, "vm.delete", "vm_ref", vm.ID)
defer func() {
if err != nil {
op.fail(err, vmLogAttrs(vm)...)