Thales Maciel
e47b8146dc
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>
94 lines
4 KiB
Go
94 lines
4 KiB
Go
package daemon
|
|
|
|
import (
|
|
"context"
|
|
"log/slog"
|
|
"time"
|
|
|
|
ws "banger/internal/daemon/workspace"
|
|
"banger/internal/model"
|
|
"banger/internal/paths"
|
|
"banger/internal/store"
|
|
"banger/internal/system"
|
|
)
|
|
|
|
// WorkspaceService owns workspace.prepare / workspace.export plus the
|
|
// ssh-key + git-identity sync that runs as part of VM start's
|
|
// prepare_work_disk capability hook. The workspaceLocks set lives here
|
|
// so its scope (serialise concurrent tar imports on the same VM) is
|
|
// obvious at the field definition.
|
|
//
|
|
// The inspect/import test seams are per-service fields so tests inject
|
|
// fakes without mutating package-level state.
|
|
type WorkspaceService struct {
|
|
runner system.CommandRunner
|
|
logger *slog.Logger
|
|
config model.DaemonConfig
|
|
layout paths.Layout
|
|
store *store.Store
|
|
|
|
// workspaceLocks serialises concurrent workspace.prepare /
|
|
// workspace.export on the same VM. Separate from vmLocks so slow
|
|
// guest I/O doesn't block lifecycle ops.
|
|
workspaceLocks vmLockSet
|
|
|
|
// Peer-service access via narrow function-typed dependencies.
|
|
// WorkspaceService doesn't hold pointers to the full VMService or
|
|
// HostNetwork; it only sees the exact operations it needs.
|
|
vmResolver func(ctx context.Context, idOrName string) (model.VMRecord, error)
|
|
aliveChecker func(vm model.VMRecord) bool
|
|
waitGuestSSH func(ctx context.Context, address string, interval time.Duration) error
|
|
dialGuest func(ctx context.Context, address string) (guestSSHClient, error)
|
|
imageResolver func(ctx context.Context, idOrName string) (model.Image, error)
|
|
imageWorkSeed func(ctx context.Context, image model.Image, fingerprint string) error
|
|
withVMLockByRef func(ctx context.Context, idOrName string, fn func(model.VMRecord) (model.VMRecord, error)) (model.VMRecord, error)
|
|
|
|
beginOperation func(ctx context.Context, name string, attrs ...any) *operationLog
|
|
|
|
// repoInspector is the Inspector used by the real InspectRepo /
|
|
// ImportRepoToGuest fallbacks when the test seams below aren't
|
|
// set. wireServices installs the production one; tests that want
|
|
// to intercept only the host-command surface (not the whole
|
|
// inspect/import hook) can assign a stub-runner Inspector here.
|
|
repoInspector *ws.Inspector
|
|
|
|
// Test seams.
|
|
workspaceInspectRepo func(ctx context.Context, sourcePath, branchName, fromRef string, includeUntracked bool) (ws.RepoSpec, error)
|
|
workspaceImport func(ctx context.Context, client ws.GuestClient, spec ws.RepoSpec, guestPath string, mode model.WorkspacePrepareMode) error
|
|
}
|
|
|
|
type workspaceServiceDeps struct {
|
|
runner system.CommandRunner
|
|
logger *slog.Logger
|
|
config model.DaemonConfig
|
|
layout paths.Layout
|
|
store *store.Store
|
|
repoInspector *ws.Inspector
|
|
vmResolver func(ctx context.Context, idOrName string) (model.VMRecord, error)
|
|
aliveChecker func(vm model.VMRecord) bool
|
|
waitGuestSSH func(ctx context.Context, address string, interval time.Duration) error
|
|
dialGuest func(ctx context.Context, address string) (guestSSHClient, error)
|
|
imageResolver func(ctx context.Context, idOrName string) (model.Image, error)
|
|
imageWorkSeed func(ctx context.Context, image model.Image, fingerprint string) error
|
|
withVMLockByRef func(ctx context.Context, idOrName string, fn func(model.VMRecord) (model.VMRecord, error)) (model.VMRecord, error)
|
|
beginOperation func(ctx context.Context, name string, attrs ...any) *operationLog
|
|
}
|
|
|
|
func newWorkspaceService(deps workspaceServiceDeps) *WorkspaceService {
|
|
return &WorkspaceService{
|
|
runner: deps.runner,
|
|
logger: deps.logger,
|
|
config: deps.config,
|
|
layout: deps.layout,
|
|
store: deps.store,
|
|
repoInspector: deps.repoInspector,
|
|
vmResolver: deps.vmResolver,
|
|
aliveChecker: deps.aliveChecker,
|
|
waitGuestSSH: deps.waitGuestSSH,
|
|
dialGuest: deps.dialGuest,
|
|
imageResolver: deps.imageResolver,
|
|
imageWorkSeed: deps.imageWorkSeed,
|
|
withVMLockByRef: deps.withVMLockByRef,
|
|
beginOperation: deps.beginOperation,
|
|
}
|
|
}
|