steve
94149a7324
Wires the existing job_detail Cancel button (which was a UI stub) into
real backend behaviour:
- internal/api already declared MsgCommandCancel + CommandCancelPayload;
promote those from forward-declarations to a working envelope. Agent
side: cmd/agent/main.go drops the TODO-stub and gains a per-job
ctx.CancelFunc map. runJob's switch is refactored around a small
spawn() helper so each kind's goroutine derives a per-job context,
registers the cancel, and removes itself on completion regardless of
outcome. command.cancel looks up the func and fires it.
- internal/agent/runner.sendFinished now takes ctx and rebadges
ctx.Canceled errors as JobCancelled (exit 130) rather than
JobFailed. All Run* call sites updated.
- internal/restic.resticCmd sets cmd.Cancel to send SIGTERM (via
build-tagged sigterm constant; os.Kill on Windows since SIGTERM
isn't deliverable there) and cmd.WaitDelay=5s for the SIGKILL
fallback. SIGTERM lets restic remove its lock file before exiting.
- New POST /api/jobs/{id}/cancel server endpoint validates the job
is non-terminal and the host is online, sends command.cancel via
the hub, writes a job.cancel audit row, returns 202. The agent's
resulting job.finished (status=cancelled) is what actually
transitions the row.
Tests:
- internal/server/http/cancel_test.go covers happy path (envelope
shape + audit row), 409 for terminal jobs, 404 for missing jobs,
503 for offline hosts.
- internal/agent/runner/cancel_test.go covers cancel mid-run: a fake
restic that exec'd into 'sleep 30' is canceled 150ms after start
and the resulting job.finished reports JobCancelled with exit 130
in well under the WaitDelay.
Foundational for P3 restore (operator needs to be able to cancel a
running backup if they need to restore urgently). Independently useful
for prune/check/backup that are stuck.
87 lines
2.4 KiB
Go
87 lines
2.4 KiB
Go
package http
|
|
|
|
import (
|
|
stdhttp "net/http"
|
|
"time"
|
|
|
|
"github.com/go-chi/chi/v5"
|
|
"github.com/oklog/ulid/v2"
|
|
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/api"
|
|
"gitea.dcglab.co.uk/steve/restic-manager/internal/store"
|
|
)
|
|
|
|
// handleCancelJob is POST /api/jobs/{id}/cancel. Sends a command.cancel
|
|
// envelope to the host that owns the job; the agent kills the running
|
|
// restic subprocess, and the resulting job.finished envelope (status =
|
|
// canceled) is what actually transitions the job row — this handler
|
|
// does not touch the jobs table directly. Returning 202 makes that
|
|
// asynchronicity explicit.
|
|
//
|
|
// 4xx cases:
|
|
// - job not found (404)
|
|
// - job already in a terminal state (409 — nothing to cancel)
|
|
// - host offline (503 — same code path the run-now endpoint uses)
|
|
//
|
|
// Audit-logged as job.cancel with the job ID as target.
|
|
func (s *Server) handleCancelJob(w stdhttp.ResponseWriter, r *stdhttp.Request) {
|
|
user, ok := s.requireUser(r)
|
|
if !ok {
|
|
writeJSONError(w, stdhttp.StatusUnauthorized, "unauthorized", "")
|
|
return
|
|
}
|
|
jobID := chi.URLParam(r, "id")
|
|
if jobID == "" {
|
|
writeJSONError(w, stdhttp.StatusBadRequest, "missing_job_id", "")
|
|
return
|
|
}
|
|
|
|
job, err := s.deps.Store.GetJob(r.Context(), jobID)
|
|
if err != nil {
|
|
writeJSONError(w, stdhttp.StatusNotFound, "job_not_found", "")
|
|
return
|
|
}
|
|
switch api.JobStatus(job.Status) {
|
|
case api.JobSucceeded, api.JobFailed, api.JobCancelled:
|
|
writeJSONError(w, stdhttp.StatusConflict, "job_terminal",
|
|
"job is already in a terminal state ("+job.Status+")")
|
|
return
|
|
}
|
|
|
|
if !s.deps.Hub.Connected(job.HostID) {
|
|
writeJSONError(w, stdhttp.StatusServiceUnavailable, "host_offline",
|
|
"agent is not connected; can't deliver cancel signal")
|
|
return
|
|
}
|
|
|
|
env, err := api.Marshal(api.MsgCommandCancel, jobID, api.CommandCancelPayload{
|
|
JobID: jobID,
|
|
})
|
|
if err != nil {
|
|
writeJSONError(w, stdhttp.StatusInternalServerError, "internal", "")
|
|
return
|
|
}
|
|
if err := s.deps.Hub.Send(r.Context(), job.HostID, env); err != nil {
|
|
writeJSONError(w, stdhttp.StatusServiceUnavailable, "host_offline", err.Error())
|
|
return
|
|
}
|
|
|
|
var actorID *string
|
|
actor := "system"
|
|
if user != nil {
|
|
actor = "user"
|
|
actorID = &user.ID
|
|
}
|
|
_ = s.deps.Store.AppendAudit(r.Context(), store.AuditEntry{
|
|
ID: ulid.Make().String(),
|
|
UserID: actorID,
|
|
Actor: actor,
|
|
Action: "job.cancel",
|
|
TargetKind: ptr("job"),
|
|
TargetID: &jobID,
|
|
TS: time.Now().UTC(),
|
|
})
|
|
|
|
w.WriteHeader(stdhttp.StatusAccepted)
|
|
}
|