feat(swarm): per-host microservices as systemd units, mutator off agents

Previously `decnet status` on an agent showed every microservice as DOWN
because deploy's auto-spawn was unihost-scoped and the agent CLI gate
hid the per-host commands. Now:

  - collect, probe, profiler, sniffer drop out of MASTER_ONLY_COMMANDS
    (they run per-host; master-side work stays master-gated).
  - mutate stays master-only (it orchestrates swarm-wide respawns).
  - decnet/mutator/ excluded from agent tarballs — never invoked there.
  - decnet/web exclusion tightened: ship db/ + auth.py + dependencies.py
    (profiler needs the repo singleton), drop api.py, swarm_api.py,
    ingester.py, router/, templates/.
  - Four new systemd unit templates (decnet-collector/prober/profiler/
    sniffer) shipped in every enrollment tarball.
  - enroll_bootstrap.sh enables + starts all four alongside agent and
    forwarder at install time.
  - updater restarts the aux units on code push so they pick up the new
    release (best-effort — legacy enrollments without the units won't
    fail the update).
  - status table hides Mutator + API rows in agent mode.
This commit is contained in:
2026-04-19 18:58:48 -04:00
parent ee9ade4cd5
commit 6d7877c679
10 changed files with 172 additions and 19 deletions

View File

@@ -237,6 +237,14 @@ def _run_pip(
AGENT_SYSTEMD_UNIT = "decnet-agent.service"
FORWARDER_SYSTEMD_UNIT = "decnet-forwarder.service"
UPDATER_SYSTEMD_UNIT = "decnet-updater.service"
# Per-host microservices that run out of the same /opt/decnet tree. An
# update replaces their code, so we must cycle them alongside the agent or
# they keep serving the pre-update image. Best-effort: legacy enrollments
# without these units installed shouldn't abort the update.
AUXILIARY_SYSTEMD_UNITS = (
"decnet-collector.service", "decnet-prober.service",
"decnet-profiler.service", "decnet-sniffer.service",
)
def _systemd_available() -> bool:
@@ -286,6 +294,13 @@ def _spawn_agent_via_systemd(install_dir: pathlib.Path) -> int:
)
if fwd.returncode != 0:
log.warning("forwarder restart failed (ignored): %s", fwd.stderr.strip())
for unit in AUXILIARY_SYSTEMD_UNITS:
aux = subprocess.run( # nosec B603 B607
["systemctl", "restart", unit],
check=False, capture_output=True, text=True,
)
if aux.returncode != 0:
log.warning("%s restart failed (ignored): %s", unit, aux.stderr.strip())
pid_out = subprocess.run( # nosec B603 B607
["systemctl", "show", "--property=MainPID", "--value", AGENT_SYSTEMD_UNIT],
check=True, capture_output=True, text=True,