Files
bot-bottle/bot_bottle/backend/firecracker/orchestrator.py
T
didericis dff811f190
tracker-policy-pr / check-pr (pull_request) Successful in 12s
lint / lint (push) Successful in 59s
test / unit (pull_request) Successful in 53s
test / integration-docker (pull_request) Successful in 1m7s
test / coverage (pull_request) Successful in 19s
fix(gateway): persist git-gate state across gateway restarts
Per-bottle git-gate state (bare repos under /git/<id>, deploy creds under
/git-gate/creds/<id>) was provisioned once at bottle launch and lived only
in the gateway's ephemeral storage. A gateway rebuild/restart wiped it and
nothing re-provisioned already-running bottles, so their agents 404'd on
fetch/push. Same class of bug as the CA (#510); the orchestrator restores
only egress tokens, not git-gate declarations.

Persist the state on both backends, mirroring the CA-persistence approach:

- firecracker: attach a second persistent data drive (/dev/vdc) to the
  gateway VM and bind-mount its git/ + creds/ subdirs onto /git and
  /git-gate/creds in the gateway guest init, before the data plane starts.
  Generalize the VM config to a stable-ordered data_drives tuple (CA=vdb,
  git=vdc; orchestrator registry stays vdb).
- docker: bind-mount host dirs (host_gateway_git_dir / creds_dir, under the
  never-pruned app-data root) onto /git and /git-gate/creds, with
  BOT_BOTTLE_DOCKER_GIT_MOUNT / _CREDS_MOUNT env overrides so CI isolates
  them to per-run volumes it cleans up.

Teardown already rm -rf's /git/<id> + creds, so the persistent store
self-cleans over the normal lifecycle.

Closes #512

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-26 17:34:22 -04:00

160 lines
7.1 KiB
Python

"""The Firecracker orchestrator (control plane) as a microVM (PRD 0070).
`FirecrackerOrchestrator` is the Firecracker implementation of the backend-neutral
`Orchestrator` service, and owns the control plane's host-side logic directly:
booting the orchestrator microVM on its NAT'd link with the persistent registry
volume (/dev/vdb — the sole opener of `bot-bottle.db`), seeding the host-canonical
signing key over SSH, and waiting for `/health`. The host CLI reaches it at its
guest IP, and so does the gateway (`bb_orch` cmdline), so `url()` == `gateway_url()`.
The plane-agnostic VM substrate the gateway VM also uses stays in `infra_vm` —
booting a VM from a per-plane rootfs (`boot_vm`), the stable SSH keypair, the
secret-push retry, the PID lifecycle, the adoption/version helpers, and the
per-plane guest inits (`role_init`). The pair coordinator (adopt-or-boot-both
under a singleton flock) is `FirecrackerInfraService` (`infra.py`).
"""
from __future__ import annotations
import subprocess
import time
from pathlib import Path
from ...log import die, info
from ...orchestrator.lifecycle import (
DEFAULT_STARTUP_TIMEOUT_SECONDS,
Orchestrator,
)
from . import firecracker_vm, infra_vm, netpool
from .infra_vm import ORCHESTRATOR_PORT
# The orchestrator microVM's name (its run dir). Fixed per host — one
# control-plane VM.
ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
# Memory ceiling (fixed at boot, demand-paged). The orchestrator keeps the build
# headroom (buildah's 2-4 GB working set during in-VM agent builds) — PRD 0070
# "Memory: fixed ceilings".
_ORCH_MEM_MIB = 4096
_HEALTH_POLL_SECONDS = 0.5
# The registry "volume": a host-side ext4 file attached to the orchestrator VM as
# a second virtio-block device (guest /dev/vdb), mounted at the control plane's DB
# dir. It outlives the ephemeral rootfs, so the bottle registry survives an
# orchestrator-VM restart — the firecracker analogue of a docker volume. A plain
# ext4 file: `sudo mount -o loop <path>` on the host (VM stopped) to inspect
# bot-bottle.db. The gateway VM has no such volume — the data plane never opens
# the DB (#469).
_REGISTRY_SIZE = "512M"
def registry_volume_path() -> Path:
return infra_vm._infra_dir() / "registry.ext4"
class FirecrackerOrchestrator(Orchestrator):
"""The control plane as a Firecracker microVM on the orchestrator link.
The orchestrator rootfs is built/downloaded by `infra_vm.ensure_built` (the
ABC's `ensure_built` no-op here); `ensure_running` boots the VM, seeds the
signing key, and blocks until `/health` answers."""
name = ORCHESTRATOR_NAME
def __init__(self, vm: infra_vm.InfraVm | None = None) -> None:
# The live VM handle when this process booted it; None when adapting an
# already-running orchestrator (health/URL go through the fixed link).
self._vm = vm
def url(self) -> str:
"""The orchestrator VM's guest IP URL — where the host CLI reaches the
control plane."""
return f"http://{netpool.orch_slot().guest_ip}:{ORCHESTRATOR_PORT}"
def gateway_url(self) -> str:
"""Same guest IP the host uses — the gateway resolves the orchestrator at
`bb_orch=<guest_ip>` off its cmdline."""
return self.url()
def ssh_target(self) -> tuple[Path, str]:
"""(private key, guest IP) for SSHing into the orchestrator VM. In-VM
agent-image builds (buildah) run here — the build host drives them over
SSH with the stable infra key."""
return infra_vm._infra_dir() / "id_ed25519", netpool.orch_slot().guest_ip
def is_running(self) -> bool:
return infra_vm._pidfile_alive(infra_vm._orch_dir())
def stop(self) -> None:
"""Stop only the orchestrator VM (idempotent). A dead orchestrator fails
`infra_vm.adoptable`'s health check, so no version marker to clear."""
infra_vm._kill_pidfile(infra_vm._orch_dir())
infra_vm._pid_file(infra_vm._orch_dir()).unlink(missing_ok=True)
def ensure_running(
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
) -> None:
"""Boot the orchestrator VM on its link with the persistent registry
volume, seed the signing key over SSH, and block until `/health` answers.
Idempotent — a live, healthy control plane is left alone (the pair
coordinator otherwise `stop()`s it before calling, so this boots fresh)."""
if self.is_running() and self.is_healthy():
return
vm = infra_vm.boot_vm(
name=ORCHESTRATOR_NAME, slot=netpool.orch_slot(),
run_dir=infra_vm._orch_dir(), role="orchestrator", mem_mib=_ORCH_MEM_MIB,
data_drives=(self._ensure_registry_volume(),),
)
# Push the host-canonical signing key (the init waits for it before
# starting the control plane). It comes through the shared provisioning
# contract (#476) — the same host token file every backend uses, so a
# co-running docker/macOS control plane keeps working and the guest
# verifies tokens with the same key the CLI signs from; fail-closed, so
# the guest is never handed an empty key that would run it OPEN.
infra_vm.push_secret(
vm, self.control_plane_key(), infra_vm._GUEST_SIGNING_KEY_PATH,
"the control-plane signing key to the orchestrator VM "
"(its control plane will not start)",
)
self._vm = vm
self._wait_for_health(vm, timeout=startup_timeout)
def _wait_for_health(
self, vm: infra_vm.InfraVm, *, timeout: float,
) -> None:
"""Poll `/health` until it answers 200 or the deadline passes. Dies (with
the console tail) if the VMM exits early."""
url = f"{self.url()}/health"
deadline = time.monotonic() + timeout
while time.monotonic() < deadline:
if vm.vm is not None and not vm.vm.is_alive():
die(f"orchestrator VM exited during boot (rc={vm.vm.process.returncode}).\n"
f"{firecracker_vm._console_tail(vm.vm.console_log)}")
if self.is_healthy():
info(f"orchestrator control plane healthy at {self.url()}")
return
time.sleep(_HEALTH_POLL_SECONDS)
tail = (firecracker_vm._console_tail(vm.vm.console_log)
if vm.vm is not None else "")
die(f"orchestrator control plane at {url} did not become healthy within "
f"{timeout:.0f}s.\n{tail}")
def _ensure_registry_volume(self) -> Path:
"""Create the empty ext4 registry volume on first use; reuse it after."""
vol = registry_volume_path()
if vol.exists():
return vol
info(f"creating infra registry volume {vol} ({_REGISTRY_SIZE})")
proc = subprocess.run(
["mke2fs", "-q", "-t", "ext4", "-F", str(vol), _REGISTRY_SIZE],
capture_output=True, text=True, check=False,
)
if proc.returncode != 0:
vol.unlink(missing_ok=True)
die(f"creating registry volume failed: {proc.stderr.strip()}")
return vol
__all__ = ["FirecrackerOrchestrator", "ORCHESTRATOR_NAME", "registry_volume_path"]