fix(firecracker): remove per-bottle run dir on teardown

Each Firecracker bottle created its run dir (holding an ~1G
rootfs.ext4) but never removed it — launch teardown only terminated
the VM. Every run leaked its rootfs, filling the CI runner's disk
(187 stale sandbox-tester dirs / 141G in one incident).

Register a run-dir rmtree callback on the ExitStack before the
vm.terminate callback so, LIFO, the VM is gone before its rootfs is
removed. ignore_errors keeps teardown resilient.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-21 21:24:35 -04:00
parent 8fed02fd1e
commit 2cd06814e6
+5
View File
@@ -26,6 +26,7 @@ from __future__ import annotations
import dataclasses import dataclasses
import os import os
import shutil
from contextlib import ExitStack, contextmanager from contextlib import ExitStack, contextmanager
from pathlib import Path from pathlib import Path
from typing import Callable, Generator from typing import Callable, Generator
@@ -167,6 +168,10 @@ def launch(
# Step 6: build the per-bottle rootfs + SSH key, then boot. # Step 6: build the per-bottle rootfs + SSH key, then boot.
run_dir = util.cache_dir() / "run" / plan.slug run_dir = util.cache_dir() / "run" / plan.slug
run_dir.mkdir(parents=True, exist_ok=True) run_dir.mkdir(parents=True, exist_ok=True)
# Remove the run dir on teardown so the per-bottle rootfs.ext4 (~1G)
# doesn't leak. Registered before vm.terminate below so it runs *after*
# it (ExitStack is LIFO): the VM is gone before we rm its rootfs.
stack.callback(lambda: shutil.rmtree(run_dir, ignore_errors=True))
rootfs = run_dir / "rootfs.ext4" rootfs = run_dir / "rootfs.ext4"
util.build_rootfs_ext4(agent_base, rootfs) util.build_rootfs_ext4(agent_base, rootfs)
private_key, pubkey = util.generate_keypair(run_dir) private_key, pubkey = util.generate_keypair(run_dir)