part 4 缺陷 1：cell 启动竞态——起步门 + init pid 轮询
RETEST3 缺陷 1：run_cell 里配网与 payload 零同步，快 payload （run -- true）在配网完成前退出即撞墙，11 次只成 6 次。 本提交先落 helper（接线在缺陷 3 的 run_cell 重写里做）： - gate_wrapper_command()：payload 包一层 sh 起步门，等 /run/chv/.cell-gate-<machine> 出现再 exec（绝对路径 /usr/bin/sh：volatile 单元根里 /bin 未必有）。 - find_cell_init_pid() 改带超时轮询（timeout 默认 0.0 = 单次， 旧调用行为不变；缺目录不再直接回 None；proc_alive 回调让 nspawn 已死时立刻回，不空等）。 新测试：CellGateTest、CellInitPidPollTest（5 个）。
This commit is contained in:
host committed
1 parent
179a86d655
commit
fc33eed262
2 files changed
+120
-15
No files matched your search
+50
-15
@@ -235,24 +235,45 @@ def host_network_cleanup_commands(uplink_iface):
|
||||
return cmds
|
||||
|
||||
|
||||
def find_cell_init_pid(nspawn_pid, proc_root="/proc"):
|
||||
def find_cell_init_pid(nspawn_pid, proc_root="/proc", timeout=0.0,
|
||||
interval=0.1, proc_alive=None):
|
||||
"""找单元 init 的 pid：nspawn 进程的第一个子进程
|
||||
（--as-pid2 时它是 stub init，payload 是 PID 2；两者同 netns）。
|
||||
timeout=0（默认）即只查一次（旧行为）；timeout>0 时带超时轮询
|
||||
（part 4 竞态修复：init 可能还没 fork，单次查找即误判）。
|
||||
proc_alive 供调用方传“nspawn 是否还活着”（如 proc.poll() is
|
||||
None 的 lambda）：nspawn 已退出即立刻回 None，不再空等超时。
|
||||
找不到返回 None。"""
|
||||
try:
|
||||
task_dir = os.path.join(proc_root, str(nspawn_pid), "task")
|
||||
for tid in os.listdir(task_dir):
|
||||
children_path = os.path.join(task_dir, tid, "children")
|
||||
try:
|
||||
with open(children_path) as fh:
|
||||
children = fh.read().split()
|
||||
except OSError:
|
||||
continue
|
||||
if children:
|
||||
return int(children[0])
|
||||
except (OSError, ValueError):
|
||||
return None
|
||||
return None
|
||||
deadline = time.time() + timeout
|
||||
while True:
|
||||
found = None
|
||||
try:
|
||||
task_dir = os.path.join(proc_root, str(nspawn_pid), "task")
|
||||
for tid in os.listdir(task_dir):
|
||||
children_path = os.path.join(task_dir, tid, "children")
|
||||
try:
|
||||
with open(children_path) as fh:
|
||||
children = fh.read().split()
|
||||
except OSError:
|
||||
continue
|
||||
if children:
|
||||
try:
|
||||
found = int(children[0])
|
||||
except ValueError:
|
||||
continue
|
||||
break
|
||||
except OSError:
|
||||
# 任务目录还没出现（init 未 fork）即当作“这次没找到”，
|
||||
# 继续轮询，不直接回 None（旧代码这里直接 return None，
|
||||
# 正是单次查找误判的根因之一）。
|
||||
found = None
|
||||
if found is not None:
|
||||
return found
|
||||
if proc_alive is not None and not proc_alive():
|
||||
return None
|
||||
if time.time() >= deadline:
|
||||
return None
|
||||
time.sleep(min(interval, max(0.0, deadline - time.time())))
|
||||
|
||||
|
||||
def cell_network_commands(cell_pid):
|
||||
@@ -282,6 +303,20 @@ def _ensure_bind_source(path, uid=CELL_UID, gid=CELL_GID):
|
||||
raise
|
||||
|
||||
|
||||
def gate_wrapper_command(command, gate_path):
|
||||
"""把单元内命令包一层起步门（纯函数）：payload 先在单元内
|
||||
等 gate 文件出现再 exec 原命令。gate 文件由 run_cell 在配网
|
||||
完成后才创建（见 run_cell）——payload 与配网零同步是 RETEST3
|
||||
新缺陷 1 的根因（快 payload 在配网完成前退出，nspawn 随之
|
||||
退出，包装器再去配网即撞墙）。/usr/bin/sh 用绝对路径：
|
||||
volatile 单元根里 /bin 未必有，/usr 是只读挂进来的，必有。
|
||||
注意：$1 是 gate 路径，shift 后 "$@" 即原命令。"""
|
||||
script = ("while [ ! -e \"$1\" ]; do sleep 0.05; done; "
|
||||
"shift; exec \"$@\"")
|
||||
return ["/usr/bin/sh", "-c", script, "chv-cell-gate",
|
||||
gate_path] + list(command)
|
||||
|
||||
|
||||
def _wait_for_iface(iface, timeout=10.0):
|
||||
deadline = time.time() + timeout
|
||||
while time.time() < deadline:
|
||||
|
||||
@@ -742,5 +742,75 @@ class BuildDryRunTest(unittest.TestCase):
|
||||
self.assertIn(needle, out, needle)
|
||||
|
||||
|
||||
class CellGateTest(unittest.TestCase):
|
||||
"""part 4：起步门包装。"""
|
||||
|
||||
def test_gate_wrapper_waits_then_execs(self):
|
||||
wrapped = CELL.gate_wrapper_command(
|
||||
["python3", "/app/host.py", "status"],
|
||||
"/run/chv/.cell-gate-chv-cell-00")
|
||||
self.assertEqual(wrapped[:4], [
|
||||
"/usr/bin/sh", "-c",
|
||||
"while [ ! -e \"$1\" ]; do sleep 0.05; done; "
|
||||
"shift; exec \"$@\"",
|
||||
"chv-cell-gate"])
|
||||
self.assertEqual(wrapped[4],
|
||||
"/run/chv/.cell-gate-chv-cell-00")
|
||||
self.assertEqual(wrapped[5:],
|
||||
["python3", "/app/host.py", "status"])
|
||||
# 绝对路径：volatile 单元根里 /bin 未必有，/usr 必有。
|
||||
self.assertTrue(wrapped[0].startswith("/usr/bin/"))
|
||||
|
||||
|
||||
class CellInitPidPollTest(unittest.TestCase):
|
||||
"""part 4：find_cell_init_pid 带超时轮询。"""
|
||||
|
||||
def _proc_root_with_child(self, tmp, pid=777, child=778):
|
||||
task_dir = os.path.join(tmp, str(pid), "task", str(pid))
|
||||
os.makedirs(task_dir)
|
||||
with open(os.path.join(task_dir, "children"), "w") as fh:
|
||||
fh.write(str(child))
|
||||
|
||||
def test_single_shot_default_unchanged(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
self._proc_root_with_child(tmp)
|
||||
self.assertEqual(
|
||||
CELL.find_cell_init_pid(777, proc_root=tmp), 778)
|
||||
self.assertIsNone(
|
||||
CELL.find_cell_init_pid(999, proc_root=tmp))
|
||||
|
||||
def test_poll_finds_late_child(self):
|
||||
import threading
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
def _late():
|
||||
import time as _time
|
||||
_time.sleep(0.3)
|
||||
self._proc_root_with_child(tmp)
|
||||
threading.Thread(target=_late, daemon=True).start()
|
||||
self.assertEqual(
|
||||
CELL.find_cell_init_pid(777, proc_root=tmp,
|
||||
timeout=5.0), 778)
|
||||
|
||||
def test_poll_returns_none_on_timeout(self):
|
||||
import time as _time
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
start = _time.time()
|
||||
self.assertIsNone(
|
||||
CELL.find_cell_init_pid(999, proc_root=tmp,
|
||||
timeout=0.3))
|
||||
self.assertLess(_time.time() - start, 5.0)
|
||||
|
||||
def test_poll_stops_when_nspawn_dead(self):
|
||||
import time as _time
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
start = _time.time()
|
||||
self.assertIsNone(
|
||||
CELL.find_cell_init_pid(999, proc_root=tmp,
|
||||
timeout=10.0,
|
||||
proc_alive=lambda: False))
|
||||
# nspawn 已死即立刻回，不空等 10 秒。
|
||||
self.assertLess(_time.time() - start, 5.0)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in new issue
Block a user