bvandeusenandClaude Opus 5.5
4639ac6e52
response_ms was the whole `ping -c 1` process, or an open_connection awaited on the event loop: about 15 ms on a LAN whose round trip is under 1, and every host read slow together whenever Steward was busy. A ping now reports the round trip ping itself printed (the elapsed time only if it printed none); a TCP connect is timed in a thread, the name resolved first and not counted. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
98 lines
3.8 KiB
Python
98 lines
3.8 KiB
Python
"""A failed ping or TCP check says why (#5430): no reply, refused, no answer
|
|
in time, a name that doesn't resolve, or ping's own complaint; an ICMP check
|
|
that fell back to TCP says so."""
|
|
import asyncio
|
|
import socket
|
|
|
|
import pytest
|
|
|
|
from steward.monitors import ping
|
|
|
|
|
|
@pytest.mark.parametrize("exc,want", [
|
|
(asyncio.TimeoutError(), "No answer on port 22 within 5 s"),
|
|
(ConnectionRefusedError(111, "Connection refused"), "Connection refused on port 22"),
|
|
(socket.gaierror(-2, "Name or service not known"), "Can't resolve nas.lan: Name or service not known"),
|
|
(OSError(113, "No route to host"), "Can't connect to port 22: No route to host"),
|
|
(RuntimeError("odd"), "odd"),
|
|
])
|
|
def test_a_tcp_failure_says_why(monkeypatch, exc, want):
|
|
def boom(*a, **kw):
|
|
raise exc
|
|
monkeypatch.setattr(ping, "_connect_ms", boom)
|
|
got = asyncio.run(ping.tcp_check("nas.lan", 22))
|
|
assert got == {"is_up": False, "response_ms": None, "error_msg": want}
|
|
|
|
|
|
class _Proc:
|
|
def __init__(self, returncode, stderr=b"", stdout=b""):
|
|
self.returncode, self._stderr, self._stdout = returncode, stderr, stdout
|
|
|
|
async def communicate(self):
|
|
return self._stdout, self._stderr
|
|
|
|
|
|
@pytest.mark.parametrize("code,stderr,want", [
|
|
(1, b"", "No reply within 2 s"),
|
|
(2, b"ping: nas.lan: Name or service not known\n", "ping: nas.lan: Name or service not known"),
|
|
(2, b"", "ping failed (exit 2)"),
|
|
])
|
|
def test_a_ping_failure_says_why(monkeypatch, code, stderr, want):
|
|
async def spawn(*a, **kw):
|
|
return _Proc(code, stderr)
|
|
monkeypatch.setattr(ping.asyncio, "create_subprocess_exec", spawn)
|
|
got = asyncio.run(ping.icmp_check("nas.lan"))
|
|
assert got == {"is_up": False, "response_ms": None, "error_msg": want}
|
|
|
|
|
|
def test_a_reply_is_up_with_no_error(monkeypatch):
|
|
async def spawn(*a, **kw):
|
|
return _Proc(0)
|
|
monkeypatch.setattr(ping.asyncio, "create_subprocess_exec", spawn)
|
|
got = asyncio.run(ping.icmp_check("nas.lan"))
|
|
assert got["is_up"] is True and got["error_msg"] is None
|
|
|
|
|
|
def test_a_reply_s_time_is_the_round_trip_ping_reports_not_the_process(monkeypatch):
|
|
out = (b"PING nas.lan (192.168.0.7) 56(84) bytes of data.\n"
|
|
b"64 bytes from 192.168.0.7: icmp_seq=1 ttl=64 time=0.412 ms\n")
|
|
|
|
async def spawn(*a, **kw):
|
|
await asyncio.sleep(0.05) # a slow process start counts for nothing
|
|
return _Proc(0, stdout=out)
|
|
monkeypatch.setattr(ping.asyncio, "create_subprocess_exec", spawn)
|
|
assert asyncio.run(ping.icmp_check("nas.lan"))["response_ms"] == 0.41
|
|
|
|
|
|
@pytest.mark.parametrize("out,want", [
|
|
(b"64 bytes from 10.0.0.1: icmp_seq=1 ttl=64 time=12.3 ms", 12.3),
|
|
(b"64 bytes from 10.0.0.1: icmp_seq=1 ttl=64 time<1 ms", 1.0),
|
|
(b"64 bytes from 10.0.0.1: icmp_seq=1 ttl=64 time=0.05ms", 0.05),
|
|
(b"", None),
|
|
])
|
|
def test_ping_s_round_trip_is_read_from_its_line(out, want):
|
|
assert ping.ping_rtt(out) == want
|
|
|
|
|
|
def test_a_tcp_connect_is_timed_apart_from_the_event_loop(monkeypatch):
|
|
import threading
|
|
|
|
def connect(address, port):
|
|
assert threading.current_thread() is not threading.main_thread()
|
|
return 0.8
|
|
|
|
monkeypatch.setattr(ping, "_connect_ms", connect)
|
|
assert asyncio.run(ping.tcp_check("nas.lan", 22)) == {"is_up": True, "response_ms": 0.8, "error_msg": None}
|
|
|
|
|
|
def test_without_ping_the_tcp_stand_in_says_so(monkeypatch):
|
|
async def no_ping(*a, **kw):
|
|
raise FileNotFoundError("ping")
|
|
|
|
def refused(*a, **kw):
|
|
raise ConnectionRefusedError(111, "Connection refused")
|
|
monkeypatch.setattr(ping.asyncio, "create_subprocess_exec", no_ping)
|
|
monkeypatch.setattr(ping, "_connect_ms", refused)
|
|
got = asyncio.run(ping.icmp_check("nas.lan"))
|
|
assert got["error_msg"] == "ping unavailable, TCP check instead: Connection refused on port 80"
|