feat(server): host presence, absent state and host-level status

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Uc9V1v7iXruubpoLiSE24M
This commit is contained in:
2026-09-21 09:25:33 -04:00
co-authored by Claude Sonnet 5
parent 1898bc52e5
commit 2f1cad9156
2 changed files with 139 additions and 1 deletions
+45 -1
View File
@@ -29,6 +29,7 @@ class Connection:
UP = "up" UP = "up"
DOWN = "down" DOWN = "down"
OVERDUE = "overdue" OVERDUE = "overdue"
ABSENT = "absent"
def __init__(self, host, cid, addr, afam): def __init__(self, host, cid, addr, afam):
self.host = host self.host = host
@@ -94,7 +95,9 @@ class Connection:
now = time.time() now = time.time()
if not Null: if not Null:
d["addr"] = self.addr d["addr"] = self.addr
if self.rtts[-1]: if self.state == Connection.ABSENT:
d["rtt"] = ""
elif self.rtts[-1]:
d["rtt"] = "%d" % round(self.rtts[-1]) d["rtt"] = "%d" % round(self.rtts[-1])
elif self.state == Connection.UNKNOWN: elif self.state == Connection.UNKNOWN:
d["rtt"] = "" d["rtt"] = ""
@@ -299,6 +302,8 @@ class Host:
self.alert_states = {} self.alert_states = {}
# Stale-data timers: {plugin_name: asyncio.TimerHandle} # Stale-data timers: {plugin_name: asyncio.TimerHandle}
self.plugin_timers = {} self.plugin_timers = {}
# Client-reported protocol presence: {afam: {"present": bool, "ts": float}}
self.presence: dict = {}
# User access control # User access control
self.owner: str | None = None # username of owner self.owner: str | None = None # username of owner
self.managers: list = [] # usernames with manager role self.managers: list = [] # usernames with manager role
@@ -322,6 +327,7 @@ class Host:
d["name"] = "<b>%s</b>" % d["name"] d["name"] = "<b>%s</b>" % d["name"]
d["dyn"] = str(self.dyn) d["dyn"] = str(self.dyn)
d["num"] = self.num d["num"] = self.num
d["status"] = self.status()
# Add alert counts (split by acknowledged status) # Add alert counts (split by acknowledged status)
warning_unacked = 0 warning_unacked = 0
@@ -444,6 +450,7 @@ class Host:
_, os_data = latest_os _, os_data = latest_os
hbc_version = os_data.get("hbc_version") hbc_version = os_data.get("hbc_version")
ddict["hbc_version"] = hbc_version ddict["hbc_version"] = hbc_version
ddict["status"] = self.status()
return ddict return ddict
@@ -459,6 +466,41 @@ class Host:
else: else:
return addr.find(".") > 0 return addr.find(".") > 0
def set_presence(self, afam, present, now):
"""Record the client's report of whether it has internet connectivity on afam."""
self.presence[afam] = {"present": bool(present), "ts": now}
def flag_present(self, afam):
"""Client-reported presence; True when the client never reported (legacy clients)."""
entry = getattr(self, "presence", {}).get(afam)
return True if entry is None else entry["present"]
def family_present(self, afam):
"""True if afam should be monitored: the client says it is present, or heartbeats
are demonstrably arriving on it (real traffic overrides a false "absent")."""
conn = self.connections.get(afam)
return self.flag_present(afam) or (conn is not None and conn.state == Connection.UP)
def status(self):
"""Host-level status: down, overdue, simplex, up or unknown.
overdue: every present family is overdue. simplex: both present, one up, one overdue
(same severity as up). Families the client reports absent are not considered.
"""
conns = self.connections
if any(c.state == Connection.DOWN for c in conns.values()):
return "down"
present = [c for afam, c in conns.items() if self.family_present(afam)]
up = sum(c.state == Connection.UP for c in present)
overdue = sum(c.state == Connection.OVERDUE for c in present)
if up and overdue:
return "simplex"
if up:
return "up"
if overdue:
return "overdue"
return "unknown"
def conndata(self, cid, addr, rtt, now): def conndata(self, cid, addr, rtt, now):
if addr[0:7] == "::ffff:": if addr[0:7] == "::ffff:":
addr = addr[7:] addr = addr[7:]
@@ -499,6 +541,8 @@ class Host:
self.monitors = [] self.monitors = []
if not hasattr(self, "plugin_timers"): if not hasattr(self, "plugin_timers"):
self.plugin_timers = {} self.plugin_timers = {}
if not hasattr(self, "presence"):
self.presence = {}
pass pass
+94
View File
@@ -0,0 +1,94 @@
import time
import pytest
from hbd.server import hbdclass
from hbd.server.hbdclass import Connection as C
def _host(name):
hbdclass.Host.hosts.pop(name, None)
return hbdclass.Host(name)
def _conn(host, afam, state):
addr = "192.0.2.1" if afam == "IPv4" else "2001:db8::1"
conn, _ = host.conndata(0, addr, None, 1000.0)
conn.state = state
return conn
CASES = [
# v4 state, v6 state, presence flags, expected status
(C.UP, C.UP, {}, "up"),
(C.UP, C.OVERDUE, {}, "simplex"), # both present (legacy) => simplex
(C.UP, C.OVERDUE, {"IPv6": True}, "simplex"),
(C.UP, C.OVERDUE, {"IPv6": False}, "up"), # v6 not present => not monitored
(C.OVERDUE, C.OVERDUE, {}, "overdue"),
(C.OVERDUE, C.ABSENT, {"IPv6": False}, "overdue"), # only present family is overdue
(C.UP, C.ABSENT, {"IPv6": False}, "up"),
(C.DOWN, C.UP, {}, "down"),
(C.UNKNOWN, C.UNKNOWN, {}, "unknown"),
(C.OVERDUE, C.UNKNOWN, {}, "overdue"),
(C.UP, C.UNKNOWN, {}, "up"),
(C.OVERDUE, C.UP, {"IPv6": False}, "simplex"), # HTB arriving => present despite flag
]
@pytest.mark.parametrize("s4,s6,flags,expected", CASES)
def test_status_matrix(s4, s6, flags, expected):
h = _host("status-matrix")
_conn(h, "IPv4", s4)
_conn(h, "IPv6", s6)
for afam, present in flags.items():
h.set_presence(afam, present, time.time())
assert h.status() == expected
def test_status_single_family_host():
h = _host("status-v4only")
_conn(h, "IPv4", C.UP)
assert h.status() == "up"
h.connections["IPv4"].state = C.OVERDUE
assert h.status() == "overdue"
def test_status_no_connections_is_unknown():
assert _host("status-empty").status() == "unknown"
def test_family_present_rules():
h = _host("fp")
v6 = _conn(h, "IPv6", C.OVERDUE)
assert h.family_present("IPv6") is True # never reported => present
h.set_presence("IPv6", False, 1.0)
assert h.family_present("IPv6") is False
v6.state = C.UP # real traffic overrides the flag
assert h.family_present("IPv6") is True
assert h.flag_present("IPv6") is False
def test_stateinfo_and_statedict_expose_status():
h = _host("status-exposed")
_conn(h, "IPv4", C.UP)
assert h.stateinfo()["status"] == "up"
assert h.statedict()["status"] == "up"
def test_absent_connection_statedict_is_neutral():
h = _host("absent-dict")
conn = _conn(h, "IPv6", C.ABSENT)
conn.rtts.append(42.0)
d = conn.statedict()
assert d["state"] == "absent" and d["rtt"] == "" and d["rttstate"] == "absent"
def test_presence_survives_pickle_and_old_pickles_get_default():
import pickle
h = _host("pickled")
h.set_presence("IPv6", False, 5.0)
h2 = pickle.loads(pickle.dumps(h))
assert h2.presence == {"IPv6": {"present": False, "ts": 5.0}}
del h2.__dict__["presence"] # simulate a pre-feature pickle
h2.fixup()
assert h2.presence == {}