bvandeusenandClaude Opus 5.5
8e890c6914
#5210 "Problems first, with since-time, across every list" (milestone 477), second batch. - Host page: an "Alerts on this host" strip first (rules on its agent series, its containers or its monitors: alert_svc.watches_host); its monitors problems first with "Down 12m · reason"; Docker above Ansible. - Uptime page and widget: worst 24h uptime first, then 7d and 30d; hosts with no uptime yet last. - Agent panel and fleet widget: last seen as "3m ago", not a clock time. - SNMP: a device is "Reachable" only while it answered within the last 3 polls; older readings say "No answer" with their age, and every device says when it was last read (was: reachable whenever any reading existed). - Traefik: a router missing from 3 scrapes in a row is listed apart as no longer reported, by when it was last seen, instead of keeping its last state (a removed router stayed Failing). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
56 lines
2.8 KiB
Python
56 lines
2.8 KiB
Python
"""Lists put what needs looking at first (#5210): hosts by their worst
|
|
signal, schedules failing first, maintenance windows active then upcoming."""
|
|
from types import SimpleNamespace as NS
|
|
|
|
from steward.ansible.routes import _schedule_order
|
|
from steward.hosts.service import host_rank
|
|
|
|
|
|
def test_hosts_sort_down_then_quiet_agent_then_pending_then_healthy():
|
|
down, up, pending = {"state": "down"}, {"state": "up"}, {"state": "pending"}
|
|
fresh, quiet = {"fresh": True}, {"fresh": False}
|
|
assert host_rank(down, fresh) == 0
|
|
assert host_rank(up, quiet) == 1 # monitors fine, but the agent went silent
|
|
assert host_rank(None, quiet) == 1
|
|
assert host_rank(pending, fresh) == 2
|
|
assert host_rank(up, fresh) == 3 and host_rank(None, fresh) == 3
|
|
assert host_rank(None, None) == 4 # nothing watches it
|
|
|
|
|
|
def _sched(name, *, enabled=True, last_error=None, status=None):
|
|
run = NS(status=NS(value=status)) if status else None
|
|
return {"s": NS(name=name, enabled=enabled, last_error=last_error), "last_run": run}
|
|
|
|
|
|
def test_schedules_sort_failing_first_and_paused_last():
|
|
rows = [_sched("nightly", status="success"), _sched("paused", enabled=False, status="failed"),
|
|
_sched("backup", status="failed"), _sched("deploy", status="running"),
|
|
_sched("broken", last_error="source not found"), _sched("cut", status="interrupted"),
|
|
_sched("busy", last_error="the last run is still going", status="success")]
|
|
assert [r["s"].name for r in sorted(rows, key=_schedule_order)] == [
|
|
"backup", "broken", "cut", "deploy", "busy", "nightly", "paused"]
|
|
|
|
|
|
def test_a_host_page_shows_only_the_alerts_on_that_host():
|
|
from steward.alerts.service import watches_host
|
|
|
|
def rule(source, resource):
|
|
return NS(source_module=source, resource_name=resource)
|
|
mine = {("http", "nas web")}
|
|
assert watches_host(rule("host_agent", "nas"), "nas", mine)
|
|
assert watches_host(rule("host_agent", "nas:/"), "nas", mine)
|
|
assert not watches_host(rule("host_agent", "nas2"), "nas", mine) # a name that merely starts alike
|
|
assert watches_host(rule("docker", "nas/plex"), "nas", mine)
|
|
assert not watches_host(rule("docker", "nas2/plex"), "nas", mine)
|
|
assert watches_host(rule("http", "nas web"), "nas", mine)
|
|
assert not watches_host(rule("http", "other web"), "nas", mine)
|
|
|
|
|
|
def test_uptime_lists_the_worst_first_and_the_unmeasured_last():
|
|
from steward.hosts.service import worst_uptime_first
|
|
hosts = [NS(id=i, name=n) for i, n in [("a", "alpha"), ("b", "bravo"), ("c", "charlie"), ("d", "delta")]]
|
|
uptime = {"a": {"24h": 100.0, "7d": 99.0, "30d": 99.5},
|
|
"b": {"24h": 92.0, "7d": 98.0, "30d": 99.0},
|
|
"c": {"24h": 100.0, "7d": 95.0, "30d": 97.0}}
|
|
assert [h.name for h in worst_uptime_first(hosts, uptime)] == ["bravo", "charlie", "alpha", "delta"]
|