Monitor: keep checking interfaces whose link-down alert is still open
Lint / JS (eslint) (push) Successful in 8s
Lint / Python (flake8) (push) Successful in 49s
Lint / Notify on failure (push) Skipped
Lint / Deploy (push) Skipped
Security / Python Security (bandit) (push) Successful in 53s
Test / Python Tests (pytest) (push) Successful in 1m3s
Lint / Python (flake8) (pull_request) Successful in 55s
Lint / JS (eslint) (pull_request) Successful in 6s
Lint / Notify on failure (pull_request) Skipped
Lint / Deploy (pull_request) Skipped
Security / Python Security (bandit) (pull_request) Successful in 1m22s
Test / Python Tests (pytest) (pull_request) Successful in 1m27s
Lint / JS (eslint) (push) Successful in 8s
Lint / Python (flake8) (push) Successful in 49s
Lint / Notify on failure (push) Skipped
Lint / Deploy (push) Skipped
Security / Python Security (bandit) (push) Successful in 53s
Test / Python Tests (pytest) (push) Successful in 1m3s
Lint / Python (flake8) (pull_request) Successful in 55s
Lint / JS (eslint) (pull_request) Successful in 6s
Lint / Notify on failure (pull_request) Skipped
Lint / Deploy (pull_request) Skipped
Security / Python Security (bandit) (pull_request) Successful in 1m22s
Test / Python Tests (pytest) (pull_request) Successful in 1m27s
After the interface baseline is reset, a port that is already down reads as "first seen down", which neither alerts nor resolves. An alert opened before the reset was then stuck open without updates: micro1's enp3s0 had sat at one failed check since March with no ticket. An interface with an open interface_down alert is now treated as previously up, so the alert keeps counting, tickets and resolves as normal. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -31,6 +31,7 @@ def db():
|
||||
mock_db.cutsheet_load.return_value = {'items': [], 'cables': [], 'port_labels': []}
|
||||
mock_db.get_pending_recovery_notes.return_value = []
|
||||
mock_db.get_device_link.return_value = ''
|
||||
mock_db.get_open_event_targets.return_value = []
|
||||
yield mock_db
|
||||
|
||||
|
||||
@@ -117,6 +118,24 @@ class TestDeadHostDetection:
|
||||
mon._process_interfaces({HOST_A: {'eth0': True}}, [])
|
||||
assert ('cluster_network_issue', 'test-cluster', '') in upserted(db)
|
||||
|
||||
def test_open_alert_survives_a_baseline_reset(self, mon, db):
|
||||
# The baseline lost eth1 (reset), but its link-down alert is still open: keep alerting
|
||||
db.get_open_event_targets.return_value = [('alpha', 'eth1')]
|
||||
db.upsert_event.return_value = (3, False, 2, None)
|
||||
mon._process_interfaces({HOST_A: {'eth0': True, 'eth1': False}, HOST_B: {'eth0': True}}, [])
|
||||
assert ('interface_down', 'alpha', 'eth1') in upserted(db)
|
||||
assert 'Interface eth1 link-down' in mon.tickets.create.call_args.args[0]
|
||||
|
||||
def test_open_alert_resolves_when_the_link_returns(self, mon, db):
|
||||
db.get_open_event_targets.return_value = [('alpha', 'eth1')]
|
||||
mon._process_interfaces({HOST_A: {'eth0': True, 'eth1': True}, HOST_B: {'eth0': True}}, [])
|
||||
db.resolve_event.assert_any_call('interface_down', 'alpha', 'eth1')
|
||||
|
||||
def test_first_seen_down_without_an_alert_still_stays_quiet(self, mon, db):
|
||||
db.get_open_event_targets.return_value = []
|
||||
mon._process_interfaces({HOST_A: {'eth0': True, 'eth1': False}, HOST_B: {'eth0': True}}, [])
|
||||
assert ('interface_down', 'alpha', 'eth1') not in upserted(db)
|
||||
|
||||
def test_dead_host_shows_as_down_on_dashboard(self, mon):
|
||||
snap = mon._collect_snapshot({HOST_A: {'eth0': True}})
|
||||
assert snap['hosts']['alpha']['status'] == 'up'
|
||||
|
||||
Reference in New Issue
Block a user