Files
sientia-dataops-opc-ingestor/tests/unit/managers/test_ingestor_manager.py
Eduardo Rios 4235ce8edb SIENTIAPDE-1974: fix(slots): guard every reader unsubscribe and count failures
Second code review round (xhigh) of 057c1fd + 085e609: 5 findings.

Fixed:
- manage_server's subscribe-failure path called reader.unsubscribe() directly;
  with the legacy OpcManager a dead session made it raise out of the except
  block and stop the main loop. Both paths now go through _unsubscribe_reader,
  the single guarded per-reader unsubscribe.
- An unsubscribe failure also increments OPC_SUBSCRIPTION_ERRORS (same tags as
  the subscription failures), besides the OPC_UNSUBSCRIBE_ERROR notification.
- The contract test creates the subscriptions through the readers' real
  create_subscription (fake pool / client) instead of writing engine
  internals, and checks the pool pin/unpin pair.

Documented (no code change):
- If delete() fails while the session is still alive (e.g. a timeout), the
  server-side subscription may keep delivering data until that session ends
  (reconnection or pod restart); noted in _unsubscribe_reader.
- manage_leases now unsubscribes before releasing the leases: if Redis fails
  while releasing them, the slots stay unread until LEASE_TTL expires, which is
  preferred to two pods reading the same slot.

284 unit tests; the 2 new behavior tests fail on 085e609.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-07 16:15:06 -03:00

1084 lines
40 KiB
Python

import gc
from unittest.mock import ANY, AsyncMock, MagicMock, call, patch
from pytest import fixture, mark
from sientia_do.notifications.models import NotificationLevel
import ingestor.metrics as metrics
from ingestor.config import GatewayConfig
from ingestor.connection.pool import OpcConnectionPool
from ingestor.io.slots import parse_slot
from ingestor.managers.ingestor_manager import IngestorManager
from ingestor.managers.opc_manager import OpcManager
from ingestor.managers.server_reader import ServerReader
metadata = {
'metadata': {
'model_id': 'test_model',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
'schema_name': 'test_schedule',
},
}
def raw_slot_v1(tag_name='Counter', address='ns=2;i=2'):
"""A slot as the current (v1) Orchestrator writes it to Redis."""
return {
'server1': {
'name': 'server1',
'server_id': '1',
'url': 'opc.tcp://localhost:4840',
'server_uri': 'urn:sientia:opc-ingestor',
'cert_path': '/app/certs/opc-ingestor-cert.pem',
'subscription_period_ms': 500.0,
'tags': {address: {'tag_name': tag_name, 'frequency': '1000', 'topics': ['raw_a']}},
}
}
@fixture(autouse=True)
def _collect_garbage_after_test():
# ponytail: IngestorManager.__del__ calls asyncio.run(self.shutdown()); if a
# cyclic-referenced instance from a previous test is swept mid-test by the
# generational GC, it can double-call whatever asyncio mock happens to be
# patched at that moment (e.g. test___del__). Force a deterministic sweep
# after each test so finalizers run in their own test's scope. Upgrade path:
# only needed if IngestorManager stops relying on __del__ for cleanup.
yield
gc.collect()
@fixture
@patch('ingestor.managers.ingestor_manager.DataManager')
@patch('ingestor.managers.ingestor_manager.ResourceManager')
def ingestor_manager(data_manager_mock, resource_manager_mock):
ingestor = IngestorManager(
redis_data={'host': 'localhost', 'port': 6379},
lease_ttl=60,
heartbeat_ttl=60,
poll_interval=5,
mongo_connection_string='mongodb://localhost:27017',
mongo_database='sientia',
logger=MagicMock(),
notification_handler=MagicMock(),
metadata=metadata['metadata'],
metrics_controller=MagicMock(),
)
ingestor.send_notification = MagicMock()
ingestor.send_notification_async = AsyncMock()
ingestor.emit_metric = AsyncMock()
return ingestor
@patch('ingestor.managers.ingestor_manager.ServerReader')
@patch('ingestor.managers.ingestor_manager.DataManager')
@patch('ingestor.managers.ingestor_manager.ResourceManager')
@patch('ingestor.managers.ingestor_manager.NotificationHandler')
def test___init__(
notification_handler_mock, resource_manager_mock, data_manager_mock, server_reader_mock
):
ingestor = IngestorManager(
redis_data={'host': 'localhost', 'port': 6379},
lease_ttl=60,
heartbeat_ttl=60,
poll_interval=5,
mongo_connection_string='mongodb://localhost:27017',
mongo_database='sientia',
logger=MagicMock(),
notification_handler=MagicMock(),
metadata=metadata['metadata'],
metrics_controller=MagicMock(),
)
server_reader_mock.assert_not_called()
data_manager_mock.assert_called_once_with(
mongo_connection_string='mongodb://localhost:27017',
mongo_database='sientia',
metadata=metadata['metadata'],
logger=ingestor.logger,
notification_handler=ingestor.notification_handler,
metrics_controller=ingestor.metrics_controller,
)
resource_manager_mock.assert_called_once_with(
host='localhost',
port=6379,
lease_ttl=60,
heartbeat_ttl=60,
metadata=metadata['metadata'],
logger=ingestor.logger,
notification_handler=ingestor.notification_handler,
username=None,
password=None,
metrics_controller=ingestor.metrics_controller,
)
assert ingestor.poll_interval == 5
assert ingestor.managed_tags == {}
assert ingestor.opc_servers == {}
assert ingestor.opc_managers == {}
assert ingestor.data_manager == data_manager_mock.return_value
assert ingestor.resource_manager == resource_manager_mock.return_value
# Read path (SIENTIAPDE-1974): pool + read sink built here, nothing connected yet.
assert isinstance(ingestor.pool, OpcConnectionPool)
assert ingestor.pool.cert_provider is ingestor.cert_provider
assert ingestor.cert_provider.mongo is data_manager_mock.return_value.mongo_repository
assert ingestor.sink.data_manager is data_manager_mock.return_value
assert ingestor.sink.postgres is None
@patch('ingestor.managers.ingestor_manager.DataManager')
@patch('ingestor.managers.ingestor_manager.ResourceManager')
def test___init___cert_provider_uses_gateway_config(resource_manager_mock, data_manager_mock):
ingestor = IngestorManager(
redis_data={'host': 'localhost', 'port': 6379},
lease_ttl=60,
heartbeat_ttl=60,
poll_interval=5,
mongo_connection_string='mongodb://localhost:27017',
mongo_database='sientia',
logger=MagicMock(),
notification_handler=MagicMock(),
metadata=metadata['metadata'],
metrics_controller=MagicMock(),
gateway_config=GatewayConfig(cert_bucket='my-bucket', cert_cache_dir='certs-cache'),
)
assert ingestor.cert_provider.bucket == 'my-bucket'
assert ingestor.cert_provider.cache_dir == 'certs-cache'
@mark.asyncio
@patch('ingestor.managers.ingestor_manager.ServerReader')
async def test_initialize_opc_from_config(server_reader, ingestor_manager):
server_config = {
'name': 'server1',
'server_id': '1',
'url': 'opc.tcp://localhost:4840',
'server_uri': 'urn:sientia:opc-ingestor',
'use_security': True,
'subscription_period_ms': 1000,
}
server_reader.return_value = MagicMock(connect=AsyncMock())
result = await ingestor_manager.initialize_opc_from_config(server_config)
server_reader.assert_called_once_with(
name=server_config['name'],
server_config=server_config,
pool=ingestor_manager.pool,
sink=ingestor_manager.sink,
logger=ingestor_manager.logger,
notification_handler=ingestor_manager.notification_handler,
metrics_controller=ingestor_manager.metrics_controller,
metadata=metadata['metadata'],
)
assert result == server_reader.return_value
assert result.config == server_config
result.connect.assert_awaited_once()
@mark.asyncio
@patch('ingestor.managers.ingestor_manager.ServerReader')
@patch('ingestor.managers.ingestor_manager.traceback')
async def test_initialize_opc_from_config_exception(
traceback_mock, server_reader, ingestor_manager
):
server_config = {
'name': 'server1',
'server_id': '1',
'url': 'opc.tcp://localhost:4840',
'server_uri': 'urn:sientia:opc-ingestor',
'use_security': True,
'subscription_period_ms': 1000,
}
ingestor_manager.logger.error = MagicMock()
# e.g. the server is unreachable or the certificate can't be fetched from MinIO
server_reader.return_value = MagicMock(
connect=AsyncMock(side_effect=Exception('Initialization error'))
)
result = await ingestor_manager.initialize_opc_from_config(server_config)
assert result is None
traceback_mock.format_exc.assert_called_once()
ingestor_manager.send_notification.assert_called_once_with(
metadata=metadata['metadata'],
notification_id=f'OPC_CONNECTION_ERROR_{server_config["name"]}',
message='Error initializing OPC manager: Initialization error',
block='opc_manager',
level=NotificationLevel.ERROR,
attachment_content=traceback_mock.format_exc.return_value,
)
@mark.asyncio
async def test_shutdown(ingestor_manager):
ingestor_manager.opc_managers = {'server1': AsyncMock(), 'server2': AsyncMock()}
ingestor_manager.data_manager.shutdown = MagicMock()
ingestor_manager.pool = MagicMock(close_all=AsyncMock())
await ingestor_manager.shutdown()
ingestor_manager.opc_managers['server1'].shutdown.assert_called_once()
ingestor_manager.opc_managers['server2'].shutdown.assert_called_once()
# The pool is owned by the read path: closed after the readers unsubscribe.
ingestor_manager.pool.close_all.assert_awaited_once()
ingestor_manager.data_manager.shutdown.assert_called_once()
@mark.asyncio
async def test_remove_server(ingestor_manager):
server1 = AsyncMock()
server2 = AsyncMock()
ingestor_manager.opc_managers = {'server1': server1, 'server2': server2}
ingestor_manager.managed_tags = {
'slot1': {'server1': {'config': 'config1'}, 'server2': {'config': 'config2'}}
}
await ingestor_manager.remove_server('server1')
server1.shutdown.assert_called_once()
server2.shutdown.assert_not_called()
assert 'server1' not in ingestor_manager.opc_managers
assert 'server2' in ingestor_manager.opc_managers
assert ingestor_manager.managed_tags == {'slot1': {'server2': {'config': 'config2'}}}
@mark.asyncio
async def test_remove_server_not_found(ingestor_manager):
server1 = AsyncMock()
server2 = AsyncMock()
ingestor_manager.opc_managers = {'server1': server1, 'server2': server2}
ingestor_manager.managed_tags = {
'slot1': {'server1': {'config': 'config1'}, 'server2': {'config': 'config2'}}
}
await ingestor_manager.remove_server('server3')
server1.shutdown.assert_not_called()
server2.shutdown.assert_not_called()
assert 'server1' in ingestor_manager.opc_managers
assert 'server2' in ingestor_manager.opc_managers
assert ingestor_manager.managed_tags == {
'slot1': {'server1': {'config': 'config1'}, 'server2': {'config': 'config2'}}
}
@mark.asyncio
@patch('ingestor.managers.ingestor_manager.metrics')
async def test_update_opc_servers(metrics, ingestor_manager):
manager1 = MagicMock(config={'config': 'config1'})
manager2 = MagicMock(config={'config': 'config2'})
manager3 = MagicMock(config={'config': 'config3'})
async def mock_initialize_from_config(config):
if config == {'config': 'config1'}:
return manager1
elif config == {'config': 'config2'}:
return manager2
elif config == {'config': 'config3'}:
return manager3
else:
return None
ingestor_manager.initialize_opc_from_config = AsyncMock(side_effect=mock_initialize_from_config)
ingestor_manager.remove_server = AsyncMock()
ingestor_manager.managed_tags = {
'slot1': {
'server1': {'config': 'config1'},
'server2': {'config': 'config2'},
'server5': {'config': 'config5'},
},
'slot2': {
'server3': {'config': 'config3'},
'server1': {'config': 'config1'},
},
}
mock = AsyncMock(config={'config': 'old_config2'})
ingestor_manager.opc_managers['server3'] = AsyncMock(config={'config': 'config3'})
ingestor_manager.opc_managers['server2'] = mock
ingestor_manager.opc_managers['server4'] = AsyncMock()
await ingestor_manager.update_opc_servers()
ingestor_manager.initialize_opc_from_config.assert_any_call({'config': 'config1'})
ingestor_manager.initialize_opc_from_config.assert_any_call({'config': 'config2'})
ingestor_manager.initialize_opc_from_config.assert_any_call({'config': 'config5'})
assert ingestor_manager.initialize_opc_from_config.call_count == 3
assert ingestor_manager.opc_managers['server1'].config == {'config': 'config1'}
assert ingestor_manager.opc_managers['server2'].config == {'config': 'config2'}
assert ingestor_manager.opc_managers['server3'].config == {'config': 'config3'}
# server4 left this pod's slots: unsubscribe only, the connection stays for writes
ingestor_manager.remove_server.assert_any_call('server4', evict=False)
# server5 failed to initialize: removed with the default (evict)
ingestor_manager.remove_server.assert_any_call('server5')
assert ingestor_manager.remove_server.call_count == 2
assert ingestor_manager.opc_managers['server2'] != mock
ingestor_manager.emit_metric.assert_called_once_with(
metric_object=metrics.OPC_MANAGERS_ACTIVE,
method='set',
value=len(ingestor_manager.opc_managers),
tags={'pod_id': ingestor_manager.pod_id},
)
@mark.asyncio
@patch('ingestor.managers.ingestor_manager.metrics')
async def test_check_opc_servers_integrity_all_healthy(metrics, ingestor_manager):
# Setup mock OPC managers
opc_manager1 = MagicMock()
opc_manager1.check_cycles = AsyncMock(return_value=None)
opc_manager1.check_opc_listenning = AsyncMock(return_value=False)
opc_manager1.config = {'config': 'config1'}
opc_manager2 = MagicMock()
opc_manager2.check_cycles = AsyncMock(return_value=None)
opc_manager2.check_opc_listenning = AsyncMock(return_value=False)
opc_manager2.config = {'config': 'config2'}
ingestor_manager.opc_managers = {'server1': opc_manager1, 'server2': opc_manager2}
# Mock the initialize_opc_from_config method
ingestor_manager.initialize_opc_from_config = MagicMock()
# Call the method
await ingestor_manager.check_opc_servers_integrity()
# Verify that check_cycles and check_opc_listenning were called for each server
opc_manager1.check_cycles.assert_called_once()
opc_manager1.check_opc_listenning.assert_called_once()
opc_manager2.check_cycles.assert_called_once()
opc_manager2.check_opc_listenning.assert_called_once()
# Verify that no reinitialization was needed
ingestor_manager.initialize_opc_from_config.assert_not_called()
ingestor_manager.emit_metric.assert_called_once_with(
metric_object=metrics.OPC_MANAGERS_ACTIVE,
method='set',
value=len(ingestor_manager.opc_managers),
tags={'pod_id': ingestor_manager.pod_id},
)
@mark.asyncio
async def test_check_opc_servers_integrity_server_lost(ingestor_manager):
# Setup mock OPC manager that will be lost
opc_manager = AsyncMock()
opc_manager.check_cycles.return_value = None
opc_manager.check_opc_listenning.return_value = True # Server is lost
opc_manager.config = {'config': 'config1'}
ingestor_manager.opc_managers = {'server1': opc_manager}
ingestor_manager.managed_tags = {'slot1': MagicMock()}
# Call the method
await ingestor_manager.check_opc_servers_integrity()
assert 'server1' not in ingestor_manager.opc_managers
ingestor_manager.managed_tags['slot1'].pop.assert_called_once_with('server1', None)
def test_check_opc_servers_integrity_server_lost_with_tags(ingestor_manager):
# Setup mock OPC manager that will be lost
opc_manager = MagicMock()
opc_manager.check_cycles.return_value = None
opc_manager.check_opc_listenning.return_value = True # Server is lost
opc_manager.config = {'config': 'config1'}
ingestor_manager.opc_managers = {'server1': opc_manager}
# Setup managed tags
ingestor_manager.managed_tags = {
'slot1': {'server1': {'config': 'config1', 'tags': {'tag1': 'value1'}}}
}
# Mock the initialize_opc_from_config method to return a new manager
new_manager = MagicMock()
ingestor_manager.initialize_opc_from_config = MagicMock(return_value=new_manager)
# Call the method
ingestor_manager.check_opc_servers_integrity()
@mark.asyncio
async def test_declare_active(ingestor_manager):
ingestor_manager.resource_manager.ingestor_heartbeat = AsyncMock()
await ingestor_manager.declare_active()
ingestor_manager.resource_manager.ingestor_heartbeat.assert_called_once()
@mark.asyncio
async def test_get_active_ingestors(ingestor_manager):
ingestor_manager.resource_manager.get_all_ingestors = AsyncMock()
await ingestor_manager.get_active_ingestors()
ingestor_manager.resource_manager.get_all_ingestors.assert_called_once()
@mark.asyncio
async def test_get_active_ingestors_empty(ingestor_manager):
ingestor_manager.resource_manager.get_all_ingestors = AsyncMock(return_value=None)
result = await ingestor_manager.get_active_ingestors()
assert result == []
ingestor_manager.resource_manager.get_all_ingestors.assert_called_once()
@patch('ingestor.managers.ingestor_manager.metrics')
@mark.asyncio
async def test_get_number_of_leases_success(metrics, ingestor_manager):
ingestor_manager.resource_manager.get_all_leases = AsyncMock(return_value=['lease1', 'lease2'])
result = await ingestor_manager.get_number_of_leases()
assert result == 2
ingestor_manager.emit_metric.assert_called_once_with(
metric_object=metrics.LEASES_TOTAL,
method='set',
value=2,
tags={'pod_id': ingestor_manager.pod_id},
)
ingestor_manager.resource_manager.get_all_leases.assert_called_once()
@patch('ingestor.managers.ingestor_manager.metrics')
@mark.asyncio
async def test_get_number_of_slots_success(metrics, ingestor_manager):
ingestor_manager.resource_manager.get_all_slots = AsyncMock(return_value=['slot1', 'slot2'])
result = await ingestor_manager.get_number_of_slots()
assert result == 2
ingestor_manager.resource_manager.get_all_slots.assert_called_once()
ingestor_manager.emit_metric.assert_called_once_with(
metric_object=metrics.SLOTS_TOTAL,
method='set',
value=2,
tags={'pod_id': ingestor_manager.pod_id},
)
@patch('ingestor.managers.ingestor_manager.metrics')
@mark.asyncio
async def test_get_number_of_slots_empty(metrics, ingestor_manager):
ingestor_manager.resource_manager.get_all_slots = AsyncMock(return_value=None)
result = await ingestor_manager.get_number_of_slots()
assert result == 0
ingestor_manager.resource_manager.get_all_slots.assert_called_once()
ingestor_manager.emit_metric.assert_called_once_with(
metric_object=metrics.SLOTS_TOTAL,
method='set',
value=0,
tags={'pod_id': ingestor_manager.pod_id},
)
@mark.asyncio
async def test_get_slot_leases_1_success(ingestor_manager):
ingestor_manager.resource_manager.lease_tag = AsyncMock(return_value=True)
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(return_value=raw_slot_v1())
ingestor_manager.number_of_slots = 1
result = await ingestor_manager.get_slot_leases()
# Stored already normalized to slot v2 (v1 converted by parse_slot).
assert result == {'1': parse_slot(raw_slot_v1())}
assert ingestor_manager.managed_tags == result
@mark.asyncio
async def test_get_slot_leases_2_success(ingestor_manager):
ingestor_manager.resource_manager.lease_tag = AsyncMock(side_effect=[True, True])
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
side_effect=[raw_slot_v1('Counter'), raw_slot_v1('Ramp', 'ns=2;i=3')]
)
ingestor_manager.number_of_slots = 2
result = await ingestor_manager.get_slot_leases(max_slots=2)
assert result == {
'1': parse_slot(raw_slot_v1('Counter')),
'2': parse_slot(raw_slot_v1('Ramp', 'ns=2;i=3')),
}
@mark.asyncio
async def test_get_slot_leases_skips_malformed_slot(ingestor_manager):
ingestor_manager.resource_manager.lease_tag = AsyncMock(return_value=True)
# tag without names/topics/frequency
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
return_value={'server1': {'server_id': '1', 'url': 'u', 'tags': {'ns=2;i=2': {}}}}
)
ingestor_manager.number_of_slots = 1
result = await ingestor_manager.get_slot_leases()
assert result == {}
_, kwargs = ingestor_manager.send_notification.call_args
assert kwargs['notification_id'] == 'OPC_SLOT_CONFIG_ERROR_1'
assert kwargs['level'] == NotificationLevel.ERROR
@mark.asyncio
async def test_get_slot_leases_2_1_none(ingestor_manager):
ingestor_manager.resource_manager.lease_tag = AsyncMock(side_effect=[True, True])
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
side_effect=[None, {'tags': ['tag1']}]
)
ingestor_manager.number_of_slots = 1
result = await ingestor_manager.get_slot_leases(max_slots=1)
assert result == {}
@mark.asyncio
async def test_get_slot_leases_1_failure(ingestor_manager):
ingestor_manager.resource_manager.lease_tag = AsyncMock(return_value=False)
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(return_value={'tags': ['tag1']})
result = await ingestor_manager.get_slot_leases()
ingestor_manager.resource_manager.get_tag_slot.assert_not_called()
assert result == {}
@mark.asyncio
async def test_unsubscribe_slot(ingestor_manager, reader_double):
ingestor_manager.managed_tags = {
'slot1': {'server1': {'tags': 'config1'}, 'server2': {'tags': 'config2'}},
'slot2': {'server3': {'tags': 'config3'}, 'server1': {'tags': 'config1'}},
}
ingestor_manager.opc_managers = {
'server1': reader_double('slot1', 'slot2'),
'server2': reader_double('slot1'),
'server3': reader_double('slot2'),
}
await ingestor_manager.unsubscribe_slot('slot1')
ingestor_manager.opc_managers['server1'].unsubscribe.assert_called_once_with('slot1')
ingestor_manager.opc_managers['server2'].unsubscribe.assert_called_once_with('slot1')
ingestor_manager.opc_managers['server3'].unsubscribe.assert_not_called()
assert list(ingestor_manager.opc_managers['server1'].subscriptions) == ['slot2']
@mark.asyncio
async def test_unsubscribe_slot_not_in_managed_tags(ingestor_manager, reader_double):
"""The slot is already gone from managed_tags: the readers still holding it are unsubscribed"""
ingestor_manager.managed_tags = {'slot1': {'server1': {'tags': 'config1'}}}
ingestor_manager.opc_managers = {
'server1': reader_double('slot1', 'slot3'),
'server2': reader_double('slot3'),
}
await ingestor_manager.unsubscribe_slot('slot3')
ingestor_manager.opc_managers['server1'].unsubscribe.assert_called_once_with('slot3')
ingestor_manager.opc_managers['server2'].unsubscribe.assert_called_once_with('slot3')
@mark.asyncio
async def test_unsubscribe_slot_twice_is_a_no_op(ingestor_manager, reader_double):
"""A second unsubscribe of the same slot (lease already dropped) does nothing and never raises"""
ingestor_manager.managed_tags = {}
ingestor_manager.opc_managers = {'server1': reader_double('slot2')}
await ingestor_manager.unsubscribe_slot('slot2')
await ingestor_manager.unsubscribe_slot('slot2')
ingestor_manager.opc_managers['server1'].unsubscribe.assert_called_once_with('slot2')
@mark.asyncio
async def test_unsubscribe_slot_reader_failure_does_not_raise(ingestor_manager, reader_double):
"""A reader that fails to unsubscribe is notified and forgotten; the others still go"""
broken = reader_double('slot1')
broken.unsubscribe = AsyncMock(side_effect=ConnectionError('session closed'))
healthy = reader_double('slot1')
ingestor_manager.opc_managers = {'server1': broken, 'server2': healthy}
await ingestor_manager.unsubscribe_slot('slot1')
healthy.unsubscribe.assert_called_once_with('slot1')
assert 'slot1' not in broken.subscriptions
ingestor_manager.emit_metric.assert_called_once_with(
metric_object=metrics.OPC_SUBSCRIPTION_ERRORS,
tags={'pod_id': ingestor_manager.pod_id, 'server': 'server1', 'slot': 'slot1'},
)
ingestor_manager.send_notification_async.assert_called_once_with(
metadata=ingestor_manager.metadata,
notification_id='OPC_UNSUBSCRIBE_ERROR_slot1:server1',
message='Failed to unsubscribe slot slot1 from server1: session closed',
block='opc_manager',
level=NotificationLevel.ERROR,
attachment_content=ANY,
)
@mark.asyncio
async def test_unsubscribe_slot_with_real_readers(ingestor_manager):
"""Contract: both real readers keep `subscriptions` keyed by slot, and
unsubscribe_slot closes the slot's subscription on each of them"""
v2_subscription = AsyncMock()
client = MagicMock(create_subscription=AsyncMock(return_value=v2_subscription))
pool = MagicMock(get=AsyncMock(return_value=client), evict=AsyncMock())
server_reader = ServerReader(
name='kepserver',
server_config={
'server_id': '1',
'url': 'opc.tcp://kepserver:49320',
'subscription_period_ms': 1000.0,
},
pool=pool,
sink=AsyncMock(),
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
metadata={},
)
server_reader.engine.emit_metric = AsyncMock()
await server_reader.create_subscription('slot1')
with patch('ingestor.managers.opc_manager.metrics'):
legacy_reader = OpcManager(
name='legacy',
url='opc.tcp://legacy:4840',
data_manager=AsyncMock(),
subscription_period_ms=1000,
logger=MagicMock(),
server_uri='opc.tcp://legacy:4840',
notification_handler=MagicMock(),
metadata={},
metrics_controller=AsyncMock(),
)
legacy_reader.emit_metric = AsyncMock()
legacy_subscription = AsyncMock()
legacy_reader.client = MagicMock(
create_subscription=AsyncMock(return_value=legacy_subscription)
)
await legacy_reader.create_subscription('slot1')
assert 'slot1' in server_reader.subscriptions
assert 'slot1' in legacy_reader.subscriptions
ingestor_manager.opc_managers = {'kepserver': server_reader, 'legacy': legacy_reader}
await ingestor_manager.unsubscribe_slot('slot1')
v2_subscription.delete.assert_awaited_once()
legacy_subscription.delete.assert_awaited_once()
assert 'slot1' not in server_reader.subscriptions
assert 'slot1' not in legacy_reader.subscriptions
pool.pin.assert_called_once_with('1')
pool.unpin.assert_called_once_with('1')
@mark.asyncio
async def test_update_slot_config_unsubscribes_removed_slot(ingestor_manager, reader_double):
"""A slot deleted from Redis is unsubscribed right away, not left to the main loop"""
ingestor_manager.managed_tags = {
'slot1': parse_slot(raw_slot_v1('Same')),
'slot2': parse_slot(raw_slot_v1('Same')),
}
reader = reader_double('slot1', 'slot2')
ingestor_manager.opc_managers = {'test_server': reader}
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
side_effect=lambda slot: raw_slot_v1('Same') if slot == 'slot1' else None
)
ingestor_manager.resource_manager.renew_tag_lease = AsyncMock()
await ingestor_manager.update_slot_config()
reader.unsubscribe.assert_called_once_with('slot2')
assert list(ingestor_manager.managed_tags) == ['slot1']
assert list(reader.subscriptions) == ['slot1']
@mark.asyncio
async def test_update_slot_config(ingestor_manager):
ingestor_manager.managed_tags = {
'slot1': parse_slot(raw_slot_v1('Old')),
'slot2': parse_slot(raw_slot_v1('Same')),
'slot3': parse_slot(raw_slot_v1('Old')),
}
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
side_effect=[raw_slot_v1('Updated'), raw_slot_v1('Same'), None]
)
ingestor_manager.resource_manager.renew_tag_lease = AsyncMock()
await ingestor_manager.update_slot_config()
assert ingestor_manager.managed_tags['slot1'] == parse_slot(raw_slot_v1('Updated'))
assert ingestor_manager.managed_tags['slot2'] == parse_slot(raw_slot_v1('Same'))
assert 'slot3' not in ingestor_manager.managed_tags
ingestor_manager.resource_manager.renew_tag_lease.assert_any_call('slot1')
ingestor_manager.resource_manager.renew_tag_lease.assert_any_call('slot3')
ingestor_manager.resource_manager.renew_tag_lease.assert_any_call('slot2')
assert ingestor_manager.resource_manager.renew_tag_lease.call_count == 3
@patch('ingestor.managers.ingestor_manager.metrics')
@mark.asyncio
async def test_drop_slot_leases(metrics, ingestor_manager):
ingestor_manager.resource_manager.drop_tag_lease = AsyncMock()
await ingestor_manager.drop_slot_leases(['1', '2'])
ingestor_manager.resource_manager.drop_tag_lease.assert_any_call('1')
ingestor_manager.resource_manager.drop_tag_lease.assert_any_call('2')
ingestor_manager.emit_metric.assert_has_calls(
[
call(
metric_object=metrics.SLOTS_RELEASED,
method='inc',
value=1,
tags={'pod_id': ingestor_manager.pod_id},
),
call(
metric_object=metrics.SLOTS_RELEASED,
method='inc',
value=1,
tags={'pod_id': ingestor_manager.pod_id},
),
]
)
@mark.asyncio
async def test_manage_server_no_server(ingestor_manager):
ingestor_manager.opc_managers = {'server1': MagicMock(), 'server2': MagicMock()}
server_config = {'tags': 'config1'}
result = await ingestor_manager.manage_server('slot1', 'server3', server_config, server_config)
assert result == 1
ingestor_manager.opc_managers['server1'].create_subscription.assert_not_called()
ingestor_manager.opc_managers['server1'].subscribe.assert_not_called()
@mark.asyncio
async def test_manage_server_create_subscription_failure(ingestor_manager):
ingestor_manager.opc_managers = {'server1': MagicMock(), 'server2': MagicMock()}
ingestor_manager.subscriptions = {'server1': MagicMock()}
server_config = {'tags': 'config1'}
ingestor_manager.opc_managers['server1'].create_subscription.side_effect = Exception(
'Subscription error'
)
result = await ingestor_manager.manage_server('slot1', 'server1', server_config, server_config)
assert result == 2
ingestor_manager.opc_managers['server1'].create_subscription.assert_called_once_with('slot1')
ingestor_manager.opc_managers['server1'].subscribe.assert_not_called()
@mark.asyncio
async def test_manage_server_subscribe_and_unsubscribe_failure(ingestor_manager):
"""subscribe() fails and so does the cleanup unsubscribe (legacy reader, session
gone): manage_server reports the failure and nothing escapes to the main loop"""
reader = AsyncMock()
reader.subscriptions = {}
reader.subscribe.side_effect = Exception('Subscription error')
reader.unsubscribe.side_effect = ConnectionError('session closed')
ingestor_manager.opc_managers = {'server1': reader}
server_config = {'tags': {'tag1': 'config1'}}
result = await ingestor_manager.manage_server('slot1', 'server1', server_config, server_config)
assert result == 2
reader.unsubscribe.assert_called_once_with('slot1')
notified = [
c.kwargs['notification_id'] for c in ingestor_manager.send_notification_async.call_args_list
]
assert notified == [
'OPC_SUBSCRIPTION_ERROR_slot1:server1',
'OPC_UNSUBSCRIBE_ERROR_slot1:server1',
]
@mark.asyncio
async def test_manage_server(ingestor_manager):
ingestor_manager.opc_managers = {'server1': AsyncMock(), 'server2': AsyncMock()}
ingestor_manager.subscriptions = {'server1': AsyncMock()}
server_config = {'tags': 'config1'}
result = await ingestor_manager.manage_server('slot1', 'server1', server_config, server_config)
assert result == 0
ingestor_manager.opc_managers['server1'].create_subscription.assert_called_once_with('slot1')
ingestor_manager.opc_managers['server1'].subscribe.assert_called_once_with(
'slot1', 'config1', ingestor_manager.poll_interval
)
@patch('ingestor.managers.ingestor_manager.traceback')
@mark.asyncio
async def test_manage_server_subscribe_failure(traceback_mock, ingestor_manager):
ingestor_manager.opc_managers = {'server1': AsyncMock(), 'server2': AsyncMock()}
ingestor_manager.subscriptions = {'server1': AsyncMock()}
server_config = {'tags': 'config1'}
ingestor_manager.opc_managers['server1'].subscribe.side_effect = Exception('Subscription error')
result = await ingestor_manager.manage_server('slot1', 'server1', server_config, server_config)
assert result == 2
ingestor_manager.opc_managers['server1'].create_subscription.assert_called_once_with('slot1')
ingestor_manager.opc_managers['server1'].subscribe.assert_called_once_with(
'slot1', 'config1', ingestor_manager.poll_interval
)
ingestor_manager.opc_managers['server1'].unsubscribe.assert_called_once_with('slot1')
traceback_mock.format_exc.assert_called_once()
ingestor_manager.send_notification_async.assert_called_once_with(
metadata=metadata['metadata'],
notification_id='OPC_SUBSCRIPTION_ERROR_slot1:server1',
message="Failed to subscribe to tags from slot1:server1\n{'tags': 'config1'}: Subscription error",
block='opc_manager',
level=NotificationLevel.ERROR,
attachment_content=traceback_mock.format_exc.return_value,
)
ingestor_manager.logger.warning.assert_any_call(
'Removing subscription from server server1 for slot slot1'
)
@mark.asyncio
async def test_subscribe_to_tags(ingestor_manager):
ingestor_manager.manage_server = AsyncMock(side_effect=[0, 1, 2])
ingestor_manager.managed_tags = {'slot1': MagicMock(), 'slot2': MagicMock()}
ingestor_manager.opc_managers = {
'server1': AsyncMock(),
'server2': AsyncMock(),
'server3': AsyncMock(),
}
ingestor_manager.subscriptions = {'server1': AsyncMock()}
tags = {
'slot1': {
'server1': {'tags': 'config1'},
'server2': {'tags': 'config2'},
'server3': {'tags': 'config3'},
}
}
await ingestor_manager.subscribe_to_tags(tags)
ingestor_manager.manage_server.assert_any_call('slot1', 'server1', {'tags': 'config1'}, tags)
ingestor_manager.manage_server.assert_any_call('slot1', 'server2', {'tags': 'config2'}, tags)
ingestor_manager.manage_server.assert_any_call('slot1', 'server3', {'tags': 'config3'}, tags)
assert ingestor_manager.manage_server.call_count == 3
ingestor_manager.managed_tags['slot1'].pop.assert_called_once_with('server3', None)
@mark.asyncio
async def test_update_slot_config_keeps_last_good_config_when_malformed(ingestor_manager):
good = parse_slot(raw_slot_v1('Counter'))
ingestor_manager.managed_tags = {'slot1': good}
ingestor_manager.resource_manager.get_tag_slot = AsyncMock(
return_value={'server1': {'server_id': '1', 'url': 'u', 'tags': {'ns=2;i=2': {}}}}
)
ingestor_manager.resource_manager.renew_tag_lease = AsyncMock()
await ingestor_manager.update_slot_config()
# Still reading with the last good config; the bad one is notified, not applied.
assert ingestor_manager.managed_tags == {'slot1': good}
_, kwargs = ingestor_manager.send_notification.call_args
assert kwargs['notification_id'] == 'OPC_SLOT_CONFIG_ERROR_slot1'
@mark.asyncio
async def test_remove_server_forwards_evict(ingestor_manager):
reader = AsyncMock()
ingestor_manager.opc_managers = {'server1': reader}
ingestor_manager.managed_tags = {'slot1': {'server1': {}}}
await ingestor_manager.remove_server('server1', evict=False)
reader.shutdown.assert_awaited_once_with(evict=False)
assert 'server1' not in ingestor_manager.opc_managers
assert ingestor_manager.managed_tags == {'slot1': {}}
@patch('ingestor.managers.ingestor_manager.DataManager')
@patch('ingestor.managers.ingestor_manager.ResourceManager')
def test___init___ignores_malformed_write_env(
resource_manager_mock, data_manager_mock, monkeypatch
):
"""A malformed write/gRPC-only env var must not stop the read path (review #1)."""
monkeypatch.setenv('GRPC_PORT', '')
monkeypatch.setenv('WRITE_MIN_PAUSE_S', '0,5')
monkeypatch.setenv('CERT_BUCKET', 'streamlit-connectors')
ingestor = IngestorManager(
redis_data={'host': 'localhost', 'port': 6379},
lease_ttl=60,
heartbeat_ttl=60,
poll_interval=5,
mongo_connection_string='mongodb://localhost:27017',
mongo_database='sientia',
logger=MagicMock(),
notification_handler=MagicMock(),
metadata=metadata['metadata'],
metrics_controller=MagicMock(),
)
assert ingestor.cert_provider.bucket == 'streamlit-connectors'
def test_parse_slot_config_warns_once_about_server_cert_path(ingestor_manager):
raw = raw_slot_v1()
raw['server1']['server_cert_path'] = '/app/certs/kepserver.der'
ingestor_manager.parse_slot_config('1', raw)
ingestor_manager.parse_slot_config('1', raw) # every loop refreshes the slot
warnings = [
c for c in ingestor_manager.logger.warning.call_args_list if 'server_cert_path' in str(c)
]
assert len(warnings) == 1
# --- READ_ENGINE=legacy: plan B with the untouched rc3 OpcManager -------------------
def make_manager(read_engine=None):
with (
patch('ingestor.managers.ingestor_manager.DataManager'),
patch('ingestor.managers.ingestor_manager.ResourceManager'),
):
manager = IngestorManager(
redis_data={'host': 'localhost', 'port': 6379},
lease_ttl=60,
heartbeat_ttl=60,
poll_interval=5,
mongo_connection_string='mongodb://localhost:27017',
mongo_database='sientia',
logger=MagicMock(),
notification_handler=MagicMock(),
metadata=metadata['metadata'],
metrics_controller=MagicMock(),
read_engine=read_engine,
)
manager.send_notification = MagicMock()
manager.emit_metric = AsyncMock()
return manager
def test_read_engine_defaults_to_v2(monkeypatch):
monkeypatch.delenv('READ_ENGINE', raising=False)
assert make_manager().read_engine == 'v2'
def test_read_engine_from_env(monkeypatch):
monkeypatch.setenv('READ_ENGINE', 'Legacy ')
assert make_manager().read_engine == 'legacy'
def test_invalid_read_engine_falls_back_to_v2(monkeypatch):
monkeypatch.setenv('READ_ENGINE', 'v3')
manager = make_manager()
assert manager.read_engine == 'v2'
assert any('Invalid READ_ENGINE' in str(c) for c in manager.logger.warning.call_args_list)
@mark.asyncio
@patch('ingestor.managers.ingestor_manager.ServerReader')
@patch('ingestor.managers.ingestor_manager.OpcManager')
async def test_legacy_initialize_builds_rc3_opc_manager(opc_manager, server_reader):
manager = make_manager('legacy')
server_config = {
'name': 'server1',
'server_id': '1',
'url': 'opc.tcp://localhost:4840',
'subscription_period_ms': 1000,
'server_uri': 'urn:sientia:opc-ingestor',
'cert_path': '/app/certs/opc-ingestor-cert.pem',
'private_key_path': '/app/certs/opc-ingestor-key.pem',
'server_cert_path': None,
}
opc_manager.return_value = MagicMock(connect=AsyncMock())
result = await manager.initialize_opc_from_config(server_config)
server_reader.assert_not_called()
opc_manager.assert_called_once_with(
name='server1',
url='opc.tcp://localhost:4840',
subscription_period_ms=1000,
data_manager=manager.data_manager,
logger=manager.logger,
server_uri='urn:sientia:opc-ingestor',
notification_handler=manager.notification_handler,
metadata=metadata['metadata'],
cert_path='/app/certs/opc-ingestor-cert.pem',
private_key_path='/app/certs/opc-ingestor-key.pem',
server_cert_path=None,
metrics_controller=manager.metrics_controller,
)
assert result is opc_manager.return_value
result.connect.assert_awaited_once()
def test_legacy_keeps_raw_slot_v1():
manager = make_manager('legacy')
raw = raw_slot_v1()
# OpcManager reads tag_name/topics and the file cert paths straight from the slot
assert manager.parse_slot_config('1', raw) is raw
def test_legacy_rejects_slot_v2():
manager = make_manager('legacy')
raw_v2 = {
'server1': {
'name': 'server1',
'server_id': '1',
'url': 'opc.tcp://localhost:4840',
'use_security': True,
'subscription_period_ms': 500,
'tags': {
'ns=2;i=2': {
'frequency': '1000',
'names': [{'collection': 'raw_a', 'tag_name': 'Counter', 'model_id': '1'}],
}
},
}
}
assert manager.parse_slot_config('1', raw_v2) is None
_, kwargs = manager.send_notification.call_args
assert kwargs['notification_id'] == 'OPC_SLOT_CONFIG_ERROR_1'
assert 'READ_ENGINE=legacy' in kwargs['message']
@mark.asyncio
async def test_legacy_remove_server_calls_plain_shutdown():
manager = make_manager('legacy')
opc_manager = MagicMock(shutdown=AsyncMock())
manager.opc_managers = {'server1': opc_manager}
manager.managed_tags = {'slot1': {'server1': {}}}
await manager.remove_server('server1', evict=False)
opc_manager.shutdown.assert_awaited_once_with()
assert manager.opc_managers == {}