Files
sientia-dataops-opc-ingestor/tests/unit/connection/test_pool.py
Eduardo Rios 50578fdba8 SIENTIAPDE-1974: feat(read): slot v2 reads via SubscriptionEngine, OPC cert from MinIO
Swaps the legacy OpcManager read path for the gateway's SubscriptionEngine over
the shared OpcConnectionPool. The OPC client certificate now always comes from
MinIO + Mongo (CertProvider, Basic256Sha256) — no more certs/ shipped in the
Gitea repository, so a new version branch no longer breaks the reads.

- io/slots.py: parse_slot accepts slot v2 (names[]) and converts the legacy
  v1 (tag_name + topics; cert_path => use_security, path dropped), so gateway
  and Orchestrator can be deployed in any order.
- managers/server_reader.py: new per-server reader with the OpcManager
  interface the IngestorManager already drives (connect, create_subscription,
  subscribe, unsubscribe, check_cycles, check_opc_listenning, shutdown).
- IngestorManager owns the read path: lazy-MinIO CertProvider, the pool and a
  read DataSink, built without touching the network. Slots from Redis are
  normalized on lease and refresh; a malformed slot is notified and the last
  good config is kept.
- GatewayRuntime borrows the pool (writes/gRPC) instead of building it, and no
  longer closes it on stop: a Postgres/NATS failure can't stop the reads.
- pool: pin/unpin per active subscription so release_idle never evicts a
  subscribed connection; public evict() for lost servers / changed config.
- SubscriptionEngine pins on subscribe, unpins on unsubscribe, and drops a
  subscription locally even when the server-side delete fails.
- DataSink: model_id only written when the name has one, keeping v1 documents
  identical to the legacy ones.
- config: CERT_BUCKET default is the legacy streamlit-connectors bucket (D7).
- Removes OpcManager, its tests and scripts/generate-and-push-opc-cert.sh;
  README/CLAUDE.md document the MinIO certificate and the slot v2 format.

Tests: 218 unit tests pass; ruff check/format clean. Local end-to-end against
an asyncua server: v1 slot with two topics -> one doc per collection, legacy
doc shape, idle sweep keeps the subscription, lost-server shutdown and
re-initialization work.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 13:27:18 -03:00

251 lines
8.3 KiB
Python

import asyncio
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
import ingestor.metrics as metrics
from ingestor.connection.pool import OpcConnectionPool
def make_pool(cert_provider=None):
pool = OpcConnectionPool(
cert_provider=cert_provider or AsyncMock(),
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
pool.emit_metric = AsyncMock()
return pool
@pytest.mark.asyncio
async def test_get_reuses_connection_per_server():
pool = make_pool()
fake_client = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client):
c1 = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
c2 = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
assert c1 is c2
assert fake_client.connect.await_count == 1
@pytest.mark.asyncio
async def test_get_failure_records_metric_and_raises():
pool = make_pool()
fake_client = AsyncMock()
fake_client.connect.side_effect = RuntimeError('boom')
with patch('ingestor.connection.pool.Client', return_value=fake_client):
with pytest.raises(RuntimeError):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
pool.emit_metric.assert_any_await(
metric_object=metrics.OPC_CONNECTIONS_FAILED,
tags={'pod_id': pool.pod_id, 'server_name': 'srv'},
)
assert 'srv' not in pool._connections
# a later successful get must reconnect (failed attempt was not cached)
fake_client2 = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client2):
client = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
assert client is fake_client2
assert fake_client2.connect.await_count == 1
@pytest.mark.asyncio
async def test_get_applies_security_when_requested():
cert_provider = AsyncMock()
cert_provider.fetch.return_value = ('cert.pem', 'key.pem')
pool = make_pool(cert_provider=cert_provider)
fake_client = AsyncMock()
with (
patch('ingestor.connection.pool.Client', return_value=fake_client),
patch('ingestor.connection.pool.apply_security', new=AsyncMock()) as mock_apply,
):
await pool.get(
'srv',
{'url': 'opc.tcp://h:4840', 'server_uri': 'urn:test', 'use_security': True},
)
cert_provider.fetch.assert_awaited_once()
mock_apply.assert_awaited_once_with(fake_client, 'urn:test', 'cert.pem', 'key.pem', None)
@pytest.mark.asyncio
async def test_release_idle_evicts_and_disconnects():
pool = make_pool()
fake_client = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
client, _ = pool._connections['srv']
pool._connections['srv'] = (client, -1000.0) # force idle
await pool.release_idle(max_idle_s=0)
fake_client.disconnect.assert_awaited_once()
assert 'srv' not in pool._connections
pool.emit_metric.assert_any_await(
metric_object=metrics.OPC_DISCONNECTIONS_TOTAL,
tags={'pod_id': pool.pod_id, 'server_name': 'srv'},
)
@pytest.mark.asyncio
async def test_release_idle_keeps_recently_used():
pool = make_pool()
fake_client = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
await pool.release_idle(max_idle_s=3600)
fake_client.disconnect.assert_not_awaited()
assert 'srv' in pool._connections
@pytest.mark.asyncio
async def test_close_all_disconnects_everything():
pool = make_pool()
fake_a, fake_b = AsyncMock(), AsyncMock()
with patch('ingestor.connection.pool.Client', side_effect=[fake_a, fake_b]):
await pool.get('a', {'url': 'opc.tcp://h:4840', 'use_security': False})
await pool.get('b', {'url': 'opc.tcp://h:4840', 'use_security': False})
await pool.close_all()
fake_a.disconnect.assert_awaited_once()
fake_b.disconnect.assert_awaited_once()
assert pool._connections == {}
@pytest.mark.asyncio
async def test_release_idle_disconnect_retries_then_gives_up():
pool = make_pool()
fake_client = AsyncMock()
fake_client.disconnect.side_effect = RuntimeError('nope')
with patch('ingestor.connection.pool.Client', return_value=fake_client):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
client, _ = pool._connections['srv']
pool._connections['srv'] = (client, -1000.0)
await pool.release_idle(max_idle_s=0)
assert fake_client.disconnect.await_count == 5
assert 'srv' not in pool._connections
@pytest.mark.asyncio
async def test_success_path_emits_connection_metrics():
pool = make_pool()
fake_client = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
pool.emit_metric.assert_any_await(
metric_object=metrics.OPC_CONNECTIONS_TOTAL,
tags={'pod_id': pool.pod_id, 'server_name': 'srv'},
)
pool.emit_metric.assert_any_await(
metric_object=metrics.OPC_CONNECTION_STATUS,
method='set',
value=1,
tags={'pod_id': pool.pod_id, 'server_name': 'srv', 'server_url': 'opc.tcp://h:4840'},
)
@pytest.mark.asyncio
async def test_concurrent_get_same_server_connects_once():
pool = make_pool()
started = asyncio.Event()
proceed = asyncio.Event()
clients = [AsyncMock(), AsyncMock()]
async def slow_connect():
started.set()
await proceed.wait()
clients[0].connect.side_effect = slow_connect
cfg = {'url': 'opc.tcp://h:4840', 'use_security': False}
with patch('ingestor.connection.pool.Client', side_effect=clients) as ctor:
t1 = asyncio.create_task(pool.get('srv', cfg))
await started.wait() # t1 is mid-connect, holding the per-server lock
t2 = asyncio.create_task(pool.get('srv', cfg))
await asyncio.sleep(0) # let t2 block on the lock (not build a 2nd Client)
proceed.set()
c1, c2 = await asyncio.gather(t1, t2)
assert c1 is c2 is clients[0]
assert ctor.call_count == 1
assert clients[0].connect.await_count == 1
@pytest.mark.asyncio
async def test_release_idle_keeps_pinned_connection():
"""A subscribed connection only gets callbacks (never get()), so it looks idle:
the pin keeps release_idle from dropping it (SIENTIAPDE-1974 G4)."""
pool = make_pool()
fake_client = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
pool.pin('srv')
await pool.release_idle(max_idle_s=0)
assert 'srv' in pool._connections
fake_client.disconnect.assert_not_awaited()
@pytest.mark.asyncio
async def test_release_idle_evicts_after_last_unpin():
pool = make_pool()
fake_client = AsyncMock()
with patch('ingestor.connection.pool.Client', return_value=fake_client):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
pool.pin('srv')
pool.pin('srv') # two slots subscribed on the same server
pool.unpin('srv')
await pool.release_idle(max_idle_s=0)
assert 'srv' in pool._connections # one subscription still active
pool.unpin('srv')
await pool.release_idle(max_idle_s=0)
assert 'srv' not in pool._connections
fake_client.disconnect.assert_awaited_once()
def test_unpin_never_goes_negative():
pool = make_pool()
pool.unpin('srv')
pool.pin('srv')
assert pool._pins == {'srv': 1}
@pytest.mark.asyncio
async def test_evict_disconnects_now_and_next_get_reconnects():
pool = make_pool()
first, second = AsyncMock(), AsyncMock()
with patch('ingestor.connection.pool.Client', side_effect=[first, second]):
await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
await pool.evict('srv')
client = await pool.get('srv', {'url': 'opc.tcp://h:4840', 'use_security': False})
first.disconnect.assert_awaited_once()
assert client is second
@pytest.mark.asyncio
async def test_evict_unknown_server_is_noop():
pool = make_pool()
await pool.evict('nope')
pool.emit_metric.assert_not_awaited()