feat: stabilize multi-region runtime sync and worker orchestration

This commit is contained in:
root
2026-04-27 15:48:12 +08:00
parent 7cbde2aa78
commit 215a364891
137 changed files with 31931 additions and 1943 deletions

View File

@@ -1,12 +1,61 @@
import json
import unittest
from datetime import datetime, timedelta
from unittest.mock import patch
from app.services.sync_record_service import (
_build_runtime_projection_payload,
_collect_recent_domain_events,
_pick_latest_projection_row,
append_runtime_projection_if_changed,
get_detect_result_sync_batches,
)
class _FakeCursor:
def __init__(self, fetchone_values):
self.fetchone_values = list(fetchone_values or [])
self.executed = []
def execute(self, sql, params=None):
self.executed.append((sql, params))
def fetchone(self):
if self.fetchone_values:
return self.fetchone_values.pop(0)
return None
def fetchall(self):
if self.fetchone_values:
value = self.fetchone_values.pop(0)
return list(value or [])
return []
def __enter__(self):
return self
def __exit__(self, exc_type, exc, tb):
return False
class _FakeConnection:
def __init__(self, fetchone_values):
self.cursor_obj = _FakeCursor(fetchone_values)
self.committed = False
def cursor(self):
return self.cursor_obj
def commit(self):
self.committed = True
def __enter__(self):
return self
def __exit__(self, exc_type, exc, tb):
return False
class SyncRecordServiceTests(unittest.TestCase):
def test_collect_recent_domain_events_filters_and_keeps_latest_slice(self) -> None:
active_job = {
@@ -130,6 +179,682 @@ class SyncRecordServiceTests(unittest.TestCase):
self.assertEqual("", projection["active_job"]["job_code"])
self.assertEqual([], projection["active_job"]["node_stats"])
@patch("app.services.sync_record_service._resolve_local_ip", return_value="121.204.244.188")
@patch("app.services.sync_record_service.socket.gethostname", return_value="mainland-controller-01")
@patch("app.services.sync_record_service.settings")
def test_build_runtime_projection_payload_prefers_runtime_queue_nodes_for_multi_process_controller(
self,
mock_settings,
_mock_hostname,
_mock_resolve_ip,
) -> None:
mock_settings.node_code = "mainland-controller-01"
mock_settings.node_region = "mainland"
mock_settings.node_role = "control"
mock_settings.sync_source_region = "mainland"
mock_settings.sync_target_region = "overseas"
payload = _build_runtime_projection_payload(
detect={
"worker_online": True,
"worker_mode": "linux-systemd",
"active_thread_count": 1,
"max_thread_count": 1000,
"aggregate_max_thread_count": 80000,
"phase_label": "运行中",
"phase_detail": "80 实例运行",
"proxy_runtime_label": "正常",
"proxy_runtime_reason": "healthy",
"progress": {
"pending": 5001,
"running": 0,
"completed": 0,
"blacklisted": 0,
"failed": 0,
},
"backlog": {"pending_total": 1157325},
"queue_health": {
"queue": {
"items_total": 5292,
"pending": 4578,
"claimed": 0,
"display_claimed": 120,
"running": 1972,
"display_running": 1972,
"completed": 690,
"blacklisted": 0,
"failed": 24,
"terminal": 714,
},
"nodes": [
{
"node_code": "mainland-controller-01-a",
"items_running": 1000,
"items_claimed": 0,
"display_running": 1000,
"active_threads": 1000,
"max_threads": 1000,
"region": "mainland",
"role": "control",
"status": "busy",
},
{
"node_code": "mainland-controller-01-b",
"items_running": 972,
"items_claimed": 120,
"display_running": 972,
"active_threads": 972,
"max_threads": 1000,
"region": "mainland",
"role": "control",
"status": "busy",
},
],
},
"active_job": {
"job_id": 55,
"job_code": "sync-overseas-55",
"status": "running",
"progress_percent": 13.49,
"items_total": 5292,
"items_terminal": 714,
"items_pending": 4578,
"items_running": 0,
"items_failed": 24,
"node_stats": [
{
"node_code": "mainland-controller-01",
"items_running": 1,
"items_claimed": 0,
"items_total": 5292,
}
],
},
"dependency_alerts": [],
},
cluster={
"nodes_total": 80,
"nodes": [
{
"node_code": "mainland-controller-01",
"current_load": 1,
"detect_participating": True,
}
],
"summary": {
"online_worker_nodes": 65,
"dedicated_online_worker_nodes": 1,
"online_control_nodes": 65,
"busy_nodes": ["mainland-controller-01-a", "mainland-controller-01-b"],
"stale_nodes": [],
"offline_nodes": [],
},
},
source_region="mainland",
target_region="overseas",
)
projection = payload["projection"]
self.assertTrue(projection["detect_participating"])
self.assertEqual(1972, projection["active_thread_count"])
self.assertEqual(80000, projection["max_thread_count"])
self.assertEqual(1972, projection["progress"]["running"])
self.assertEqual(2, len(projection["active_job"]["node_stats"]))
self.assertEqual(2, len(projection["active_job"]["distributed_node_stats"]))
self.assertEqual(1, len(projection["cluster_nodes"]))
self.assertEqual("mainland-controller-01", projection["cluster_nodes"][0]["node_code"])
self.assertEqual(1972, projection["active_job"]["items_running"])
self.assertEqual(1972, projection["active_job"]["display_items_running"])
self.assertEqual(80000, projection["active_job"]["display_max_threads"])
@patch("app.services.sync_record_service._resolve_local_ip", return_value="121.204.244.188")
@patch("app.services.sync_record_service.socket.gethostname", return_value="mainland-controller-01")
@patch("app.services.sync_record_service.settings")
@patch("app.services.sync_record_service.get_db")
def test_append_runtime_projection_if_changed_writes_heartbeat_for_unchanged_projection_after_interval(
self,
mock_get_db,
mock_settings,
_mock_hostname,
_mock_resolve_ip,
) -> None:
mock_settings.node_code = "mainland-controller-01"
mock_settings.node_region = "mainland"
mock_settings.node_role = "control"
mock_settings.sync_source_region = "mainland"
mock_settings.sync_target_region = "overseas"
detect = {
"worker_online": True,
"worker_mode": "linux-systemd",
"active_thread_count": 3200,
"max_thread_count": 80000,
"phase_label": "运行中",
"phase_detail": "80 实例运行",
"proxy_runtime_label": "正常",
"proxy_runtime_reason": "healthy",
"progress": {
"pending": 1200000,
"running": 6400,
"completed": 50000,
"blacklisted": 1200,
"failed": 88,
},
"backlog": {"pending_total": 1200000},
"active_job": {
"job_id": 55,
"job_code": "sync-overseas-55",
"status": "running",
"progress_percent": 12.5,
"items_total": 1300000,
"items_terminal": 51288,
"items_pending": 1200000,
"items_running": 6400,
"items_failed": 88,
"node_stats": [
{
"node_code": "mainland-controller-01",
"items_running": 6400,
"items_claimed": 7000,
"items_total": 1300000,
}
],
},
"dependency_alerts": [],
}
cluster = {
"nodes_total": 1,
"nodes": [
{
"node_code": "mainland-controller-01",
"current_load": 6400,
"detect_participating": True,
}
],
"summary": {
"online_worker_nodes": 1,
"dedicated_online_worker_nodes": 0,
"online_control_nodes": 1,
"busy_nodes": ["mainland-controller-01"],
"stale_nodes": [],
"offline_nodes": [],
},
}
previous_payload = _build_runtime_projection_payload(
detect=detect,
cluster=cluster,
source_region="mainland",
target_region="overseas",
)
fake_conn = _FakeConnection(
[
[(previous_payload, datetime.now() - timedelta(seconds=90))],
(321,),
]
)
mock_get_db.return_value = fake_conn
record_id = append_runtime_projection_if_changed(
detect=detect,
cluster=cluster,
source_region="mainland",
target_region="overseas",
)
self.assertEqual(321, record_id)
self.assertTrue(fake_conn.committed)
self.assertTrue(
any("INSERT INTO detect_sync_records" in sql for sql, _params in fake_conn.cursor_obj.executed)
)
@patch("app.services.sync_record_service._resolve_local_ip", return_value="121.204.244.188")
@patch("app.services.sync_record_service.socket.gethostname", return_value="mainland-controller-01")
@patch("app.services.sync_record_service.settings")
@patch("app.services.sync_record_service.get_db")
def test_append_runtime_projection_if_changed_writes_when_cluster_nodes_change_within_window(
self,
mock_get_db,
mock_settings,
_mock_hostname,
_mock_resolve_ip,
) -> None:
mock_settings.node_code = "mainland-controller-01"
mock_settings.node_region = "mainland"
mock_settings.node_role = "control"
mock_settings.sync_source_region = "mainland"
mock_settings.sync_target_region = "overseas"
previous_payload = {
"projection": {
"worker_online": True,
"worker_mode": "linux-systemd",
"phase_label": "运行中",
"phase_detail": "等待中",
"proxy_runtime_label": "正常",
"proxy_runtime_reason": "healthy",
"active_thread_count": 0,
"max_thread_count": 60000,
"progress": {"pending": 10000, "running": 0, "completed": 0, "blacklisted": 0, "failed": 0},
"active_job": {
"job_id": None,
"job_code": "",
"status": "",
"items_total": 0,
"items_running": 0,
"items_claimed": 0,
"display_items_running": 0,
"display_items_claimed": 0,
"display_max_threads": 0,
"node_stats": [],
"distributed_node_stats": [],
},
"cluster_summary": {
"nodes_total": 43,
"online_worker_nodes": 43,
"dedicated_online_worker_nodes": 42,
"online_control_nodes": 1,
"busy_nodes": [],
"stale_nodes": [],
"offline_nodes": [],
},
"cluster_nodes": [
{
"node_code": "mainland-controller-01",
"role": "control",
"status": "online",
"current_load": 0,
"active_threads": 0,
"max_threads": 60000,
"detect_participating": False,
}
],
"dependency_alerts": [],
}
}
fake_conn = _FakeConnection(
[
[(previous_payload, datetime.now() - timedelta(seconds=10))],
(911,),
]
)
mock_get_db.return_value = fake_conn
record_id = append_runtime_projection_if_changed(
detect={
"worker_online": True,
"worker_mode": "linux-systemd",
"phase_label": "运行中",
"phase_detail": "等待中",
"proxy_runtime_label": "正常",
"proxy_runtime_reason": "healthy",
"progress": {"pending": 10000, "running": 0, "completed": 0, "blacklisted": 0, "failed": 0},
"backlog": {},
"active_job": {},
"dependency_alerts": [],
},
cluster={
"nodes_total": 61,
"nodes": [
{
"node_code": "mainland-controller-01",
"role": "control",
"status": "online",
"current_load": 0,
"metadata": {"active_threads": 0, "max_threads": 60000},
},
{
"node_code": "mainland-controller-01-a",
"role": "worker",
"status": "online",
"current_load": 0,
"metadata": {"active_threads": 0, "max_threads": 1000},
},
],
"summary": {
"online_worker_nodes": 61,
"dedicated_online_worker_nodes": 60,
"online_control_nodes": 1,
"busy_nodes": [],
"stale_nodes": [],
"offline_nodes": [],
},
},
source_region="mainland",
target_region="overseas",
)
self.assertEqual(911, record_id)
self.assertTrue(fake_conn.committed)
self.assertTrue(
any("INSERT INTO detect_sync_records" in sql for sql, _params in fake_conn.cursor_obj.executed)
)
@patch("app.services.sync_record_service._resolve_local_ip", return_value="121.204.244.188")
@patch("app.services.sync_record_service.socket.gethostname", return_value="mainland-controller-01")
@patch("app.services.sync_record_service.settings")
@patch("app.services.sync_record_service.get_db")
def test_append_runtime_projection_if_changed_skips_unchanged_projection_within_heartbeat_window(
self,
mock_get_db,
mock_settings,
_mock_hostname,
_mock_resolve_ip,
) -> None:
mock_settings.node_code = "mainland-controller-01"
mock_settings.node_region = "mainland"
mock_settings.node_role = "control"
mock_settings.sync_source_region = "mainland"
mock_settings.sync_target_region = "overseas"
detect = {
"worker_online": True,
"worker_mode": "linux-systemd",
"active_thread_count": 3200,
"max_thread_count": 80000,
"phase_label": "运行中",
"phase_detail": "80 实例运行",
"proxy_runtime_label": "正常",
"proxy_runtime_reason": "healthy",
"progress": {
"pending": 1200000,
"running": 6400,
"completed": 50000,
"blacklisted": 1200,
"failed": 88,
},
"backlog": {"pending_total": 1200000},
"active_job": {
"job_id": 55,
"job_code": "sync-overseas-55",
"status": "running",
"progress_percent": 12.5,
"items_total": 1300000,
"items_terminal": 51288,
"items_pending": 1200000,
"items_running": 6400,
"items_failed": 88,
"node_stats": [
{
"node_code": "mainland-controller-01",
"items_running": 6400,
"items_claimed": 7000,
"items_total": 1300000,
}
],
},
"dependency_alerts": [],
}
cluster = {
"nodes_total": 1,
"nodes": [
{
"node_code": "mainland-controller-01",
"current_load": 6400,
"detect_participating": True,
}
],
"summary": {
"online_worker_nodes": 1,
"dedicated_online_worker_nodes": 0,
"online_control_nodes": 1,
"busy_nodes": ["mainland-controller-01"],
"stale_nodes": [],
"offline_nodes": [],
},
}
previous_payload = _build_runtime_projection_payload(
detect=detect,
cluster=cluster,
source_region="mainland",
target_region="overseas",
)
fake_conn = _FakeConnection(
[
[(previous_payload, datetime.now() - timedelta(seconds=10))],
]
)
mock_get_db.return_value = fake_conn
record_id = append_runtime_projection_if_changed(
detect=detect,
cluster=cluster,
source_region="mainland",
target_region="overseas",
)
self.assertIsNone(record_id)
self.assertFalse(fake_conn.committed)
self.assertFalse(
any("INSERT INTO detect_sync_records" in sql for sql, _params in fake_conn.cursor_obj.executed)
)
@patch("app.services.sync_record_service._resolve_local_ip", return_value="121.204.244.188")
@patch("app.services.sync_record_service.socket.gethostname", return_value="mainland-controller-01")
@patch("app.services.sync_record_service.settings")
@patch("app.services.sync_record_service.get_db")
def test_append_runtime_projection_if_changed_writes_when_activity_signature_changes_within_window(
self,
mock_get_db,
mock_settings,
_mock_hostname,
_mock_resolve_ip,
) -> None:
mock_settings.node_code = "mainland-controller-01"
mock_settings.node_region = "mainland"
mock_settings.node_role = "control"
mock_settings.sync_source_region = "mainland"
mock_settings.sync_target_region = "overseas"
previous_detect = {
"worker_online": True,
"worker_mode": "linux-systemd",
"active_thread_count": 300,
"max_thread_count": 60000,
"phase_label": "运行中",
"phase_detail": "60 实例运行",
"proxy_runtime_label": "正常",
"proxy_runtime_reason": "healthy",
"progress": {
"pending": 5000,
"running": 600,
"completed": 1000,
"blacklisted": 0,
"failed": 10,
},
"queue_health": {
"queue": {
"items_total": 6610,
"pending": 5000,
"claimed": 10,
"display_claimed": 10,
"running": 600,
"display_running": 600,
"completed": 1000,
"blacklisted": 0,
"failed": 10,
"terminal": 1010,
"display_max_threads": 60000,
},
"nodes": [
{
"node_code": "mainland-controller-01-a",
"items_running": 300,
"items_claimed": 10,
"display_running": 300,
"active_threads": 300,
"max_threads": 1000,
"region": "mainland",
"role": "control",
"status": "busy",
}
],
},
"active_job": {
"job_id": 867,
"job_code": "sync-overseas-19835",
"status": "running",
"progress_percent": 15.0,
"items_total": 6610,
"items_terminal": 1010,
"items_pending": 5000,
"items_claimed": 10,
"items_running": 600,
"items_failed": 10,
"node_stats": [
{
"node_code": "mainland-controller-01-a",
"items_running": 300,
"items_claimed": 10,
"items_total": 6610,
}
],
},
"dependency_alerts": [],
}
current_detect = {
**previous_detect,
"active_thread_count": 900,
"queue_health": {
"queue": {
"items_total": 6610,
"pending": 4300,
"claimed": 30,
"display_claimed": 30,
"running": 900,
"display_running": 900,
"completed": 1370,
"blacklisted": 0,
"failed": 10,
"terminal": 1380,
"display_max_threads": 60000,
},
"nodes": [
{
"node_code": "mainland-controller-01-a",
"items_running": 420,
"items_claimed": 20,
"display_running": 420,
"active_threads": 420,
"max_threads": 1000,
"region": "mainland",
"role": "control",
"status": "busy",
},
{
"node_code": "mainland-controller-01-b",
"items_running": 480,
"items_claimed": 10,
"display_running": 480,
"active_threads": 480,
"max_threads": 1000,
"region": "mainland",
"role": "control",
"status": "busy",
},
],
},
"active_job": {
**previous_detect["active_job"],
"items_pending": 4300,
"items_claimed": 30,
"items_running": 900,
"node_stats": [
{
"node_code": "mainland-controller-01-a",
"items_running": 420,
"items_claimed": 20,
"items_total": 6610,
},
{
"node_code": "mainland-controller-01-b",
"items_running": 480,
"items_claimed": 10,
"items_total": 6610,
},
],
},
}
cluster = {
"nodes_total": 2,
"nodes": [
{
"node_code": "mainland-controller-01",
"current_load": 900,
"detect_participating": True,
}
],
"summary": {
"online_worker_nodes": 60,
"dedicated_online_worker_nodes": 0,
"online_control_nodes": 60,
"busy_nodes": ["mainland-controller-01-a", "mainland-controller-01-b"],
"stale_nodes": [],
"offline_nodes": [],
},
}
previous_payload = _build_runtime_projection_payload(
detect=previous_detect,
cluster=cluster,
source_region="mainland",
target_region="overseas",
)
fake_conn = _FakeConnection(
[
[(previous_payload, datetime.now() - timedelta(seconds=10))],
(654,),
]
)
mock_get_db.return_value = fake_conn
record_id = append_runtime_projection_if_changed(
detect=current_detect,
cluster=cluster,
source_region="mainland",
target_region="overseas",
)
self.assertEqual(654, record_id)
self.assertTrue(fake_conn.committed)
self.assertTrue(
any("INSERT INTO detect_sync_records" in sql for sql, _params in fake_conn.cursor_obj.executed)
)
def test_pick_latest_projection_row_skips_future_dated_rows(self) -> None:
rows = [
("future", datetime.now() + timedelta(hours=6)),
("recent", datetime.now() - timedelta(seconds=10)),
("older", datetime.now() - timedelta(minutes=2)),
]
selected = _pick_latest_projection_row(rows, created_at_index=1)
self.assertEqual("recent", selected[0])
@patch("app.services.sync_record_service.get_db")
@patch("app.services.sync_record_service.settings")
def test_get_detect_result_sync_batches_marks_overseas_control_as_not_applicable(
self,
mock_settings,
mock_get_db,
) -> None:
mock_settings.node_code = "overseas-control-01"
mock_settings.node_region = "overseas"
mock_settings.node_role = "control"
mock_settings.sync_source_region = "overseas"
mock_settings.sync_target_region = "mainland"
payload = get_detect_result_sync_batches(limit=5)
self.assertFalse(payload["applicable"])
self.assertFalse(payload["local_worker_expected"])
self.assertEqual(0, payload["jobs_total"])
self.assertEqual([], payload["batches"])
self.assertIn("不适用", payload["reason"])
mock_get_db.assert_not_called()
if __name__ == "__main__":
unittest.main()