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

@@ -1,7 +1,10 @@
from __future__ import annotations
import json
from app.core.config import settings
from app.core.files import read_runtime_json, write_runtime_json
from app.core.redis_client import get_redis
DEFAULT_RUNTIME_SETTINGS = {
@@ -11,13 +14,50 @@ DEFAULT_RUNTIME_SETTINGS = {
"sync_agent_service_name": settings.sync_agent_service_name,
"worker_log_sync_enabled": False,
"worker_log_sync_mode": "key",
"control_node_autoresume_enabled": False,
"claim_recent_jobs_first": False,
"claim_recent_jobs_limit": 0,
"claim_recent_jobs_window_hours": 0,
"claim_batch_floor": 0,
"claim_batch_ceil": 0,
"submit_backlog_floor": 0,
"submit_backlog_ceil": 0,
"dispatch_cap_multiplier": 1,
"pending_buffer_cap_multiplier": 1,
}
RUNTIME_SETTINGS_REDIS_KEY = "domain_tool:runtime_settings"
CONFIG_UPDATE_CHANNEL = "domain_tool:config_update"
def _normalize_worker_log_sync_mode(value: object) -> str:
return "full" if str(value or "").strip().lower() == "full" else "key"
def _normalize_bool(value: object, default: bool = False) -> bool:
if value is None:
return bool(default)
if isinstance(value, bool):
return value
return str(value or "").strip().lower() not in {"", "0", "false", "no", "off"}
def _normalize_non_negative_int(value: object, default: int = 0) -> int:
try:
normalized = int(value)
except (TypeError, ValueError):
normalized = int(default)
return max(0, normalized)
def _normalize_positive_int(value: object, default: int = 1) -> int:
try:
normalized = int(value)
except (TypeError, ValueError):
normalized = int(default)
return max(1, normalized)
def normalize_runtime_settings(payload: dict | None) -> dict:
merged = dict(DEFAULT_RUNTIME_SETTINGS)
if isinstance(payload, dict):
@@ -33,8 +73,28 @@ def normalize_runtime_settings(payload: dict | None) -> dict:
value = str(merged.get(key) or "").strip()
merged[key] = value or DEFAULT_RUNTIME_SETTINGS[key]
merged["worker_log_sync_enabled"] = bool(merged.get("worker_log_sync_enabled", False))
merged["worker_log_sync_enabled"] = _normalize_bool(merged.get("worker_log_sync_enabled", False), default=False)
merged["worker_log_sync_mode"] = _normalize_worker_log_sync_mode(merged.get("worker_log_sync_mode"))
merged["control_node_autoresume_enabled"] = _normalize_bool(
merged.get("control_node_autoresume_enabled", False),
default=False,
)
merged["claim_recent_jobs_first"] = _normalize_bool(
merged.get("claim_recent_jobs_first", False),
default=False,
)
for key in ("claim_batch_floor", "claim_batch_ceil", "submit_backlog_floor", "submit_backlog_ceil"):
merged[key] = _normalize_non_negative_int(merged.get(key), DEFAULT_RUNTIME_SETTINGS[key])
for key in (
"claim_recent_jobs_limit",
"claim_recent_jobs_window_hours",
"dispatch_cap_multiplier",
"pending_buffer_cap_multiplier",
):
if key in {"claim_recent_jobs_limit", "claim_recent_jobs_window_hours"}:
merged[key] = _normalize_non_negative_int(merged.get(key), DEFAULT_RUNTIME_SETTINGS[key])
continue
merged[key] = _normalize_positive_int(merged.get(key), DEFAULT_RUNTIME_SETTINGS[key])
return merged
@@ -43,7 +103,17 @@ def get_runtime_settings() -> dict:
return normalize_runtime_settings(stored)
def _sync_runtime_settings_update(runtime_settings: dict) -> None:
try:
redis_client = get_redis()
redis_client.set(RUNTIME_SETTINGS_REDIS_KEY, json.dumps(runtime_settings, ensure_ascii=False))
redis_client.publish(CONFIG_UPDATE_CHANNEL, "runtime_settings")
except Exception:
pass
def update_runtime_settings(payload: dict) -> dict:
merged = normalize_runtime_settings({**get_runtime_settings(), **(payload or {})})
write_runtime_json("runtime_settings.json", merged)
_sync_runtime_settings_update(merged)
return merged