common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix(gateway): write restart markers atomically and fix Windows lock collisions

Browse Source
This commit is contained in:
johnncenae
2026-04-30 11:44:27 +03:00
committed by Teknium
parent 447a2bba3a
commit 1ef9e88549
5 changed files with 162 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
gateway/run.py
View File

@@ -239,7 +239,7 @@ sys.path.insert(0, str(Path(__file__).parent.parent))
# Resolve Hermes home directory (respects HERMES_HOME override)
from hermes_constants import get_hermes_home
from utils import atomic_yaml_write, base_url_host_matches, is_truthy_value
from utils import atomic_json_write, atomic_yaml_write, base_url_host_matches, is_truthy_value
_hermes_home = get_hermes_home()
# Load environment variables from ~/.hermes/.env first.
@@ -2245,7 +2245,7 @@ class GatewayRunner:
# (they might become active again next restart)
try:
path.write_text(json.dumps(new_counts))
atomic_json_write(path, new_counts, indent=None)
except Exception:
pass
@@ -2313,7 +2313,7 @@ class GatewayRunner:
if session_key in counts:
del counts[session_key]
if counts:
path.write_text(json.dumps(counts))
atomic_json_write(path, counts, indent=None)
else:
path.unlink(missing_ok=True)
except Exception:
@@ -6734,8 +6734,10 @@ class GatewayRunner:
}
if event.source.thread_id:
notify_data["thread_id"] = event.source.thread_id
(_hermes_home / ".restart_notify.json").write_text(
json.dumps(notify_data)
atomic_json_write(
_hermes_home / ".restart_notify.json",
notify_data,
indent=None,
)
except Exception as e:
logger.debug("Failed to write restart notify file: %s", e)
@@ -6752,8 +6754,10 @@ class GatewayRunner:
}
if event.platform_update_id is not None:
dedup_data["update_id"] = event.platform_update_id
(_hermes_home / ".restart_last_processed.json").write_text(
json.dumps(dedup_data)
atomic_json_write(
_hermes_home / ".restart_last_processed.json",
dedup_data,
indent=None,
)
except Exception as e:
logger.debug("Failed to write restart dedup marker: %s", e)

12
gateway/status.py
View File

@@ -21,6 +21,7 @@ from datetime import datetime, timezone
from pathlib import Path
from hermes_constants import get_hermes_home
from typing import Any, Optional
from utils import atomic_json_write
if sys.platform == "win32":
import msvcrt
@@ -34,6 +35,10 @@ _IS_WINDOWS = sys.platform == "win32"
_UNSET = object()
_GATEWAY_LOCK_FILENAME = "gateway.lock"
_gateway_lock_handle = None
# Windows byte-range locks are mandatory for other readers. Lock a byte well
# past the JSON payload so runtime status / PID readers can still read the file
# while another process holds the mutual-exclusion lock.
_WINDOWS_LOCK_OFFSET = 1024 * 1024
def _get_pid_path() -> Path:
@@ -205,8 +210,7 @@ def _read_json_file(path: Path) -> Optional[dict[str, Any]]:
def _write_json_file(path: Path, payload: dict[str, Any]) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(json.dumps(payload))
atomic_json_write(path, payload, indent=None, separators=(",", ":"))
def _read_pid_record(pid_path: Optional[Path] = None) -> Optional[dict]:
@@ -286,7 +290,7 @@ def _try_acquire_file_lock(handle) -> bool:
if handle.tell() == 0:
handle.write("\n")
handle.flush()
handle.seek(0)
handle.seek(_WINDOWS_LOCK_OFFSET)
msvcrt.locking(handle.fileno(), msvcrt.LK_NBLCK, 1)
else:
fcntl.flock(handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB)
@@ -298,7 +302,7 @@ def _try_acquire_file_lock(handle) -> bool:
def _release_file_lock(handle) -> None:
try:
if _IS_WINDOWS:
handle.seek(0)
handle.seek(_WINDOWS_LOCK_OFFSET)
msvcrt.locking(handle.fileno(), msvcrt.LK_UNLCK, 1)
else:
fcntl.flock(handle.fileno(), fcntl.LOCK_UN)