mirror of
https://github.com/ChuckBuilds/LEDMatrix.git
synced 2026-10-10 17:16:36 +00:00
refactor(web): one thread-safe TTL cache for the web process
web_interface/cache.py becomes a small TTLCache class (lock-guarded, monotonic clock) with the existing get_cached/set_cached/delete_cached/ invalidate_cache helpers kept on top of a shared instance, so the api_v3 callers are unchanged. Bugs fixed: - set_cached(ttl_seconds=...) ignored its TTL; only the reader's value counted and get_cached defaulted to 60s. An entry now expires after the TTL it was stored with; a reader's ttl_seconds can only shorten that. Both current callers pass the same value on both sides (fonts_catalog 300s, system_status 10s), so their observable TTLs are unchanged. - get_cached deleted expired keys without a lock; two threads reading the same expired key could raise KeyError (reproduced), which the endpoints turned into a 500. app.py's two hand-rolled systemctl caches (_ap_mode_cache, 30s, and _ledmatrix_service_cache, 15s) now share one helper over a private TTLCache, with the same TTLs. The AP-mode check used to retry on every request after a failure (and log an ERROR each time); a failure now keeps the last known answer for the TTL, as the display-service check already did. With no systemctl at all (a dev machine) it answers False without forking. Left alone as not TTL memoisation: the gzip cache (size-bounded, keyed by URL and version), the settings search index (keyed by installed-plugin set), the widget bundle (keyed by file fingerprint) and CacheManager (cross-process). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
+28
-31
@@ -295,34 +295,41 @@ try:
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# Cached AP mode check — avoids creating a WiFiManager per request
|
||||
_ap_mode_cache = {'value': False, 'timestamp': 0}
|
||||
# systemctl answers, memoised so they are not a subprocess fork per request
|
||||
# (AP mode) or per SSE tick (display service). A failed check keeps the last
|
||||
# known answer for the same TTL rather than retrying on every request.
|
||||
from web_interface.cache import TTLCache
|
||||
_service_status_cache = TTLCache()
|
||||
_AP_MODE_CACHE_TTL = 30 # seconds — AP mode is user-initiated; 30s is fine
|
||||
|
||||
# Cached ledmatrix service status for SSE stats stream
|
||||
_ledmatrix_service_cache = {'active': False, 'timestamp': 0}
|
||||
_LEDMATRIX_SERVICE_CACHE_TTL = 15 # seconds
|
||||
|
||||
def _unit_is_active(unit, ttl):
|
||||
"""`systemctl is-active <unit>`, cached for ``ttl`` seconds.
|
||||
|
||||
False where there is no systemctl (a dev machine); on a failed check, the
|
||||
last known answer.
|
||||
"""
|
||||
active = _service_status_cache.get(unit)
|
||||
if active is not None:
|
||||
return active
|
||||
active = _service_status_cache.peek(unit, False)
|
||||
if _SYSTEMCTL:
|
||||
try:
|
||||
result = subprocess.run([_SYSTEMCTL, 'is-active', unit],
|
||||
capture_output=True, text=True, timeout=2)
|
||||
active = result.stdout.strip() == 'active'
|
||||
except (subprocess.SubprocessError, OSError) as e:
|
||||
logging.getLogger('web_interface').warning(
|
||||
"systemctl is-active %s failed: %s", unit, e)
|
||||
_service_status_cache.set(unit, active, ttl=ttl)
|
||||
return active
|
||||
|
||||
def is_ap_mode_active():
|
||||
"""
|
||||
Check if access point mode is currently active (cached, 30s TTL).
|
||||
Uses a direct systemctl check instead of instantiating WiFiManager.
|
||||
"""
|
||||
now = time.time()
|
||||
if (now - _ap_mode_cache['timestamp']) < _AP_MODE_CACHE_TTL:
|
||||
return _ap_mode_cache['value']
|
||||
try:
|
||||
result = subprocess.run(
|
||||
['systemctl', 'is-active', 'hostapd'],
|
||||
capture_output=True, text=True, timeout=2
|
||||
)
|
||||
active = result.stdout.strip() == 'active'
|
||||
_ap_mode_cache['value'] = active
|
||||
_ap_mode_cache['timestamp'] = now
|
||||
return active
|
||||
except (subprocess.SubprocessError, OSError) as e:
|
||||
logging.getLogger('web_interface').error(f"AP mode check failed: {e}")
|
||||
return _ap_mode_cache['value']
|
||||
return _unit_is_active('hostapd', _AP_MODE_CACHE_TTL)
|
||||
|
||||
# Captive portal detection endpoints
|
||||
# When AP mode is active, return responses that TRIGGER the captive portal popup.
|
||||
@@ -672,17 +679,7 @@ def system_status_generator():
|
||||
cpu_temp = metrics['cpu_temp']
|
||||
|
||||
# Check if display service is running (cached to avoid per-client subprocess forks)
|
||||
now = time.time()
|
||||
if (now - _ledmatrix_service_cache['timestamp']) >= _LEDMATRIX_SERVICE_CACHE_TTL:
|
||||
if _SYSTEMCTL:
|
||||
try:
|
||||
result = subprocess.run([_SYSTEMCTL, 'is-active', 'ledmatrix'],
|
||||
capture_output=True, text=True, timeout=2)
|
||||
_ledmatrix_service_cache['active'] = result.stdout.strip() == 'active'
|
||||
except (subprocess.SubprocessError, OSError) as e:
|
||||
app.logger.warning("systemctl status check failed: %s", e)
|
||||
_ledmatrix_service_cache['timestamp'] = now
|
||||
service_active = _ledmatrix_service_cache['active']
|
||||
service_active = _unit_is_active('ledmatrix', _LEDMATRIX_SERVICE_CACHE_TTL)
|
||||
|
||||
status = {
|
||||
'timestamp': time.time(),
|
||||
|
||||
Reference in New Issue
Block a user