feat: periodically checkpoint server/sud logs to disk
Both loggers previously only wrote their JSON log on their end trigger (shutdown / Stop-or-DONE), losing the whole session/run's data on a hard crash or power loss. Add a log_interval (config.json, default 300s) that rewrites the same file whole every N seconds in between. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TvgC7oy9MxaA4ZQxXqkNdS
This commit is contained in:
@@ -689,20 +689,22 @@ Both loggers record the same six signals the GUI's Automatic tab plots live
|
||||
(`temp_ist`/`temp_soll`, `rate_ist`/`rate_soll`, `power_set`/`power_eff`),
|
||||
each sample with both simulated-elapsed-seconds and a real wall-clock
|
||||
timestamp, plus any plant-param changes along the way (see
|
||||
`apply_plant_params()`) - written as JSON via `write()`, whole and only
|
||||
once, never partially mid-run.
|
||||
`apply_plant_params()`) - written as JSON via `write()`, always the whole
|
||||
accumulated sample list rewritten to the same file, never appended.
|
||||
|
||||
`tasks/server_log.py`'s `ServerLogTask` records continuously for the whole
|
||||
server session, regardless of Sud state - useful for verifying controller
|
||||
and heater behaviour outside of a scheduled brew. It starts on construction
|
||||
and is written to `logs/log_<date>T<time>.json` on shutdown.
|
||||
and is written to `logs/log_<date>T<time>.json` on shutdown, and again
|
||||
every `log_interval` seconds (`config.json`, default 300) in between so a
|
||||
hard crash or power loss only loses up to that much data.
|
||||
|
||||
`tasks/sud_log.py`'s `SudLogTask` subclasses `ServerLogTask` to reuse the
|
||||
same sample format, but only records while a Sud run is actually active. A
|
||||
fresh run starts recording on a genuine `Start` from `IDLE`/`DONE` (a
|
||||
`Pause`→resume `Start` is a no-op - it's still the same run) and is written
|
||||
out on `Stop` or natural completion (`DONE`), to
|
||||
`logs/log_<date>T<time>_<sud-name>.log`.
|
||||
same sample format and `log_interval` checkpointing, but only records while
|
||||
a Sud run is actually active. A fresh run starts recording on a genuine
|
||||
`Start` from `IDLE`/`DONE` (a `Pause`→resume `Start` is a no-op - it's still
|
||||
the same run) and is written out on `Stop` or natural completion (`DONE`),
|
||||
to `logs/log_<date>T<time>_<sud-name>.log`.
|
||||
|
||||
`server/brewpi.py` also mirrors everything it prints (every component's
|
||||
`print()`-based status/debug output) to a plain text log,
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
{
|
||||
"ambient_temperature": 20,
|
||||
"log_interval": 300,
|
||||
"TempCtrl": {
|
||||
"pid_type": "Smith",
|
||||
"beta": 0.05,
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
{
|
||||
"ambient_temperature": 20,
|
||||
"log_interval": 300,
|
||||
"TempCtrl": {
|
||||
"pid_type": "Smith",
|
||||
"beta": 0.05,
|
||||
|
||||
+13
-4
@@ -131,16 +131,25 @@ if __name__ == '__main__':
|
||||
sud_task = SudTask(sud, tc, stirrer, pot, DT, DT_TASK, dispatcher.msgio_get("Sud"), forecast_estimator)
|
||||
taskmgr.add(sud_task)
|
||||
|
||||
# How often the server/sud logs checkpoint themselves to disk (in
|
||||
# addition to always writing on their own end trigger) - so a hard
|
||||
# crash/power loss only loses up to this much data. Config-only (no CLI
|
||||
# flag): it's a plant/deployment concern like the rest of config.json,
|
||||
# not a per-invocation run-mode knob.
|
||||
log_interval = config.get('log_interval', 300)
|
||||
|
||||
# Continuous server-session log - records from startup to shutdown
|
||||
# regardless of Sud state; written to logs/log_{date_time}.json on exit.
|
||||
server_log_task = ServerLogTask(tc, heater, heater_task, DT_TASK, args.logdir, config=config, dt=DT)
|
||||
# regardless of Sud state; written to logs/log_{date_time}.json on exit
|
||||
# and every log_interval seconds in between.
|
||||
server_log_task = ServerLogTask(tc, heater, heater_task, DT_TASK, args.logdir, config=config, dt=DT, log_interval=log_interval)
|
||||
if startup_params is not None:
|
||||
server_log_task.log_plant_params(0, startup_params)
|
||||
taskmgr.add(server_log_task)
|
||||
|
||||
# Per-run log - only records while a Sud is actually playing; written to
|
||||
# logs/log_{date_time}_{sud_name}.log on Stop (or natural completion).
|
||||
sud_log_task = SudLogTask(tc, heater, heater_task, sud, DT_TASK, args.logdir, config=config, dt=DT)
|
||||
# logs/log_{date_time}_{sud_name}.log on Stop (or natural completion) and
|
||||
# every log_interval seconds in between.
|
||||
sud_log_task = SudLogTask(tc, heater, heater_task, sud, DT_TASK, args.logdir, config=config, dt=DT, log_interval=log_interval)
|
||||
taskmgr.add(sud_log_task)
|
||||
|
||||
sud_task.set_on_plant_params(lambda elapsed, params: (
|
||||
|
||||
+10
-1
@@ -16,7 +16,7 @@ class ServerLogTask(ATask):
|
||||
Sud state — useful for verifying controller and heater behaviour
|
||||
outside of a scheduled brew."""
|
||||
|
||||
def __init__(self, tc: APid, heater: AHeater, heater_task, interval, path='./logs', config=None, dt=None):
|
||||
def __init__(self, tc: APid, heater: AHeater, heater_task, interval, path='./logs', config=None, dt=None, log_interval=None):
|
||||
ATask.__init__(self, interval)
|
||||
self.tc = tc
|
||||
self.heater = heater
|
||||
@@ -24,10 +24,12 @@ class ServerLogTask(ATask):
|
||||
self.path = path
|
||||
self.config = config
|
||||
self.dt = dt
|
||||
self.log_interval = log_interval
|
||||
self._samples = []
|
||||
self._param_events = []
|
||||
self._t0 = time.monotonic()
|
||||
self._run_id = time.strftime("%Y%m%dT%H%M%S", time.localtime())
|
||||
self._last_write = self._t0
|
||||
|
||||
def log_plant_params(self, elapsed, params):
|
||||
self._param_events.append({'t': time.monotonic() - self._t0, 'params': params})
|
||||
@@ -36,6 +38,13 @@ class ServerLogTask(ATask):
|
||||
while True:
|
||||
if self._should_sample():
|
||||
self._samples.append(self._take_sample())
|
||||
# Periodically checkpoints to disk (same file, overwritten whole
|
||||
# each time - see write()) so a hard crash/power loss only loses
|
||||
# up to log_interval seconds, not the whole session/run.
|
||||
now = time.monotonic()
|
||||
if self.log_interval and now - self._last_write >= self.log_interval:
|
||||
self.write()
|
||||
self._last_write = now
|
||||
await asyncio.sleep(self.interval)
|
||||
|
||||
def _should_sample(self):
|
||||
|
||||
+3
-2
@@ -14,8 +14,8 @@ class SudLogTask(ServerLogTask):
|
||||
logs/log_{date_time}_{sud_name}.log. A Pause/resume doesn't start a new
|
||||
file - only a fresh Play (from IDLE/DONE) does."""
|
||||
|
||||
def __init__(self, tc: APid, heater: AHeater, heater_task, sud, interval, path='./logs', config=None, dt=None):
|
||||
ServerLogTask.__init__(self, tc, heater, heater_task, interval, path, config, dt)
|
||||
def __init__(self, tc: APid, heater: AHeater, heater_task, sud, interval, path='./logs', config=None, dt=None, log_interval=None):
|
||||
ServerLogTask.__init__(self, tc, heater, heater_task, interval, path, config, dt, log_interval)
|
||||
self.sud = sud
|
||||
self._active = False
|
||||
|
||||
@@ -31,6 +31,7 @@ class SudLogTask(ServerLogTask):
|
||||
return
|
||||
self._samples = []
|
||||
self._t0 = time.monotonic()
|
||||
self._last_write = self._t0
|
||||
self._run_id = time.strftime("%Y%m%dT%H%M%S", time.localtime())
|
||||
self._active = True
|
||||
|
||||
|
||||
Reference in New Issue
Block a user