way/pigway-frame-flow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 29 Wiki Activity

Fix webhook starvation and isolate scheduled job failures for v0.1.2 [skip ci]

Browse Source
This commit is contained in:
渡口浪人
2026-10-16 09:48:51 +08:00
parent e1b001a431
commit 8a3c616b5f
8 changed files with 158 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pigway_frame_flow/scheduler/engine.py
+65 -54
View File
@@ -147,61 +147,72 @@ class Scheduler:
"SELECT * FROM jobs WHERE enabled=1 AND next_run<=?",
(current.isoformat(),),
):
job = JobInput.model_validate_json(row["payload"])
slot = row["next_run"]
if self.db.one(
"SELECT * FROM job_runs WHERE job_id=? AND scheduled_at=?",
(row["id"], slot),
):
continue
# Skip overdue tasks (>5 minutes): avoid an unexpected artwork
# overwrite after downtime. One-time tasks are retired too.
late = (current - datetime.fromisoformat(slot)).total_seconds() > 300
operation_id = None
if not late:
action = "restore" if job.source.type == "restore" else "display"
payload = (
{}
if isinstance(job.source, RestoreContent)
else DisplayRequest(
device_id=job.device_id,
content=job.source,
options=Options(
duration=job.display_duration,
restore_previous=job.restore_previous,
priority=job.priority,
cleanup_unstarred=job.cleanup_unstarred,
try:
job = JobInput.model_validate_json(row["payload"])
slot = row["next_run"]
if self.db.one(
"SELECT * FROM job_runs WHERE job_id=? AND scheduled_at=?",
(row["id"], slot),
):
continue
# Skip overdue tasks (>5 minutes): avoid an unexpected artwork
# overwrite after downtime. One-time tasks are retired too.
late = (
current - datetime.fromisoformat(slot)
).total_seconds() > 300
operation_id = None
if not late:
action = (
"restore" if job.source.type == "restore" else "display"
)
payload = (
{}
if isinstance(job.source, RestoreContent)
else DisplayRequest(
device_id=job.device_id,
content=job.source,
options=Options(
duration=job.display_duration,
restore_previous=job.restore_previous,
priority=job.priority,
cleanup_unstarred=job.cleanup_unstarred,
),
).model_dump(mode="json")
)
operation_id = self.service.submit(
action,
payload,
job.device_id,
"scheduler",
"schedule-" + uuid4().hex,
"job-" + row["id"] + "-" + slot,
)
following = next_run(job.schedule, current)
enabled = bool(following)
updated = job.model_copy(update={"enabled": enabled}).model_dump(
mode="json"
)
with self.db.transaction() as tx:
tx.execute(
"INSERT OR IGNORE INTO job_runs VALUES(?,?,?)",
(row["id"], slot, operation_id),
)
tx.execute(
"UPDATE jobs SET payload=?,enabled=?,next_run=?,last_run=?,last_result=? WHERE id=?",
(
encode(updated),
int(enabled),
following,
now_iso(),
"SKIPPED_OVERDUE" if late else operation_id,
row["id"],
),
).model_dump(mode="json")
)
operation_id = self.service.submit(
action,
payload,
job.device_id,
"scheduler",
"schedule-" + uuid4().hex,
"job-" + row["id"] + "-" + slot,
)
following = next_run(job.schedule, current)
enabled = bool(following)
updated = job.model_copy(update={"enabled": enabled}).model_dump(
mode="json"
)
with self.db.transaction() as tx:
tx.execute(
"INSERT OR IGNORE INTO job_runs VALUES(?,?,?)",
(row["id"], slot, operation_id),
)
tx.execute(
"UPDATE jobs SET payload=?,enabled=?,next_run=?,last_run=?,last_result=? WHERE id=?",
(
encode(updated),
int(enabled),
following,
now_iso(),
"SKIPPED_OVERDUE" if late else operation_id,
row["id"],
),
)
except Exception:
# Keep this slot pending for retry or the existing overdue policy.
# A single device must not prevent other jobs or queue consumption.
logging.getLogger("frame-flow").error(
"Scheduled job failed; details suppressed"
)
for row in self.db.all(
"SELECT * FROM playlists WHERE next_run<=?", (current.isoformat(),)