OrgTJWater/next-tjwater-server
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(scada): add calibrated monitoring and incident recovery

Browse Source
This commit is contained in:
jiang
2026-11-07 19:44:58 +08:00
parent 26fa5d1909
commit ff8aba4964
109 changed files with 9165 additions and 629 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/infra/db/postgresql/calculation_jobs.py
+9 -15
View File
@@ -7,10 +7,10 @@ from app.mcp.errors import CalculationCapacityExceeded
# Explicit metadata projection prevents status polling from decoding large JSON results.
JOB_COLUMNS = "job_id,project_id,owner_user_id,request_key,tool,parameters,binding,timeout_seconds,status,error,lease_generation,lease_owner,lease_expires_at,created_at,updated_at,started_at,finished_at,queue_expires_at,result_expires_at"
JOB_COLUMNS = "job_id,project_id,owner_user_id,request_key,tool,parameters,binding,timeout_seconds,status,error,lease_generation,lease_owner,lease_expires_at,created_at,updated_at,started_at,finished_at,result_expires_at"
PUBLIC_JOB_COLUMNS = "job_id,status,tool,error,created_at,updated_at,started_at,finished_at,queue_expires_at,result_expires_at"
PUBLIC_JOB_COLUMNS = "job_id,status,tool,error,created_at,updated_at,started_at,finished_at,result_expires_at"
class CalculationJobRepository:
@@ -19,12 +19,6 @@ class CalculationJobRepository:
self.project_id = str(project_id)
async def maintain(self):
await self.connection.execute(
"""UPDATE workbench.calculation_jobs SET status='timed_out',
error='{"code":"QUEUE_TIMEOUT"}'::jsonb,finished_at=clock_timestamp(),updated_at=clock_timestamp()
WHERE project_id=%s AND status='queued' AND queue_expires_at<=clock_timestamp()""",
(self.project_id,),
)
await self.connection.execute(
"""UPDATE workbench.calculation_jobs SET result=NULL
WHERE project_id=%s AND result IS NOT NULL AND result_expires_at<=clock_timestamp()""",
@@ -32,14 +26,14 @@ class CalculationJobRepository:
)
async def enqueue(self, *, owner_user_id, request_key, tool, parameters, binding, timeout_seconds,
queue_wait_seconds=3600, max_active_jobs=100):
max_active_jobs=100):
async with self.connection.transaction():
return await self._enqueue(owner_user_id=owner_user_id, request_key=request_key,
tool=tool, parameters=parameters, binding=binding, timeout_seconds=timeout_seconds,
queue_wait_seconds=queue_wait_seconds, max_active_jobs=max_active_jobs)
max_active_jobs=max_active_jobs)
async def _enqueue(self, *, owner_user_id, request_key, tool, parameters, binding,
timeout_seconds, queue_wait_seconds, max_active_jobs):
timeout_seconds, max_active_jobs):
# Serialize admission within the caller's transaction, across every API process.
await self.connection.execute(
"SELECT pg_advisory_xact_lock(hashtextextended(%s, 1748531781))", (self.project_id,))
@@ -64,11 +58,11 @@ class CalculationJobRepository:
raise CalculationCapacityExceeded()
cursor = await self.connection.execute(
f"""INSERT INTO workbench.calculation_jobs
(job_id,project_id,owner_user_id,request_key,tool,parameters,binding,timeout_seconds,queue_expires_at)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s,clock_timestamp()+%s*interval '1 second')
(job_id,project_id,owner_user_id,request_key,tool,parameters,binding,timeout_seconds)
VALUES (%s,%s,%s,%s,%s,%s,%s,%s)
RETURNING {JOB_COLUMNS}""",
(uuid4(), self.project_id, owner_user_id, request_key, tool,
Jsonb(parameters), Jsonb(binding), timeout_seconds, queue_wait_seconds),
Jsonb(parameters), Jsonb(binding), timeout_seconds),
)
return dict(await cursor.fetchone())
@@ -118,7 +112,7 @@ class CalculationJobRepository:
lease_generation=j.lease_generation+1,
lease_expires_at=clock_timestamp()+%s*interval '1 second',updated_at=clock_timestamp()
WHERE j.job_id=(SELECT job_id FROM workbench.calculation_jobs
WHERE project_id=%s AND status='queued' AND queue_expires_at>clock_timestamp() ORDER BY created_at,job_id
WHERE project_id=%s AND status='queued' ORDER BY created_at,job_id
FOR UPDATE SKIP LOCKED LIMIT 1) RETURNING j.*""",
(owner, lease_seconds, self.project_id),
)