def startMonitoring(conn, metricId, swarmParams, logger):
""" Start monitoring an UNMONITORED metric.
NOTE: typically called either inside a transaction and/or with locked tables
Starts the CLA model if provided non-None swarmParams; otherwise defers model
creation to a later time and places the metric in MetricStatus.PENDING_DATA
state.
:param conn: SQLAlchemy Connection object for executing SQL
:type conn: sqlalchemy.engine.Connection
:param metricId: unique identifier of the metric row
:param swarmParams: swarmParams generated via
scalar_metric_utils.generateSwarmParams() or None.
:param logger: logger object
:returns: True if model was started; False if not
:raises htmengine.exceptions.ObjectNotFoundError: if metric with the
referenced metric uid doesn't exist
:raises htmengine.exceptions.MetricStatusChangedError: if Metric status was
changed by someone else (most likely another process) before this
operation could complete
"""
modelStarted = False
startTime = time.time()
metricObj = repository.getMetric(conn, metricId)
assert metricObj.status == MetricStatus.UNMONITORED, (
"startMonitoring: metric=%s is already monitored; status=%s" % (
metricId,
metricObj.status,
))
if swarmParams is not None:
# We have swarmParams, so start the model
modelStarted = _startModelHelper(conn=conn,
metricObj=metricObj,
swarmParams=swarmParams,
logger=logger)
else:
# Put the metric into the PENDING_DATA state until enough data arrives for
# stats
refStatus = metricObj.status
repository.setMetricStatus(conn,
metricId,
MetricStatus.PENDING_DATA,
refStatus=refStatus)
# refresh
metricStatus = repository.getMetric(conn,
metricId,
fields=[schema.metric.c.status
]).status
if metricStatus == MetricStatus.PENDING_DATA:
logger.info(
"startMonitoring: promoted metric to model in PENDING_DATA; "
"metric=%s; duration=%.4fs", metricId,
time.time() - startTime)
else:
raise app_exceptions.MetricStatusChangedError(
"startMonitoring: unable to promote metric=%s to model as "
"PENDING_DATA; metric status morphed from %s to %s" % (
metricId,
refStatus,
metricStatus,
))
return modelStarted
def _startModelHelper(conn, metricObj, swarmParams, logger):
""" Start the model
:param conn: SQLAlchemy Connection object for executing SQL
:type conn: sqlalchemy.engine.Connection
:param metricObj: metric, freshly-loaded
:type metricObj: sqlalchemy.engine.RowProxy (see repository.getMetric())
:param swarmParams: non-None swarmParams generated via
scalar_metric_utils.generateSwarmParams().
:param logger: logger object
:returns: True if model was started; False if not
:raises htmengine.exceptions.ObjectNotFoundError: if the metric doesn't exist;
this may happen if it got deleted by another process in the meantime.
:raises htmengine.exceptions.MetricStatusChangedError: if Metric status was
changed by someone else (most likely another process) before this
operation could complete
"""
if swarmParams is None:
raise ValueError(
"startModel: 'swarmParams' must be non-None: metric=%s" %
(metricObj.uid, ))
if metricObj.status not in (MetricStatus.UNMONITORED,
MetricStatus.PENDING_DATA):
if metricObj.status in (MetricStatus.CREATE_PENDING,
MetricStatus.ACTIVE):
return False
logger.error("Unexpected metric status; metric=%r", metricObj)
raise ValueError("startModel: unexpected metric status; metric=%r" %
(metricObj, ))
startTime = time.time()
# Save swarm parameters and update metric status
refStatus = metricObj.status
repository.updateMetricColumnsForRefStatus(
conn, metricObj.uid, refStatus, {
"status": MetricStatus.CREATE_PENDING,
"model_params": htmengine.utils.jsonEncode(swarmParams)
})
metricObj = repository.getMetric(
conn,
metricObj.uid,
fields=[schema.metric.c.uid, schema.metric.c.status]) # refresh
if metricObj.status != MetricStatus.CREATE_PENDING:
raise app_exceptions.MetricStatusChangedError(
"startModel: unable to start model=%s; "
"metric status morphed from %s to %s" % (
metricObj.uid,
refStatus,
metricObj.status,
))
# Request to create the CLA model
try:
model_swapper_utils.createHTMModel(metricObj.uid, swarmParams)
except Exception:
logger.exception("startModel: createHTMModel failed.")
repository.setMetricStatus(conn,
metricObj.uid,
status=MetricStatus.ERROR,
message=repr(sys.exc_info()[1]))
raise
logger.info("startModel: started model=%r; duration=%.4fs", metricObj,
time.time() - startTime)
return True