def _statistics(self, rule, start, end): try: # FIXME(sileht): In case of a heat autoscaling stack decide to # delete an instance, the gnocchi metrics associated to this # instance will be no more updated and when the alarm will ask # for the aggregation, gnocchi will raise a 'No overlap' # exception. # So temporary set 'needed_overlap' to 0 to disable the # gnocchi checks about missing points. For more detail see: # https://bugs.launchpad.net/gnocchi/+bug/1479429 return self._gnocchi_client.metric.aggregation( metrics=rule['metrics'], start=start, stop=end, aggregation=rule['aggregation_method'], needed_overlap=0) except exceptions.MetricNotFound: raise threshold.InsufficientDataError( 'At least of metrics in %s does not exist' % rule['metrics'], []) except exceptions.NotFound: # TODO(sileht): gnocchiclient should raise a explicit # exception for AggregationNotFound, this API endpoint # can only raise 3 different 404, so we are safe to # assume this is an AggregationNotFound for now. raise threshold.InsufficientDataError( 'aggregation %s does not exist for at least one ' 'metrics in %s' % (rule['aggregation_method'], rule['metrics']), []) except Exception as e: msg = 'alarm statistics retrieval failed: %s' % e LOG.warning(msg) raise threshold.InsufficientDataError(msg, [])
def _statistics(self, rule, start, end): try: return self._gnocchi_client.metric.get_measures( metric=rule['metric'], start=start, stop=end, resource_id=rule['resource_id'], aggregation=rule['aggregation_method']) except exceptions.MetricNotFound: raise threshold.InsufficientDataError( 'metric %s for resource %s does not exists' % (rule['metric'], rule['resource_id']), []) except exceptions.ResourceNotFound: raise threshold.InsufficientDataError( 'resource %s does not exists' % rule['resource_id'], []) except exceptions.NotFound: # TODO(sileht): gnocchiclient should raise a explicit # exception for AggregationNotFound, this API endpoint # can only raise 3 different 404, so we are safe to # assume this is an AggregationNotFound for now. raise threshold.InsufficientDataError( 'aggregation %s does not exist for ' 'metric %s of resource %s' % (rule['aggregation_method'], rule['metric'], rule['resource_id']), []) except Exception as e: msg = 'alarm statistics retrieval failed: %s' % e LOG.warning(msg) raise threshold.InsufficientDataError(msg, [])
def _get_unhealthy_members(self, pool_id): """Get number of unhealthy members in a pool. The member(virutual machine) operating_status keeps ERROR after creation before the application is up and running inside, it should be ignored during the check. """ unhealthy_members = [] try: ret = self.lb_client.member_list(pool_id) except Exception as e: LOG.warning("Failed to communicate with load balancing service, " "error: %s", six.text_type(e)) raise threshold.InsufficientDataError( 'failed to communicate with load balancing service', [] ) if getattr(ret, 'status_code', None): # Some error happened raise threshold.InsufficientDataError(ret.content, []) for m in ret.get("members", []): try: created_time = parser.parse(m['created_at'], ignoretz=True) except ValueError: LOG.warning('Failed to parse the member created time.') continue now = timeutils.utcnow() t = self.conf.member_creation_time if now - created_time < datetime.timedelta(seconds=t): LOG.debug("Ignore member which was created within %ss", t) continue if m["admin_state_up"] and m["operating_status"] == "ERROR": unhealthy_members.append(m) return unhealthy_members
def _sanitize(rule, statistics): """Return the datapoints that correspond to the alarm granularity""" # TODO(sileht): if there's no direct match, but there is an archive # policy with granularity that's an even divisor or the period, # we could potentially do a mean-of-means (or max-of-maxes or whatever, # but not a stddev-of-stddevs). # TODO(sileht): support alarm['exclude_outliers'] LOG.debug('sanitize stats %s', statistics) statistics = [ stats[VALUE] for stats in statistics if stats[GRANULARITY] == rule['granularity'] ] if not statistics: raise threshold.InsufficientDataError( "No datapoint for granularity %s" % rule['granularity'], []) statistics = statistics[-rule['evaluation_periods']:] LOG.debug('pruned statistics to %d', len(statistics)) return statistics