def report(pods, rs_statuses, nag_statuses):
if not pods:
print "%s: Unable to locate any pods running mongodb" % (
nagios.status_code_to_label(nagios.UNKNOWN),)
return nagios.UNKNOWN
unique_rs_statuses = Counter(rs_status for rs_status in rs_statuses)
unique_nag_statuses = Counter(nag_status for nag_status in nag_statuses)
ret = max(unique_nag_statuses)
if unique_rs_statuses[REPLSET_STATUS.PRIMARY] != 1:
ret = nagios.CRIT
print "%s: There are %s nodes claiming to be primary members of the replica set" % (
nagios.status_code_to_label(ret), unique_rs_statuses[REPLSET_STATUS.PRIMARY])
elif len(rs_statuses) % 2 == 0:
ret = nagios.WARN
print "%s: There are an even number of voting members (%s) partipating in the replica set" % (
nagios.status_code_to_label(ret), len(rs_statuses))
else:
print "%s: There are %s primary and %s secondary members in the replica set" % (
(nagios.status_code_to_label(ret)),
unique_rs_statuses[REPLSET_STATUS.PRIMARY],
unique_rs_statuses[REPLSET_STATUS.SECONDARY])
for pod, rs_status, nag_status in zip(pods, rs_statuses, nag_statuses):
print "%s: %s - %s" % (
nagios.status_code_to_label(nag_status),
pod,
REPLSET_STATUS.reverse_mapping[rs_status])
return ret
def report(results, errors):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(
status for pod, container, cpu_limit, mem_limit, status in results)
ret = max(unique_statuses)
if ret == nagios.OK:
print "%s: All %s containers have memory and cpu limits set" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.UNKNOWN:
print "%s: Unable to determine cpu and memory limits on %s containers" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.UNKNOWN])
elif ret == nagios.WARN:
print "%s: There are %s containers that do not have both a cpu and memory limit set" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.WARN])
for pod, container, cpu_limit, mem_limit, status in results:
print "%s: %s:%s: - memory limit: %s - cpu limit: %s" % (
nagios.status_code_to_label(status), pod, container, mem_limit,
cpu_limit)
if errors:
ret = nagios.UNKNOWN
for pod_name, container_name, ex in errors:
print "%s: %s:%s %s" % (nagios.status_code_to_label("WARNING"),
pod_name, container_name, ex)
return ret
def report(results, errors, minimum):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(disk_status for pod, container, mount,
space_usage, inode_usage, disk_status in results)
ret = max(unique_statuses)
print "Checked %s volumes (%s critical, %s warning)" % (len(
results), unique_statuses[nagios.CRIT], unique_statuses[nagios.WARN])
for pod, container, mount, disk_usage, inode_usage, status in results:
if max(disk_usage, inode_usage) > minimum:
print "%s: %s:%s:%s - bytes used: %s%%, inodes used: %s%%" % (
nagios.status_code_to_label(status), pod, container, mount,
disk_usage, inode_usage)
if errors:
ret = nagios.UNKNOWN
for pod_name, container_name, ex in errors:
print "%s: %s:%s %s" % (nagios.status_code_to_label("WARNING"),
pod_name, container_name, ex)
return ret
def report(results, errors, minimum):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(
disk_status
for pod, container, mount, space_usage, inode_usage, disk_status in results
)
ret = max(unique_statuses)
print "Checked %s volumes (%s critical, %s warning)" % (
len(results), unique_statuses[nagios.CRIT], unique_statuses[nagios.WARN])
for pod, container, mount, disk_usage, inode_usage, status in results:
if max(disk_usage, inode_usage) > minimum:
print "%s: %s:%s:%s - bytes used: %s%%, inodes used: %s%%" % (
nagios.status_code_to_label(status), pod, container, mount, disk_usage, inode_usage)
if errors:
ret = nagios.UNKNOWN
for pod_name, container_name, ex in errors:
print "%s: %s:%s %s" % (
nagios.status_code_to_label("WARNING"), pod_name, container_name, ex)
return ret
def report(results):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(
disk_status
for pod, mount, space_usage, inode_usage, disk_status in results)
ret = max(unique_statuses)
if ret == nagios.OK:
print "%s: All %s volumes are under the warning threshold" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.UNKNOWN:
print "%s: Unable to determine usage on %s volumes" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.UNKNOWN])
elif ret == nagios.WARN:
print "%s: There are %s volumes over the warning threshold" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.WARN])
else:
print "%s: There are %s volumes over the critical threshold and %s volumes over the warning threshold" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.CRIT],
unique_statuses[nagios.WARN])
for pod, mount, disk_usage, inode_usage, status in results:
print "%s: %s:%s - bytes used: %s%%, inodes used: %s%%" % (
nagios.status_code_to_label(status), pod, mount, disk_usage,
inode_usage)
return ret
def report(results, errors):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(
status
for pod, container, cpu_limit, mem_limit, status in results
)
ret = max(unique_statuses)
if ret == nagios.OK:
print "%s: All %s containers have memory and cpu limits set" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.UNKNOWN:
print "%s: Unable to determine cpu and memory limits on %s containers" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.UNKNOWN])
elif ret == nagios.WARN:
print "%s: There are %s containers that do not have both a cpu and memory limit set" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.WARN])
for pod, container, cpu_limit, mem_limit, status in results:
print "%s: %s:%s: - memory limit: %s - cpu limit: %s" % (
nagios.status_code_to_label(status), pod, container, mem_limit, cpu_limit)
if errors:
ret = nagios.UNKNOWN
for pod_name, container_name, ex in errors:
print "%s: %s:%s %s" % (
nagios.status_code_to_label("WARNING"), pod_name, container_name, ex)
return ret
def report(pods, rs_statuses, nag_statuses):
if not pods:
print "%s: Unable to locate any pods running mongodb" % (
nagios.status_code_to_label(nagios.UNKNOWN), )
return nagios.UNKNOWN
unique_rs_statuses = Counter(rs_status for rs_status in rs_statuses)
unique_nag_statuses = Counter(nag_status for nag_status in nag_statuses)
ret = max(unique_nag_statuses)
if unique_rs_statuses[REPLSET_STATUS.PRIMARY] != 1:
ret = nagios.CRIT
print "%s: There are %s nodes claiming to be primary members of the replica set" % (
nagios.status_code_to_label(ret),
unique_rs_statuses[REPLSET_STATUS.PRIMARY])
elif len(rs_statuses) % 2 == 0:
ret = nagios.WARN
print "%s: There are an even number of voting members (%s) partipating in the replica set" % (
nagios.status_code_to_label(ret), len(rs_statuses))
else:
print "%s: There are %s primary and %s secondary members in the replica set" % (
(nagios.status_code_to_label(ret)),
unique_rs_statuses[REPLSET_STATUS.PRIMARY],
unique_rs_statuses[REPLSET_STATUS.SECONDARY])
for pod, rs_status, nag_status in zip(pods, rs_statuses, nag_statuses):
print "%s: %s - %s" % (nagios.status_code_to_label(nag_status), pod,
REPLSET_STATUS.reverse_mapping[rs_status])
return ret
def report(results, errors):
if errors:
return nagios.UNKNOWN
for result in results:
if result == nagios.CRIT:
print 'Unable to contact the androidsdk - Status %s' % (
nagios.status_code_to_label(result))
return result
elif result == nagios.OK:
print 'Able to contact the androidsdk - Status %s' % (
nagios.status_code_to_label(result))
return result
return nagios.UNKNOWN
def report(results, errors):
if errors:
for status, ex in errors:
print "%s , %s" % (nagios.status_code_to_label("WARNING"), ex)
return nagios.UNKNOWN
for result in results:
if result == nagios.CRIT:
print 'AndroidSDK PersistentVolumeClaim is not Bound - Status %s' % (
nagios.status_code_to_label(result))
return result
elif result == nagios.OK:
print 'AndroidSDK PersistentVolumeClaim is Bound - Status %s' % (
nagios.status_code_to_label(result))
return result
elif result == nagios.UNKNOWN:
print 'Unable to determine the status of the AndroidSDK PersistentVolumeClaim'
def report(results, errors):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(status for pod, container, memory_total,
memory_used, usage, status in results)
ret = max(unique_statuses)
if ret == nagios.OK:
print "%s: All %s containers are under the warning threshold" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.UNKNOWN:
print "%s: Unable to determine usage on %s containers" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.UNKNOWN])
elif ret == nagios.WARN:
print "%s: There are %s containers over the warning threshold" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.WARN])
else:
print "%s: There are %s containers over the critical threshold and %s containers over the warning threshold" % (
nagios.status_code_to_label(ret), unique_statuses[nagios.CRIT],
unique_statuses[nagios.WARN])
for pod, container, memory_total, memory_used, usage, status in results:
print "%s: %s:%s: - usage: %.1f%%" % (
nagios.status_code_to_label(status), pod, container, usage)
if errors:
ret = nagios.UNKNOWN
for pod_name, container_name, ex in errors:
print "%s: %s:%s %s" % (nagios.status_code_to_label("WARNING"),
pod_name, container_name, ex)
return ret
def report(results, errors):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(computer[1] for computer in results)
ret = max(unique_statuses)
for computer in results:
if computer[1] == nagios.CRIT:
print 'Machine: %s is unavailable to Jenkins - Status is %s ' % (
computer[0], nagios.status_code_to_label(computer[1]))
elif computer[1] == nagios.OK:
print 'Machine: %s is available to Jenkins - Status is %s ' % (
computer[0], nagios.status_code_to_label(computer[1]))
elif computer[1] == nagios.UNKNOWN:
print 'Machine: %s status is %s ' % (
computer[0], nagios.status_code_to_label(computer[1]))
else:
print 'Unable to determine the status of the mac machine'
if ret == nagios.OK:
print "%s: %s ios slave machine(s) is/are available" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.UNKNOWN:
print "%s: Unable to determine status of %s ios slave machine(s)" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.CRIT:
print "%s: Unable to contact %s ios slave machine(s)" % (
nagios.status_code_to_label(ret), len(results))
if errors:
ret = nagios.UNKNOWN
return ret
def report(pods, project, result):
if not pods:
print "%s: Unable to locate any pods running mongodb" % (
nagios.status_code_to_label(nagios.UNKNOWN), )
return nagios.UNKNOWN
code = nagios.OK
today = time.strftime('%Y%m%d')
collections_missing_count = 0
for topic, exist in result.iteritems():
# fh-reporting fhact_yyyymmdd collections are not stored in the core database
if project == "rhmap-core" and topic == "fhact":
continue
# fh-reporting database on the mbaas contains only the fhact_yyyymmdd collections
elif project != "rhmap-core" and topic != "fhact":
continue
if not exist:
print "Collection %s_%s does not exist" % (topic, today)
code = nagios.WARN
collections_missing_count += 1
# If more than one of the collections is missing on the core its potentially an issue
# with millicore
if project == "rhmap-core" and collections_missing_count > 1:
code = nagios.CRIT
# If the fhact collection is missing in the mbaas, its potentially an issue with millicore
elif project != "rhmap-core" and collections_missing_count == 1:
code = nagios.CRIT
if code == nagios.OK:
print "OK. Collections exist"
return code
def report(results, errors):
if not results:
return nagios.UNKNOWN
unique_statuses = Counter(
computer[1]
for computer in results
)
ret = max(unique_statuses)
for computer in results:
if computer[1] == nagios.CRIT:
print 'Machine: %s is unavailable to Jenkins - Status is %s ' % (
computer[0], nagios.status_code_to_label(computer[1]))
elif computer[1] == nagios.OK:
print 'Machine: %s is available to Jenkins - Status is %s ' % (
computer[0], nagios.status_code_to_label(computer[1]))
elif computer[1] == nagios.UNKNOWN:
print 'Machine: %s status is %s ' % (
computer[0], nagios.status_code_to_label(computer[1]))
else:
print 'Unable to determine the status of the mac machine'
if ret == nagios.OK:
print "%s: %s ios slave machine(s) is/are available" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.UNKNOWN:
print "%s: Unable to determine status of %s ios slave machine(s)" % (
nagios.status_code_to_label(ret), len(results))
elif ret == nagios.CRIT:
print "%s: Unable to contact %s ios slave machine(s)" % (
nagios.status_code_to_label(ret), len(results))
if errors:
ret = nagios.UNKNOWN
return ret