Skip to content

Removed alarms that aren't needed because the threshold was changed to 100% #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
kcantrel wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Removed alarms that aren't needed because the threshold was changed to 100% #46

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f5017a0
Removed alarms that aren't needed because the threshold was changed t…
kcantrel Jan 31, 2026
5c48c4c
Removed alarms that aren't needed because the threshold was changed t…
kcantrel Jan 31, 2026
27655c8
Apply automatic changes
kcantrel Jan 31, 2026
b70c307
Adjust the CPU alert threshold.
kcantrel Feb 1, 2026
7d73ee5
Adjusted the CPU threshold.
kcantrel Feb 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 24 additions & 13 deletions FSx_Alerting/Auto-Add-CloudWatch-Alarms/auto_add_cw_alarms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,8 +142,8 @@ def add_cpu_alarm(cw, fsId, alarmName, alarmDescription, threshold, region):
ActionsEnabled=True,
AlarmActions=[action],
AlarmDescription=alarmDescription,
EvaluationPeriods=3,
DatapointsToAlarm=2,
EvaluationPeriods=1,
DatapointsToAlarm=1,
Threshold=threshold,
ComparisonOperator='GreaterThanThreshold',
MetricName="CPUUtilization",
Expand Down Expand Up @@ -487,6 +487,10 @@ def lambda_handler(event, context):
for region in regions:
if region in fsxRegions:
print(f'Scanning {region}')
cpuThresholds = {}
ssdThresholds = {}
volumeThresholds = {}
volumeFileThresholds = {}
try:
fsxClient = boto3.client('fsx', region_name=region, config=boto3Config)
cwClient = boto3.client('cloudwatch', region_name=region, config=boto3Config)
Expand All @@ -500,8 +504,9 @@ def lambda_handler(event, context):
for fs in fss:
if(fs['FileSystemType'] == "ONTAP"):
threshold = int(getCPUAlarmThresholdTagValue(fs['Tags']))
fsId = fs['FileSystemId']
cpuThresholds[fsId] = threshold
if(threshold != 100):
fsId = fs['FileSystemId']
fsName = fsId.replace('fs-', 'FsxId')
alarmName = alarmPrefixCPU + fsId
alarmDescription = f"CPU utilization alarm for file system {fsName}{customerId} in region {region}."
Expand All @@ -517,16 +522,18 @@ def lambda_handler(event, context):
if(alarmName[:len(alarmPrefixCPU)] == alarmPrefixCPU):
fsId = alarmName[len(alarmPrefixCPU):]
if(not contains_fs(fsId, fss) and onlyFilesystemId == None or
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId):
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId or
cpuThresholds.get(fsId) == 100):
print("Deleting alarm: " + alarmName + " in region " + region)
delete_alarm(cwClient, alarmName)
#
# Scan for filesystems without SSD Utilization Alarm.
for fs in fss:
if(fs['FileSystemType'] == "ONTAP"):
fsId = fs['FileSystemId']
threshold = int(getSSDAlarmThresholdTagValue(fs['Tags']))
ssdThresholds[fsId] = threshold
if(threshold != 100):
fsId = fs['FileSystemId']
fsName = fsId.replace('fs-', 'FsxId')
alarmName = alarmPrefixSSD + fsId
alarmDescription = f"SSD utilization alarm for file system {fsName}{customerId} in region {region}."
Expand All @@ -542,7 +549,8 @@ def lambda_handler(event, context):
if(alarmName[:len(alarmPrefixSSD)] == alarmPrefixSSD):
fsId = alarmName[len(alarmPrefixSSD):]
if(not contains_fs(fsId, fss) and onlyFilesystemId == None or
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId):
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId or
ssdThresholds.get(fsId) == 100):
print("Deleting alarm: " + alarmName + " in region " + region)
delete_alarm(cwClient, alarmName)
#
Expand All @@ -556,6 +564,7 @@ def lambda_handler(event, context):
volumeTags = getVolumeTags(fsxClient, volumeARN)

threshold = int(getAlarmThresholdTagValue(volumeTags, "alarm_threshold"))
volumeThresholds[volumeId] = threshold
if(threshold != 100): # No alarm if the value is set to 100.
alarmName = alarmPrefixVolume + volumeId
fsName = fsId.replace('fs-', 'FsxId')
Expand All @@ -566,6 +575,7 @@ def lambda_handler(event, context):
add_volume_alarm(cwClient, volumeId, alarmName, alarmDescription, fsId, threshold, region)

threshold = int(getAlarmThresholdTagValue(volumeTags, "files_threshold"))
volumeFileThresholds[volumeId] = threshold
if(threshold != 100): # No alarm if the value is set to 100.
alarmName = alarmFilesPrefixVolume + volumeId
fsName = fsId.replace('fs-', 'FsxId')
Expand All @@ -578,18 +588,20 @@ def lambda_handler(event, context):
# Scan for volume alarms without volumes.
for alarm in alarms:
alarmName = alarm['AlarmName']
if(alarmName[:len(alarmPrefixVolume)] == alarmPrefixVolume):
if alarmName[:len(alarmPrefixVolume)] == alarmPrefixVolume:
volumeId = alarmName[len(alarmPrefixVolume):]
if(not contains_volume(volumeId, volumes) and onlyFilesystemId == None or
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm)):
print("Deleting alarm: " + alarmName + " in region " + region)
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm) or
volumeThresholds.get(volumeId) == 100):
print(f"Deleting alarm: {alarmName} in region {region}")
delete_alarm(cwClient, alarmName)

if(alarmName[:len(alarmFilesPrefixVolume)] == alarmFilesPrefixVolume):
if alarmName[:len(alarmFilesPrefixVolume)] == alarmFilesPrefixVolume:
volumeId = alarmName[len(alarmFilesPrefixVolume):]
if(not contains_volume(volumeId, volumes) and onlyFilesystemId == None or
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm)):
print("Deleting alarm: " + alarmName + " in region " + region)
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm) or
volumeFileThresholds.get(volumeId) == 100):
print(f"Deleting alarm: {alarmName} in region {region}")
delete_alarm(cwClient, alarmName)

except botocore.exceptions.ClientError as e:
Expand All @@ -602,7 +614,6 @@ def lambda_handler(event, context):
except botocore.exceptions.EndpointConnectionError as e:
print(f"Warning: Endpoint Connection fault while scanning {region}. Skipping")
continue

return

################################################################################
Expand Down
41 changes: 26 additions & 15 deletions FSx_Alerting/Auto-Add-CloudWatch-Alarms/cloudformation.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,8 +199,8 @@ Resources:
# Lastly, you can create an override for the SSD alarm, by creating a tag
# with the name "SSD_Alarm_Threshold" on the file system resource.
#
# Version: v2.4
# Date: 2025-12-23-17:10:05
# Version: v2.7
# Date: 2026-02-01-08:53:08
#
################################################################################
#
Expand Down Expand Up @@ -314,8 +314,8 @@ Resources:
ActionsEnabled=True,
AlarmActions=[action],
AlarmDescription=alarmDescription,
EvaluationPeriods=3,
DatapointsToAlarm=2,
EvaluationPeriods=1,
DatapointsToAlarm=1,
Threshold=threshold,
ComparisonOperator='GreaterThanThreshold',
MetricName="CPUUtilization",
Expand Down Expand Up @@ -659,6 +659,10 @@ Resources:
for region in regions:
if region in fsxRegions:
print(f'Scanning {region}')
cpuThresholds = {}
ssdThresholds = {}
volumeThresholds = {}
volumeFileThresholds = {}
try:
fsxClient = boto3.client('fsx', region_name=region, config=boto3Config)
cwClient = boto3.client('cloudwatch', region_name=region, config=boto3Config)
Expand All @@ -672,8 +676,9 @@ Resources:
for fs in fss:
if(fs['FileSystemType'] == "ONTAP"):
threshold = int(getCPUAlarmThresholdTagValue(fs['Tags']))
fsId = fs['FileSystemId']
cpuThresholds[fsId] = threshold
if(threshold != 100):
fsId = fs['FileSystemId']
fsName = fsId.replace('fs-', 'FsxId')
alarmName = alarmPrefixCPU + fsId
alarmDescription = f"CPU utilization alarm for file system {fsName}{customerId} in region {region}."
Expand All @@ -689,16 +694,18 @@ Resources:
if(alarmName[:len(alarmPrefixCPU)] == alarmPrefixCPU):
fsId = alarmName[len(alarmPrefixCPU):]
if(not contains_fs(fsId, fss) and onlyFilesystemId == None or
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId):
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId or
cpuThresholds.get(fsId) == 100):
print("Deleting alarm: " + alarmName + " in region " + region)
delete_alarm(cwClient, alarmName)
#
# Scan for filesystems without SSD Utilization Alarm.
for fs in fss:
if(fs['FileSystemType'] == "ONTAP"):
fsId = fs['FileSystemId']
threshold = int(getSSDAlarmThresholdTagValue(fs['Tags']))
ssdThresholds[fsId] = threshold
if(threshold != 100):
fsId = fs['FileSystemId']
fsName = fsId.replace('fs-', 'FsxId')
alarmName = alarmPrefixSSD + fsId
alarmDescription = f"SSD utilization alarm for file system {fsName}{customerId} in region {region}."
Expand All @@ -714,7 +721,8 @@ Resources:
if(alarmName[:len(alarmPrefixSSD)] == alarmPrefixSSD):
fsId = alarmName[len(alarmPrefixSSD):]
if(not contains_fs(fsId, fss) and onlyFilesystemId == None or
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId):
not contains_fs(fsId, fss) and onlyFilesystemId != None and onlyFilesystemId == fsId or
ssdThresholds.get(fsId) == 100):
print("Deleting alarm: " + alarmName + " in region " + region)
delete_alarm(cwClient, alarmName)
#
Expand All @@ -728,6 +736,7 @@ Resources:
volumeTags = getVolumeTags(fsxClient, volumeARN)

threshold = int(getAlarmThresholdTagValue(volumeTags, "alarm_threshold"))
volumeThresholds[volumeId] = threshold
if(threshold != 100): # No alarm if the value is set to 100.
alarmName = alarmPrefixVolume + volumeId
fsName = fsId.replace('fs-', 'FsxId')
Expand All @@ -738,6 +747,7 @@ Resources:
add_volume_alarm(cwClient, volumeId, alarmName, alarmDescription, fsId, threshold, region)

threshold = int(getAlarmThresholdTagValue(volumeTags, "files_threshold"))
volumeFileThresholds[volumeId] = threshold
if(threshold != 100): # No alarm if the value is set to 100.
alarmName = alarmFilesPrefixVolume + volumeId
fsName = fsId.replace('fs-', 'FsxId')
Expand All @@ -750,18 +760,20 @@ Resources:
# Scan for volume alarms without volumes.
for alarm in alarms:
alarmName = alarm['AlarmName']
if(alarmName[:len(alarmPrefixVolume)] == alarmPrefixVolume):
if alarmName[:len(alarmPrefixVolume)] == alarmPrefixVolume:
volumeId = alarmName[len(alarmPrefixVolume):]
if(not contains_volume(volumeId, volumes) and onlyFilesystemId == None or
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm)):
print("Deleting alarm: " + alarmName + " in region " + region)
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm) or
volumeThresholds.get(volumeId) == 100):
print(f"Deleting alarm: {alarmName} in region {region}")
delete_alarm(cwClient, alarmName)

if(alarmName[:len(alarmFilesPrefixVolume)] == alarmFilesPrefixVolume):
if alarmName[:len(alarmFilesPrefixVolume)] == alarmFilesPrefixVolume:
volumeId = alarmName[len(alarmFilesPrefixVolume):]
if(not contains_volume(volumeId, volumes) and onlyFilesystemId == None or
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm)):
print("Deleting alarm: " + alarmName + " in region " + region)
not contains_volume(volumeId, volumes) and onlyFilesystemId != None and onlyFilesystemId == getFileSystemId(alarm) or
volumeFileThresholds.get(volumeId) == 100):
print(f"Deleting alarm: {alarmName} in region {region}")
delete_alarm(cwClient, alarmName)

except botocore.exceptions.ClientError as e:
Expand All @@ -774,7 +786,6 @@ Resources:
except botocore.exceptions.EndpointConnectionError as e:
print(f"Warning: Endpoint Connection fault while scanning {region}. Skipping")
continue

return

################################################################################
Expand Down