Skip to content

Bugfix #153

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

Merged
merged 6 commits into from
Jun 15, 2023
Merged

Bugfix #153

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
f99af21
fix extra } in monitor
ErinWeisbart May 24, 2023
e0f56d7
revert to old S3 mount
ErinWeisbart May 24, 2023
bdd664e
dashboard read app name correctly
ErinWeisbart May 24, 2023
8707080
can only delete 100 alarms at a time
ErinWeisbart May 24, 2023
9a09a65
missed deleting last chunk of instances
ErinWeisbart May 24, 2023
f57acdc
missing comma
ErinWeisbart Jun 15, 2023
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
14 changes: 12 additions & 2 deletions lambda_function.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,12 @@ def killdeadAlarms(fleetId, monitorapp, project):
if eachevent["EventInformation"]["EventSubType"] == "terminated":
todel.append(eachevent["EventInformation"]["InstanceId"])
todel = [f"{project}_{x}" for x in todel]
cloudwatch.delete_alarms(AlarmNames=todel)
while len(todel) > 100:
dellist = todel[:100]
cloudwatch.delete_alarms(AlarmNames=dellist)
todel = todel[100:]
if len(todel) <= 100:
cloudwatch.delete_alarms(AlarmNames=todel)
print("Old alarms deleted")


Expand Down Expand Up @@ -115,7 +120,12 @@ def lambda_handler(event, lambda_context):
active_instances = []
for instance in active_dictionary["ActiveInstances"]:
active_instances.append(instance["InstanceId"])
cloudwatch.delete_alarms(AlarmNames=active_instances)
while len(active_instances) > 100:
dellist = active_instances[:100]
cloudwatch.delete_alarms(AlarmNames=dellist)
active_instances = active_instances[100:]
if len(active_instances) <= 100:
cloudwatch.delete_alarms(AlarmNames=active_instances)
killdeadAlarms(fleetId, monitorapp, project)

# Read spot fleet id and terminate all EC2 instances
Expand Down
8 changes: 4 additions & 4 deletions run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -398,7 +398,7 @@ def create_dashboard(requestInfo):
"x": 12,
"type": "log",
"properties": {
"query": f"SOURCE {APP_NAME} | fields @message| filter @message like 'cellprofiler -c'| stats count_distinct(@message)\n",
"query": f"SOURCE '{APP_NAME}' | fields @message| filter @message like 'cellprofiler -c'| stats count_distinct(@message)\n",
"region": AWS_REGION,
"stacked": False,
"title": "Distinct Logs with \"cellprofiler -c\"",
Expand All @@ -412,7 +412,7 @@ def create_dashboard(requestInfo):
"x": 0,
"type": "log",
"properties": {
"query": f"SOURCE {APP_NAME} | fields @message| filter @message like 'cellprofiler -c'| stats count(@message)",
"query": f"SOURCE '{APP_NAME}' | fields @message| filter @message like 'cellprofiler -c'| stats count(@message)",
"region": AWS_REGION,
"stacked": False,
"title": "All Logs \"cellprofiler -c\"",
Expand All @@ -426,7 +426,7 @@ def create_dashboard(requestInfo):
"x": 0,
"type": "log",
"properties": {
"query": f"SOURCE {APP_NAME} | fields @message | filter @message like \"Error\" | display @message",
"query": f"SOURCE '{APP_NAME}' | fields @message | filter @message like \"Error\" | display @message",
"region": AWS_REGION,
"stacked": False,
"title": "Errors",
Expand Down Expand Up @@ -598,7 +598,7 @@ def startCluster():
createMonitor.write('"MONITOR_QUEUE_NAME" : "'+SQS_QUEUE_NAME+'",\n')
createMonitor.write('"MONITOR_BUCKET_NAME" : "'+AWS_BUCKET+'",\n')
createMonitor.write('"MONITOR_LOG_GROUP_NAME" : "'+LOG_GROUP_NAME+'",\n')
createMonitor.write('"MONITOR_START_TIME" : "'+ starttime+'"}\n')
createMonitor.write('"MONITOR_START_TIME" : "'+ starttime+'",\n')
createMonitor.write('"CLEAN_DASHBOARD" : "'+ CLEAN_DASHBOARD+'"}\n')
createMonitor.close()

Expand Down
16 changes: 5 additions & 11 deletions worker/run-worker.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,19 +19,13 @@ aws ec2 create-tags --resources $VOL_0_ID --tags Key=Name,Value=${APP_NAME}Worke
VOL_1_ID=$(aws ec2 describe-instance-attribute --instance-id $MY_INSTANCE_ID --attribute blockDeviceMapping --output text --query BlockDeviceMappings[1].Ebs.[VolumeId])
aws ec2 create-tags --resources $VOL_1_ID --tags Key=Name,Value=${APP_NAME}Worker

# 2. MOUNT S3

# 2. MOUNT S3
echo $AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY > /credentials.txt
chmod 600 /credentials.txt
mkdir -p /home/ubuntu/bucket
mkdir -p /home/ubuntu/local_output
if [[ -z "$AWS_ACCESS_KEY_ID" ]]
then
AWS_ACCESS_KEY_ID=$(curl 169.254.170.2$AWS_CONTAINER_CREDENTIALS_RELATIVE_URI | jq '.AccessKeyId')
AWS_SECRET_ACCESS_KEY=$(curl 169.254.170.2$AWS_CONTAINER_CREDENTIALS_RELATIVE_URI | jq '.SecretAccessKey')
echo $AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY > /credentials.txt
chmod 600 /credentials.txt
stdbuf -o0 s3fs $AWS_BUCKET /home/ubuntu/bucket -o passwd_file=/credentials.txt -o dbglevel=info
else
stdbuf -o0 s3fs $AWS_BUCKET /home/ubuntu/bucket -o ecs -o dbglevel=info
fi
stdbuf -o0 s3fs $AWS_BUCKET /home/ubuntu/bucket -o passwd_file=/credentials.txt


# 3. SET UP ALARMS
Expand Down