Health check for a host

cmd = f"aws ec2 describe-instances --filters Name=ip-address,Values={hostname} --query 'Reservations[*].Instances[*].[InstanceId]' --output text --region us-west-2" print("cmd: ", cmd) cred_label = "aws_read_only_user" op = _exe(None, cmd, cred_label=cred_label) print("op: ", op) instance_id = op.strip() print("Instance Id: ", instance_id)

import re import math import datetime period = period_str max_data_points = 1430 tt = re.search("(\d+)\s*d|(\d+)\s*day|(\d+)\s*days", period_str, re.IGNORECASE) if tt: days = tt.group(1) period = int(days) * 3600 *24 tt = re.search("(\d+)\s*h|(\d+)\s*hr|(\d+)\s*hrs|(\d+)\s*hour|(\d+)\s*hours", period_str, re.IGNORECASE) if tt: hours = tt.group(1) period = int(hours) * 3600 tt = re.search("(\d+)\s*m|(\d+)\s*min|(\d+)\s*mins|(\d+)\s*minute|(\d+)\s*minutes", period_str, re.IGNORECASE) if tt: minutes = tt.group(1) period = int(minutes) * 60 interval = 1 if math.ceil(period) <= 1440: interval = 1 elif math.ceil(period/5) <= 1440: interval = 5 elif math.ceil(period/10) <= 1440: interval = 10 elif math.ceil(period/30) <= 1440: interval = 30 else: interval = math.ceil(period/max_data_points) interval = 60*math.ceil(interval/60) interval = str(interval) now = datetime.datetime.now().timestamp() end_time = datetime.datetime.now().isoformat() then = now - period start_time = datetime.datetime.fromtimestamp(then).isoformat() print("Start time: ", start_time) print("End time: ", end_time) print("Interval: ", interval)

import json cmd = 'aws cloudwatch get-metric-statistics --metric-name CPUUtilization' cmd += ' --region ' + 'us-west-2' cmd += ' --start-time ' + start_time cmd += ' --end-time ' + end_time cmd += ' --period ' + interval cmd += ' --namespace AWS/EC2 --statistics Maximum --dimensions Name=InstanceId,Value=' + instance_id op = _exe(None, cmd, cred_label="aws_read_only_user") # print(op) exception_msg = "" try: jsn = json.loads(op) except Exception as e: exception_msg = "Got this exception: \n" exception_msg += str(e) exception_msg += "\n" exception_msg += op if not exception_msg: datapoints = sorted(jsn['Datapoints'], key = lambda i: i['Timestamp']) x = [x['Timestamp'] for x in datapoints] y = [x['Maximum'] for x in datapoints] # trace['type'] = 'scatter' # trace['mode'] = 'lines' context.plot.xlabel = 'timestamp' context.plot.ylabel = 'CPU % util' context.plot.title = 'CPU util for instance: ' + str(instance_id) context.plot.add_trace(name="CPU util", xpts=x, ypts=y, tracetype="lines")

lines = procdata.split('\n')[1:] xs = [] ys = [] for line in lines: parts = line.split() if len(parts) == 12: ys.append(float(parts[9])) xs.append(str(parts[11])) context.plot.xlabel = "processes" context.plot.ylabel = "% memory consumed" context.plot.title = "Top memory consumers" context.plot.add_trace(name="Top memory consumers", xpts=xs, ypts=ys, tracetype="bar")

parts = dfoutput.split() perc_parts = [x for x in parts if '%' in x] used_disk_space = float(perc_parts[1].strip('%')) available_disk = 100.0 - used_disk_space print(available_disk)

if available_disk > 25.0: context.skip_sub_tasks = True