def monitor_processes(monitor_process_list, command_list, machine_name):
"""
<Purpose>
Checks to make sure that the critical processes on the machine 'seattle' are still running
<Exceptions>
None
<Arguments>
monitor_process_list - a list of all the critical processes that should be checked to
see if they are up and running.
command_list - a list of all the commands required to find all the relevant processes
<Return>
None
"""
#string that holds the name of all the processes that are found to be running using the
#ps commands that was passed in as argument
processes_string=""
integrationtestlib.log("Starting monitoring process on "+machine_name)
#run a command on the linux machine to find all the relevant processes
for command in command_list:
try:
relevant_processes, command_error = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE).communicate()
except:
integrationtestlib.handle_exception("Failed to run command: "+command)
sys.exit(1)
#make a string of all the processes
processes_string = processes_string+relevant_processes
print processes_string
#keeps track to see if any processes are down
critical_process_down=False
error_message="WARNING: Critical processes down! Seattle developers please start the processes up as soon as possible\n"
error_message=error_message+"Listing processes that are down:\n"
#goes through the list of monitor_process_list to ensure that all processes are running
for critical_process in monitor_process_list:
integrationtestlib.log("Checking process: "+critical_process+".......")
if not critical_process in processes_string:
critical_process_down=True
error_message = error_message+critical_process+" is down on "+machine_name+".cs.washington.edu\n"
print "FAIL"
else:
print "PASS"
error_message=error_message+"end of list of processes that are down.\n................................"
if critical_process_down:
integrationtestlib.notify(error_message)
irc_seattlebot.send_msg(error_message)
else:
integrationtestlib.log("All critical processes on "+machine_name+" are up and running")
print(".........................................................")
def monitor_processes(monitor_process_list, command_list, machine_name):
"""
<Purpose>
Checks to make sure that the critical processes on the machine 'seattle' are still running
<Exceptions>
None
<Arguments>
monitor_process_list - a list of all the critical processes that should be checked to
see if they are up and running.
command_list - a list of all the commands required to find all the relevant processes
<Return>
None
"""
#string that holds the name of all the processes that are found to be running using the
#ps commands that was passed in as argument
processes_string=""
integrationtestlib.log("Starting monitoring process on "+machine_name)
#run a command on the linux machine to find all the relevant processes
for command in command_list:
try:
relevant_processes, command_error = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE).communicate()
except:
integrationtestlib.handle_exception("Failed to run command: "+command)
sys.exit(1)
#make a string of all the processes
processes_string = processes_string+relevant_processes
print processes_string
#keeps track to see if any processes are down
critical_process_down=False
error_message="WARNING: Critical processes down! Seattle developers please start the processes up as soon as possible\n"
error_message=error_message+"Listing processes that are down:\n"
#goes through the list of monitor_process_list to ensure that all processes are running
for critical_process in monitor_process_list:
integrationtestlib.log("Checking process: "+critical_process+".......")
if not critical_process in processes_string:
critical_process_down=True
error_message = error_message+critical_process+" is down on "+machine_name+".poly.edu\n"
print "FAIL"
else:
print "PASS"
error_message=error_message+"end of list of processes that are down.\n................................"
if critical_process_down:
integrationtestlib.notify(error_message, "Critical process down!")
irc_seattlebot.send_msg(error_message)
else:
integrationtestlib.log("All critical processes on "+machine_name+" are up and running")
print(".........................................................")
def main():
success,explanation_str = send_gmail.init_gmail()
if not success:
integrationtestlib.log(explanation_str)
sys.exit(0)
command = "df -h | grep '/dev/sda' | awk '{print $5}'"
command_output_fd = os.popen(command)
# Get the output and get rid of the extra lines and % sign.
disk_use_percent = int(command_output_fd.read().split()[0][:-1])
hostname = socket.gethostname() + ".cs.washington.edu"
subject = "High disk usage"
if disk_use_percent > 95:
message = "CRITICAL: Very High Disk Usage on %s: %s percent used" % ( hostname, disk_use_percent)
integrationtestlib.notify(message, subject)
irc_seattlebot.send_msg(message)
elif disk_use_percent > 90:
message = "WARNING: High disk usage on %s: %s percent used" % ( hostname, disk_use_percent)
integrationtestlib.notify(message, subject)
def main():
success,explanation_str = send_gmail.init_gmail()
#integrationtestlib.notify_list=['*****@*****.**']
if not success:
integrationtestlib.log(explanation_str)
sys.exit(0)
command = "df -h | grep '/dev/sda' | awk '{print $5}'"
command_output_fd = os.popen(command)
# Get the output and get rid of the extra lines and % sign.
disk_use_percent = int(command_output_fd.read().split()[0][:-1])
command_output_fd.close()
disk_free_command = "df -h | grep '/dev/sda' | awk '{print $4}'"
disk_free_fd = os.popen(disk_free_command)
free_space = disk_free_fd.read()
disk_free_fd.close()
hostname = socket.gethostname() + ".poly.edu"
subject = "High disk usage"
if disk_use_percent >= 95:
message = "CRITICAL: Very High Disk Usage on %s: %s percent used.\n" % ( hostname, disk_use_percent)
message += "Disk space free: %s" % free_space
integrationtestlib.log(message)
integrationtestlib.notify(message, subject)
irc_seattlebot.send_msg(message)
elif disk_use_percent > 90:
message = "WARNING: High disk usage on %s: %s percent used.\n" % ( hostname, disk_use_percent)
message += "Disk space free: %s" % free_space
integrationtestlib.log(message)
integrationtestlib.notify(message, subject)
print "Current disk usage: %s percent" % disk_use_percent
print "Free disk space: %s" % free_space
def main():
success, explanation_str = send_gmail.init_gmail()
#integrationtestlib.notify_list=['*****@*****.**']
if not success:
integrationtestlib.log(explanation_str)
sys.exit(0)
command = "df -h | grep '/dev/sda' | awk '{print $5}'"
command_output_fd = os.popen(command)
# Get the output and get rid of the extra lines and % sign.
disk_use_percent = int(command_output_fd.read().split()[0][:-1])
command_output_fd.close()
disk_free_command = "df -h | grep '/dev/sda' | awk '{print $4}'"
disk_free_fd = os.popen(disk_free_command)
free_space = disk_free_fd.read()
disk_free_fd.close()
hostname = socket.gethostname() + ".poly.edu"
subject = "High disk usage"
if disk_use_percent >= 95:
message = "CRITICAL: Very High Disk Usage on %s: %s percent used.\n" % (
hostname, disk_use_percent)
message += "Disk space free: %s" % free_space
integrationtestlib.log(message)
integrationtestlib.notify(message, subject)
irc_seattlebot.send_msg(message)
elif disk_use_percent > 90:
message = "WARNING: High disk usage on %s: %s percent used.\n" % (
hostname, disk_use_percent)
message += "Disk space free: %s" % free_space
integrationtestlib.log(message)
integrationtestlib.notify(message, subject)
print "Current disk usage: %s percent" % disk_use_percent
print "Free disk space: %s" % free_space
def main():
"""
<Purpose>
Ping all the machines to see if they are up
<Exceptions>
none
<Side Effects>
Prints the ping result
<Returns>
None.
"""
# setup the gmail user/password to use when sending email
success, explanation_str = send_gmail.init_gmail()
if not success:
integrationtestlib.log(explanation_str)
sys.exit(0)
integrationtestlib.log("pinging critical machines")
#list of machines thats getting pinged
pinglist = []
#list that contains all the ping results
result_queue = []
#create a thread for each machine and ping them
for host in machine_list:
ping_current_machine = ping(str(host), result_queue)
pinglist.append(ping_current_machine)
ping_current_machine.start()
#join all the threads
for ping_host in pinglist:
ping_host.join()
#variable that keeps track if any machines are down
ALL_MACHINES_RUNNING = True
error_message = "WARNING: Seattle machines are down! Seattle developers please check on the machines.\n"
error_message += "Displaying ping result:\n"
#check to see if all the results were successful
#on failures notify the admins and send a message to the irc
for (success, ping_result) in result_queue:
if not success:
ALL_MACHINES_RUNNING = False
error_message += ping_result + "\n"
#if all machines were pinged successfully, notify on irc if option -m was used to run ping_machines.py
if ALL_MACHINES_RUNNING:
if len(sys.argv) >= 2 and sys.argv[1] == '-m':
irc_seattlebot.send_msg("The machines: " + str(machine_list) +
" were pinged successfully")
else:
integrationtestlib.notify(error_message, "Seattle machines down!")
irc_seattlebot.send_msg(error_message)
print time.ctime() + " : Done pinging all machiens."
print "--------------------------------------------"
def main():
"""
<Purpose>
Ping all the machines to see if they are up
<Exceptions>
none
<Side Effects>
Prints the ping result
<Returns>
None.
"""
# setup the gmail user/password to use when sending email
success,explanation_str = send_gmail.init_gmail()
if not success:
integrationtestlib.log(explanation_str)
sys.exit(0)
integrationtestlib.log("pinging critical machines")
#list of machines thats getting pinged
pinglist = []
#list that contains all the ping results
result_queue = []
#create a thread for each machine and ping them
for host in machine_list:
ping_current_machine = ping(str(host), result_queue)
pinglist.append(ping_current_machine)
ping_current_machine.start()
#join all the threads
for ping_host in pinglist:
ping_host.join()
#variable that keeps track if any machines are down
ALL_MACHINES_RUNNING = True
error_message="WARNING: Seattle machines are down! Seattle developers please check on the machines.\n"
error_message+="Displaying ping result:\n"
#check to see if all the results were successful
#on failures notify the admins and send a message to the irc
for (success, ping_result) in result_queue:
if not success:
ALL_MACHINES_RUNNING = False
error_message += ping_result+"\n"
#if all machines were pinged successfully, notify on irc if option -m was used to run ping_machines.py
if ALL_MACHINES_RUNNING:
if len(sys.argv) >= 2 and sys.argv[1] == '-m':
irc_seattlebot.send_msg("The machines: "+str(machine_list)+" were pinged successfully")
else:
integrationtestlib.notify(error_message, "Seattle machines down!")
irc_seattlebot.send_msg(error_message)
print time.ctime() + " : Done pinging all machiens."
print "--------------------------------------------"