sonic-buildimage/files/image_config/monit/memory_checker

174 lines
6.9 KiB
Plaintext
Raw Normal View History

#!/usr/bin/env python3
"""
memory_checker
This script is part of the feature which will restart the container if memory
usage of it is larger than the threshold value.
This script is used to check the memory usage of specified cotnainer and
is intended to be run by Monit. It will write an alerting message into
syslog if memory usage of the container is larger than the threshold value for X
times within Y cycles/minutes. Note that if print(...) statement in this script
was executed, the string in it will be appended to Monit syslog messages.
The following is an example in Monit configuration file to show how Monit will run
this script:
check program container_memory_<container_name> with path "/usr/bin/memory_checker <container_name> <threshold_value>"
if status == 3 for X times within Y cycles exec "/usr/bin/restart_service <container_name>"
"""
import argparse
import subprocess
import sys
import syslog
import re
import docker
from swsscommon import swsscommon
EVENTS_PUBLISHER_SOURCE = "sonic-events-host"
EVENTS_PUBLISHER_TAG = "mem-threshold-exceeded"
def get_command_result(command):
"""Executes the command and return the resulting output.
Args:
command: A string contains the command to be executed.
Returns:
A string which contains the output of command.
"""
command_stdout = ""
try:
proc_instance = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE,
universal_newlines=True)
command_stdout, command_stderr = proc_instance.communicate()
if proc_instance.returncode != 0:
syslog.syslog(syslog.LOG_ERR, "[memory_checker] Failed to execute the command '{}'. Return code: '{}'"
.format(command, proc_instance.returncode))
sys.exit(1)
except (OSError, ValueError) as err:
syslog.syslog(syslog.LOG_ERR, "[memory_checker] Failed to execute the command '{}'. Error: '{}'"
.format(command, err))
sys.exit(2)
return command_stdout.strip()
def publish_events(events_handle, container_name, mem_usage_bytes, threshold_value):
params = swsscommon.FieldValueMap()
params["ctr_name"] = container_name
params["mem_usage"] = mem_usage_bytes
params["threshold"] = threshold_value
swsscommon.event_publish(events_handle, EVENTS_PUBLISHER_TAG, params)
def check_memory_usage(events_handle, container_name, threshold_value):
"""Checks the memory usage of a container and writes an alerting messages into
the syslog if the memory usage is larger than the threshold value.
Args:
container_name: A string represtents name of a container
threshold_value: An integer indicates the threshold value (Bytes) of memory usage.
Returns:
None.
"""
command = ["docker", "stats", "--no-stream", "--format", "{{.MemUsage}}", container_name]
command_stdout = get_command_result(command)
mem_usage = command_stdout.split("/")[0].strip()
match_obj = re.match(r"\d+\.?\d*", mem_usage)
if match_obj:
mem_usage_value = float(mem_usage[match_obj.start():match_obj.end()])
mem_usage_unit = mem_usage[match_obj.end():]
mem_usage_bytes = 0.0
if mem_usage_unit == "B":
mem_usage_bytes = mem_usage_value
elif mem_usage_unit == "KiB":
mem_usage_bytes = mem_usage_value * 1024
elif mem_usage_unit == "MiB":
mem_usage_bytes = mem_usage_value * 1024 ** 2
elif mem_usage_unit == "GiB":
mem_usage_bytes = mem_usage_value * 1024 ** 3
if mem_usage_bytes > threshold_value:
print("[{}]: Memory usage ({} Bytes) is larger than the threshold ({} Bytes)!"
.format(container_name, mem_usage_bytes, threshold_value))
[Monit] Fix the issue which shows Monit can not reset its counter. (#10288) Signed-off-by: Yong Zhao <yozhao@microsoft.com> Why I did it This PR aims to fix the Monit issue which shows Monit can't reset its counter when monitoring memory usage of telemetry container. Specifically the Monit configuration file related to monitoring memory usage of telemetry container is as following: check program container_memory_telemetry with path "/usr/bin/memory_checker telemetry 419430400" if status == 3 for 10 times within 20 cycles then exec "/usr/bin/restart_service telemetry" If memory usage of telemetry container is larger than 400MB for 10 times within 20 cycles (minutes), then it will be restarted. Recently we observed, after telemetry container was restarted, its memory usage continuously increased from 400MB to 11GB within 1 hour, but it was not restarted anymore during this 1 hour sliding window. The reason is Monit can't reset its counter to count again and Monit can reset its counter if and only if the status of monitored service was changed from Status failed to Status ok. However, during this 1 hour sliding window, the status of monitored service was not changed from Status failed to Status ok. Currently for each service monitored by Monit, there will be an entry showing the monitoring status, monitoring mode etc. For example, the following output from command sudo monit status shows the status of monitored service to monitor memory usage of telemetry: Program 'container_memory_telemetry' status Status ok monitoring status Monitored monitoring mode active on reboot start last exit value 0 last output - data collected Sat, 19 Mar 2022 19:56:26 Every 1 minute, Monit will run the script to check the memory usage of telemetry and update the counter if memory usage is larger than 400MB. If Monit checked the counter and found memory usage of telemetry is larger than 400MB for 10 times within 20 minutes, then telemetry container was restarted. Following is an example status of monitored service: Program 'container_memory_telemetry' status Status failed monitoring status Monitored monitoring mode active on reboot start last exit value 0 last output - data collected Tue, 01 Feb 2022 22:52:55 After telemetry container was restarted. we found memory usage of telemetry increased rapidly from around 100MB to more than 400MB during 1 minute and status of monitored service did not have a chance to be changed from Status failed to Status ok. How I did it In order to provide a workaround for this issue, Monit recently introduced another syntax format repeat every <n> cycles related to exec. This new syntax format will enable Monit repeat executing the background script if the error persists for a given number of cycles. How to verify it I verified this change on lab device str-s6000-acs-12. Another pytest PR (Azure/sonic-mgmt#5492) is submitted in sonic-mgmt repo for review.
2022-04-20 20:08:06 -05:00
syslog.syslog(syslog.LOG_INFO, "[{}]: Memory usage ({} Bytes) is larger than the threshold ({} Bytes)!"
.format(container_name, mem_usage_bytes, threshold_value))
# publish event
publish_events(events_handle, container_name, str(mem_usage_bytes), str(threshold_value))
sys.exit(3)
else:
syslog.syslog(syslog.LOG_ERR, "[memory_checker] Failed to retrieve memory value from '{}'"
.format(mem_usage))
sys.exit(4)
def is_service_active(service_name):
"""Test if service is running.
Args:
service_name: A string contains the service name
Returns:
True if service is running, False otherwise
"""
status = subprocess.run(["systemctl", "is-active", "--quiet", service_name])
return status.returncode == 0
def get_running_container_names():
"""Retrieves names of running containers by talking to the docker daemon.
Args:
None.
Returns:
running_container_names: A list indicates names of running containers.
"""
try:
docker_client = docker.DockerClient(base_url='unix://var/run/docker.sock')
running_container_list = docker_client.containers.list(filters={"status": "running"})
running_container_names = [ container.name for container in running_container_list ]
except (docker.errors.APIError, docker.errors.DockerException) as err:
syslog.syslog(syslog.LOG_ERR,
"Failed to retrieve the running container list from docker daemon! Error message is: '{}'"
.format(err))
sys.exit(5)
return running_container_names
def main():
parser = argparse.ArgumentParser(description="Check memory usage of a container \
and an alerting message will be written into syslog if memory usage \
is larger than the threshold value", usage="/usr/bin/memory_checker <container_name> <threshold_value_in_bytes>")
parser.add_argument("container_name", help="container name")
# TODO: Currently the threshold value is hard coded as a command line argument and will
# remove this in the new version since we want to read this value from 'CONFIG_DB'.
parser.add_argument("threshold_value", type=int, help="threshold value in bytes")
args = parser.parse_args()
if not is_service_active("docker"):
syslog.syslog(syslog.LOG_INFO,
"[memory_checker] Exits without checking memory usage of container '{}' since docker daemon is not running!"
.format(args.container_name))
sys.exit(0)
running_container_names = get_running_container_names()
events_handle = swsscommon.events_init_publisher(EVENTS_PUBLISHER_SOURCE)
if args.container_name in running_container_names:
check_memory_usage(events_handle, args.container_name, args.threshold_value)
else:
syslog.syslog(syslog.LOG_INFO,
"[memory_checker] Exits without checking memory usage since container '{}' is not running!"
.format(args.container_name))
swsscommon.events_deinit_publisher(events_handle)
if __name__ == "__main__":
main()