monit: fix module detection of monitored process state (#1107)

* refactor and test

* require version >= 5.21.0

Prior to this version the status output was different

* python version compatability

* use exception classes from utils

* modify monit to use 'status' output instead of 'summary' output

The summary output is a fixed width table which truncates the
contents and prevents us from parsing the actual status of the
program.

* add integration tests + fixes

* remove unused handlers in monit integration test

* fix lint

* add '__metaclass__ = type' to integration python files

* raise AttributeError

* simplify status

* lint: add type to parameter docs

* remove lint ignore

* move monit process config into main file

* specify path to monit PID file

* set config location based on os_family

* create required directories

* update aliases to set group and skips

* add changelog

* add author

* add types to docs

* add EPEL repo

* custom vars for centos-6

* uninstall EPEL

* support older versions

* wait for status to change before exiting

* use 'validate' to force status updates

* handle 'execution failed'

* better status output for errors

* add more context to failure + standardize

* don't check rc for validate

* legacy string format support

* add integration test for 'reloaded' and 'present'

* don't wait after reload

* lint

* Revert "uninstall EPEL"

This reverts commit 4d548718d0.

* make 'present' more robust

* Apply suggestions from code review

Co-authored-by: Andrew Klychkov <aaklychkov@mail.ru>

* add license header

* drop daemon.py and use python-daemon instead

* skip python2.6 which is not supported by python-daemon

* refactor test tasks for reuse

* cleanup files after test

* lint

* start process before enabling monit

This shouldn't be necessary but I'm adding it in the hopes
it will make tests more robust.

* retry task

* attempt to rescue the task on failure

* fix indentation

* ignore check if rescue ran

* restart monit instead of reload

Co-authored-by: Andrew Klychkov <aaklychkov@mail.ru>
This commit is contained in:
Simon Kelly 2020-10-23 12:26:23 +02:00 committed by GitHub
parent 6d960e9e10
commit 8de1c0c205
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
21 changed files with 698 additions and 127 deletions

View file

@ -0,0 +1,8 @@
destructive
needs/target/setup_epel
shippable/posix/group2
skip/osx
skip/macos
skip/freebsd
skip/aix
skip/python2.6 # python-daemon package used in integration tests requires >=2.7

View file

@ -0,0 +1,4 @@
process_root: /opt/httpd_echo
process_file: "{{ process_root }}/httpd_echo.py"
process_venv: "{{ process_root }}/venv"
process_run_cmd: "{{ process_venv }}/bin/python {{ process_file }}"

View file

@ -0,0 +1,50 @@
# (c) 2020, Simon Kelly <simongdkelly@gmail.com>
# GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)
from __future__ import (absolute_import, division, print_function)
__metaclass__ = type
import daemon
try:
from BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer
def write_to_output(stream, content):
stream.write(content)
except ImportError:
from http.server import BaseHTTPRequestHandler, HTTPServer
def write_to_output(stream, content):
stream.write(bytes(content, "utf-8"))
hostname = "localhost"
server_port = 8082
class EchoServer(BaseHTTPRequestHandler):
def do_GET(self):
self.send_response(200)
self.send_header("Content-type", "text/plain")
self.end_headers()
write_to_output(self.wfile, self.path)
def run_webserver():
webServer = HTTPServer((hostname, server_port), EchoServer)
print("Server started http://%s:%s" % (hostname, server_port))
try:
webServer.serve_forever()
except KeyboardInterrupt:
pass
webServer.server_close()
print("Server stopped.")
if __name__ == "__main__":
context = daemon.DaemonContext()
with context:
run_webserver()

View file

@ -0,0 +1,2 @@
dependencies:
- setup_pkg_mgr

View file

@ -0,0 +1,20 @@
- name: "{{ reason }} ('up')"
command: "curl -sf http://localhost:8082/hello"
args:
warn: false
when: service_state == 'up'
register: curl_result
until: not curl_result.failed
retries: 5
delay: 1
- name: "{{ reason }} ('down')"
command: "curl -sf http://localhost:8082/hello"
args:
warn: false
register: curl_result
failed_when: curl_result == 0
when: service_state == 'down'
until: not curl_result.failed
retries: 5
delay: 1

View file

@ -0,0 +1,78 @@
####################################################################
# WARNING: These are designed specifically for Ansible tests #
# and should not be used as examples of how to write Ansible roles #
####################################################################
- block:
- name: Install EPEL repository (RHEL only)
include_role:
name: setup_epel
- name: create required directories
become: yes
file:
path: "{{ item }}"
state: directory
loop:
- /var/lib/monit
- /var/run/monit
- "{{ process_root }}"
- name: install monit
become: yes
package:
name: monit
state: present
- include_vars: '{{ item }}'
with_first_found:
- files:
- "{{ ansible_facts.distribution }}-{{ ansible_facts.distribution_major_version }}.yml"
- '{{ ansible_os_family }}.yml'
- 'defaults.yml'
- name: monit config
become: yes
template:
src: "monitrc.j2"
dest: "{{ monitrc }}"
- name: copy process file
become: yes
copy:
src: httpd_echo.py
dest: "{{ process_file }}"
- name: install dependencies
pip:
name: "{{ item }}"
virtualenv: "{{ process_venv }}"
loop:
- setuptools==44
- python-daemon
- name: restart monit
become: yes
service:
name: monit
state: restarted
- include_tasks: test.yml
always:
- name: stop monit
become: yes
service:
name: monit
state: stopped
- name: uninstall monit
become: yes
package:
name: monit
state: absent
- name: remove process files
file:
path: "{{ process_root }}"
state: absent

View file

@ -0,0 +1,28 @@
# order is important
- import_tasks: test_reload_present.yml
- import_tasks: test_state.yml
vars:
state: stopped
initial_state: up
expected_state: down
- import_tasks: test_state.yml
vars:
state: started
initial_state: down
expected_state: up
- import_tasks: test_state.yml
vars:
state: unmonitored
initial_state: up
expected_state: down
- import_tasks: test_state.yml
vars:
state: monitored
initial_state: down
expected_state: up
- import_tasks: test_errors.yml

View file

@ -0,0 +1,6 @@
- name: Check an error occurs when wrong process name is used
monit:
name: missing
state: started
register: result
failed_when: result is not skip and (result is success or result is not failed)

View file

@ -0,0 +1,60 @@
- name: reload monit when process is missing
monit:
name: httpd_echo
state: reloaded
register: result
- name: check that state is changed
assert:
that:
- result is success
- result is changed
- name: test process not present
monit:
name: httpd_echo
state: present
timeout: 5
register: result
failed_when: result is not skip and result is success
- name: test monitor missing process
monit:
name: httpd_echo
state: monitored
register: result
failed_when: result is not skip and result is success
- name: start process
shell: "{{ process_run_cmd }}"
- import_tasks: check_state.yml
vars:
reason: verify service running
service_state: "up"
- name: add process config
blockinfile:
path: "{{ monitrc }}"
block: |
check process httpd_echo with matching "httpd_echo"
start program = "{{ process_run_cmd }}"
stop program = "/bin/sh -c 'kill `pgrep -f httpd_echo`'"
if failed host localhost port 8082 then restart
- name: restart monit
service:
name: monit
state: restarted
- name: test process present again
monit:
name: httpd_echo
state: present
register: result
- name: check that state is unchanged
assert:
that:
- result is success
- result is not changed

View file

@ -0,0 +1,33 @@
- import_tasks: check_state.yml
vars:
reason: verify initial service state
service_state: "{{ initial_state }}"
- name: change httpd_echo process state to {{ state }}
monit:
name: httpd_echo
state: "{{ state }}"
register: result
- name: check that state changed
assert:
that:
- result is success
- result is changed
- import_tasks: check_state.yml
vars:
reason: check service state after action
service_state: "{{ expected_state }}"
- name: try change state again to {{ state }}
monit:
name: httpd_echo
state: "{{ state }}"
register: result
- name: check that state is not changed
assert:
that:
- result is success
- result is not changed

View file

@ -0,0 +1,13 @@
set daemon 2
set logfile /var/log/monit.log
set idfile /var/lib/monit/id
set statefile /var/lib/monit/state
set pidfile /var/run/monit.pid
set eventqueue
basedir /var/lib/monit/events
slots 100
set httpd port 2812 and
use address localhost
allow localhost

View file

@ -0,0 +1 @@
monitrc: "/etc/monit.conf"

View file

@ -0,0 +1 @@
monitrc: "/etc/monitrc"

View file

@ -0,0 +1 @@
monitrc: "/etc/monitrc"

View file

@ -0,0 +1 @@
monitrc: "/etc/monit/monitrc"