-
Notifications
You must be signed in to change notification settings - Fork 716
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[202205] Improve the cleanup of PTF container (#10523)
Cherry-pick #10069 and #10286 to 202205 branch. * Improve the cleanup of processes and interfaces before stopping PTF container (#10244 What is the motivation for this PR? We still observe issues with "testbed-cli.sh remove-topo" and "testbed-cli.sh restart-ptf": Server may crash and run into CPU softlock issue. Some exabgp process cannot be fully stopped and "restart-ptf" may fail. The expectation is that remove-topo and restart-ptf can always be successful. And of course, no server crash. Possible reason of server crash: Some exabgp processes are still running in PTF container while we remove the container. This could cause server crash. Some network interfaces are in the PTF container's network namespace while we remove the container. How did you do it? Added a customized module "ptf_control" to stop&kill processes running in PTF container in a more aggressive and reliable way. Improve the vm_topology module to remove network interfaces from the PTF container in the "unbind" procedure. Added a vm_topology "unbind" step in the "testbed-cli.sh restart-ptf" procedure. Updated some "ip link" commands to fully compliant with the syntax in "ip link help". How did you verify/test it? Tested the add-topo/remove-topo on both physical and KVM testbed. Tested restart-ptf on phsycial testbed. * Avoid running command in exited ptf docker container (#10286) While stopping PTF container, "ptf_control" module is executed to kill all processes in the PTF container. The original code checks if the PTF container's Pid exists before running command in the PTF container. Unfortunately, this check is not enough. PTF docker container in exited status still has Pid. This change improved the code for getting PTF container's Pid. When PTF container is not in "running" status, always return None for PTF container's Pid. Signed-off-by: Xin Wang <[email protected]>
- Loading branch information
Showing
5 changed files
with
246 additions
and
130 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,141 @@ | ||
| #!/usr/bin/python | ||
|
|
||
| import json | ||
| import logging | ||
| import traceback | ||
|
|
||
| import docker | ||
|
|
||
| from ansible.module_utils.debug_utils import config_module_logging | ||
| from ansible.module_utils.basic import AnsibleModule | ||
|
|
||
| DOCUMENTATION = ''' | ||
| --- | ||
| module: ptf_control | ||
| version_added: "0.1" | ||
| author: Xin Wang ([email protected]) | ||
| short_description: Control PTF container | ||
| description: For controlling PTF container, for example killing processes running in PTF container before stopping it. | ||
| Parameters: | ||
| - ctn_name: Name of the PTF container | ||
| - command: Command to run, currently only support "kill" | ||
| ''' | ||
|
|
||
| EXAMPLES = ''' | ||
| - name: Kill exabgp and ptf_nn_agent processes in PTF container | ||
| ptf_control: | ||
| ctn_name: "ptf_vms6-1" | ||
| command: kill | ||
| ''' | ||
|
|
||
|
|
||
| class PtfControl(object): | ||
| """This class is for controlling PTF container | ||
| """ | ||
|
|
||
| def __init__(self, module, ctn_name): | ||
| self.module = module | ||
| self.ctn_name = ctn_name | ||
|
|
||
| self.pid = PtfControl.get_pid(self.ctn_name) | ||
|
|
||
| def cmd(self, cmdline, use_unsafe_shell=False, ignore_failure=False, verbose=True): | ||
| rc, out, err = self.module.run_command(cmdline, use_unsafe_shell=use_unsafe_shell) | ||
| if verbose: | ||
| msg = { | ||
| 'cmd': cmdline, | ||
| 'rc': rc, | ||
| 'stdout_lines': out.splitlines(), | ||
| 'stderr_lines': err.splitlines() | ||
| } | ||
| logging.debug('***** RUN CMD:\n%s' % json.dumps(msg, indent=2)) | ||
|
|
||
| if rc != 0 and not ignore_failure: | ||
| raise Exception("Failed to run command: %s, rc=%d, out=%s, err=%s" % (cmdline, rc, out, err)) | ||
| return rc, out, err | ||
|
|
||
| @staticmethod | ||
| def get_pid(ctn_name): | ||
| cli = docker.from_env() | ||
| try: | ||
| ctn = cli.containers.get(ctn_name) | ||
| if ctn.status == 'running': | ||
| return ctn.attrs['State']['Pid'] | ||
| except Exception as e: | ||
| logging.debug("Failed to get pid for container %s: %s" % (ctn_name, str(e))) | ||
|
|
||
| return None | ||
|
|
||
| def get_process_pids(self, process): | ||
| cmd = 'docker exec -t {} bash -c "pgrep -f \'{}\'"'.format(self.ctn_name, process) | ||
| _, out, _ = self.cmd(cmd, ignore_failure=True) | ||
| return [int(pid.strip()) for pid in out.splitlines()] | ||
|
|
||
| def get_supervisord_processes(self): | ||
| _, out, _ = self.cmd( | ||
| 'docker exec -t {} bash -c "supervisorctl status"'.format(self.ctn_name), ignore_failure=True | ||
| ) | ||
| processes = [line.strip().split()[0] for line in out.splitlines() if "sshd" not in line] | ||
| return processes | ||
|
|
||
| def kill_process(self, pid): | ||
| self.cmd('docker exec -t {} bash -c "kill -9 {}"'.format(self.ctn_name, pid), ignore_failure=True) | ||
|
|
||
| def kill_processes(self): | ||
| supervisord_processes = self.get_supervisord_processes() | ||
| self.cmd('docker exec -t {} bash -c "ps -ef"'.format(self.ctn_name)) | ||
| for i in range(3): | ||
| logging.info("=== Attempt %d ===" % (i + 1)) | ||
| logging.info("=== Use supervisorctl to stop processes ===") | ||
| for process in supervisord_processes: | ||
| self.cmd( | ||
| 'docker exec -t {} bash -c "supervisorctl stop {}"'.format(self.ctn_name, process), | ||
| ignore_failure=True | ||
| ) | ||
| self.cmd( | ||
| 'docker exec -t {} bash -c "ps -ef"'.format(self.ctn_name) | ||
| ) | ||
|
|
||
| for pattern in [ | ||
| "/usr/share/exabgp/http_api.py", | ||
| "/usr/local/bin/exabgp", | ||
| "ptf_nn_agent.py" | ||
| ]: | ||
| logging.info("=== Kill process %s ===" % pattern) | ||
| for pid in self.get_process_pids(pattern): | ||
| self.kill_process(pid) | ||
|
|
||
| self.cmd('docker exec -t {} bash -c "ps -ef"'.format(self.ctn_name)) | ||
|
|
||
|
|
||
| def main(): | ||
| module = AnsibleModule( | ||
| argument_spec=dict( | ||
| ctn_name=dict(required=True, type='str'), | ||
| command=dict(required=True, type='str') | ||
| ), | ||
| supports_check_mode=False) | ||
|
|
||
| ctn_name = module.params['ctn_name'] | ||
| command = module.params['command'] | ||
| if command not in ['kill']: | ||
| module.fail_json(msg="command %s is not supported" % command) | ||
|
|
||
| config_module_logging('ptf_control_' + ctn_name) | ||
|
|
||
| try: | ||
| ptf = PtfControl(module, ctn_name) | ||
| if command == "kill": | ||
| if ptf.pid is not None: | ||
| ptf.kill_processes() | ||
| except Exception as error: | ||
| logging.error(traceback.format_exc()) | ||
| module.fail_json(msg=str(error)) | ||
|
|
||
| module.exit_json(changed=True) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| main() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.