#!/usr/bin/python3

DEFAULT_IMAGE='docker.io/ceph/ceph:v15'
DATA_DIR='/var/lib/ceph'
LOG_DIR='/var/log/ceph'
LOCK_DIR='/run/cephadm'
LOGROTATE_DIR='/etc/logrotate.d'
UNIT_DIR='/etc/systemd/system'
LOG_DIR_MODE=0o770
DATA_DIR_MODE=0o700
CONTAINER_PREFERENCE = ['podman', 'docker']  # prefer podman to docker
CUSTOM_PS1=r'[ceph: \u@\h \W]\$ '
DEFAULT_TIMEOUT=None # in seconds
DEFAULT_RETRY=10
SHELL_DEFAULT_CONF='/etc/ceph/ceph.conf'
SHELL_DEFAULT_KEYRING='/etc/ceph/ceph.client.admin.keyring'

"""
You can invoke cephadm in two ways:

1. The normal way, at the command line.

2. By piping the script to the python3 binary.  In this latter case, you should
   prepend one or more lines to the beginning of the script.

   For arguments,

       injected_argv = [...]

   e.g.,

       injected_argv = ['ls']

   For reading stdin from the '--config-json -' argument,

       injected_stdin = '...'
"""

import argparse
import datetime
import fcntl
import json
import logging
import os
import platform
import random
import re
import select
import shutil
import socket
import string
import subprocess
import sys
import tempfile
import time
import errno
try:
    from typing import Dict, List, Tuple, Optional, Union, Any, NoReturn, Callable
except ImportError:
    pass
import uuid

from functools import wraps
from glob import glob
from threading import Thread

if sys.version_info >= (3, 0):
    from io import StringIO
else:
    from StringIO import StringIO

if sys.version_info >= (3, 2):
    from configparser import ConfigParser
else:
    from ConfigParser import SafeConfigParser

if sys.version_info >= (3, 0):
    from urllib.request import urlopen
    from urllib.error import HTTPError
else:
    from urllib2 import urlopen, HTTPError

container_path = ''
cached_stdin = None

DATEFMT = '%Y-%m-%dT%H:%M:%S.%f'

class Error(Exception):
    pass

class TimeoutExpired(Error):
    pass

##################################

class Ceph(object):
    daemons = ('mon', 'mgr', 'mds', 'osd', 'rgw', 'rbd-mirror',
               'crash')

##################################

class Monitoring(object):
    """Define the configs for the monitoring containers"""

    port_map = {
        "prometheus": [9095],  # Avoid default 9090, due to conflict with cockpit UI
        "node-exporter": [9100],
        "grafana": [3000],
        "alertmanager": [9093, 9094],
    }

    components = {
        "prometheus": {
            "image": "prom/prometheus:latest",
            "cpus": '2',
            "memory": '4GB',
            "args": [
                "--config.file=/etc/prometheus/prometheus.yml",
                "--storage.tsdb.path=/prometheus",
                "--web.listen-address=:{}".format(port_map['prometheus'][0]),
            ],
            "config-json-files": [
                "prometheus.yml",
            ],
        },
        "node-exporter": {
            "image": "prom/node-exporter",
            "cpus": "1",
            "memory": "1GB",
            "args": [
                "--no-collector.timex",
            ],
        },
        "grafana": {
            "image": "ceph/ceph-grafana:latest",
            "cpus": "2",
            "memory": "4GB",
            "args": [],
            "config-json-files": [
                "grafana.ini",
                "provisioning/datasources/ceph-dashboard.yml",
                "certs/cert_file",
                "certs/cert_key",
            ],
        },
        "alertmanager": {
            "image": "prom/alertmanager",
            "cpus": "2",
            "memory": "2GB",
            "args": [],
            "config-json-files": [
                "alertmanager.yml",
            ],
            "config-json-args": [
                "peers",
            ],
        },
    }  # type: ignore

##################################

class NFSGanesha(object):
    """Defines a NFS-Ganesha container"""

    daemon_type = 'nfs'
    entrypoint = '/usr/bin/ganesha.nfsd'
    daemon_args = ['-F', '-L', 'STDERR']

    required_files = ['ganesha.conf']

    port_map = {
        "nfs" : 2049,
    }

    def __init__(self,
                 fsid,
                 daemon_id,
                 config_json,
                 image=DEFAULT_IMAGE):
        # type: (str, Union[int, str], Dict, str) -> None
        self.fsid = fsid
        self.daemon_id = daemon_id
        self.image = image

        def json_get(key, default=None, require=False):
            if require and not key in config_json.keys():
                raise Error('{} missing from config-json'.format(key))
            return config_json.get(key, default)

        # config-json options
        self.pool = json_get('pool', require=True)
        self.namespace = json_get('namespace')
        self.files = json_get('files', {})

        # validate the supplied args
        self.validate()

    @classmethod
    def init(cls, fsid, daemon_id):
        # type: (str, Union[int, str]) -> NFSGanesha
        return cls(fsid, daemon_id, get_parm(args.config_json), args.image)

    @staticmethod
    def port_in_use():
        # type () -> None
        for (srv, port) in NFSGanesha.port_map.items():
            if port_in_use(port):
                msg = 'TCP port {} required for {} is already in use'.format(port, srv)
                raise Error(msg)

    @staticmethod
    def get_container_mounts(data_dir):
        # type: (str) -> Dict[str, str]
        mounts = dict()
        mounts[os.path.join(data_dir, 'config')] = '/etc/ceph/ceph.conf:z'
        mounts[os.path.join(data_dir, 'keyring')] = '/etc/ceph/keyring:z'
        mounts[os.path.join(data_dir, 'etc/ganesha')] = '/etc/ganesha:z'
        return mounts

    @staticmethod
    def get_container_envs():
        # type: () -> List[str]
        envs = [
            'CEPH_CONF=%s' % ('/etc/ceph/ceph.conf')
        ]
        return envs

    @staticmethod
    def get_version(container_id):
        # type(str) -> Optional[str]
        version = None
        out, err, code = call(
            [container_path, 'exec', container_id,
             NFSGanesha.entrypoint, '-v'])
        if code == 0:
            match = re.search(r'NFS-Ganesha Release\s*=\s*[V]*([\d.]+)', out)
            if match:
                version = match.group(1)
        return version

    def validate(self):
        # type () -> None
        if not is_fsid(self.fsid):
            raise Error('not an fsid: %s' % self.fsid)
        if not self.daemon_id:
            raise Error('invalid daemon_id: %s' % self.daemon_id)
        if not self.image:
            raise Error('invalid image: %s' % self.image)

        # check for the required files
        if self.required_files:
            for fname in self.required_files:
                if fname not in self.files:
                    raise Error('required file missing from config-json: %s' % fname)

    def get_daemon_name(self):
        # type: () -> str
        return '%s.%s' % (self.daemon_type, self.daemon_id)

    def get_container_name(self, desc=None):
        # type: (Optional[str]) -> str
        cname = 'ceph-%s-%s' % (self.fsid, self.get_daemon_name())
        if desc:
            cname = '%s-%s' % (cname, desc)
        return cname

    def get_file_content(self, fname):
        # type: (str) -> str
        """Normalize the json file content into a string"""
        content = self.files.get(fname)
        if isinstance(content, list):
            content = '\n'.join(content)
        return content

    def create_daemon_dirs(self, data_dir, uid, gid):
        # type: (str, int, int) -> None
        """Create files under the container data dir"""
        if not os.path.isdir(data_dir):
            raise OSError('data_dir is not a directory: %s' % (data_dir))

        logger.info('Creating ganesha config...')

        # create the ganesha conf dir
        config_dir = os.path.join(data_dir, 'etc/ganesha')
        makedirs(config_dir, uid, gid, 0o755)

        # populate files from the config-json
        for fname in self.files:
            config_file = os.path.join(config_dir, fname)
            config_content = self.get_file_content(fname)
            logger.info('Write file: %s' % (config_file))
            with open(config_file, 'w') as f:
                os.fchown(f.fileno(), uid, gid)
                os.fchmod(f.fileno(), 0o600)
                f.write(config_content)

    def get_rados_grace_container(self, action):
        # type: (str) -> CephContainer
        """Container for a ganesha action on the grace db"""
        entrypoint = '/usr/bin/ganesha-rados-grace'

        assert self.pool
        args=['--pool', self.pool]
        if self.namespace:
            args += ['--ns', self.namespace]
        args += [action, self.get_daemon_name()]

        data_dir = get_data_dir(self.fsid, self.daemon_type, self.daemon_id)
        volume_mounts = self.get_container_mounts(data_dir)
        envs = self.get_container_envs()

        logger.info('Creating RADOS grace for action: %s' % (action))
        c = CephContainer(
            image=self.image,
            entrypoint=entrypoint,
            args=args,
            volume_mounts=volume_mounts,
            cname=self.get_container_name(desc='grace-%s' % (action)),
            envs=envs
        )
        return c

##################################

def get_supported_daemons():
    supported_daemons = list(Ceph.daemons)
    supported_daemons.extend(Monitoring.components)
    supported_daemons.append(NFSGanesha.daemon_type)
    assert len(supported_daemons) == len(set(supported_daemons))
    return supported_daemons

##################################

def attempt_bind(s, address, port):
    # type (str) -> None
    try:
        s.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
        s.bind((address, port))
    except (socket.error, OSError) as e:  # py2 and py3
        msg = 'Cannot bind to IP %s port %d: %s' % (address, port, e)
        logger.warning(msg)
        if e.errno == errno.EADDRINUSE:
            raise OSError(msg)
        elif e.errno == errno.EADDRNOTAVAIL:
            pass
    finally:
        s.close()

def port_in_use(port_num):
    # type (int) -> bool
    """Detect whether a port is in use on the local machine - IPv4 and IPv6"""
    logger.info('Verifying port %d ...' % (port_num))
    try:
        s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        attempt_bind(s, '0.0.0.0', port_num)

        s = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
        attempt_bind(s, '::', port_num)
    except OSError:
        return True
    else:
        return False

def check_ip_port(ip, port):
    if not args.skip_ping_check:
        logger.info('Verifying IP %s port %d ...' % (ip, port))
        if ip.startswith('[') or '::' in ip:
            s = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
        else:
            s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        try:
            attempt_bind(s, ip, port)
        except OSError as e:
            raise Error(e)

##################################

# this is an abbreviated version of
# https://github.com/benediktschmitt/py-filelock/blob/master/filelock.py
# that drops all of the compatibility (this is Unix/Linux only).

try:
    TimeoutError
except NameError:
    TimeoutError = OSError

class Timeout(TimeoutError):
    """
    Raised when the lock could not be acquired in *timeout*
    seconds.
    """

    def __init__(self, lock_file):
        """
        """
        #: The path of the file lock.
        self.lock_file = lock_file
        return None

    def __str__(self):
        temp = "The file lock '{}' could not be acquired."\
               .format(self.lock_file)
        return temp


class _Acquire_ReturnProxy(object):
    def __init__(self, lock):
        self.lock = lock
        return None

    def __enter__(self):
        return self.lock

    def __exit__(self, exc_type, exc_value, traceback):
        self.lock.release()
        return None


class FileLock(object):
    def __init__(self, name, timeout = -1):
        if not os.path.exists(LOCK_DIR):
            os.mkdir(LOCK_DIR, 0o700)
        self._lock_file = os.path.join(LOCK_DIR, name + '.lock')

        # The file descriptor for the *_lock_file* as it is returned by the
        # os.open() function.
        # This file lock is only NOT None, if the object currently holds the
        # lock.
        self._lock_file_fd = None
        self.timeout = timeout
        # The lock counter is used for implementing the nested locking
        # mechanism. Whenever the lock is acquired, the counter is increased and
        # the lock is only released, when this value is 0 again.
        self._lock_counter = 0
        return None

    @property
    def is_locked(self):
        return self._lock_file_fd is not None

    def acquire(self, timeout=None, poll_intervall=0.05):
        """
        Acquires the file lock or fails with a :exc:`Timeout` error.
        .. code-block:: python
            # You can use this method in the context manager (recommended)
            with lock.acquire():
                pass
            # Or use an equivalent try-finally construct:
            lock.acquire()
            try:
                pass
            finally:
                lock.release()
        :arg float timeout:
            The maximum time waited for the file lock.
            If ``timeout < 0``, there is no timeout and this method will
            block until the lock could be acquired.
            If ``timeout`` is None, the default :attr:`~timeout` is used.
        :arg float poll_intervall:
            We check once in *poll_intervall* seconds if we can acquire the
            file lock.
        :raises Timeout:
            if the lock could not be acquired in *timeout* seconds.
        .. versionchanged:: 2.0.0
            This method returns now a *proxy* object instead of *self*,
            so that it can be used in a with statement without side effects.
        """
        # Use the default timeout, if no timeout is provided.
        if timeout is None:
            timeout = self.timeout

        # Increment the number right at the beginning.
        # We can still undo it, if something fails.
        self._lock_counter += 1

        lock_id = id(self)
        lock_filename = self._lock_file
        start_time = time.time()
        try:
            while True:
                if not self.is_locked:
                    logger.debug('Acquiring lock %s on %s', lock_id,
                                 lock_filename)
                    self._acquire()

                if self.is_locked:
                    logger.debug('Lock %s acquired on %s', lock_id,
                                 lock_filename)
                    break
                elif timeout >= 0 and time.time() - start_time > timeout:
                    logger.warning('Timeout acquiring lock %s on %s', lock_id,
                                   lock_filename)
                    raise Timeout(self._lock_file)
                else:
                    logger.debug(
                        'Lock %s not acquired on %s, waiting %s seconds ...',
                        lock_id, lock_filename, poll_intervall
                    )
                    time.sleep(poll_intervall)
        except:
            # Something did go wrong, so decrement the counter.
            self._lock_counter = max(0, self._lock_counter - 1)

            raise
        return _Acquire_ReturnProxy(lock = self)

    def release(self, force = False):
        """
        Releases the file lock.
        Please note, that the lock is only completly released, if the lock
        counter is 0.
        Also note, that the lock file itself is not automatically deleted.
        :arg bool force:
            If true, the lock counter is ignored and the lock is released in
            every case.
        """
        if self.is_locked:
            self._lock_counter -= 1

            if self._lock_counter == 0 or force:
                lock_id = id(self)
                lock_filename = self._lock_file

                logger.debug('Releasing lock %s on %s', lock_id, lock_filename)
                self._release()
                self._lock_counter = 0
                logger.debug('Lock %s released on %s', lock_id, lock_filename)

        return None

    def __enter__(self):
        self.acquire()
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self.release()
        return None

    def __del__(self):
        self.release(force = True)
        return None


    def _acquire(self):
        open_mode = os.O_RDWR | os.O_CREAT | os.O_TRUNC
        fd = os.open(self._lock_file, open_mode)

        try:
            fcntl.flock(fd, fcntl.LOCK_EX | fcntl.LOCK_NB)
        except (IOError, OSError):
            os.close(fd)
        else:
            self._lock_file_fd = fd
        return None

    def _release(self):
        # Do not remove the lockfile:
        #
        #   https://github.com/benediktschmitt/py-filelock/issues/31
        #   https://stackoverflow.com/questions/17708885/flock-removing-locked-file-without-race-condition
        fd = self._lock_file_fd
        self._lock_file_fd = None
        fcntl.flock(fd, fcntl.LOCK_UN)
        os.close(fd)
        return None


##################################
# Popen wrappers, lifted from ceph-volume

def call(command,  # type: List[str]
         desc=None,  # type: Optional[str]
         verbose=False,  # type: bool
         verbose_on_failure=True,  # type: bool
         timeout=DEFAULT_TIMEOUT,  # type: Optional[int]
         **kwargs):
    """
    Wrap subprocess.Popen to

    - log stdout/stderr to a logger,
    - decode utf-8
    - cleanly return out, err, returncode

    If verbose=True, log at info (instead of debug) level.

    :param verbose_on_failure: On a non-zero exit status, it will forcefully set
                               logging ON for the terminal
    :param timeout: timeout in seconds
    """
    if not desc:
        desc = command[0]
    timeout = timeout or args.timeout

    logger.debug("Running command: %s" % ' '.join(command))
    process = subprocess.Popen(
        command,
        stdout=subprocess.PIPE,
        stderr=subprocess.PIPE,
        close_fds=True,
        **kwargs
    )
    # get current p.stdout flags, add O_NONBLOCK
    assert process.stdout is not None
    assert process.stderr is not None
    stdout_flags = fcntl.fcntl(process.stdout, fcntl.F_GETFL)
    stderr_flags = fcntl.fcntl(process.stderr, fcntl.F_GETFL)
    fcntl.fcntl(process.stdout, fcntl.F_SETFL, stdout_flags | os.O_NONBLOCK)
    fcntl.fcntl(process.stderr, fcntl.F_SETFL, stderr_flags | os.O_NONBLOCK)

    out = ''
    err = ''
    reads = None
    stop = False
    out_buffer = ''   # partial line (no newline yet)
    err_buffer = ''   # partial line (no newline yet)
    start_time = time.time()
    end_time = None
    if timeout:
        end_time = start_time + timeout
    while not stop:
        if end_time and (time.time() >= end_time):
            logger.info(desc + ':timeout after %s seconds' % timeout)
            stop = True
            process.kill()
        if reads and process.poll() is not None:
            # we want to stop, but first read off anything remaining
            # on stdout/stderr
            stop = True
        else:
            reads, _, _ = select.select(
                [process.stdout.fileno(), process.stderr.fileno()],
                [], [], timeout
            )
        for fd in reads:
            try:
                message_b = os.read(fd, 1024)
                if isinstance(message_b, bytes):
                    message = message_b.decode('utf-8')
                if isinstance(message_b, str):
                    message = message_b
                if stop and message:
                    # process has terminated, but have more to read still, so not stopping yet
                    # (os.read returns '' when it encounters EOF)
                    stop = False
                if not message:
                    continue
                if fd == process.stdout.fileno():
                    out += message
                    message = out_buffer + message
                    lines = message.split('\n')
                    out_buffer = lines.pop()
                    for line in lines:
                        if verbose:
                            logger.info(desc + ':stdout ' + line)
                        else:
                            logger.debug(desc + ':stdout ' + line)
                elif fd == process.stderr.fileno():
                    err += message
                    message = err_buffer + message
                    lines = message.split('\n')
                    err_buffer = lines.pop()
                    for line in lines:
                        if verbose:
                            logger.info(desc + ':stderr ' + line)
                        else:
                            logger.debug(desc + ':stderr ' + line)
                else:
                    assert False
            except (IOError, OSError):
                pass

    returncode = process.wait()

    if out_buffer != '':
        if verbose:
            logger.info(desc + ':stdout ' + out_buffer)
        else:
            logger.debug(desc + ':stdout ' + out_buffer)
    if err_buffer != '':
        if verbose:
            logger.info(desc + ':stderr ' + err_buffer)
        else:
            logger.debug(desc + ':stderr ' + err_buffer)

    if returncode != 0 and verbose_on_failure and not verbose:
        # dump stdout + stderr
        logger.info('Non-zero exit code %d from %s' % (returncode, ' '.join(command)))
        for line in out.splitlines():
            logger.info(desc + ':stdout ' + line)
        for line in err.splitlines():
            logger.info(desc + ':stderr ' + line)

    return out, err, returncode


def call_throws(command, **kwargs):
    # type: (List[str], Any) -> Tuple[str, str, int]
    out, err, ret = call(command, **kwargs)
    if ret:
        raise RuntimeError('Failed command: %s' % ' '.join(command))
    return out, err, ret


def call_timeout(command, timeout):
    # type: (List[str], int) -> int

    logger.debug('Running command (timeout=%s): %s'
            % (timeout, ' '.join(command)))

    def raise_timeout(command, timeout):
        # type: (List[str], int) -> NoReturn
        msg = 'Command \'%s\' timed out after %s seconds' % (command, timeout)
        logger.debug(msg)
        raise TimeoutExpired(msg)

    def call_timeout_py2(command, timeout):
        # type: (List[str], int) -> int
        proc = subprocess.Popen(command)
        thread = Thread(target=proc.wait)
        thread.start()
        thread.join(timeout)
        if thread.is_alive():
            proc.kill()
            thread.join()
            raise_timeout(command, timeout)
        return proc.returncode

    def call_timeout_py3(command, timeout):
        # type: (List[str], int) -> int
        try:
            return subprocess.call(command, timeout=timeout)
        except subprocess.TimeoutExpired as e:
            raise_timeout(command, timeout)

    ret = 1
    if sys.version_info >= (3, 3):
        ret = call_timeout_py3(command, timeout)
    else:
        # py2 subprocess has no timeout arg
        ret = call_timeout_py2(command, timeout)
    return ret

##################################

def is_available(what, func):
    # type: (str, Callable[[], bool]) -> None
    """
    Wait for a service to become available

    :param what: the name of the service
    :param func: the callable object that determines availability
    """
    retry = args.retry
    logger.info('Waiting for %s...' % (what))
    num = 1
    while True:
        if func():
            break
        elif num > retry:
            raise Error('%s not available after %s tries'
                    % (what, retry))

        logger.info('%s not available, waiting (%s/%s)...'
                % (what, num, retry))

        num += 1
        time.sleep(1)


def read_config(fn):
    # type: (Optional[str]) -> ConfigParser
    # bend over backwards here because py2's ConfigParser doesn't like
    # whitespace before config option names (e.g., '\n foo = bar\n').
    # Yeesh!
    if sys.version_info >= (3, 2):
        cp = ConfigParser()
    else:
        cp = SafeConfigParser()

    if fn:
        with open(fn, 'r') as f:
            raw_conf = f.read()
        nice_conf = re.sub(r'\n(\s)+', r'\n', raw_conf)
        s_io = StringIO(nice_conf)
        if sys.version_info >= (3, 2):
            cp.read_file(s_io)
        else:
            cp.readfp(s_io)

    return cp

def pathify(p):
    # type: (str) -> str
    if not p.startswith('/'):
        return os.path.join(os.getcwd(), p)
    return p

def get_file_timestamp(fn):
    try:
        mt = os.path.getmtime(fn)
        return datetime.datetime.fromtimestamp(
            mt, tz=datetime.timezone.utc
        ).strftime(DATEFMT)
    except Exception as e:
        return None

def try_convert_datetime(s):
    # This is super irritating because
    #  1) podman and docker use different formats
    #  2) python's strptime can't parse either one
    #
    # I've seen:
    #  docker 18.09.7:  2020-03-03T09:21:43.636153304Z
    #  podman 1.7.0:    2020-03-03T15:52:30.136257504-06:00
    #                   2020-03-03 15:52:30.136257504 -0600 CST
    # (In the podman case, there is a different string format for
    # 'inspect' and 'inspect --format {{.Created}}'!!)

    # In *all* cases, the 9 digit second precision is too much for
    # python's strptime.  Shorten it to 6 digits.
    p = re.compile(r'(\.[\d]{6})[\d]*')
    s = p.sub(r'\1', s)

    # replace trailling Z with -0000, since (on python 3.6.8) it won't parse
    if s and s[-1] == 'Z':
        s = s[:-1] + '-0000'

    # cut off the redundnat 'CST' part that strptime can't parse, if
    # present.
    v = s.split(' ')
    s = ' '.join(v[0:3])

    # try parsing with several format strings
    fmts = [
        '%Y-%m-%dT%H:%M:%S.%f%z',
        '%Y-%m-%d %H:%M:%S.%f %z',
    ]
    for f in fmts:
        try:
            # return timestamp normalized to UTC, rendered as DATEFMT.
            return datetime.datetime.strptime(s, f).astimezone(tz=datetime.timezone.utc).strftime(DATEFMT)
        except ValueError:
            pass
    return None

def get_podman_version():
    # type: () -> Tuple[int, ...]
    if 'podman' not in container_path:
        raise ValueError('not using podman')
    out, _, _ = call_throws([container_path, '--version'])
    return _parse_podman_version(out)

def _parse_podman_version(out):
    # type: (str) -> Tuple[int, ...]
    _, _, version_str = out.strip().split()

    def to_int(val, org_e=None):
        if not val and org_e:
            raise org_e
        try:
            return int(val)
        except ValueError as e:
            return to_int(val[0:-1], org_e or e)

    return tuple(map(to_int, version_str.split('.')))


def get_hostname():
    # type: () -> str
    return socket.gethostname()

def get_fqdn():
    # type: () -> str
    return socket.getfqdn() or socket.gethostname()

def get_arch():
    # type: () -> str
    return platform.uname().machine

def generate_service_id():
    # type: () -> str
    return get_hostname() + '.' + ''.join(random.choice(string.ascii_lowercase)
                                          for _ in range(6))

def generate_password():
    # type: () -> str
    return ''.join(random.choice(string.ascii_lowercase + string.digits)
                   for i in range(10))

def normalize_container_id(i):
    # type: (str) -> str
    # docker adds the sha256: prefix, but AFAICS both
    # docker (18.09.7 in bionic at least) and podman
    # both always use sha256, so leave off the prefix
    # for consistency.
    prefix = 'sha256:'
    if i.startswith(prefix):
        i = i[len(prefix):]
    return i

def make_fsid():
    # type: () -> str
    return str(uuid.uuid1())

def is_fsid(s):
    # type: (str) -> bool
    try:
        uuid.UUID(s)
    except ValueError:
        return False
    return True

def infer_fsid(func):
    """
    If we only find a single fsid in /var/lib/ceph/*, use that
    """
    @wraps(func)
    def _infer_fsid():
        if args.fsid:
            logger.debug('Using specified fsid: %s' % args.fsid)
            return func()

        fsids = set()
        daemon_list = list_daemons(detail=False)
        for daemon in daemon_list:
            if 'name' not in args or not args.name:
                fsids.add(daemon['fsid'])
            elif daemon['name'] == args.name:
                fsids.add(daemon['fsid'])
        fsids = list(fsids)

        if not fsids:
            # some commands do not always require an fsid
            pass
        elif len(fsids) == 1:
            logger.info('Inferring fsid %s' % fsids[0])
            args.fsid = fsids[0]
        else:
            raise Error('Cannot infer an fsid, one must be specified: %s' % fsids)
        return func()

    return _infer_fsid

def infer_image(func):
    """
    Use the most recent ceph image
    """
    @wraps(func)
    def _infer_image():
        if not args.image:
            args.image = os.environ.get('CEPHADM_IMAGE')
        if not args.image:
            args.image = get_last_local_ceph_image()
        if not args.image:
            args.image = DEFAULT_IMAGE
        return func()

    return _infer_image

def default_image(func):
    @wraps(func)
    def _default_image():
        if not args.image:
            if 'name' in args and args.name:
                type_ = args.name.split('.', 1)[0]
                if type_ in Monitoring.components:
                    args.image = Monitoring.components[type_]['image']
            if not args.image:
                args.image = os.environ.get('CEPHADM_IMAGE')
            if not args.image:
                args.image = DEFAULT_IMAGE
        return func()

    return _default_image

def get_last_local_ceph_image():
    """
    :return: The most recent local ceph image (already pulled)
    """
    out, _, _ = call_throws(
        [container_path, 'images',
         '--filter', 'label=ceph=True',
         '--format', '{{.Repository}} {{.Tag}}'])
    out_lines = out.splitlines()
    if len(out_lines) > 0:
        repository, tag = out_lines[0].split()
        r = '{}:{}'.format(repository, tag)
        logger.info('Using recent ceph image %s' % r)
        return r
    return None

def write_tmp(s, uid, gid):
    tmp_f = tempfile.NamedTemporaryFile(mode='w',
                                        prefix='ceph-tmp')
    os.fchown(tmp_f.fileno(), uid, gid)
    tmp_f.write(s)
    tmp_f.flush()

    return tmp_f

def makedirs(dir, uid, gid, mode):
    # type: (str, int, int, int) -> None
    if not os.path.exists(dir):
        os.makedirs(dir, mode=mode)
    else:
        os.chmod(dir, mode)
    os.chown(dir, uid, gid)
    os.chmod(dir, mode)   # the above is masked by umask...

def get_data_dir(fsid, t, n):
    # type: (str, str, Union[int, str]) -> str
    return os.path.join(args.data_dir, fsid, '%s.%s' % (t, n))

def get_log_dir(fsid):
    # type: (str) -> str
    return os.path.join(args.log_dir, fsid)

def make_data_dir_base(fsid, uid, gid):
    # type: (str, int, int) -> str
    data_dir_base = os.path.join(args.data_dir, fsid)
    makedirs(data_dir_base, uid, gid, DATA_DIR_MODE)
    makedirs(os.path.join(data_dir_base, 'crash'), uid, gid, DATA_DIR_MODE)
    makedirs(os.path.join(data_dir_base, 'crash', 'posted'), uid, gid,
             DATA_DIR_MODE)
    return data_dir_base

def make_data_dir(fsid, daemon_type, daemon_id, uid=None, gid=None):
    # type: (str, str, Union[int, str], int, int) -> str
    if not uid or not gid:
        (uid, gid) = extract_uid_gid()
    make_data_dir_base(fsid, uid, gid)
    data_dir = get_data_dir(fsid, daemon_type, daemon_id)
    makedirs(data_dir, uid, gid, DATA_DIR_MODE)
    return data_dir

def make_log_dir(fsid, uid=None, gid=None):
    # type: (str, int, int) -> str
    if not uid or not gid:
        (uid, gid) = extract_uid_gid()
    log_dir = get_log_dir(fsid)
    makedirs(log_dir, uid, gid, LOG_DIR_MODE)
    return log_dir

def make_var_run(fsid, uid, gid):
    # type: (str, int, int) -> None
    call_throws(['install', '-d', '-m0770', '-o', str(uid), '-g', str(gid),
                 '/var/run/ceph/%s' % fsid])

def copy_tree(src, dst, uid=None, gid=None):
    # type: (List[str], str, int, int) -> None
    """
    Copy a directory tree from src to dst
    """
    if not uid or not gid:
        (uid, gid) = extract_uid_gid()

    for src_dir in src:
        dst_dir = dst
        if os.path.isdir(dst):
            dst_dir = os.path.join(dst, os.path.basename(src_dir))

        logger.debug('copy directory \'%s\' -> \'%s\'' % (src_dir, dst_dir))
        shutil.rmtree(dst_dir, ignore_errors=True)
        shutil.copytree(src_dir, dst_dir) # dirs_exist_ok needs python 3.8

        for dirpath, dirnames, filenames in os.walk(dst_dir):
            logger.debug('chown %s:%s \'%s\'' % (uid, gid, dirpath))
            os.chown(dirpath, uid, gid)
            for filename in filenames:
                logger.debug('chown %s:%s \'%s\'' % (uid, gid, filename))
                os.chown(os.path.join(dirpath, filename), uid, gid)


def copy_files(src, dst, uid=None, gid=None):
    # type: (List[str], str, int, int) -> None
    """
    Copy a files from src to dst
    """
    if not uid or not gid:
        (uid, gid) = extract_uid_gid()

    for src_file in src:
        dst_file = dst
        if os.path.isdir(dst):
            dst_file = os.path.join(dst, os.path.basename(src_file))

        logger.debug('copy file \'%s\' -> \'%s\'' % (src_file, dst_file))
        shutil.copyfile(src_file, dst_file)

        logger.debug('chown %s:%s \'%s\'' % (uid, gid, dst_file))
        os.chown(dst_file, uid, gid)

def move_files(src, dst, uid=None, gid=None):
    # type: (List[str], str, int, int) -> None
    """
    Move files from src to dst
    """
    if not uid or not gid:
        (uid, gid) = extract_uid_gid()

    for src_file in src:
        dst_file = dst
        if os.path.isdir(dst):
            dst_file = os.path.join(dst, os.path.basename(src_file))

        if os.path.islink(src_file):
            # shutil.move() in py2 does not handle symlinks correctly
            src_rl = os.readlink(src_file)
            logger.debug("symlink '%s' -> '%s'" % (dst_file, src_rl))
            os.symlink(src_rl, dst_file)
            os.unlink(src_file)
        else:
            logger.debug("move file '%s' -> '%s'" % (src_file, dst_file))
            shutil.move(src_file, dst_file)
            logger.debug('chown %s:%s \'%s\'' % (uid, gid, dst_file))
            os.chown(dst_file, uid, gid)

## copied from distutils ##
def find_executable(executable, path=None):
    """Tries to find 'executable' in the directories listed in 'path'.
    A string listing directories separated by 'os.pathsep'; defaults to
    os.environ['PATH'].  Returns the complete filename or None if not found.
    """
    _, ext = os.path.splitext(executable)
    if (sys.platform == 'win32') and (ext != '.exe'):
        executable = executable + '.exe'

    if os.path.isfile(executable):
        return executable

    if path is None:
        path = os.environ.get('PATH', None)
        if path is None:
            try:
                path = os.confstr("CS_PATH")
            except (AttributeError, ValueError):
                # os.confstr() or CS_PATH is not available
                path = os.defpath
        # bpo-35755: Don't use os.defpath if the PATH environment variable is
        # set to an empty string

    # PATH='' doesn't match, whereas PATH=':' looks in the current directory
    if not path:
        return None

    paths = path.split(os.pathsep)
    for p in paths:
        f = os.path.join(p, executable)
        if os.path.isfile(f):
            # the file exists, we have a shot at spawn working
            return f
    return None

def find_program(filename):
    # type: (str) -> str
    name = find_executable(filename)
    if name is None:
        raise ValueError('%s not found' % filename)
    return name

def get_unit_name(fsid, daemon_type, daemon_id=None):
    # type: (str, str, Optional[Union[int, str]]) -> str
    # accept either name or type + id
    if daemon_id is not None:
        return 'ceph-%s@%s.%s' % (fsid, daemon_type, daemon_id)
    else:
        return 'ceph-%s@%s' % (fsid, daemon_type)

def check_unit(unit_name):
    # type: (str) -> Tuple[bool, str, bool]
    # NOTE: we ignore the exit code here because systemctl outputs
    # various exit codes based on the state of the service, but the
    # string result is more explicit (and sufficient).
    enabled = False
    installed = False
    try:
        out, err, code = call(['systemctl', 'is-enabled', unit_name],
                              verbose_on_failure=False)
        if code == 0:
            enabled = True
            installed = True
        elif "disabled" in out:
            installed = True
    except Exception as e:
        logger.warning('unable to run systemctl: %s' % e)
        enabled = False
        installed = False

    state = 'unknown'
    try:
        out, err, code = call(['systemctl', 'is-active', unit_name],
                              verbose_on_failure=False)
        out = out.strip()
        if out in ['active']:
            state = 'running'
        elif out in ['inactive']:
            state = 'stopped'
        elif out in ['failed', 'auto-restart']:
            state = 'error'
        else:
            state = 'unknown'
    except Exception as e:
        logger.warning('unable to run systemctl: %s' % e)
        state = 'unknown'
    return (enabled, state, installed)

def check_units(units, enabler=None):
    # type: (List[str], Optional[Packager]) -> bool
    for u in units:
        (enabled, state, installed) = check_unit(u)
        if enabled and state == 'running':
            logger.info('Unit %s is enabled and running' % u)
            return True
        if enabler is not None:
            if installed:
                logger.info('Enabling unit %s' % u)
                enabler.enable_service(u)
    return False

def get_legacy_config_fsid(cluster, legacy_dir=None):
    # type: (str, str) -> Optional[str]
    config_file = '/etc/ceph/%s.conf' % cluster
    if legacy_dir is not None:
        config_file = os.path.abspath(legacy_dir + config_file)

    if os.path.exists(config_file):
        config = read_config(config_file)
        if config.has_section('global') and config.has_option('global', 'fsid'):
            return config.get('global', 'fsid')
    return None

def get_legacy_daemon_fsid(cluster, daemon_type, daemon_id, legacy_dir=None):
    # type: (str, str, Union[int, str], str) -> Optional[str]
    fsid = None
    if daemon_type == 'osd':
        try:
            fsid_file = os.path.join(args.data_dir,
                                     daemon_type,
                                     'ceph-%s' % daemon_id,
                                     'ceph_fsid')
            if legacy_dir is not None:
                fsid_file = os.path.abspath(legacy_dir + fsid_file)
            with open(fsid_file, 'r') as f:
                fsid = f.read().strip()
        except IOError:
            pass
    if not fsid:
        fsid = get_legacy_config_fsid(cluster, legacy_dir=legacy_dir)
    return fsid

def get_daemon_args(fsid, daemon_type, daemon_id):
    # type: (str, str, Union[int, str]) -> List[str]
    r = list()  # type: List[str]

    if daemon_type in Ceph.daemons and daemon_type != 'crash':
        r += [
            '--setuser', 'ceph',
            '--setgroup', 'ceph',
            '--default-log-to-file=false',
            '--default-log-to-stderr=true',
            '--default-log-stderr-prefix="debug "',
        ]
        if daemon_type == 'mon':
            r += [
                '--default-mon-cluster-log-to-file=false',
                '--default-mon-cluster-log-to-stderr=true',
            ]
    elif daemon_type in Monitoring.components:
        metadata = Monitoring.components[daemon_type]
        r += metadata.get('args', list())
        if daemon_type == 'alertmanager':
            config = get_parm(args.config_json)
            peers = config.get('peers', list())  # type: ignore
            for peer in peers:
                r += ["--cluster.peer={}".format(peer)]
    elif daemon_type == NFSGanesha.daemon_type:
        r += NFSGanesha.daemon_args

    return r

def create_daemon_dirs(fsid, daemon_type, daemon_id, uid, gid,
                       config=None, keyring=None,
                       reconfig=False):
    # type: (str, str, Union[int, str], int, int, Optional[str], Optional[str], Optional[bool]) ->  None
    data_dir = make_data_dir(fsid, daemon_type, daemon_id, uid=uid, gid=gid)
    make_log_dir(fsid, uid=uid, gid=gid)

    if config:
        config_path = os.path.join(data_dir, 'config')
        with open(config_path, 'w') as f:
            os.fchown(f.fileno(), uid, gid)
            os.fchmod(f.fileno(), 0o600)
            f.write(config)
    if keyring:
        keyring_path = os.path.join(data_dir, 'keyring')
        with open(keyring_path, 'w') as f:
            os.fchmod(f.fileno(), 0o600)
            os.fchown(f.fileno(), uid, gid)
            f.write(keyring)

    if daemon_type in Monitoring.components.keys():
        config = get_parm(args.config_json) # type: ignore
        required_files = Monitoring.components[daemon_type].get('config-json-files', list())

        # Set up directories specific to the monitoring component
        config_dir = ''
        if daemon_type == 'prometheus':
            data_dir_root = get_data_dir(fsid, daemon_type, daemon_id)
            config_dir = 'etc/prometheus'
            makedirs(os.path.join(data_dir_root, config_dir), uid, gid, 0o755)
            makedirs(os.path.join(data_dir_root, config_dir, 'alerting'), uid, gid, 0o755)
            makedirs(os.path.join(data_dir_root, 'data'), uid, gid, 0o755)
        elif daemon_type == 'grafana':
            data_dir_root = get_data_dir(fsid, daemon_type, daemon_id)
            config_dir = 'etc/grafana'
            makedirs(os.path.join(data_dir_root, config_dir), uid, gid, 0o755)
            makedirs(os.path.join(data_dir_root, config_dir, 'certs'), uid, gid, 0o755)
            makedirs(os.path.join(data_dir_root, config_dir, 'provisioning/datasources'), uid, gid, 0o755)
            makedirs(os.path.join(data_dir_root, 'data'), uid, gid, 0o755)
        elif daemon_type == 'alertmanager':
            data_dir_root = get_data_dir(fsid, daemon_type, daemon_id)
            config_dir = 'etc/alertmanager'
            makedirs(os.path.join(data_dir_root, config_dir), uid, gid, 0o755)
            makedirs(os.path.join(data_dir_root, config_dir, 'data'), uid, gid, 0o755)


        # populate the config directory for the component from the config-json
        for fname in required_files:
            if 'files' in config: # type: ignore
                if isinstance(config['files'][fname], list):  # type: ignore
                    content = '\n'.join(config['files'][fname])  # type: ignore
                else:
                    content = config['files'][fname]  # type: ignore

                with open(os.path.join(data_dir_root, config_dir, fname), 'w') as f:
                    os.fchown(f.fileno(), uid, gid)
                    os.fchmod(f.fileno(), 0o600)
                    f.write(content)

    if daemon_type == NFSGanesha.daemon_type:
        nfs_ganesha = NFSGanesha.init(fsid, daemon_id)
        nfs_ganesha.create_daemon_dirs(data_dir, uid, gid)

def get_parm(option):
    # type: (str) -> Dict[str, str]

    if not option:
        return dict()

    global cached_stdin
    if option == '-':
        if cached_stdin is not None:
            j = cached_stdin
        else:
            try:
                j = injected_stdin  # type: ignore
            except NameError:
                j = sys.stdin.read()
                cached_stdin = j
    else:
        # inline json string
        if option[0] == '{' and option[-1] == '}':
            j = option
        # json file
        elif os.path.exists(option):
            with open(option, 'r') as f:
                j = f.read()
        else:
            raise Error("Config file {} not found".format(option))

    try:
        js = json.loads(j)
    except ValueError as e:
        raise Error("Invalid JSON in {}: {}".format(option, e))
    else:
        return js

def get_config_and_keyring():
    # type: () -> Tuple[Optional[str], Optional[str]]
    config = None
    keyring = None

    if 'config_json' in args and args.config_json:
        d = get_parm(args.config_json)
        config = d.get('config')
        keyring = d.get('keyring')

    if 'config' in args and args.config:
        with open(args.config, 'r') as f:
            config = f.read()

    if 'key' in args and args.key:
        keyring = '[%s]\n\tkey = %s\n' % (args.name, args.key)
    elif 'keyring' in args and args.keyring:
        with open(args.keyring, 'r') as f:
            keyring = f.read()

    return (config, keyring)

def get_container_mounts(fsid, daemon_type, daemon_id,
                         no_config=False):
    # type: (str, str, Union[int, str, None], Optional[bool]) -> Dict[str, str]
    mounts = dict()

    if daemon_type in Ceph.daemons:
        if fsid:
            run_path = os.path.join('/var/run/ceph', fsid);
            if os.path.exists(run_path):
                mounts[run_path] = '/var/run/ceph:z'
            log_dir = get_log_dir(fsid)
            mounts[log_dir] = '/var/log/ceph:z'
            crash_dir = '/var/lib/ceph/%s/crash' % fsid
            if os.path.exists(crash_dir):
                mounts[crash_dir] = '/var/lib/ceph/crash:z'

    if daemon_type in Ceph.daemons and daemon_id:
        data_dir = get_data_dir(fsid, daemon_type, daemon_id)
        if daemon_type == 'rgw':
            cdata_dir = '/var/lib/ceph/radosgw/ceph-rgw.%s' % (daemon_id)
        else:
            cdata_dir = '/var/lib/ceph/%s/ceph-%s' % (daemon_type, daemon_id)
        if daemon_type != 'crash':
            mounts[data_dir] = cdata_dir + ':z'
        if not no_config:
            mounts[data_dir + '/config'] = '/etc/ceph/ceph.conf:z'
        if daemon_type == 'rbd-mirror' or daemon_type == 'crash':
            # these do not search for their keyrings in a data directory
            mounts[data_dir + '/keyring'] = '/etc/ceph/ceph.client.%s.%s.keyring' % (daemon_type, daemon_id)

    if daemon_type in ['mon', 'osd']:
        mounts['/dev'] = '/dev'  # FIXME: narrow this down?
        mounts['/run/udev'] = '/run/udev'
    if daemon_type == 'osd':
        mounts['/sys'] = '/sys'  # for numa.cc, pick_address, cgroups, ...
        mounts['/run/lvm'] = '/run/lvm'
        mounts['/run/lock/lvm'] = '/run/lock/lvm'

    if daemon_type in Monitoring.components and daemon_id:
        data_dir = get_data_dir(fsid, daemon_type, daemon_id)
        if daemon_type == 'prometheus':
            mounts[os.path.join(data_dir, 'etc/prometheus')] = '/etc/prometheus:Z'
            mounts[os.path.join(data_dir, 'data')] = '/prometheus:Z'
        elif daemon_type == 'node-exporter':
            mounts['/proc'] = '/host/proc:ro'
            mounts['/sys'] = '/host/sys:ro'
            mounts['/'] = '/rootfs:ro'
        elif daemon_type == "grafana":
            mounts[os.path.join(data_dir, 'etc/grafana/grafana.ini')] = '/etc/grafana/grafana.ini:Z'
            mounts[os.path.join(data_dir, 'etc/grafana/provisioning/datasources')] = '/etc/grafana/provisioning/datasources:Z'
            mounts[os.path.join(data_dir, 'etc/grafana/certs')] = '/etc/grafana/certs:Z'
        elif daemon_type == 'alertmanager':
            mounts[os.path.join(data_dir, 'etc/alertmanager')] = '/alertmanager:Z'

    if daemon_type == NFSGanesha.daemon_type:
        assert daemon_id
        data_dir = get_data_dir(fsid, daemon_type, daemon_id)
        mounts.update(NFSGanesha.get_container_mounts(data_dir))

    return mounts

def get_container(fsid, daemon_type, daemon_id,
                  privileged=False,
                  ptrace=False,
                  container_args=[]):
    # type: (str, str, Union[int, str], bool, bool, List[str]) -> CephContainer
    if daemon_type in ['mon', 'osd']:
        # mon and osd need privileged in order for libudev to query devices
        privileged = True
    if daemon_type == 'rgw':
        entrypoint = '/usr/bin/radosgw'
        name = 'client.rgw.%s' % daemon_id
    elif daemon_type == 'rbd-mirror':
        entrypoint = '/usr/bin/rbd-mirror'
        name = 'client.rbd-mirror.%s' % daemon_id
    elif daemon_type == 'crash':
        entrypoint = '/usr/bin/ceph-crash'
        name = 'client.crash.%s' % daemon_id
    elif daemon_type in ['mon', 'mgr', 'mds', 'osd']:
        entrypoint = '/usr/bin/ceph-' + daemon_type
        name = '%s.%s' % (daemon_type, daemon_id)
    elif daemon_type in Monitoring.components:
        entrypoint = ''
        name = ''
    elif daemon_type == NFSGanesha.daemon_type:
        entrypoint = NFSGanesha.entrypoint
        name = '%s.%s' % (daemon_type, daemon_id)
    else:
        entrypoint = ''
        name = ''

    ceph_args = [] # type: List[str]
    if daemon_type in Monitoring.components:
        uid, gid = extract_uid_gid_monitoring(daemon_type)
        m = Monitoring.components[daemon_type]  # type: ignore
        metadata = m.get('image', dict())  # type: ignore
        monitoring_args = [
            '--user',
            str(uid),
            # FIXME: disable cpu/memory limits for the time being (not supported
            # by ubuntu 18.04 kernel!)
            #'--cpus',
            #metadata.get('cpus', '2'),
            #'--memory',
            #metadata.get('memory', '4GB')
        ]
        container_args.extend(monitoring_args)
    elif daemon_type == 'crash':
        ceph_args = ['-n', name]
    elif daemon_type in Ceph.daemons:
        ceph_args = ['-n', name, '-f']

    envs=[] # type: List[str]
    if daemon_type == NFSGanesha.daemon_type:
        envs.extend(NFSGanesha.get_container_envs())

    return CephContainer(
        image=args.image,
        entrypoint=entrypoint,
        args=ceph_args + get_daemon_args(fsid, daemon_type, daemon_id),
        container_args=container_args,
        volume_mounts=get_container_mounts(fsid, daemon_type, daemon_id),
        cname='ceph-%s-%s.%s' % (fsid, daemon_type, daemon_id),
        envs=envs,
        privileged=privileged,
        ptrace=ptrace,
    )

def extract_uid_gid(img='', file_path='/var/lib/ceph'):
    # type: (str, str) -> Tuple[int, int]

    if not img:
        img = args.image

    out = CephContainer(
        image=img,
        entrypoint='stat',
        args=['-c', '%u %g', file_path]
    ).run()
    (uid, gid) = out.split(' ')
    return (int(uid), int(gid))

def deploy_daemon(fsid, daemon_type, daemon_id, c, uid, gid,
                  config=None, keyring=None,
                  osd_fsid=None,
                  reconfig=False):
    # type: (str, str, Union[int, str], CephContainer, int, int, Optional[str], Optional[str], Optional[str], Optional[bool]) -> None
    data_dir = get_data_dir(fsid, daemon_type, daemon_id)
    if reconfig and not os.path.exists(data_dir):
        raise Error('cannot reconfig, data path %s does not exist' % data_dir)
    if daemon_type == 'mon' and not os.path.exists(data_dir):
        assert config
        assert keyring
        # tmp keyring file
        tmp_keyring = write_tmp(keyring, uid, gid)

        # tmp config file
        tmp_config = write_tmp(config, uid, gid)

        # --mkfs
        create_daemon_dirs(fsid, daemon_type, daemon_id, uid, gid)
        mon_dir = get_data_dir(fsid, 'mon', daemon_id)
        log_dir = get_log_dir(fsid)
        out = CephContainer(
            image=args.image,
            entrypoint='/usr/bin/ceph-mon',
            args=['--mkfs',
                  '-i', str(daemon_id),
                  '--fsid', fsid,
                  '-c', '/tmp/config',
                  '--keyring', '/tmp/keyring',
            ] + get_daemon_args(fsid, 'mon', daemon_id),
            volume_mounts={
                log_dir: '/var/log/ceph:z',
                mon_dir: '/var/lib/ceph/mon/ceph-%s:z' % (daemon_id),
                tmp_keyring.name: '/tmp/keyring:z',
                tmp_config.name: '/tmp/config:z',
            },
        ).run()

        # write conf
        with open(mon_dir + '/config', 'w') as f:
            os.fchown(f.fileno(), uid, gid)
            os.fchmod(f.fileno(), 0o600)
            f.write(config)
    else:
        # dirs, conf, keyring
        create_daemon_dirs(
            fsid, daemon_type, daemon_id,
            uid, gid,
            config, keyring)

    if not reconfig:
        deploy_daemon_units(fsid, uid, gid, daemon_type, daemon_id, c,
                            osd_fsid=osd_fsid)

    if not os.path.exists(data_dir + '/unit.created'):
        with open(data_dir + '/unit.created', 'w') as f:
            os.fchmod(f.fileno(), 0o600)
            os.fchown(f.fileno(), uid, gid)
            f.write('mtime is time the daemon deployment was created\n')

    with open(data_dir + '/unit.configured', 'w') as f:
        f.write('mtime is time we were last configured\n')
        os.fchmod(f.fileno(), 0o600)
        os.fchown(f.fileno(), uid, gid)

    update_firewalld(daemon_type)

    if reconfig and daemon_type not in Ceph.daemons:
        # ceph daemons do not need a restart; others (presumably) do to pick
        # up the new config
        call_throws(['systemctl', 'reset-failed',
                     get_unit_name(fsid, daemon_type, daemon_id)])
        call_throws(['systemctl', 'restart',
                     get_unit_name(fsid, daemon_type, daemon_id)])

def deploy_daemon_units(fsid, uid, gid, daemon_type, daemon_id, c,
                        enable=True, start=True,
                        osd_fsid=None):
    # type: (str, int, int, str, Union[int, str], CephContainer, bool, bool, Optional[str]) -> None
    # cmd
    data_dir = get_data_dir(fsid, daemon_type, daemon_id)
    with open(data_dir + '/unit.run.new', 'w') as f:
        # pre-start cmd(s)
        if daemon_type == 'osd':
            # osds have a pre-start step
            assert osd_fsid
            prestart = CephContainer(
                image=args.image,
                entrypoint='/usr/sbin/ceph-volume',
                args=[
                    'lvm', 'activate',
                    str(daemon_id), osd_fsid,
                    '--no-systemd'
                ],
                privileged=True,
                volume_mounts=get_container_mounts(fsid, daemon_type, daemon_id),
                cname='ceph-%s-%s.%s-activate' % (fsid, daemon_type, daemon_id),
            )
            f.write(' '.join(prestart.run_cmd()) + '\n')
        elif daemon_type == NFSGanesha.daemon_type:
            # add nfs to the rados grace db
            nfs_ganesha = NFSGanesha.init(fsid, daemon_id)
            prestart = nfs_ganesha.get_rados_grace_container('add')
            f.write(' '.join(prestart.run_cmd()) + '\n')

        # container run command
        f.write(' '.join(c.run_cmd()) + '\n')
        os.fchmod(f.fileno(), 0o600)
        os.rename(data_dir + '/unit.run.new',
                  data_dir + '/unit.run')

    # post-stop command(s)
    with open(data_dir + '/unit.poststop.new', 'w') as f:
        if daemon_type == 'osd':
            assert osd_fsid
            poststop = CephContainer(
                image=args.image,
                entrypoint='/usr/sbin/ceph-volume',
                args=[
                    'lvm', 'deactivate',
                    str(daemon_id), osd_fsid,
                ],
                privileged=True,
                volume_mounts=get_container_mounts(fsid, daemon_type, daemon_id),
                cname='ceph-%s-%s.%s-deactivate' % (fsid, daemon_type,
                                                    daemon_id),
            )
            f.write(' '.join(poststop.run_cmd()) + '\n')
        elif daemon_type == NFSGanesha.daemon_type:
            # remove nfs from the rados grace db
            nfs_ganesha = NFSGanesha.init(fsid, daemon_id)
            poststop = nfs_ganesha.get_rados_grace_container('remove')
            f.write(' '.join(poststop.run_cmd()) + '\n')
        os.fchmod(f.fileno(), 0o600)
        os.rename(data_dir + '/unit.poststop.new',
                  data_dir + '/unit.poststop')

    with open(data_dir + '/unit.image.new', 'w') as f:
        f.write(c.image + '\n')
        os.fchmod(f.fileno(), 0o600)
        os.rename(data_dir + '/unit.image.new',
                  data_dir + '/unit.image')

    # systemd
    install_base_units(fsid)
    unit = get_unit_file(fsid, uid, gid)
    unit_file = 'ceph-%s@.service' % (fsid)
    with open(args.unit_dir + '/' + unit_file + '.new', 'w') as f:
        f.write(unit)
        os.rename(args.unit_dir + '/' + unit_file + '.new',
                  args.unit_dir + '/' + unit_file)
    call_throws(['systemctl', 'daemon-reload'])

    unit_name = get_unit_name(fsid, daemon_type, daemon_id)
    call(['systemctl', 'stop', unit_name],
         verbose_on_failure=False)
    call(['systemctl', 'reset-failed', unit_name],
         verbose_on_failure=False)
    if enable:
        call_throws(['systemctl', 'enable', unit_name])
    if start:
        call_throws(['systemctl', 'start', unit_name])

def update_firewalld(daemon_type):
    # type: (str) -> None
    if args.skip_firewalld:
        return
    cmd = find_executable('firewall-cmd')
    if not cmd:
        logger.debug('firewalld does not appear to be present')
        return
    (enabled, state, _) = check_unit('firewalld.service')
    if not enabled:
        logger.debug('firewalld.service is not enabled')
        return

    fw_services = []
    fw_ports = []
    if daemon_type == 'mon':
        fw_services.append('ceph-mon')
    elif daemon_type in ['mgr', 'mds', 'osd']:
        fw_services.append('ceph')
    if daemon_type == 'mgr':
        fw_ports.append(8080)  # dashboard
        fw_ports.append(8443)  # dashboard
        fw_ports.append(9283)  # mgr/prometheus exporter
    elif daemon_type in Monitoring.port_map.keys():
        fw_ports.extend(Monitoring.port_map[daemon_type])  # prometheus etc
    elif daemon_type == NFSGanesha.daemon_type:
        fw_services.append('nfs')

    for svc in fw_services:
        out, err, ret = call([cmd, '--permanent', '--query-service', svc])
        if ret:
            logger.info('Enabling firewalld service %s in current zone...' % svc)
            out, err, ret = call([cmd, '--permanent', '--add-service', svc])
            if ret:
                raise RuntimeError(
                    'unable to add service %s to current zone: %s' % (svc, err))
        else:
            logger.debug('firewalld service %s is enabled in current zone' % svc)
    for port in fw_ports:
        tcp_port = str(port) + '/tcp'
        out, err, ret = call([cmd, '--permanent', '--query-port', tcp_port])
        if ret:
            logger.info('Enabling firewalld port %s in current zone...' % tcp_port)
            out, err, ret = call([cmd, '--permanent', '--add-port', tcp_port])
            if ret:
                raise RuntimeError('unable to add port %s to current zone: %s' %
                                   (tcp_port, err))
        else:
            logger.debug('firewalld port %s is enabled in current zone' % tcp_port)
    call_throws([cmd, '--reload'])

def install_base_units(fsid):
    # type: (str) -> None
    """
    Set up ceph.target and ceph-$fsid.target units.
    """
    # global unit
    existed = os.path.exists(args.unit_dir + '/ceph.target')
    with open(args.unit_dir + '/ceph.target.new', 'w') as f:
        f.write('[Unit]\n'
                'Description=All Ceph clusters and services\n'
                '\n'
                '[Install]\n'
                'WantedBy=multi-user.target\n')
        os.rename(args.unit_dir + '/ceph.target.new',
                  args.unit_dir + '/ceph.target')
    if not existed:
        # we disable before enable in case a different ceph.target
        # (from the traditional package) is present; while newer
        # systemd is smart enough to disable the old
        # (/lib/systemd/...) and enable the new (/etc/systemd/...),
        # some older versions of systemd error out with EEXIST.
        call_throws(['systemctl', 'disable', 'ceph.target'])
        call_throws(['systemctl', 'enable', 'ceph.target'])
        call_throws(['systemctl', 'start', 'ceph.target'])

    # cluster unit
    existed = os.path.exists(args.unit_dir + '/ceph-%s.target' % fsid)
    with open(args.unit_dir + '/ceph-%s.target.new' % fsid, 'w') as f:
        f.write('[Unit]\n'
                'Description=Ceph cluster {fsid}\n'
                'PartOf=ceph.target\n'
                'Before=ceph.target\n'
                '\n'
                '[Install]\n'
                'WantedBy=multi-user.target ceph.target\n'.format(
                    fsid=fsid)
        )
        os.rename(args.unit_dir + '/ceph-%s.target.new' % fsid,
                  args.unit_dir + '/ceph-%s.target' % fsid)
    if not existed:
        call_throws(['systemctl', 'enable', 'ceph-%s.target' % fsid])
        call_throws(['systemctl', 'start', 'ceph-%s.target' % fsid])

    # logrotate for the cluster
    with open(args.logrotate_dir + '/ceph-%s' % fsid, 'w') as f:
        """
        This is a bit sloppy in that the killall/pkill will touch all ceph daemons
        in all containers, but I don't see an elegant way to send SIGHUP *just* to
        the daemons for this cluster.  (1) systemd kill -s will get the signal to
        podman, but podman will exit.  (2) podman kill will get the signal to the
        first child (bash), but that isn't the ceph daemon.  This is simpler and
        should be harmless.
        """
        f.write("""# created by cephadm
/var/log/ceph/%s/*.log {
    rotate 7
    daily
    compress
    sharedscripts
    postrotate
        killall -q -1 ceph-mon ceph-mgr ceph-mds ceph-osd ceph-fuse radosgw rbd-mirror || pkill -1 -x "ceph-mon|ceph-mgr|ceph-mds|ceph-osd|ceph-fuse|radosgw|rbd-mirror" || true
    endscript
    missingok
    notifempty
    su root root
}
""" % fsid)

def get_unit_file(fsid, uid, gid):
    # type: (str, int, int) -> str
    install_path = find_program('install')
    u = """# generated by cephadm
[Unit]
Description=Ceph %i for {fsid}

# According to:
#   http://www.freedesktop.org/wiki/Software/systemd/NetworkTarget
# these can be removed once ceph-mon will dynamically change network
# configuration.
After=network-online.target local-fs.target time-sync.target
Wants=network-online.target local-fs.target time-sync.target

PartOf=ceph-{fsid}.target
Before=ceph-{fsid}.target

[Service]
LimitNOFILE=1048576
LimitNPROC=1048576
EnvironmentFile=-/etc/environment
ExecStartPre=-{container_path} rm ceph-{fsid}-%i
ExecStartPre=-{install_path} -d -m0770 -o {uid} -g {gid} /var/run/ceph/{fsid}
ExecStart=/bin/bash {data_dir}/{fsid}/%i/unit.run
ExecStop=-{container_path} stop ceph-{fsid}-%i
ExecStopPost=-/bin/bash {data_dir}/{fsid}/%i/unit.poststop
KillMode=none
Restart=on-failure
RestartSec=10s
TimeoutStartSec=120
TimeoutStopSec=15
StartLimitInterval=30min
StartLimitBurst=5

[Install]
WantedBy=ceph-{fsid}.target
""".format(
    container_path=container_path,
    install_path=install_path,
    fsid=fsid,
    uid=uid,
    gid=gid,
    data_dir=args.data_dir)
    return u

##################################

class CephContainer:
    def __init__(self,
                 image,
                 entrypoint,
                 args=[],
                 volume_mounts={},
                 cname='',
                 container_args=[],
                 envs=None,
                 privileged=False,
                 ptrace=False):
        # type: (str, str, List[str], Dict[str, str], str, List[str], Optional[List[str]], bool, bool) -> None
        self.image = image
        self.entrypoint = entrypoint
        self.args = args
        self.volume_mounts = volume_mounts
        self.cname = cname
        self.container_args = container_args
        self.envs = envs
        self.privileged = privileged
        self.ptrace = ptrace

    def run_cmd(self):
        # type: () -> List[str]
        vols = [] # type: List[str]
        envs = [] # type: List[str]
        cname = [] # type: List[str]
        entrypoint = [] # type: List[str]
        if self.entrypoint:
            entrypoint = ['--entrypoint', self.entrypoint]

        priv = [] # type: List[str]
        if self.privileged:
            priv = ['--privileged',
                    # let OSD etc read block devs that haven't been chowned
                    '--group-add=disk']
        if self.ptrace:
            priv.append('--cap-add=SYS_PTRACE')
        vols = sum(
            [['-v', '%s:%s' % (host_dir, container_dir)]
             for host_dir, container_dir in self.volume_mounts.items()], [])
        envs = [
            '-e', 'CONTAINER_IMAGE=%s' % self.image,
            '-e', 'NODE_NAME=%s' % get_hostname(),
        ]
        if self.envs:
            for e in self.envs:
                envs.extend(['-e', e])
        cname = ['--name', self.cname] if self.cname else []
        return [
            str(container_path),
            'run',
            '--rm',
            '--net=host',
        ] + self.container_args + priv + \
        cname + envs + \
        vols + entrypoint + \
        [
            self.image
        ] + self.args # type: ignore

    def shell_cmd(self, cmd):
        # type: (List[str]) -> List[str]
        priv = [] # type: List[str]
        if self.privileged:
            priv = ['--privileged',
                    # let OSD etc read block devs that haven't been chowned
                    '--group-add=disk']
        vols = [] # type: List[str]
        vols = sum(
            [['-v', '%s:%s' % (host_dir, container_dir)]
             for host_dir, container_dir in self.volume_mounts.items()], [])
        envs = [
            '-e', 'CONTAINER_IMAGE=%s' % self.image,
            '-e', 'NODE_NAME=%s' % get_hostname(),
        ]
        if self.envs:
            for e in self.envs:
                envs.extend(['-e', e])
        cmd_args = [] # type: List[str]
        if cmd:
            cmd_args = ['-c'] + cmd
        return [
            str(container_path),
            'run',
            '--rm',
            '--net=host',
        ] + self.container_args + priv + envs + vols + [
            '--entrypoint', cmd[0],
            self.image
        ] + cmd[1:]

    def exec_cmd(self, cmd):
        # type: (List[str]) -> List[str]
        return [
            str(container_path),
            'exec',
        ] + self.container_args + [
            self.cname,
        ] + cmd

    def run(self, timeout=DEFAULT_TIMEOUT):
        # type: (Optional[int]) -> str
        logger.debug(self.run_cmd())
        out, _, _ = call_throws(
                self.run_cmd(), desc=self.entrypoint, timeout=timeout)
        return out

##################################

@infer_image
def command_version():
    # type: () -> int
    out = CephContainer(args.image, 'ceph', ['--version']).run()
    print(out.strip())
    return 0

##################################

@infer_image
def command_pull():
    # type: () -> int
    logger.info('Pulling latest %s...' % args.image)
    call_throws([container_path, 'pull', args.image])
    return command_inspect_image()

##################################

@infer_image
def command_inspect_image():
    # type: () -> int
    out, err, ret = call_throws([
        container_path, 'inspect',
        '--format', '{{.Id}}',
        args.image])
    if ret:
        return errno.ENOENT
    image_id = normalize_container_id(out.strip())
    ver = CephContainer(args.image, 'ceph', ['--version']).run().strip()
    r = {
        'image_id': image_id,
        'ceph_version': ver,
    }
    print(json.dumps(r, indent=4, sort_keys=True))
    return 0

##################################

@default_image
def command_bootstrap():
    # type: () -> int

    if not args.output_config:
        args.output_config = os.path.join(args.output_dir, 'ceph.conf')
    if not args.output_keyring:
        args.output_keyring = os.path.join(args.output_dir,
                                           'ceph.client.admin.keyring')
    if not args.output_pub_ssh_key:
        args.output_pub_ssh_key = os.path.join(args.output_dir, 'ceph.pub')

    # verify output files
    for f in [args.output_config, args.output_keyring, args.output_pub_ssh_key]:
        if not args.allow_overwrite:
            if os.path.exists(f):
                raise Error('%s already exists; delete or pass '
                              '--allow-overwrite to overwrite' % f)
        dirname = os.path.dirname(f)
        if dirname and not os.path.exists(dirname):
            raise Error('%s directory %s does not exist' % (f, dirname))

    if not args.skip_prepare_host:
        command_prepare_host()
    else:
        logger.info('Skip prepare_host')

    # initial vars
    fsid = args.fsid or make_fsid()
    hostname = get_hostname()
    if '.' in hostname and not args.allow_fqdn_hostname:
        raise Error('hostname is a fully qualified domain name (%s); either fix (e.g., "sudo hostname %s" or similar) or pass --allow-fqdn-hostname' % (hostname, hostname.split('.')[0]))
    mon_id = args.mon_id or hostname
    mgr_id = args.mgr_id or generate_service_id()
    logging.info('Cluster fsid: %s' % fsid)

    l = FileLock(fsid)
    l.acquire()

    # ip
    r = re.compile(r':(\d+)$')
    base_ip = None
    if args.mon_ip:
        hasport = r.findall(args.mon_ip)
        if hasport:
            port = int(hasport[0])
            if port == 6789:
                addr_arg = '[v1:%s]' % args.mon_ip
            elif port == 3300:
                addr_arg = '[v2:%s]' % args.mon_ip
            else:
                logger.warning('Using msgr2 protocol for unrecognized port %d' %
                               port)
                addr_arg = '[v2:%s]' % args.mon_ip
            base_ip = args.mon_ip[0:-(len(str(port)))-1]
            check_ip_port(base_ip, port)
        else:
            base_ip = args.mon_ip
            addr_arg = '[v2:%s:3300,v1:%s:6789]' % (args.mon_ip, args.mon_ip)
            check_ip_port(args.mon_ip, 3300)
            check_ip_port(args.mon_ip, 6789)
    elif args.mon_addrv:
        addr_arg = args.mon_addrv
        if addr_arg[0] != '[' or addr_arg[-1] != ']':
            raise Error('--mon-addrv value %s must use square backets' %
                        addr_arg)
        for addr in addr_arg[1:-1].split(','):
            hasport = r.findall(addr)
            if not hasport:
                raise Error('--mon-addrv value %s must include port number' %
                            addr_arg)
            port = int(hasport[0])
            # strip off v1: or v2: prefix
            addr = re.sub(r'^\w+:', '', addr)
            base_ip = addr[0:-(len(str(port)))-1]
            check_ip_port(base_ip, port)
    else:
        raise Error('must specify --mon-ip or --mon-addrv')
    logger.debug('Base mon IP is %s, final addrv is %s' % (base_ip, addr_arg))

    mon_network = None
    if not args.skip_mon_network:
        # make sure IP is configured locally, and then figure out the
        # CIDR network
        for net, ips in list_networks().items():
            if base_ip in ips:
                mon_network = net
                logger.info('Mon IP %s is in CIDR network %s' % (base_ip,
                                                                 mon_network))
                break
        if not mon_network:
            raise Error('Failed to infer CIDR network for mon ip %s; pass '
                        '--skip-mon-network to configure it later' % base_ip)

    # config
    cp = read_config(args.config)
    if not cp.has_section('global'):
        cp.add_section('global')
    cp.set('global', 'fsid', fsid);
    cp.set('global', 'mon host', addr_arg)
    cp.set('global', 'container_image', args.image)
    cpf = StringIO()
    cp.write(cpf)
    config = cpf.getvalue()

    if not args.skip_pull:
        logger.info('Pulling latest %s container...' % args.image)
        call_throws([container_path, 'pull', args.image])

    logger.info('Extracting ceph user uid/gid from container image...')
    (uid, gid) = extract_uid_gid()

    # create some initial keys
    logger.info('Creating initial keys...')
    mon_key = CephContainer(
        image=args.image,
        entrypoint='/usr/bin/ceph-authtool',
        args=['--gen-print-key'],
    ).run().strip()
    admin_key = CephContainer(
        image=args.image,
        entrypoint='/usr/bin/ceph-authtool',
        args=['--gen-print-key'],
    ).run().strip()
    mgr_key = CephContainer(
        image=args.image,
        entrypoint='/usr/bin/ceph-authtool',
        args=['--gen-print-key'],
    ).run().strip()

    keyring = ('[mon.]\n'
               '\tkey = %s\n'
               '\tcaps mon = allow *\n'
               '[client.admin]\n'
               '\tkey = %s\n'
               '\tcaps mon = allow *\n'
               '\tcaps mds = allow *\n'
               '\tcaps mgr = allow *\n'
               '\tcaps osd = allow *\n'
               '[mgr.%s]\n'
               '\tkey = %s\n'
               '\tcaps mon = profile mgr\n'
               '\tcaps mds = allow *\n'
               '\tcaps osd = allow *\n'
               % (mon_key, admin_key, mgr_id, mgr_key))

    # tmp keyring file
    tmp_bootstrap_keyring = write_tmp(keyring, uid, gid)

    # create initial monmap, tmp monmap file
    logger.info('Creating initial monmap...')
    tmp_monmap = write_tmp('', 0, 0)
    out = CephContainer(
        image=args.image,
        entrypoint='/usr/bin/monmaptool',
        args=['--create',
              '--clobber',
              '--fsid', fsid,
              '--addv', mon_id, addr_arg,
              '/tmp/monmap'
        ],
        volume_mounts={
            tmp_monmap.name: '/tmp/monmap:z',
        },
    ).run()

    # pass monmap file to ceph user for use by ceph-mon --mkfs below
    os.fchown(tmp_monmap.fileno(), uid, gid)

    # create mon
    logger.info('Creating mon...')
    create_daemon_dirs(fsid, 'mon', mon_id, uid, gid)
    mon_dir = get_data_dir(fsid, 'mon', mon_id)
    log_dir = get_log_dir(fsid)
    out = CephContainer(
        image=args.image,
        entrypoint='/usr/bin/ceph-mon',
        args=['--mkfs',
              '-i', mon_id,
              '--fsid', fsid,
              '-c', '/dev/null',
              '--monmap', '/tmp/monmap',
              '--keyring', '/tmp/keyring',
        ] + get_daemon_args(fsid, 'mon', mon_id),
        volume_mounts={
            log_dir: '/var/log/ceph:z',
            mon_dir: '/var/lib/ceph/mon/ceph-%s:z' % (mon_id),
            tmp_bootstrap_keyring.name: '/tmp/keyring:z',
            tmp_monmap.name: '/tmp/monmap:z',
        },
    ).run()

    with open(mon_dir + '/config', 'w') as f:
        os.fchown(f.fileno(), uid, gid)
        os.fchmod(f.fileno(), 0o600)
        f.write(config)

    make_var_run(fsid, uid, gid)
    mon_c = get_container(fsid, 'mon', mon_id)
    deploy_daemon(fsid, 'mon', mon_id, mon_c, uid, gid,
                  config=None, keyring=None)

    # client.admin key + config to issue various CLI commands
    tmp_admin_keyring = write_tmp('[client.admin]\n'
                                  '\tkey = ' + admin_key + '\n',
                                       uid, gid)
    tmp_config = write_tmp(config, uid, gid)

    # a CLI helper to reduce our typing
    def cli(cmd, extra_mounts={}, timeout=DEFAULT_TIMEOUT):
        # type: (List[str], Dict[str, str], Optional[int]) -> str
        mounts = {
            log_dir: '/var/log/ceph:z',
            tmp_admin_keyring.name: '/etc/ceph/ceph.client.admin.keyring:z',
            tmp_config.name: '/etc/ceph/ceph.conf:z',
        }
        for k, v in extra_mounts.items():
            mounts[k] = v
        timeout = timeout or args.timeout
        return CephContainer(
            image=args.image,
            entrypoint='/usr/bin/ceph',
            args=cmd,
            volume_mounts=mounts,
        ).run(timeout=timeout)

    logger.info('Waiting for mon to start...')
    c = CephContainer(
        image=args.image,
        entrypoint='/usr/bin/ceph',
        args=[
            'status'],
        volume_mounts={
            mon_dir: '/var/lib/ceph/mon/ceph-%s:z' % (mon_id),
            tmp_admin_keyring.name: '/etc/ceph/ceph.client.admin.keyring:z',
            tmp_config.name: '/etc/ceph/ceph.conf:z',
        },
    )

    # wait for the service to become available
    def is_mon_available():
        # type: () -> bool
        timeout=args.timeout if args.timeout else 30 # seconds
        out, err, ret = call(c.run_cmd(),
                             desc=c.entrypoint,
                             timeout=timeout)
        return ret == 0
    is_available('mon', is_mon_available)

    # assimilate and minimize config
    if not args.no_minimize_config:
        logger.info('Assimilating anything we can from ceph.conf...')
        cli([
            'config', 'assimilate-conf',
            '-i', '/var/lib/ceph/mon/ceph-%s/config' % mon_id
        ], {
            mon_dir: '/var/lib/ceph/mon/ceph-%s:z' % mon_id
        })
        logger.info('Generating new minimal ceph.conf...')
        cli([
            'config', 'generate-minimal-conf',
            '-o', '/var/lib/ceph/mon/ceph-%s/config' % mon_id
        ], {
            mon_dir: '/var/lib/ceph/mon/ceph-%s:z' % mon_id
        })
        # re-read our minimized config
        with open(mon_dir + '/config', 'r') as f:
            config = f.read()
        logger.info('Restarting the monitor...')
        call_throws([
            'systemctl',
            'restart',
            get_unit_name(fsid, 'mon', mon_id)
        ])

    if mon_network:
        logger.info('Setting mon public_network...')
        cli(['config', 'set', 'mon', 'public_network', mon_network])

    # create mgr
    logger.info('Creating mgr...')
    mgr_keyring = '[mgr.%s]\n\tkey = %s\n' % (mgr_id, mgr_key)
    mgr_c = get_container(fsid, 'mgr', mgr_id)
    deploy_daemon(fsid, 'mgr', mgr_id, mgr_c, uid, gid,
                  config=config, keyring=mgr_keyring)

    # output files
    with open(args.output_keyring, 'w') as f:
        os.fchmod(f.fileno(), 0o600)
        f.write('[client.admin]\n'
                '\tkey = ' + admin_key + '\n')
    logger.info('Wrote keyring to %s' % args.output_keyring)

    with open(args.output_config, 'w') as f:
        f.write(config)
    logger.info('Wrote config to %s' % args.output_config)

    # wait for the service to become available
    logger.info('Waiting for mgr to start...')
    def is_mgr_available():
        # type: () -> bool
        timeout=args.timeout if args.timeout else 30 # seconds
        out = cli(['status', '-f', 'json-pretty'], timeout=timeout)
        j = json.loads(out)
        return j.get('mgrmap', {}).get('available', False)
    is_available('mgr', is_mgr_available)

    # wait for mgr to restart (after enabling a module)
    def wait_for_mgr_restart():
        # first get latest mgrmap epoch from the mon
        out = cli(['mgr', 'dump'])
        j = json.loads(out)
        epoch = j['epoch']
        # wait for mgr to have it
        logger.info('Waiting for the mgr to restart...')
        def mgr_has_latest_epoch():
            # type: () -> bool
            try:
                out = cli(['tell', 'mgr', 'mgr_status'])
                j = json.loads(out)
                return j['mgrmap_epoch'] >= epoch
            except Exception as e:
                logger.debug('tell mgr mgr_status failed: %s' % e)
                return False
        is_available('Mgr epoch %d' % epoch, mgr_has_latest_epoch)

    # ssh
    if not args.skip_ssh:
        logger.info('Enabling cephadm module...')
        cli(['mgr', 'module', 'enable', 'cephadm'])
        wait_for_mgr_restart()

        logger.info('Setting orchestrator backend to cephadm...')
        cli(['orch', 'set', 'backend', 'cephadm'])

        logger.info('Generating ssh key...')
        cli(['cephadm', 'generate-key'])
        ssh_pub = cli(['cephadm', 'get-pub-key'])

        with open(args.output_pub_ssh_key, 'w') as f:
            f.write(ssh_pub)
        logger.info('Wrote public SSH key to to %s' % args.output_pub_ssh_key)

        logger.info('Adding key to root@localhost\'s authorized_keys...')
        if not os.path.exists('/root/.ssh'):
            os.mkdir('/root/.ssh', 0o700)
        auth_keys_file = '/root/.ssh/authorized_keys'
        add_newline = False
        if os.path.exists(auth_keys_file):
            with open(auth_keys_file, 'r') as f:
                f.seek(0, os.SEEK_END)
                if f.tell() > 0:
                    f.seek(f.tell()-1, os.SEEK_SET) # go to last char
                    if f.read() != '\n':
                        add_newline = True
        with open(auth_keys_file, 'a') as f:
            os.fchmod(f.fileno(), 0o600)  # just in case we created it
            if add_newline:
                f.write('\n')
            f.write(ssh_pub.strip() + '\n')

        host = get_hostname()
        logger.info('Adding host %s...' % host)
        cli(['orch', 'host', 'add', host])

        if not args.orphan_initial_daemons:
            for t in ['mon', 'mgr', 'crash']:
                logger.info('Deploying %s service with default placement...' % t)
                cli(['orch', 'apply', t])

        if not args.skip_monitoring_stack:
            logger.info('Enabling mgr prometheus module...')
            cli(['mgr', 'module', 'enable', 'prometheus'])
            for t in ['prometheus', 'grafana', 'node-exporter', 'alertmanager']:
                logger.info('Deploying %s service with default placement...' % t)
                cli(['orch', 'apply', t])

    if not args.skip_dashboard:
        logger.info('Enabling the dashboard module...')
        cli(['mgr', 'module', 'enable', 'dashboard'])
        wait_for_mgr_restart()

        # dashboard crt and key
        if args.dashboard_key and args.dashboard_crt:
            logger.info('Using provided dashboard certificate...')
            mounts = {}
            mounts[pathify(args.dashboard_crt)] = '/tmp/dashboard.crt:z'
            mounts[pathify(args.dashboard_key)] = '/tmp/dashboard.key:z'
            cli(['dashboard', 'set-ssl-certificate', '-i', '/tmp/dashboard.crt'], extra_mounts=mounts)
            cli(['dashboard', 'set-ssl-certificate-key', '-i', '/tmp/dashboard.key'], extra_mounts=mounts)
        else:
            logger.info('Generating a dashboard self-signed certificate...')
            cli(['dashboard', 'create-self-signed-cert'])

        logger.info('Creating initial admin user...')
        password = args.initial_dashboard_password or generate_password()
        cmd = ['dashboard', 'ac-user-create', args.initial_dashboard_user, password, 'administrator', '--force-password']
        if not args.dashboard_password_noupdate:
            cmd.append('--pwd-update-required')
        cli(cmd)   
        logger.info('Fetching dashboard port number...')
        out = cli(['config', 'get', 'mgr', 'mgr/dashboard/ssl_server_port'])
        port = int(out)

        logger.info('Ceph Dashboard is now available at:\n\n'
                    '\t     URL: https://%s:%s/\n'
                    '\t    User: %s\n'
                    '\tPassword: %s\n' % (
                        get_fqdn(), port,
                        args.initial_dashboard_user,
                        password))

    logger.info('You can access the Ceph CLI with:\n\n'
                '\tsudo %s shell --fsid %s -c %s -k %s\n' % (
                    sys.argv[0],
                    fsid,
                    args.output_config,
                    args.output_keyring))
    logger.info('Please consider enabling telemetry to help improve Ceph:\n\n'
                '\tceph telemetry on\n\n'
                'For more information see:\n\n'
                '\thttps://docs.ceph.com/docs/master/mgr/telemetry/\n')
    logger.info('Bootstrap complete.')
    return 0

##################################

def extract_uid_gid_monitoring(daemon_type):
    # type: (str) -> Tuple[int, int]

    if daemon_type == 'prometheus':
        uid, gid = extract_uid_gid(file_path='/etc/prometheus')
    elif daemon_type == 'node-exporter':
        uid, gid = 65534, 65534
    elif daemon_type == 'grafana':
        uid, gid = extract_uid_gid(file_path='/var/lib/grafana')
    elif daemon_type == 'alertmanager':
        uid, gid = extract_uid_gid(file_path='/etc/alertmanager')
    else:
        raise Error("{} not implemented yet".format(daemon_type))
    return uid, gid


@default_image
def command_deploy():
    # type: () -> None
    (daemon_type, daemon_id) = args.name.split('.', 1)

    l = FileLock(args.fsid)
    l.acquire()

    if daemon_type not in get_supported_daemons():
        raise Error('daemon type %s not recognized' % daemon_type)

    logger.info('Deploying daemon %s.%s ...' % (daemon_type, daemon_id))

    if daemon_type in Ceph.daemons:
        (config, keyring) = get_config_and_keyring()
        (uid, gid) = extract_uid_gid()
        make_var_run(args.fsid, uid, gid)
        c = get_container(args.fsid, daemon_type, daemon_id,
                          ptrace=args.allow_ptrace)
        deploy_daemon(args.fsid, daemon_type, daemon_id, c, uid, gid,
                      config=config, keyring=keyring,
                      osd_fsid=args.osd_fsid,
                      reconfig=args.reconfig)

    elif daemon_type in Monitoring.components:
        # monitoring daemon - prometheus, grafana, alertmanager, node-exporter
        monitoring_args = []  # type: List[str]

        # Default Checks
        if not args.reconfig:
            daemon_ports = Monitoring.port_map[daemon_type]  # type: List[int]
            if any([port_in_use(port) for port in daemon_ports]):
                raise Error("TCP Port(s) '{}' required for {} is already in use".format(",".join(map(str, daemon_ports)), daemon_type))

        # make sure provided config-json is sufficient
        config = get_parm(args.config_json) # type: ignore
        required_files = Monitoring.components[daemon_type].get('config-json-files', list())
        required_args = Monitoring.components[daemon_type].get('config-json-args', list())
        if required_files:
            if not config or not all(c in config.get('files', {}).keys() for c in required_files):  # type: ignore
                raise Error("{} deployment requires config-json which must "
                            "contain file content for {}".format(daemon_type.capitalize(), ', '.join(required_files)))
        if required_args:
            if not config or not all(c in config.keys() for c in required_args):  # type: ignore
                raise Error("{} deployment requires config-json which must "
                            "contain arg for {}".format(daemon_type.capitalize(), ', '.join(required_args)))


        uid, gid = extract_uid_gid_monitoring(daemon_type)
        c = get_container(args.fsid, daemon_type, daemon_id)
        deploy_daemon(args.fsid, daemon_type, daemon_id, c, uid, gid,
                      reconfig=args.reconfig)

    elif daemon_type == NFSGanesha.daemon_type:
        NFSGanesha.port_in_use()
        (config, keyring) = get_config_and_keyring()
        # TODO: extract ganesha uid/gid (997, 994) ?
        (uid, gid) = extract_uid_gid()
        c = get_container(args.fsid, daemon_type, daemon_id)
        deploy_daemon(args.fsid, daemon_type, daemon_id, c, uid, gid,
                      config=config, keyring=keyring,
                      reconfig=args.reconfig)
    else:
        raise Error("{} not implemented in command_deploy function".format(daemon_type))

##################################

@infer_image
def command_run():
    # type: () -> int
    (daemon_type, daemon_id) = args.name.split('.', 1)
    c = get_container(args.fsid, daemon_type, daemon_id)
    command = c.run_cmd()
    return call_timeout(command, args.timeout)

##################################

@infer_fsid
@infer_image
def command_shell():
    # type: () -> int
    if args.fsid:
        make_log_dir(args.fsid)
    if args.name:
        if '.' in args.name:
            (daemon_type, daemon_id) = args.name.split('.', 1)
        else:
            daemon_type = args.name
            daemon_id = None
    else:
        daemon_type = 'osd'  # get the most mounts
        daemon_id = None

    if daemon_id and not args.fsid:
        raise Error('must pass --fsid to specify cluster')

    # use /etc/ceph files by default, if present.  we do this instead of
    # making these defaults in the arg parser because we don't want an error
    # if they don't exist.
    if not args.config and os.path.exists(SHELL_DEFAULT_CONF):
        args.config = SHELL_DEFAULT_CONF
    if not args.keyring and os.path.exists(SHELL_DEFAULT_KEYRING):
        args.keyring = SHELL_DEFAULT_KEYRING

    container_args = [] # type: List[str]
    mounts = get_container_mounts(args.fsid, daemon_type, daemon_id,
                                  no_config=True if args.config else False)
    if args.config:
        mounts[pathify(args.config)] = '/etc/ceph/ceph.conf:z'
    if args.keyring:
        mounts[pathify(args.keyring)] = '/etc/ceph/ceph.keyring:z'
    if args.command:
        command = args.command
    else:
        command = ['bash']
        container_args += [
            '-it',
            '-e', 'LANG=C',
            '-e', "PS1=%s" % CUSTOM_PS1,
        ]
        if args.fsid:
            home = os.path.join(args.data_dir, args.fsid, 'home')
            if not os.path.exists(home):
                logger.debug('Creating root home at %s' % home)
                makedirs(home, 0, 0, 0o660)
                if os.path.exists('/etc/skel'):
                    for f in os.listdir('/etc/skel'):
                        if f.startswith('.bash'):
                            shutil.copyfile(os.path.join('/etc/skel', f),
                                            os.path.join(home, f))
            mounts[home] = '/root'

    c = CephContainer(
        image=args.image,
        entrypoint='doesnotmatter',
        args=[],
        container_args=container_args,
        volume_mounts=mounts,
        envs=args.env,
        privileged=True)
    command = c.shell_cmd(command)

    return call_timeout(command, args.timeout)

##################################

@infer_fsid
def command_enter():
    # type: () -> int
    if not args.fsid:
        raise Error('must pass --fsid to specify cluster')
    (daemon_type, daemon_id) = args.name.split('.', 1)
    container_args = [] # type: List[str]
    if args.command:
        command = args.command
    else:
        command = ['sh']
        container_args += [
            '-it',
            '-e', 'LANG=C',
            '-e', "PS1=%s" % CUSTOM_PS1,
        ]
    c = get_container(args.fsid, daemon_type, daemon_id,
                      container_args=container_args)
    command = c.exec_cmd(command)
    return call_timeout(command, args.timeout)

##################################

@infer_fsid
@infer_image
def command_ceph_volume():
    # type: () -> None
    if args.fsid:
        make_log_dir(args.fsid)

    (uid, gid) = (0, 0) # ceph-volume runs as root
    mounts = get_container_mounts(args.fsid, 'osd', None)

    tmp_config = None
    tmp_keyring = None

    (config, keyring) = get_config_and_keyring()

    if config:
        # tmp config file
        tmp_config = write_tmp(config, uid, gid)
        mounts[tmp_config.name] = '/etc/ceph/ceph.conf:z'

    if keyring:
        # tmp keyring file
        tmp_keyring = write_tmp(keyring, uid, gid)
        mounts[tmp_keyring.name] = '/var/lib/ceph/bootstrap-osd/ceph.keyring:z'

    c = CephContainer(
        image=args.image,
        entrypoint='/usr/sbin/ceph-volume',
        args=args.command,
        privileged=True,
        volume_mounts=mounts,
    )
    out, err, code = call_throws(c.run_cmd(), verbose=True)
    if not code:
        print(out)

##################################

@infer_fsid
def command_unit():
    # type: () -> None
    if not args.fsid:
        raise Error('must pass --fsid to specify cluster')
    (daemon_type, daemon_id) = args.name.split('.', 1)
    unit_name = get_unit_name(args.fsid, daemon_type, daemon_id)
    call_throws([
        'systemctl',
        args.command,
        unit_name])

##################################

@infer_fsid
def command_logs():
    # type: () -> None
    if not args.fsid:
        raise Error('must pass --fsid to specify cluster')

    (daemon_type, daemon_id) = args.name.split('.', 1)
    unit_name = get_unit_name(args.fsid, daemon_type, daemon_id)

    cmd = [find_program('journalctl')]
    cmd.extend(['-u', unit_name])
    if args.command:
        cmd.extend(args.command)

    # call this directly, without our wrapper, so that we get an unmolested
    # stdout with logger prefixing.
    logger.debug("Running command: %s" % ' '.join(cmd))
    subprocess.call(cmd) # type: ignore

##################################

def list_networks():
    # type: () -> Dict[str,List[str]]

    ## sadly, 18.04's iproute2 4.15.0-2ubun doesn't support the -j flag,
    ## so we'll need to use a regex to parse 'ip' command output.
    #out, _, _ = call_throws(['ip', '-j', 'route', 'ls'])
    #j = json.loads(out)
    #for x in j:

    out, _, _ = call_throws([find_executable('ip'), 'route', 'ls'])
    return _parse_ip_route(out)

def _parse_ip_route(out):
    r = {}  # type: Dict[str,List[str]]
    p = re.compile(r'^(\S+) (.*)scope link (.*)src (\S+)')
    for line in out.splitlines():
        m = p.findall(line)
        if not m:
            continue
        net = m[0][0]
        ip = m[0][3]
        if net not in r:
            r[net] = []
        r[net].append(ip)
    return r

def command_list_networks():
    # type: () -> None
    r = list_networks()
    print(json.dumps(r, indent=4))

##################################

def command_ls():
    # type: () -> None
    ls = list_daemons(detail=not args.no_detail,
                      legacy_dir=args.legacy_dir)
    print(json.dumps(ls, indent=4))

def list_daemons(detail=True, legacy_dir=None):
    # type: (bool, Optional[str]) -> List[Dict[str, str]]
    host_version = None
    ls = []

    data_dir = args.data_dir
    if legacy_dir is not None:
        data_dir = os.path.abspath(legacy_dir + data_dir)

    # keep track of ceph versions we see
    seen_versions = {}  # type: Dict[str, Optional[str]]

    # /var/lib/ceph
    if os.path.exists(data_dir):
        for i in os.listdir(data_dir):
            if i in ['mon', 'osd', 'mds', 'mgr']:
                daemon_type = i
                for j in os.listdir(os.path.join(data_dir, i)):
                    if '-' not in j:
                        continue
                    (cluster, daemon_id) = j.split('-', 1)
                    fsid = get_legacy_daemon_fsid(
                            cluster, daemon_type, daemon_id,
                            legacy_dir=legacy_dir)
                    i = {
                        'style': 'legacy',
                        'name': '%s.%s' % (daemon_type, daemon_id),
                        'fsid': fsid if fsid is not None else 'unknown',
                    }
                    if detail:
                        (i['enabled'], i['state'], _) = check_unit(
                            'ceph-%s@%s' % (daemon_type, daemon_id))
                        if not host_version:
                            try:
                                out, err, code = call(['ceph', '-v'])
                                if not code and out.startswith('ceph version '):
                                    host_version = out.split(' ')[2]
                            except Exception:
                                pass
                        i['host_version'] = host_version
                    ls.append(i)
            elif is_fsid(i):
                fsid = str(i)  # convince mypy that fsid is a str here
                for j in os.listdir(os.path.join(data_dir, i)):
                    if '.' in j:
                        name = j
                        (daemon_type, daemon_id) = j.split('.', 1)
                        unit_name = get_unit_name(fsid,
                                                  daemon_type,
                                                  daemon_id)
                    else:
                        continue
                    i = {
                        'style': 'cephadm:v1',
                        'name': name,
                        'fsid': fsid,
                    }
                    if detail:
                        # get container id
                        (i['enabled'], i['state'], _) = check_unit(unit_name)
                        container_id = None
                        image_name = None
                        image_id = None
                        version = None
                        start_stamp = None

                        if 'podman' in container_path and get_podman_version() < (1, 6, 2):
                            image_field = '.ImageID'
                        else:
                            image_field = '.Image'

                        out, err, code = call(
                            [
                                container_path, 'inspect',
                                '--format', '{{.Id}},{{.Config.Image}},{{%s}},{{.Created}},{{index .Config.Labels "io.ceph.version"}}' % image_field,
                                'ceph-%s-%s' % (fsid, j)
                            ],
                            verbose_on_failure=False)
                        if not code:
                            (container_id, image_name, image_id, start,
                             version) = out.strip().split(',')
                            image_id = normalize_container_id(image_id)
                            daemon_type = name.split('.', 1)[0]
                            start_stamp = try_convert_datetime(start)
                            if not version or '.' not in version:
                                version = seen_versions.get(image_id, None)
                            if daemon_type == NFSGanesha.daemon_type:
                                version = NFSGanesha.get_version(container_id)
                            elif not version:
                                if daemon_type in Ceph.daemons:
                                    out, err, code = call(
                                        [container_path, 'exec', container_id,
                                         'ceph', '-v'])
                                    if not code and \
                                       out.startswith('ceph version '):
                                        version = out.split(' ')[2]
                                        seen_versions[image_id] = version
                                elif daemon_type == 'grafana':
                                    out, err, code = call(
                                        [container_path, 'exec', container_id,
                                         'grafana-server', '-v'])
                                    if not code and \
                                       out.startswith('Version '):
                                        version = out.split(' ')[1]
                                        seen_versions[image_id] = version
                                elif daemon_type in ['prometheus',
                                                     'alertmanager',
                                                     'node-exporter']:
                                    cmd = daemon_type.replace('-', '_')
                                    out, err, code = call(
                                        [container_path, 'exec', container_id,
                                         cmd, '--version'])
                                    if not code and \
                                       err.startswith('%s, version ' % cmd):
                                        version = err.split(' ')[2]
                                        seen_versions[image_id] = version
                                else:
                                    logging.warning('version for unknown daemon type %s' % daemon_type)
                        else:
                            vfile = os.path.join(data_dir, fsid, j, 'unit.image') # type: ignore
                            try:
                                with open(vfile, 'r') as f:
                                    image_name = f.read().strip() or None
                            except IOError:
                                pass
                        i['container_id'] = container_id
                        i['container_image_name'] = image_name
                        i['container_image_id'] = image_id
                        i['version'] = version
                        i['started'] = start_stamp
                        i['created'] = get_file_timestamp(
                            os.path.join(data_dir, fsid, j, 'unit.created')
                        )
                        i['deployed'] = get_file_timestamp(
                            os.path.join(data_dir, fsid, j, 'unit.image'))
                        i['configured'] = get_file_timestamp(
                            os.path.join(data_dir, fsid, j, 'unit.configured'))

                    ls.append(i)

    # /var/lib/rook
    # WRITE ME
    return ls


##################################

@default_image
def command_adopt():
    # type: () -> None

    if not args.skip_pull:
        logger.info('Pulling latest %s container...' % args.image)
        call_throws([container_path, 'pull', args.image])

    (daemon_type, daemon_id) = args.name.split('.', 1)

    # legacy check
    if args.style != 'legacy':
        raise Error('adoption of style %s not implemented' % args.style)

    # lock
    fsid = get_legacy_daemon_fsid(args.cluster,
                                  daemon_type,
                                  daemon_id,
                                  legacy_dir=args.legacy_dir)
    if not fsid:
        raise Error('could not detect legacy fsid; set fsid in ceph.conf')
    l = FileLock(fsid)
    l.acquire()

    # call correct adoption
    if daemon_type in Ceph.daemons:
        command_adopt_ceph(daemon_type, daemon_id, fsid);
    elif daemon_type == 'prometheus':
        command_adopt_prometheus(daemon_id, fsid)
    elif daemon_type == 'grafana':
        command_adopt_grafana(daemon_id, fsid)
    elif daemon_type == 'node-exporter':
        raise Error('adoption of node-exporter not implemented')
    elif daemon_type == 'alertmanager':
        command_adopt_alertmanager(daemon_id, fsid)
    else:
        raise Error('daemon type %s not recognized' % daemon_type)



def command_adopt_ceph(daemon_type, daemon_id, fsid):
    # type: (str, str, str) -> None

    (uid, gid) = extract_uid_gid()

    data_dir_src = ('/var/lib/ceph/%s/%s-%s' %
                    (daemon_type, args.cluster, daemon_id))
    data_dir_src = os.path.abspath(args.legacy_dir + data_dir_src)

    osd_fsid = None
    if daemon_type == 'osd':
        path = os.path.join(data_dir_src, 'fsid')
        try:
            with open(path, 'r') as f:
                osd_fsid = f.read().strip()
        except IOError:
            raise Error('unable to read OSD fsid from %s' % path)
        os_type = None
        if os.path.exists(os.path.join(data_dir_src, 'type')):
            with open(os.path.join(data_dir_src, 'type')) as f:
                os_type = f.read().strip()
        else:
            raise Error('"type" file missing for OSD data dir')
        logger.info('objectstore_type is %s' % os_type)
        if os_type == 'filestore':
            raise Error('FileStore is not supported by cephadm')

    # NOTE: implicit assumption here that the units correspond to the
    # cluster we are adopting based on the /etc/{defaults,sysconfig}/ceph
    # CLUSTER field.
    unit_name = 'ceph-%s@%s' % (daemon_type, daemon_id)
    (enabled, state, _) = check_unit(unit_name)
    if state == 'running':
        logger.info('Stopping old systemd unit %s...' % unit_name)
        call_throws(['systemctl', 'stop', unit_name])
    if enabled:
        logger.info('Disabling old systemd unit %s...' % unit_name)
        call_throws(['systemctl', 'disable', unit_name])

    # data
    logger.info('Moving data...')
    data_dir_dst = make_data_dir(fsid, daemon_type, daemon_id,
                                 uid=uid, gid=gid)
    move_files(glob(os.path.join(data_dir_src, '*')),
               data_dir_dst,
               uid=uid, gid=gid)
    logger.debug('Remove dir \'%s\'' % (data_dir_src))
    if os.path.ismount(data_dir_src):
        call_throws(['umount', data_dir_src])
    os.rmdir(data_dir_src)

    logger.info('Chowning content...')
    call_throws(['chown', '-c', '-R', '%d.%d' % (uid, gid), data_dir_dst])

    if daemon_type == 'mon':
        # rename *.ldb -> *.sst, in case they are coming from ubuntu
        store = os.path.join(data_dir_dst, 'store.db')
        num_renamed = 0
        if os.path.exists(store):
            for oldf in os.listdir(store):
                if oldf.endswith('.ldb'):
                    newf = oldf.replace('.ldb', '.sst')
                    oldp = os.path.join(store, oldf)
                    newp = os.path.join(store, newf)
                    logger.debug('Renaming %s -> %s' % (oldp, newp))
                    os.rename(oldp, newp)
        if num_renamed:
            logger.info('Renamed %d leveldb *.ldb files to *.sst',
                        num_renamed)
    if daemon_type == 'osd':
        for n in ['block', 'block.db', 'block.wal']:
            p = os.path.join(data_dir_dst, n)
            if os.path.exists(p):
                logger.info('Chowning %s...' % p)
                os.chown(p, uid, gid)
        # disable the ceph-volume 'simple' mode files on the host
        simple_fn = os.path.join('/etc/ceph/osd',
                                 '%s-%s.json' % (daemon_id, osd_fsid))
        if os.path.exists(simple_fn):
            new_fn = simple_fn + '.adopted-by-cephadm'
            logger.info('Renaming %s -> %s', simple_fn, new_fn)
            os.rename(simple_fn, new_fn)
            logger.info('Disabling host unit ceph-volume@ simple unit...')
            call_throws(['systemctl', 'disable',
                         'ceph-volume@simple-%s-%s.service' % (
                             daemon_id, osd_fsid)])
        else:
            # assume this is an 'lvm' c-v for now, but don't error
            # out if it's not.
            logger.info('Disabling host unit ceph-volume@ lvm unit...')
            call(['systemctl', 'disable',
                  'ceph-volume@lvm-%s-%s.service' % (daemon_id, osd_fsid)])

    # config
    config_src = '/etc/ceph/%s.conf' % (args.cluster)
    config_src = os.path.abspath(args.legacy_dir + config_src)
    config_dst = os.path.join(data_dir_dst, 'config')
    copy_files([config_src], config_dst, uid=uid, gid=gid)

    # logs
    logger.info('Moving logs...')
    log_dir_src = ('/var/log/ceph/%s-%s.%s.log*' %
                    (args.cluster, daemon_type, daemon_id))
    log_dir_src = os.path.abspath(args.legacy_dir + log_dir_src)
    log_dir_dst = make_log_dir(fsid, uid=uid, gid=gid)
    move_files(glob(log_dir_src),
               log_dir_dst,
               uid=uid, gid=gid)

    logger.info('Creating new units...')
    make_var_run(fsid, uid, gid)
    c = get_container(fsid, daemon_type, daemon_id)
    deploy_daemon_units(fsid, uid, gid, daemon_type, daemon_id, c,
                        enable=True,  # unconditionally enable the new unit
                        start=(state == 'running'),
                        osd_fsid=osd_fsid)
    update_firewalld(daemon_type)


def command_adopt_prometheus(daemon_id, fsid):
    # type: (str, str) -> None

    daemon_type = 'prometheus'
    (uid, gid) = extract_uid_gid_monitoring(daemon_type)

    _stop_and_disable('prometheus')

    data_dir_dst = make_data_dir(fsid, daemon_type, daemon_id,
                                     uid=uid, gid=gid)

    # config
    config_src = '/etc/prometheus/prometheus.yml'
    config_src = os.path.abspath(args.legacy_dir + config_src)
    config_dst = os.path.join(data_dir_dst, 'etc/prometheus')
    copy_files([config_src], config_dst, uid=uid, gid=gid)

    # data
    data_src = '/var/lib/prometheus/metrics/'
    data_src = os.path.abspath(args.legacy_dir + data_src)
    data_dst = os.path.join(data_dir_dst, 'data')
    copy_tree([data_src], data_dst, uid=uid, gid=gid)

    make_var_run(fsid, uid, gid)
    c = get_container(fsid, daemon_type, daemon_id)
    deploy_daemon(fsid, daemon_type, daemon_id, c, uid, gid)
    update_firewalld(daemon_type)

def command_adopt_grafana(daemon_id, fsid):
    # type: (str, str) -> None

    daemon_type = 'grafana'
    (uid, gid) = extract_uid_gid_monitoring(daemon_type)

    _stop_and_disable('grafana-server')

    data_dir_dst = make_data_dir(fsid, daemon_type, daemon_id,
                                     uid=uid, gid=gid)

    # config
    config_src = '/etc/grafana/grafana.ini'
    config_src = os.path.abspath(args.legacy_dir + config_src)
    config_dst = os.path.join(data_dir_dst, 'etc/grafana')
    makedirs(config_dst, uid, gid, 0o755)
    copy_files([config_src], config_dst, uid=uid, gid=gid)

    prov_src = '/etc/grafana/provisioning/'
    prov_src = os.path.abspath(args.legacy_dir + prov_src)
    prov_dst = os.path.join(data_dir_dst, 'etc/grafana')
    copy_tree([prov_src], prov_dst, uid=uid, gid=gid)

    # cert
    cert = '/etc/grafana/grafana.crt'
    key = '/etc/grafana/grafana.key'
    if os.path.exists(cert) and os.path.exists(key):
        cert_src = '/etc/grafana/grafana.crt'
        cert_src = os.path.abspath(args.legacy_dir + cert_src)
        makedirs(os.path.join(data_dir_dst, 'etc/grafana/certs'), uid, gid, 0o755)
        cert_dst = os.path.join(data_dir_dst, 'etc/grafana/certs/cert_file')
        copy_files([cert_src], cert_dst, uid=uid, gid=gid)

        key_src = '/etc/grafana/grafana.key'
        key_src = os.path.abspath(args.legacy_dir + key_src)
        key_dst = os.path.join(data_dir_dst, 'etc/grafana/certs/cert_key')
        copy_files([key_src], key_dst, uid=uid, gid=gid)

        _adjust_grafana_ini(os.path.join(config_dst, 'grafana.ini'))
    else:
        logger.debug("Skipping ssl, missing cert {} or key {}".format(cert, key))


    # data - possible custom dashboards/plugins
    data_src = '/var/lib/grafana/'
    data_src = os.path.abspath(args.legacy_dir + data_src)
    data_dst = os.path.join(data_dir_dst, 'data')
    copy_tree([data_src], data_dst, uid=uid, gid=gid)

    make_var_run(fsid, uid, gid)
    c = get_container(fsid, daemon_type, daemon_id)
    deploy_daemon(fsid, daemon_type, daemon_id, c, uid, gid)
    update_firewalld(daemon_type)

def command_adopt_alertmanager(daemon_id, fsid):
    # type: (str, str) -> None

    daemon_type = 'alertmanager'
    (uid, gid) = extract_uid_gid_monitoring(daemon_type)

    _stop_and_disable('prometheus-alertmanager')

    data_dir_dst = make_data_dir(fsid, daemon_type, daemon_id,
                                     uid=uid, gid=gid)

    # config
    config_src = '/etc/prometheus/alertmanager.yml'
    config_src = os.path.abspath(args.legacy_dir + config_src)
    config_dst = os.path.join(data_dir_dst, 'etc/alertmanager')
    makedirs(config_dst, uid, gid, 0o755)
    copy_files([config_src], config_dst, uid=uid, gid=gid)

    # data
    data_src = '/var/lib/prometheus/alertmanager/'
    data_src = os.path.abspath(args.legacy_dir + data_src)
    data_dst = os.path.join(data_dir_dst, 'etc/alertmanager/data')
    copy_tree([data_src], data_dst, uid=uid, gid=gid)

    make_var_run(fsid, uid, gid)
    c = get_container(fsid, daemon_type, daemon_id)
    deploy_daemon(fsid, daemon_type, daemon_id, c, uid, gid)
    update_firewalld(daemon_type)

def _adjust_grafana_ini(filename):
    # type: (str) -> None

    # Update cert_file, cert_key pathnames in server section
    # ConfigParser does not preserve comments
    try:
        with open(filename, "r") as grafana_ini:
            lines = grafana_ini.readlines()
        with open("{}.new".format(filename), "w") as grafana_ini:
            server_section=False
            for line in lines:
                if line.startswith('['):
                    server_section=False
                if line.startswith('[server]'):
                    server_section=True
                if server_section:
                    line = re.sub(r'^cert_file.*',
                            'cert_file = /etc/grafana/certs/cert_file', line)
                    line = re.sub(r'^cert_key.*',
                            'cert_key = /etc/grafana/certs/cert_key', line)
                grafana_ini.write(line)
        os.rename("{}.new".format(filename), filename)
    except OSError as err:
        raise Error("Cannot update {}: {}".format(filename, err))


def _stop_and_disable(unit_name):
    # type: (str) -> None

    (enabled, state, _) = check_unit(unit_name)
    if state == 'running':
        logger.info('Stopping old systemd unit %s...' % unit_name)
        call_throws(['systemctl', 'stop', unit_name])
    if enabled:
        logger.info('Disabling old systemd unit %s...' % unit_name)
        call_throws(['systemctl', 'disable', unit_name])


##################################

def command_rm_daemon():
    # type: () -> None

    l = FileLock(args.fsid)
    l.acquire()

    (daemon_type, daemon_id) = args.name.split('.', 1)
    if daemon_type in ['mon', 'osd'] and not args.force:
        raise Error('must pass --force to proceed: '
                      'this command may destroy precious data!')
    unit_name = get_unit_name(args.fsid, daemon_type, daemon_id)
    call(['systemctl', 'stop', unit_name],
         verbose_on_failure=False)
    call(['systemctl', 'reset-failed', unit_name],
         verbose_on_failure=False)
    call(['systemctl', 'disable', unit_name],
         verbose_on_failure=False)
    data_dir = get_data_dir(args.fsid, daemon_type, daemon_id)
    if daemon_type in ['mon', 'osd', 'prometheus'] and \
       not args.force_delete_data:
        # rename it out of the way -- do not delete
        backup_dir = os.path.join(args.data_dir, args.fsid, 'removed')
        if not os.path.exists(backup_dir):
            makedirs(backup_dir, 0, 0, DATA_DIR_MODE)
        dirname = '%s.%s_%s' % (daemon_type, daemon_id,
                                datetime.datetime.utcnow().strftime(DATEFMT))
        os.rename(data_dir,
                  os.path.join(backup_dir, dirname))
    else:
        call_throws(['rm', '-rf', data_dir])

##################################

def command_rm_cluster():
    # type: () -> None
    if not args.force:
        raise Error('must pass --force to proceed: '
                      'this command may destroy precious data!')

    l = FileLock(args.fsid)
    l.acquire()

    # stop + disable individual daemon units
    for d in list_daemons(detail=False):
        if d['fsid'] != args.fsid:
            continue
        if d['style'] != 'cephadm:v1':
            continue
        unit_name = get_unit_name(args.fsid, d['name'])
        call(['systemctl', 'stop', unit_name],
             verbose_on_failure=False)
        call(['systemctl', 'reset-failed', unit_name],
             verbose_on_failure=False)
        call(['systemctl', 'disable', unit_name],
             verbose_on_failure=False)

    # cluster units
    for unit_name in ['ceph-%s.target' % args.fsid]:
        call(['systemctl', 'stop', unit_name],
             verbose_on_failure=False)
        call(['systemctl', 'reset-failed', unit_name],
             verbose_on_failure=False)
        call(['systemctl', 'disable', unit_name],
             verbose_on_failure=False)

    slice_name = 'system-%s.slice' % (('ceph-%s' % args.fsid).replace('-',
                                                                      '\\x2d'))
    call(['systemctl', 'stop', slice_name],
         verbose_on_failure=False)

    # rm units
    call_throws(['rm', '-f', args.unit_dir +
                             '/ceph-%s@.service' % args.fsid])
    call_throws(['rm', '-f', args.unit_dir +
                             '/ceph-%s.target' % args.fsid])
    call_throws(['rm', '-rf',
                  args.unit_dir + '/ceph-%s.target.wants' % args.fsid])
    # rm data
    call_throws(['rm', '-rf', args.data_dir + '/' + args.fsid])
    # rm logs
    call_throws(['rm', '-rf', args.log_dir + '/' + args.fsid])
    call_throws(['rm', '-rf', args.log_dir +
                             '/*.wants/ceph-%s@*' % args.fsid])
    # rm logrotate config
    call_throws(['rm', '-f', args.logrotate_dir + '/ceph-%s' % args.fsid])


##################################

def check_time_sync(enabler=None):
    # type: (Optional[Packager]) -> bool
    units = [
        'chrony.service',  # 18.04 (at least)
        'chronyd.service', # el / opensuse
        'systemd-timesyncd.service',
        'ntpd.service', # el7 (at least)
        'ntp.service',  # 18.04 (at least)
    ]
    if not check_units(units, enabler=None):
        logger.warning('No time sync service is running; checked for %s' % units)
        return False
    return True

def command_check_host():
    # type: () -> None
    # caller already checked for docker/podman
    logger.info('podman|docker (%s) is present' % container_path)

    commands = ['systemctl', 'lvcreate']

    for command in commands:
        try:
            find_program(command)
            logger.info('%s is present' % command)
        except ValueError:
            raise Error('%s binary does not appear to be installed' % command)

    # check for configured+running chronyd or ntp
    if not check_time_sync():
        raise Error('No time synchronization is active')

    if 'expect_hostname' in args and args.expect_hostname:
        if get_hostname() != args.expect_hostname:
            raise Error('hostname "%s" does not match expected hostname "%s"' % (
                get_hostname(), args.expect_hostname))
        logger.info('Hostname "%s" matches what is expected.',
                    args.expect_hostname)

    logger.info('Host looks OK')

##################################

def command_prepare_host():
    # type: () -> None
    logger.info('Verifying podman|docker is present...')
    pkg = None
    if not container_path:
        if not pkg:
            pkg = create_packager()
        pkg.install_podman()

    logger.info('Verifying lvm2 is present...')
    if not find_executable('lvcreate'):
        if not pkg:
            pkg = create_packager()
        pkg.install(['lvm2'])

    logger.info('Verifying time synchronization is in place...')
    if not check_time_sync():
        if not pkg:
            pkg = create_packager()
        pkg.install(['chrony'])
        # check again, and this time try to enable
        # the service
        check_time_sync(enabler=pkg)

    if 'expect_hostname' in args and args.expect_hostname and args.expect_hostname != get_hostname():
        logger.warning('Adjusting hostname from %s -> %s...' % (get_hostname(), args.expect_hostname))
        call_throws(['hostname', args.expect_hostname])
        with open('/etc/hostname', 'w') as f:
            f.write(args.expect_hostname + '\n')

    logger.info('Repeating the final host check...')
    command_check_host()

##################################

class CustomValidation(argparse.Action):

    def _check_name(self, values):
        try:
            (daemon_type, daemon_id) = values.split('.', 1)
        except ValueError:
            raise argparse.ArgumentError(self,
                                         "must be of the format <type>.<id>. For example, osd.1 or prometheus.myhost.com")

        daemons = get_supported_daemons()
        if daemon_type not in daemons:
            raise argparse.ArgumentError(self,
                                         "name must declare the type of daemon e.g. "
                                         "{}".format(', '.join(daemons)))

    def __call__(self, parser, namespace, values, option_string=None):
        if self.dest == "name":
            self._check_name(values)
            setattr(namespace, self.dest, values)

##################################

def get_distro():
    distro = None
    distro_version = None
    distro_codename = None
    with open('/etc/os-release', 'r') as f:
        for line in f.readlines():
            line = line.strip()
            if '=' not in line or line.startswith('#'):
                continue
            (var, val) = line.split('=', 1)
            if val[0] == '"' and val[-1] == '"':
                val = val[1:-1]
            if var == 'ID':
                distro = val.lower()
            elif var == 'VERSION_ID':
                distro_version = val.lower()
            elif var == 'VERSION_CODENAME':
                distro_codename = val.lower()
    return distro, distro_version, distro_codename

class Packager(object):
    def __init__(self, stable=None, version=None, branch=None, commit=None):
        assert \
            (stable and not version and not branch and not commit) or \
            (not stable and version and not branch and not commit) or \
            (not stable and not version and branch) or \
            (not stable and not version and not branch and not commit)
        self.stable = stable
        self.version = version
        self.branch = branch
        self.commit = commit

    def add_repo(self):
        raise NotImplementedError

    def rm_repo(self):
        raise NotImplementedError

    def query_shaman(self, distro, distro_version, branch, commit):
        # query shaman
        logging.info('Fetching repo metadata from shaman and chacra...')
        shaman_url = 'https://shaman.ceph.com/api/repos/ceph/{branch}/{sha1}/{distro}/{distro_version}/repo/?arch={arch}'.format(
            distro=distro,
            distro_version=distro_version,
            branch=branch,
            sha1=commit or 'latest',
            arch=get_arch()
        )
        try:
            shaman_response = urlopen(shaman_url)
        except HTTPError as err:
            logging.error('repository not found in shaman (might not be available yet)')
            raise Error('%s, failed to fetch %s' % (err, shaman_url))
        try:
            chacra_url = shaman_response.geturl()
            chacra_response = urlopen(chacra_url)
        except HTTPError as err:
            logging.error('repository not found in chacra (might not be available yet)')
            raise Error('%s, failed to fetch %s' % (err, chacra_url))
        return chacra_response.read().decode('utf-8')

    def repo_gpgkey(self):
        if args.gpg_url:
            return args.gpg_url
        if self.stable or self.version:
            return 'https://download.ceph.com/keys/release.asc', 'release'
        else:
            return 'https://download.ceph.com/keys/autobuild.asc', 'autobuild'

    def enable_service(self, service):
        """
        Start and enable the service (typically using systemd).
        """
        call_throws(['systemctl', 'enable', '--now', service])


class Apt(Packager):
    DISTRO_NAMES = {
        'ubuntu': 'ubuntu',
        'debian': 'debian',
    }

    def __init__(self, stable, version, branch, commit,
                 distro, distro_version, distro_codename):
        super(Apt, self).__init__(stable=stable, version=version,
                                  branch=branch, commit=commit)
        self.distro = self.DISTRO_NAMES[distro]
        self.distro_codename = distro_codename

    def repo_path(self):
        return '/etc/apt/sources.list.d/ceph.list'

    def add_repo(self):
        url, name = self.repo_gpgkey()
        logging.info('Installing repo GPG key from %s...' % url)
        try:
            response = urlopen(url)
        except HTTPError as err:
            logging.error('failed to fetch GPG repo key from %s: %s' % (
                url, err))
            raise Error('failed to fetch GPG key')
        key = response.read().decode('utf-8')
        with open('/etc/apt/trusted.gpg.d/ceph.%s.gpg' % name, 'w') as f:
            f.write(key)

        if self.version:
            content = 'deb %s/debian-%s/ %s main\n' % (
                args.repo_url, self.version, self.distro_codename)
        elif self.stable:
            content = 'deb %s/debian-%s/ %s main\n' % (
                args.repo_url, self.stable, self.distro_codename)
        else:
            content = self.query_shaman(self.distro, self.distro_codename, self.branch,
                                        self.commit)

        logging.info('Installing repo file at %s...' % self.repo_path())
        with open(self.repo_path(), 'w') as f:
            f.write(content)

    def rm_repo(self):
        for name in ['autobuild', 'release']:
            p = '/etc/apt/trusted.gpg.d/ceph.%s.gpg' % name
            if os.path.exists(p):
                logging.info('Removing repo GPG key %s...' % p)
                os.unlink(p)
        if os.path.exists(self.repo_path()):
            logging.info('Removing repo at %s...' % self.repo_path())
            os.unlink(self.repo_path())

    def install(self, ls):
        logging.info('Installing packages %s...' % ls)
        call_throws(['apt', 'install', '-y'] + ls)

    def install_podman(self):
        if self.distro == 'ubuntu':
            logging.info('Setting up repo for pdoman...')
            self.install(['software-properties-common'])
            call_throws(['add-apt-repository', '-y', 'ppa:projectatomic/ppa'])
            call_throws(['apt', 'update'])

        logging.info('Attempting podman install...')
        try:
            self.install(['podman'])
        except Error as e:
            logging.info('Podman did not work.  Falling back to docker...')
            self.install(['docker.io'])

class YumDnf(Packager):
    DISTRO_NAMES = {
        'centos': ('centos', 'el'),
        'rhel': ('centos', 'el'),
        'scientific': ('centos', 'el'),
        'fedora': ('fedora', 'fc'),
    }

    def __init__(self, stable, version, branch, commit,
                 distro, distro_version):
        super(YumDnf, self).__init__(stable=stable, version=version,
                                     branch=branch, commit=commit)
        self.major = int(distro_version.split('.')[0])
        self.distro_normalized = self.DISTRO_NAMES[distro][0]
        self.distro_code = self.DISTRO_NAMES[distro][1] + str(self.major)
        if (self.distro_code == 'fc' and self.major >= 30) or \
           (self.distro_code == 'el' and self.major >= 8):
            self.tool = 'dnf'
        else:
            self.tool = 'yum'

    def custom_repo(self, **kw):
        """
        Repo files need special care in that a whole line should not be present
        if there is no value for it. Because we were using `format()` we could
        not conditionally add a line for a repo file. So the end result would
        contain a key with a missing value (say if we were passing `None`).

        For example, it could look like::

        [ceph repo]
        name= ceph repo
        proxy=
        gpgcheck=

        Which breaks. This function allows us to conditionally add lines,
        preserving an order and be more careful.

        Previously, and for historical purposes, this is how the template used
        to look::

        custom_repo =
        [{repo_name}]
        name={name}
        baseurl={baseurl}
        enabled={enabled}
        gpgcheck={gpgcheck}
        type={_type}
        gpgkey={gpgkey}
        proxy={proxy}

        """
        lines = []

        # by using tuples (vs a dict) we preserve the order of what we want to
        # return, like starting with a [repo name]
        tmpl = (
            ('reponame', '[%s]'),
            ('name', 'name=%s'),
            ('baseurl', 'baseurl=%s'),
            ('enabled', 'enabled=%s'),
            ('gpgcheck', 'gpgcheck=%s'),
            ('_type', 'type=%s'),
            ('gpgkey', 'gpgkey=%s'),
            ('proxy', 'proxy=%s'),
            ('priority', 'priority=%s'),
        )

        for line in tmpl:
            tmpl_key, tmpl_value = line  # key values from tmpl

            # ensure that there is an actual value (not None nor empty string)
            if tmpl_key in kw and kw.get(tmpl_key) not in (None, ''):
                lines.append(tmpl_value % kw.get(tmpl_key))

        return '\n'.join(lines)

    def repo_path(self):
        return '/etc/yum.repos.d/ceph.repo'

    def repo_baseurl(self):
        assert self.stable or self.version
        if self.version:
            return '%s/rpm-%s/%s' % (args.repo_url, self.version,
                                     self.distro_code)
        else:
            return '%s/rpm-%s/%s' % (args.repo_url, self.stable,
                                     self.distro_code)

    def add_repo(self):
        if self.stable or self.version:
            content = ''
            for n, t in {
                    'Ceph': '$basearch',
                    'Ceph-noarch': 'noarch',
                    'Ceph-source': 'SRPMS'}.items():
                content += '[%s]\n' % (n)
                content += self.custom_repo(
                    name='Ceph %s' % t,
                    baseurl=self.repo_baseurl() + '/' + t,
                    enabled=1,
                    gpgcheck=1,
                    gpgkey=self.repo_gpgkey()[0],
                )
                content += '\n\n'
        else:
            content = self.query_shaman(self.distro_normalized, self.major,
                                        self.branch,
                                        self.commit)

        logging.info('Writing repo to %s...' % self.repo_path())
        with open(self.repo_path(), 'w') as f:
            f.write(content)

        if self.distro_code.startswith('el'):
            logger.info('Enabling EPEL...')
            call_throws([self.tool, 'install', '-y', 'epel-release'])
        if self.distro_code == 'el8':
            # we also need Ken's copr repo, at least for now
            logger.info('Enabling supplementary copr repo ktdreyer/ceph-el8...')
            call_throws(['dnf', 'copr', 'enable', '-y', 'ktdreyer/ceph-el8'])

    def rm_repo(self):
        if os.path.exists(self.repo_path()):
            os.unlink(self.repo_path())
        if self.distro_code == 'el8':
            logger.info('Disabling supplementary copr repo ktdreyer/ceph-el8...')
            call_throws(['dnf', 'copr', 'disable', '-y', 'ktdreyer/ceph-el8'])

    def install(self, ls):
        logger.info('Installing packages %s...' % ls)
        call_throws([self.tool, 'install', '-y'] + ls)

    def install_podman(self):
        self.install(['podman'])


class Zypper(Packager):
    DISTRO_NAMES = [
        'sles',
        'opensuse-tumbleweed',
        'opensuse-leap'
    ]

    def __init__(self, stable, version, branch, commit,
                 distro, distro_version):
        super(Zypper, self).__init__(stable=stable, version=version,
                                     branch=branch, commit=commit)
        self.tool = 'zypper'
        self.distro = 'opensuse'
        self.distro_version = '15.1'
        if 'tumbleweed' not in distro and distro_version is not None:
            self.distro_version = distro_version

    def custom_repo(self, **kw):
        """
        See YumDnf for format explanation.
        """
        lines = []

        # by using tuples (vs a dict) we preserve the order of what we want to
        # return, like starting with a [repo name]
        tmpl = (
            ('reponame', '[%s]'),
            ('name', 'name=%s'),
            ('baseurl', 'baseurl=%s'),
            ('enabled', 'enabled=%s'),
            ('gpgcheck', 'gpgcheck=%s'),
            ('_type', 'type=%s'),
            ('gpgkey', 'gpgkey=%s'),
            ('proxy', 'proxy=%s'),
            ('priority', 'priority=%s'),
        )

        for line in tmpl:
            tmpl_key, tmpl_value = line  # key values from tmpl

            # ensure that there is an actual value (not None nor empty string)
            if tmpl_key in kw and kw.get(tmpl_key) not in (None, ''):
                lines.append(tmpl_value % kw.get(tmpl_key))

        return '\n'.join(lines)

    def repo_path(self):
        return '/etc/zypp/repos.d/ceph.repo'

    def repo_baseurl(self):
        assert self.stable or self.version
        if self.version:
            return '%s/rpm-%s/%s' % (args.repo_url, self.stable, self.distro)
        else:
            return '%s/rpm-%s/%s' % (args.repo_url, self.stable, self.distro)

    def add_repo(self):
        if self.stable or self.version:
            content = ''
            for n, t in {
                    'Ceph': '$basearch',
                    'Ceph-noarch': 'noarch',
                    'Ceph-source': 'SRPMS'}.items():
                content += '[%s]\n' % (n)
                content += self.custom_repo(
                    name='Ceph %s' % t,
                    baseurl=self.repo_baseurl() + '/' + t,
                    enabled=1,
                    gpgcheck=1,
                    gpgkey=self.repo_gpgkey()[0],
                )
                content += '\n\n'
        else:
            content = self.query_shaman(self.distro, self.distro_version,
                                        self.branch,
                                        self.commit)

        logging.info('Writing repo to %s...' % self.repo_path())
        with open(self.repo_path(), 'w') as f:
            f.write(content)

    def rm_repo(self):
        if os.path.exists(self.repo_path()):
            os.unlink(self.repo_path())

    def install(self, ls):
        logger.info('Installing packages %s...' % ls)
        call_throws([self.tool, 'in', '-y'] + ls)

    def install_podman(self):
        self.install(['podman'])


def create_packager(stable=None, version=None, branch=None, commit=None):
    distro, distro_version, distro_codename = get_distro()
    if distro in YumDnf.DISTRO_NAMES:
        return YumDnf(stable=stable, version=version,
                      branch=branch, commit=commit,
                   distro=distro, distro_version=distro_version)
    elif distro in Apt.DISTRO_NAMES:
        return Apt(stable=stable, version=version,
                   branch=branch, commit=commit,
                   distro=distro, distro_version=distro_version,
                   distro_codename=distro_codename)
    elif distro in Zypper.DISTRO_NAMES:
        return Zypper(stable=stable, version=version,
                      branch=branch, commit=commit,
                      distro=distro, distro_version=distro_version)
    raise Error('Distro %s version %s not supported' % (distro, distro_version))


def command_add_repo():
    if args.version and args.release:
        raise Error('you can specify either --release or --version but not both')
    if args.version:
        try:
            (x, y, z) = args.version.split('.')
        except Exception as e:
            raise Error('version must be in the form x.y.z (e.g., 15.2.0)')

    pkg = create_packager(stable=args.release,
                          version=args.version,
                          branch=args.dev,
                          commit=args.dev_commit)
    pkg.add_repo()

def command_rm_repo():
    pkg = create_packager()
    pkg.rm_repo()

def command_install():
    pkg = create_packager()
    pkg.install(args.packages)

##################################

def _get_parser():
    # type: () -> argparse.ArgumentParser
    parser = argparse.ArgumentParser(
        description='Bootstrap Ceph daemons with systemd and containers.',
        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    parser.add_argument(
        '--image',
        help='container image. Can also be set via the "CEPHADM_IMAGE" '
        'env var')
    parser.add_argument(
        '--docker',
        action='store_true',
        help='use docker instead of podman')
    parser.add_argument(
        '--data-dir',
        default=DATA_DIR,
        help='base directory for daemon data')
    parser.add_argument(
        '--log-dir',
        default=LOG_DIR,
        help='base directory for daemon logs')
    parser.add_argument(
        '--logrotate-dir',
        default=LOGROTATE_DIR,
        help='location of logrotate configuration files')
    parser.add_argument(
        '--unit-dir',
        default=UNIT_DIR,
        help='base directory for systemd units')
    parser.add_argument(
        '--verbose', '-v',
        action='store_true',
        help='Show debug-level log messages')
    parser.add_argument(
        '--timeout',
        type=int,
        default=DEFAULT_TIMEOUT,
        help='timeout in seconds')
    parser.add_argument(
        '--retry',
        type=int,
        default=DEFAULT_RETRY,
        help='max number of retries')

    subparsers = parser.add_subparsers(help='sub-command')

    parser_version = subparsers.add_parser(
        'version', help='get ceph version from container')
    parser_version.set_defaults(func=command_version)

    parser_pull = subparsers.add_parser(
        'pull', help='pull latest image version')
    parser_pull.set_defaults(func=command_pull)

    parser_inspect_image = subparsers.add_parser(
        'inspect-image', help='inspect local container image')
    parser_inspect_image.set_defaults(func=command_inspect_image)

    parser_ls = subparsers.add_parser(
        'ls', help='list daemon instances on this host')
    parser_ls.set_defaults(func=command_ls)
    parser_ls.add_argument(
        '--no-detail',
        action='store_true',
        help='Do not include daemon status')
    parser_ls.add_argument(
        '--legacy-dir',
        default='/',
        help='base directory for legacy daemon data')

    parser_list_networks = subparsers.add_parser(
        'list-networks', help='list IP networks')
    parser_list_networks.set_defaults(func=command_list_networks)

    parser_adopt = subparsers.add_parser(
        'adopt', help='adopt daemon deployed with a different tool')
    parser_adopt.set_defaults(func=command_adopt)
    parser_adopt.add_argument(
        '--name', '-n',
        required=True,
        help='daemon name (type.id)')
    parser_adopt.add_argument(
        '--style',
        required=True,
        help='deployment style (legacy, ...)')
    parser_adopt.add_argument(
        '--cluster',
        default='ceph',
        help='cluster name')
    parser_adopt.add_argument(
        '--legacy-dir',
        default='/',
        help='base directory for legacy daemon data')
    parser_adopt.add_argument(
        '--config-json',
        help='Additional configuration information in JSON format')
    parser_adopt.add_argument(
        '--skip-firewalld',
        action='store_true',
        help='Do not configure firewalld')
    parser_adopt.add_argument(
        '--skip-pull',
        action='store_true',
        help='do not pull the latest image before adopting')

    parser_rm_daemon = subparsers.add_parser(
        'rm-daemon', help='remove daemon instance')
    parser_rm_daemon.set_defaults(func=command_rm_daemon)
    parser_rm_daemon.add_argument(
        '--name', '-n',
        required=True,
        action=CustomValidation,
        help='daemon name (type.id)')
    parser_rm_daemon.add_argument(
        '--fsid',
        required=True,
        help='cluster FSID')
    parser_rm_daemon.add_argument(
        '--force',
        action='store_true',
        help='proceed, even though this may destroy valuable data')
    parser_rm_daemon.add_argument(
        '--force-delete-data',
        action='store_true',
        help='delete valuable daemon data instead of making a backup')

    parser_rm_cluster = subparsers.add_parser(
        'rm-cluster', help='remove all daemons for a cluster')
    parser_rm_cluster.set_defaults(func=command_rm_cluster)
    parser_rm_cluster.add_argument(
        '--fsid',
        required=True,
        help='cluster FSID')
    parser_rm_cluster.add_argument(
        '--force',
        action='store_true',
        help='proceed, even though this may destroy valuable data')

    parser_run = subparsers.add_parser(
        'run', help='run a ceph daemon, in a container, in the foreground')
    parser_run.set_defaults(func=command_run)
    parser_run.add_argument(
        '--name', '-n',
        required=True,
        help='daemon name (type.id)')
    parser_run.add_argument(
        '--fsid',
        required=True,
        help='cluster FSID')

    parser_shell = subparsers.add_parser(
        'shell', help='run an interactive shell inside a daemon container')
    parser_shell.set_defaults(func=command_shell)
    parser_shell.add_argument(
        '--fsid',
        help='cluster FSID')
    parser_shell.add_argument(
        '--name', '-n',
        help='daemon name (type.id)')
    parser_shell.add_argument(
        '--config', '-c',
        help='ceph.conf to pass through to the container')
    parser_shell.add_argument(
        '--keyring', '-k',
        help='ceph.keyring to pass through to the container')
    parser_shell.add_argument(
        '--env', '-e',
        action='append',
        default=[],
        help='set environment variable')
    parser_shell.add_argument(
        'command', nargs='*',
        help='command (optional)')

    parser_enter = subparsers.add_parser(
        'enter', help='run an interactive shell inside a running daemon container')
    parser_enter.set_defaults(func=command_enter)
    parser_enter.add_argument(
        '--fsid',
        help='cluster FSID')
    parser_enter.add_argument(
        '--name', '-n',
        required=True,
        help='daemon name (type.id)')
    parser_enter.add_argument(
        'command', nargs='*',
        help='command')

    parser_ceph_volume = subparsers.add_parser(
        'ceph-volume', help='run ceph-volume inside a container')
    parser_ceph_volume.set_defaults(func=command_ceph_volume)
    parser_ceph_volume.add_argument(
        '--fsid',
        help='cluster FSID')
    parser_ceph_volume.add_argument(
        '--config-json',
        help='JSON file with config and (client.bootrap-osd) key')
    parser_ceph_volume.add_argument(
        '--config', '-c',
        help='ceph conf file')
    parser_ceph_volume.add_argument(
        '--keyring', '-k',
        help='ceph.keyring to pass through to the container')
    parser_ceph_volume.add_argument(
        'command', nargs='+',
        help='command')

    parser_unit = subparsers.add_parser(
        'unit', help='operate on the daemon\'s systemd unit')
    parser_unit.set_defaults(func=command_unit)
    parser_unit.add_argument(
        'command',
        help='systemd command (start, stop, restart, enable, disable, ...)')
    parser_unit.add_argument(
        '--fsid',
        help='cluster FSID')
    parser_unit.add_argument(
        '--name', '-n',
        required=True,
        help='daemon name (type.id)')

    parser_logs = subparsers.add_parser(
        'logs', help='print journald logs for a daemon container')
    parser_logs.set_defaults(func=command_logs)
    parser_logs.add_argument(
        '--fsid',
        help='cluster FSID')
    parser_logs.add_argument(
        '--name', '-n',
        required=True,
        help='daemon name (type.id)')
    parser_logs.add_argument(
        'command', nargs='*',
        help='additional journalctl args')

    parser_bootstrap = subparsers.add_parser(
        'bootstrap', help='bootstrap a cluster (mon + mgr daemons)')
    parser_bootstrap.set_defaults(func=command_bootstrap)
    parser_bootstrap.add_argument(
        '--config', '-c',
        help='ceph conf file to incorporate')
    parser_bootstrap.add_argument(
        '--mon-id',
        required=False,
        help='mon id (default: local hostname)')
    parser_bootstrap.add_argument(
        '--mon-addrv',
        help='mon IPs (e.g., [v2:localipaddr:3300,v1:localipaddr:6789])')
    parser_bootstrap.add_argument(
        '--mon-ip',
        help='mon IP')
    parser_bootstrap.add_argument(
        '--mgr-id',
        required=False,
        help='mgr id (default: randomly generated)')
    parser_bootstrap.add_argument(
        '--fsid',
        help='cluster FSID')
    parser_bootstrap.add_argument(
        '--output-dir',
        default='/etc/ceph',
        help='directory to write config, keyring, and pub key files')
    parser_bootstrap.add_argument(
        '--output-keyring',
        help='location to write keyring file with new cluster admin and mon keys')
    parser_bootstrap.add_argument(
        '--output-config',
        help='location to write conf file to connect to new cluster')
    parser_bootstrap.add_argument(
        '--output-pub-ssh-key',
        help='location to write the cluster\'s public SSH key')
    parser_bootstrap.add_argument(
        '--skip-ssh',
        action='store_true',
        help='skip setup of ssh key on local host')
    parser_bootstrap.add_argument(
        '--initial-dashboard-user',
        default='admin',
        help='Initial user for the dashboard')
    parser_bootstrap.add_argument(
        '--initial-dashboard-password',
        help='Initial password for the initial dashboard user')

    parser_bootstrap.add_argument(
        '--dashboard-key',
        help='Dashboard key')
    parser_bootstrap.add_argument(
        '--dashboard-crt',
        help='Dashboard certificate')

    parser_bootstrap.add_argument(
        '--skip-mon-network',
        action='store_true',
        help='set mon public_network based on bootstrap mon ip')
    parser_bootstrap.add_argument(
        '--skip-dashboard',
        action='store_true',
        help='do not enable the Ceph Dashboard')
    parser_bootstrap.add_argument(
        '--dashboard-password-noupdate',
        action='store_true',
        help='stop forced dashboard password change')
    parser_bootstrap.add_argument(
        '--no-minimize-config',
        action='store_true',
        help='do not assimilate and minimize the config file')
    parser_bootstrap.add_argument(
        '--skip-ping-check',
        action='store_true',
        help='do not verify that mon IP is pingable')
    parser_bootstrap.add_argument(
        '--skip-pull',
        action='store_true',
        help='do not pull the latest image before bootstrapping')
    parser_bootstrap.add_argument(
        '--skip-firewalld',
        action='store_true',
        help='Do not configure firewalld')
    parser_bootstrap.add_argument(
        '--allow-overwrite',
        action='store_true',
        help='allow overwrite of existing --output-* config/keyring/ssh files')
    parser_bootstrap.add_argument(
        '--allow-fqdn-hostname',
        action='store_true',
        help='allow hostname that is fully-qualified (contains ".")')
    parser_bootstrap.add_argument(
        '--skip-prepare-host',
        action='store_true',
        help='Do not prepare host')
    parser_bootstrap.add_argument(
        '--orphan-initial-daemons',
        action='store_true',
        help='Do not create initial mon, mgr, and crash service specs')
    parser_bootstrap.add_argument(
        '--skip-monitoring-stack',
        action='store_true',
        help='Do not automatically provision monitoring stack (prometheus, grafana, alertmanager, node-exporter)')

    parser_deploy = subparsers.add_parser(
        'deploy', help='deploy a daemon')
    parser_deploy.set_defaults(func=command_deploy)
    parser_deploy.add_argument(
        '--name',
        required=True,
        action=CustomValidation,
        help='daemon name (type.id)')
    parser_deploy.add_argument(
        '--fsid',
        required=True,
        help='cluster FSID')
    parser_deploy.add_argument(
        '--config', '-c',
        help='config file for new daemon')
    parser_deploy.add_argument(
        '--config-json',
        help='Additional configuration information in JSON format')
    parser_deploy.add_argument(
        '--keyring',
        help='keyring for new daemon')
    parser_deploy.add_argument(
        '--key',
        help='key for new daemon')
    parser_deploy.add_argument(
        '--osd-fsid',
        help='OSD uuid, if creating an OSD container')
    parser_deploy.add_argument(
        '--skip-firewalld',
        action='store_true',
        help='Do not configure firewalld')
    parser_deploy.add_argument(
        '--reconfig',
        action='store_true',
        help='Reconfigure a previously deployed daemon')
    parser_deploy.add_argument(
        '--allow-ptrace',
        action='store_true',
        help='Allow SYS_PTRACE on daemon container')

    parser_check_host = subparsers.add_parser(
        'check-host', help='check host configuration')
    parser_check_host.set_defaults(func=command_check_host)
    parser_check_host.add_argument(
        '--expect-hostname',
        help='Check that hostname matches an expected value')

    parser_prepare_host = subparsers.add_parser(
        'prepare-host', help='prepare a host for cephadm use')
    parser_prepare_host.set_defaults(func=command_prepare_host)
    parser_prepare_host.add_argument(
        '--expect-hostname',
        help='Set hostname')

    parser_add_repo = subparsers.add_parser(
        'add-repo', help='configure package repository')
    parser_add_repo.set_defaults(func=command_add_repo)
    parser_add_repo.add_argument(
        '--release',
        help='use latest version of a named release (e.g., octopus)')
    parser_add_repo.add_argument(
        '--version',
        help='use specific upstream version (x.y.z)')
    parser_add_repo.add_argument(
        '--dev',
        help='use specified bleeding edge build from git branch or tag')
    parser_add_repo.add_argument(
        '--dev-commit',
        help='use specified bleeding edge build from git commit')
    parser_add_repo.add_argument(
        '--gpg-url',
        help='specify alternative GPG key location')
    parser_add_repo.add_argument(
        '--repo-url',
        default='https://download.ceph.com',
        help='specify alternative repo location')
    # TODO: proxy?

    parser_rm_repo = subparsers.add_parser(
        'rm-repo', help='remove package repository configuration')
    parser_rm_repo.set_defaults(func=command_rm_repo)

    parser_install = subparsers.add_parser(
        'install', help='install ceph package(s)')
    parser_install.set_defaults(func=command_install)
    parser_install.add_argument(
        'packages', nargs='*',
        default=['cephadm'],
        help='packages')

    return parser

def _parse_args(av):
    parser = _get_parser()
    return parser.parse_args(av)

if __name__ == "__main__":
    # allow argv to be injected
    try:
        av = injected_argv # type: ignore
    except NameError:
        av = sys.argv[1:]
    args = _parse_args(av)

    if args.verbose:
        logging.basicConfig(level=logging.DEBUG)
    else:
        logging.basicConfig(level=logging.INFO)
    logger = logging.getLogger('cephadm')

    # root?
    if os.geteuid() != 0:
        sys.stderr.write('ERROR: cephadm should be run as root\n')
        sys.exit(1)

    # podman or docker?
    if args.docker:
        container_path = find_program('docker')
    else:
        for i in CONTAINER_PREFERENCE:
            try:
                container_path = find_program(i)
                break
            except Exception as e:
                logger.debug('Could not locate %s: %s' % (i, e))
        if not container_path and args.func != command_prepare_host:
            sys.stderr.write('Unable to locate any of %s\n' % CONTAINER_PREFERENCE)
            sys.exit(1)

    if 'func' not in args:
        sys.stderr.write('No command specified; pass -h or --help for usage\n')
        sys.exit(1)

    try:
        r = args.func()
    except Error as e:
        if args.verbose:
            raise
        sys.stderr.write('ERROR: %s\n' % e)
        sys.exit(1)
    if not r:
        r = 0
    sys.exit(r)
