def _make_option_parser():
usage = '%prog [options] <time-untouched> <URIs>'
description = (
'Delete all files in a given URI that are older than a specified'
' time.\n\nThe time parameter defines the threshold for removing'
' files. If the file has not been accessed for *time*, the file is'
' removed. The time argument is a number with an optional'
' single-character suffix specifying the units: m for minutes, h for'
' hours, d for days. If no suffix is specified, time is in hours.')
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'-t', '--test', dest='test', default=False,
action='store_true',
help="Don't actually delete any files; just log that we would")
_add_basic_opts(option_parser)
scrape_options_into_new_groups(MRJob().all_option_groups(), {
option_parser: ('aws_region', 's3_endpoint'),
})
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = (
'Create a persistent EMR cluster to run jobs in, and print its ID to'
' stdout. WARNING: Do not run'
' this without mrjob terminate-idle-clusters in your'
' crontab; clusters left idle can quickly become expensive!')
option_parser = OptionParser(usage=usage, description=description)
_add_basic_opts(option_parser)
# these aren't nicely broken down, just scrape specific options
scrape_options_into_new_groups(MRJob().all_option_groups(), {
option_parser: (
'bootstrap_mrjob',
'label',
'owner',
),
})
_add_emr_connect_opts(option_parser)
_add_emr_launch_opts(option_parser)
_add_dataproc_emr_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options] <time-untouched> <URIs>'
description = (
'Delete all files in a given URI that are older than a specified'
' time.\n\nThe time parameter defines the threshold for removing'
' files. If the file has not been accessed for *time*, the file is'
' removed. The time argument is a number with an optional'
' single-character suffix specifying the units: m for minutes, h for'
' hours, d for days. If no suffix is specified, time is in hours.')
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'-t',
'--test',
dest='test',
default=False,
action='store_true',
help="Don't actually delete any files; just log that we would")
_add_basic_opts(option_parser)
scrape_options_into_new_groups(MRJob().all_option_groups(), {
option_parser: ('aws_region', 's3_endpoint'),
})
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = (
'Create a persistent EMR cluster to run jobs in, and print its ID to'
' stdout. WARNING: Do not run'
' this without mrjob terminate-idle-clusters in your'
' crontab; clusters left idle can quickly become expensive!')
option_parser = OptionParser(usage=usage, description=description)
_add_basic_opts(option_parser)
# these aren't nicely broken down, just scrape specific options
scrape_options_into_new_groups(MRJob().all_option_groups(), {
option_parser: (
'bootstrap_mrjob',
'label',
'owner',
),
})
_add_emr_connect_opts(option_parser)
_add_emr_launch_opts(option_parser)
_add_dataproc_emr_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = ('Terminate idle EMR clusters that meet the criteria'
' passed in on the command line (or, by default,'
' clusters that have been idle for one hour).')
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'--max-hours-idle',
dest='max_hours_idle',
default=None,
type='float',
help=('Max number of hours a cluster can go without bootstrapping,'
' running a step, or having a new step created. This will fire'
' even if there are pending steps which EMR has failed to'
' start. Make sure you set this higher than the amount of time'
' your jobs can take to start instances and bootstrap.'))
option_parser.add_option(
'--max-mins-locked',
dest='max_mins_locked',
default=_DEFAULT_MAX_MINUTES_LOCKED,
type='float',
help='Max number of minutes a cluster can be locked while idle.')
option_parser.add_option(
'--mins-to-end-of-hour',
dest='mins_to_end_of_hour',
default=None,
type='float',
help=('Terminate clusters that are within this many minutes of'
' the end of a full hour since the job started running'
' AND have no pending steps.'))
option_parser.add_option('--unpooled-only',
dest='unpooled_only',
action='store_true',
default=False,
help='Only terminate un-pooled clusters')
option_parser.add_option('--pooled-only',
dest='pooled_only',
action='store_true',
default=False,
help='Only terminate pooled clusters')
option_parser.add_option(
'--pool-name',
dest='pool_name',
default=None,
help='Only terminate clusters in the given named pool.')
option_parser.add_option(
'--dry-run',
dest='dry_run',
default=False,
action='store_true',
help="Don't actually kill idle jobs; just log that we would")
_add_basic_opts(option_parser)
_add_dataproc_emr_connect_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def __init__(self, script_path=None, args=None, from_cl=False):
"""
:param script_path: Path to script unless it's the first item of *args*
:param args: Command line arguments
:param from_cl: If not using sys.argv but still comming from the
command line (as opposed to a script, e.g. from
mrjob.cmd), don't override the option parser error
function (exit instead of throwing ValueError).
"""
if script_path is not None:
script_path = os.path.abspath(script_path)
self._script_path = script_path
# make sure we respect the $TZ (time zone) environment variable
if hasattr(time, 'tzset'):
time.tzset()
self._passthrough_options = []
self._file_options = []
self.option_parser = OptionParser(usage=self._usage(),
option_class=self.OPTION_CLASS,
add_help_option=False)
self.configure_options()
for opt_group in self.all_option_groups():
_alphabetize_options(opt_group)
# don't pass None to parse_args unless we're actually running
# the MRJob script
if args is _READ_ARGS_FROM_SYS_ARGV:
self._cl_args = sys.argv[1:]
else:
# don't pass sys.argv to self.option_parser, and have it
# raise an exception on error rather than printing to stderr
# and exiting.
self._cl_args = args or []
def error(msg):
raise ValueError(msg)
if not from_cl:
self.option_parser.error = error
self.load_options(self._cl_args)
# Make it possible to redirect stdin, stdout, and stderr, for testing
# See sandbox(), below.
#
# These should always read/write bytes, not unicode
if PY2:
self.stdin = sys.stdin
self.stdout = sys.stdout
self.stderr = sys.stderr
else:
self.stdin = sys.stdin.buffer
self.stdout = sys.stdout.buffer
self.stderr = sys.stderr.buffer
def __init__(self, script_path=None, args=None, from_cl=False):
"""
:param script_path: Path to script unless it's the first item of *args*
:param args: Command line arguments
:param from_cl: If not using sys.argv but still comming from the
command line (as opposed to a script, e.g. from
mrjob.cmd), don't override the option parser error
function (exit instead of throwing ValueError).
"""
if script_path is not None:
script_path = os.path.abspath(script_path)
self._script_path = script_path
# make sure we respect the $TZ (time zone) environment variable
if hasattr(time, 'tzset'):
time.tzset()
self._passthrough_options = []
self._file_options = []
self.option_parser = OptionParser(usage=self._usage(),
option_class=self.OPTION_CLASS,
add_help_option=False)
self.configure_options()
for opt_group in self.all_option_groups():
_alphabetize_options(opt_group)
# don't pass None to parse_args unless we're actually running
# the MRJob script
if args is _READ_ARGS_FROM_SYS_ARGV:
self._cl_args = sys.argv[1:]
else:
# don't pass sys.argv to self.option_parser, and have it
# raise an exception on error rather than printing to stderr
# and exiting.
self._cl_args = args or []
def error(msg):
raise ValueError(msg)
if not from_cl:
self.option_parser.error = error
self.load_options(self._cl_args)
# Make it possible to redirect stdin, stdout, and stderr, for testing
# See sandbox(), below.
#
# These should always read/write bytes, not unicode
if PY2:
self.stdin = sys.stdin
self.stdout = sys.stdout
self.stderr = sys.stderr
else:
self.stdin = sys.stdin.buffer
self.stdout = sys.stdout.buffer
self.stderr = sys.stderr.buffer
def _make_option_parser():
usage = '%prog [options]'
description = ('Terminate idle EMR clusters that meet the criteria'
' passed in on the command line (or, by default,'
' clusters that have been idle for one hour).')
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'--max-hours-idle', dest='max_hours_idle',
default=None, type='float',
help=('Max number of hours a cluster can go without bootstrapping,'
' running a step, or having a new step created. This will fire'
' even if there are pending steps which EMR has failed to'
' start. Make sure you set this higher than the amount of time'
' your jobs can take to start instances and bootstrap.'))
option_parser.add_option(
'--max-mins-locked', dest='max_mins_locked',
default=DEFAULT_MAX_MINUTES_LOCKED, type='float',
help='Max number of minutes a cluster can be locked while idle.')
option_parser.add_option(
'--mins-to-end-of-hour', dest='mins_to_end_of_hour',
default=None, type='float',
help=('Terminate clusters that are within this many minutes of'
' the end of a full hour since the job started running'
' AND have no pending steps.'))
option_parser.add_option(
'--unpooled-only', dest='unpooled_only', action='store_true',
default=False,
help='Only terminate un-pooled clusters')
option_parser.add_option(
'--pooled-only', dest='pooled_only', action='store_true',
default=False,
help='Only terminate pooled clusters')
option_parser.add_option(
'--pool-name', dest='pool_name', default=None,
help='Only terminate clusters in the given named pool.')
option_parser.add_option(
'--dry-run', dest='dry_run', default=False,
action='store_true',
help="Don't actually kill idle jobs; just log that we would")
option_parser.add_option(
'-t', '--test', dest='test', default=False,
action='store_true',
help="Don't actually delete any files; just log that we would")
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = (
'Create a persistent EMR cluster to run jobs in, and print its ID to'
' stdout. WARNING: Do not run'
' this without mrjob terminate-idle-clusters in your'
' crontab; clusters left idle can quickly become expensive!')
option_parser = OptionParser(usage=usage, description=description)
_add_basic_options(option_parser)
_add_runner_options(option_parser, (_pick_runner_opts('emr', 'connect')
| _pick_runner_opts('emr', 'launch')))
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options] cluster-id'
description = 'Terminate an existing EMR cluster.'
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'-t', '--test', dest='test', default=False,
action='store_true',
help="Don't actually delete any files; just log that we would")
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options] cluster-id'
description = 'Terminate an existing EMR cluster.'
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'-t', '--test', dest='test', default=False,
action='store_true',
help="Don't actually delete any files; just log that we would")
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = 'Print a giant report on EMR usage.'
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'--max-days-ago', dest='max_days_ago', type='float', default=None,
help=('Max number of days ago to look at jobs. By default, we go back'
' as far as EMR supports (currently about 2 months)'))
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = (
'Create a persistent EMR cluster to run jobs in, and print its ID to'
' stdout. WARNING: Do not run'
' this without mrjob terminate-idle-clusters in your'
' crontab; clusters left idle can quickly become expensive!')
option_parser = OptionParser(usage=usage, description=description)
_add_basic_options(option_parser)
_add_runner_options(
option_parser,
(_pick_runner_opts('emr', 'connect') |
_pick_runner_opts('emr', 'launch')))
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = 'Print a giant report on EMR usage.'
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'--max-days-ago', dest='max_days_ago', type='float', default=None,
help=('Max number of days ago to look at jobs. By default, we go back'
' as far as EMR supports (currently about 2 months)'))
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = ('Report jobs running for more than a certain number of'
' hours (by default, %.1f). This can help catch buggy jobs'
' and Hadoop/EMR operational issues.' % DEFAULT_MIN_HOURS)
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'--min-hours', dest='min_hours', type='float',
default=DEFAULT_MIN_HOURS,
help=('Minimum number of hours a job can run before we report it.'
' Default: %default'))
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def _make_option_parser():
usage = '%prog [options]'
description = ('Report jobs running for more than a certain number of'
' hours (by default, %.1f). This can help catch buggy jobs'
' and Hadoop/EMR operational issues.' % DEFAULT_MIN_HOURS)
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
'--min-hours',
dest='min_hours',
type='float',
default=DEFAULT_MIN_HOURS,
help=('Minimum number of hours a job can run before we report it.'
' Default: %default'))
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser
def main(cl_args=None):
usage = 'usage: %prog CLUSTER_ID [options] "command string"'
description = ('Run a command on the master and all slaves of an EMR'
' cluster. Store stdout/stderr for results in OUTPUT_DIR.')
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option('-o',
'--output-dir',
dest='output_dir',
default=None,
help="Specify an output directory (default:"
" CLUSTER_ID)")
_add_basic_opts(option_parser)
_add_dataproc_emr_connect_opts(option_parser)
_add_emr_connect_opts(option_parser)
scrape_options_into_new_groups(MRJob().all_option_groups(), {
option_parser: ('ec2_key_pair_file', 'ssh_bin'),
})
_alphabetize_options(option_parser)
options, args = option_parser.parse_args(cl_args)
MRJob.set_up_logging(quiet=options.quiet, verbose=options.verbose)
runner_kwargs = options.__dict__.copy()
for unused_arg in ('output_dir', 'quiet', 'verbose'):
del runner_kwargs[unused_arg]
if len(args) < 2:
option_parser.print_help()
sys.exit(1)
cluster_id, cmd_string = args[:2]
cmd_args = shlex_split(cmd_string)
output_dir = os.path.abspath(options.output_dir or cluster_id)
with EMRJobRunner(cluster_id=cluster_id, **runner_kwargs) as runner:
_run_on_all_nodes(runner, output_dir, cmd_args)
def main(cl_args=None):
usage = 'usage: %prog CLUSTER_ID [options] "command string"'
description = ('Run a command on the master and all slaves of an EMR'
' cluster. Store stdout/stderr for results in OUTPUT_DIR.')
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option('-o', '--output-dir', dest='output_dir',
default=None,
help="Specify an output directory (default:"
" CLUSTER_ID)")
_add_basic_options(option_parser)
_add_runner_options(
option_parser,
_pick_runner_opts('emr', 'connect') | set(
['ssh_bin', 'ec2_key_pair_file'])
)
_alphabetize_options(option_parser)
options, args = option_parser.parse_args(cl_args)
MRJob.set_up_logging(quiet=options.quiet, verbose=options.verbose)
runner_kwargs = options.__dict__.copy()
for unused_arg in ('output_dir', 'quiet', 'verbose'):
del runner_kwargs[unused_arg]
if len(args) < 2:
option_parser.print_help()
sys.exit(1)
cluster_id, cmd_string = args[:2]
cmd_args = shlex_split(cmd_string)
output_dir = os.path.abspath(options.output_dir or cluster_id)
with EMRJobRunner(cluster_id=cluster_id, **runner_kwargs) as runner:
_run_on_all_nodes(runner, output_dir, cmd_args)
def _make_option_parser():
usage = "%prog [options]"
description = (
"Report jobs running for more than a certain number of"
" hours (by default, %.1f). This can help catch buggy jobs"
" and Hadoop/EMR operational issues." % DEFAULT_MIN_HOURS
)
option_parser = OptionParser(usage=usage, description=description)
option_parser.add_option(
"--min-hours",
dest="min_hours",
type="float",
default=DEFAULT_MIN_HOURS,
help=("Minimum number of hours a job can run before we report it." " Default: %default"),
)
_add_basic_opts(option_parser)
_add_emr_connect_opts(option_parser)
_alphabetize_options(option_parser)
return option_parser