-#!/usr/bin/env python
+#!/usr/bin/env python3
# Copyright (C) The Arvados Authors. All rights reserved.
#
# SPDX-License-Identifier: Apache-2.0
# Implement cwl-runner interface for submitting and running work on Arvados, using
-# either the Crunch jobs API or Crunch containers API.
+# the Crunch containers API.
from future.utils import viewitems
from builtins import str
import cwltool.workflow
import cwltool.process
import cwltool.argparser
+from cwltool.errors import WorkflowException
from cwltool.process import shortname, UnsupportedRequirement, use_custom_schema
-from cwltool.pathmapper import adjustFileObjs, adjustDirObjs, get_listing
+from cwltool.utils import adjustFileObjs, adjustDirObjs, get_listing
import arvados
import arvados.config
from .perf import Perf
from ._version import __version__
from .executor import ArvCwlExecutor
+from .fsaccess import workflow_uuid_pattern
-# These arn't used directly in this file but
+# These aren't used directly in this file but
# other code expects to import them from here
from .arvcontainer import ArvadosContainer
-from .arvjob import ArvadosJob
from .arvtool import ArvadosCommandTool
from .fsaccess import CollectionFsAccess, CollectionCache, CollectionFetcher
from .util import get_current_container
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--enable-reuse", action="store_true",
default=True, dest="enable_reuse",
- help="Enable job or container reuse (default)")
+ help="Enable container reuse (default)")
exgroup.add_argument("--disable-reuse", action="store_false",
default=True, dest="enable_reuse",
- help="Disable job or container reuse")
+ help="Disable container reuse")
- parser.add_argument("--project-uuid", metavar="UUID", help="Project that will own the workflow jobs, if not provided, will go to home project.")
+ parser.add_argument("--project-uuid", metavar="UUID", help="Project that will own the workflow containers, if not provided, will go to home project.")
parser.add_argument("--output-name", help="Name to use for collection that stores the final output.", default=None)
parser.add_argument("--output-tags", help="Tags for the final output collection separated by commas, e.g., '--output-tags tag0,tag1,tag2'.", default=None)
parser.add_argument("--ignore-docker-for-reuse", action="store_true",
- help="Ignore Docker image version when deciding whether to reuse past jobs.",
+ help="Ignore Docker image version when deciding whether to reuse past containers.",
default=False)
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--submit", action="store_true", help="Submit workflow to run on Arvados.",
default=True, dest="submit")
- exgroup.add_argument("--local", action="store_false", help="Run workflow on local host (submits jobs to Arvados).",
+ exgroup.add_argument("--local", action="store_false", help="Run workflow on local host (submits containers to Arvados).",
default=True, dest="submit")
exgroup.add_argument("--create-template", action="store_true", help="(Deprecated) synonym for --create-workflow.",
dest="create_workflow")
- exgroup.add_argument("--create-workflow", action="store_true", help="Create an Arvados workflow (if using the 'containers' API) or pipeline template (if using the 'jobs' API). See --api.")
- exgroup.add_argument("--update-workflow", metavar="UUID", help="Update an existing Arvados workflow or pipeline template with the given UUID.")
+ exgroup.add_argument("--create-workflow", action="store_true", help="Register an Arvados workflow that can be run from Workbench")
+ exgroup.add_argument("--update-workflow", metavar="UUID", help="Update an existing Arvados workflow with the given UUID.")
exgroup = parser.add_mutually_exclusive_group()
- exgroup.add_argument("--wait", action="store_true", help="After submitting workflow runner job, wait for completion.",
+ exgroup.add_argument("--wait", action="store_true", help="After submitting workflow runner, wait for completion.",
default=True, dest="wait")
- exgroup.add_argument("--no-wait", action="store_false", help="Submit workflow runner job and exit.",
+ exgroup.add_argument("--no-wait", action="store_false", help="Submit workflow runner and exit.",
default=True, dest="wait")
exgroup = parser.add_mutually_exclusive_group()
parser.add_argument("--api",
default=None, dest="work_api",
- choices=("jobs", "containers"),
- help="Select work submission API. Default is 'jobs' if that API is available, otherwise 'containers'.")
+ choices=("containers",),
+ help="Select work submission API. Only supports 'containers'")
parser.add_argument("--compute-checksum", action="store_true", default=False,
help="Compute checksum of contents while collecting outputs",
help="When invoked with --submit --wait, always submit a runner to manage the workflow, even when only running a single CommandLineTool",
default=False)
+ parser.add_argument("--match-submitter-images", action="store_true",
+ default=False, dest="match_local_docker",
+ help="Where Arvados has more than one Docker image of the same name, use image from the Docker instance on the submitting node.")
+
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--submit-request-uuid",
default=None,
- help="Update and commit to supplied container request instead of creating a new one (containers API only).",
+ help="Update and commit to supplied container request instead of creating a new one.",
metavar="UUID")
exgroup.add_argument("--submit-runner-cluster",
- help="Submit workflow runner to a remote cluster (containers API only)",
+ help="Submit workflow runner to a remote cluster",
default=None,
metavar="CLUSTER_ID")
parser.add_argument("--enable-dev", action="store_true",
help="Enable loading and running development versions "
- "of CWL spec.", default=False)
+ "of the CWL standards.", default=False)
parser.add_argument('--storage-classes', default="default",
- help="Specify comma separated list of storage classes to be used when saving workflow output to Keep.")
+ help="Specify comma separated list of storage classes to be used when saving final workflow output to Keep.")
+ parser.add_argument('--intermediate-storage-classes', default="default",
+ help="Specify comma separated list of storage classes to be used when saving intermediate workflow output to Keep.")
parser.add_argument("--intermediate-output-ttl", type=int, metavar="N",
help="If N > 0, intermediate output collections will be trashed N seconds after creation. Default is 0 (don't trash).",
default=0)
parser.add_argument("--priority", type=int,
- help="Workflow priority (range 1..1000, higher has precedence over lower, containers api only)",
+ help="Workflow priority (range 1..1000, higher has precedence over lower)",
default=DEFAULT_PRIORITY)
parser.add_argument("--disable-validate", dest="do_validate",
action="store_false", default=True,
help=argparse.SUPPRESS)
+ parser.add_argument("--disable-git", dest="git_info",
+ action="store_false", default=True,
+ help=argparse.SUPPRESS)
+
+ parser.add_argument("--disable-color", dest="enable_color",
+ action="store_false", default=True,
+ help=argparse.SUPPRESS)
+
parser.add_argument("--disable-js-validation",
action="store_true", default=False,
help=argparse.SUPPRESS)
+ parser.add_argument("--fast-parser", dest="fast_parser",
+ action="store_true", default=False,
+ help=argparse.SUPPRESS)
+
parser.add_argument("--thread-count", type=int,
- default=1, help="Number of threads to use for job submit and output collection.")
+ default=0, help="Number of threads to use for job submit and output collection.")
parser.add_argument("--http-timeout", type=int,
default=5*60, dest="http_timeout", help="API request timeout in seconds. Default is 300 seconds (5 minutes).")
+ parser.add_argument("--defer-downloads", action="store_true", default=False,
+ help="When submitting a workflow, defer downloading HTTP URLs to workflow launch instead of downloading to Keep before submit.")
+
+ parser.add_argument("--varying-url-params", type=str, default="",
+ help="A comma separated list of URL query parameters that should be ignored when storing HTTP URLs in Keep.")
+
+ parser.add_argument("--prefer-cached-downloads", action="store_true", default=False,
+ help="If a HTTP URL is found in Keep, skip upstream URL freshness check (will not notice if the upstream has changed, but also not error if upstream is unavailable).")
+
+ exgroup = parser.add_mutually_exclusive_group()
+ exgroup.add_argument("--enable-preemptible", dest="enable_preemptible", default=None, action="store_true", help="Use preemptible instances. Control individual steps with arv:UsePreemptible hint.")
+ exgroup.add_argument("--disable-preemptible", dest="enable_preemptible", default=None, action="store_false", help="Don't use preemptible instances.")
+
+ exgroup = parser.add_mutually_exclusive_group()
+ exgroup.add_argument("--copy-deps", dest="copy_deps", default=None, action="store_true", help="Copy dependencies into the destination project.")
+ exgroup.add_argument("--no-copy-deps", dest="copy_deps", default=None, action="store_false", help="Leave dependencies where they are.")
+
+ parser.add_argument(
+ "--skip-schemas",
+ action="store_true",
+ help="Skip loading of schemas",
+ default=False,
+ dest="skip_schemas",
+ )
+
exgroup = parser.add_mutually_exclusive_group()
exgroup.add_argument("--trash-intermediate", action="store_true",
default=False, dest="trash_intermediate",
def add_arv_hints():
cwltool.command_line_tool.ACCEPTLIST_EN_RELAXED_RE = re.compile(r".*")
cwltool.command_line_tool.ACCEPTLIST_RE = cwltool.command_line_tool.ACCEPTLIST_EN_RELAXED_RE
- res = pkg_resources.resource_stream(__name__, 'arv-cwl-schema.yml')
- use_custom_schema("v1.0", "http://arvados.org/cwl", res.read())
- res.close()
+ supported_versions = ["v1.0", "v1.1", "v1.2"]
+ for s in supported_versions:
+ res = pkg_resources.resource_stream(__name__, 'arv-cwl-schema-%s.yml' % s)
+ customschema = res.read().decode('utf-8')
+ use_custom_schema(s, "http://arvados.org/cwl", customschema)
+ res.close()
cwltool.process.supportedProcessRequirements.extend([
"http://arvados.org/cwl#RunInSingleContainer",
"http://arvados.org/cwl#OutputDirType",
"http://commonwl.org/cwltool#LoadListingRequirement",
"http://arvados.org/cwl#IntermediateOutput",
"http://arvados.org/cwl#ReuseRequirement",
- "http://arvados.org/cwl#ClusterTarget"
+ "http://arvados.org/cwl#ClusterTarget",
+ "http://arvados.org/cwl#OutputStorageClass",
+ "http://arvados.org/cwl#ProcessProperties",
+ "http://commonwl.org/cwltool#CUDARequirement",
+ "http://arvados.org/cwl#UsePreemptible",
+ "http://arvados.org/cwl#OutputCollectionProperties",
+ "http://arvados.org/cwl#KeepCacheTypeRequirement",
+ "http://arvados.org/cwl#OutOfMemoryRetry",
])
def exit_signal_handler(sigcode, frame):
logger.error(str(u"Caught signal {}, exiting.").format(sigcode))
sys.exit(-sigcode)
-def main(args, stdout, stderr, api_client=None, keep_client=None,
+def main(args=sys.argv[1:],
+ stdout=sys.stdout,
+ stderr=sys.stderr,
+ api_client=None,
+ keep_client=None,
install_sig_handlers=True):
parser = arg_parser()
job_order_object = None
arvargs = parser.parse_args(args)
- if len(arvargs.storage_classes.strip().split(',')) > 1:
- logger.error(str(u"Multiple storage classes are not supported currently."))
- return 1
-
arvargs.use_container = True
arvargs.relax_path_checks = True
arvargs.print_supported_versions = False
if arvargs.update_workflow:
if arvargs.update_workflow.find('-7fd4e-') == 5:
want_api = 'containers'
- elif arvargs.update_workflow.find('-p5p6p-') == 5:
- want_api = 'jobs'
else:
want_api = None
if want_api and arvargs.work_api and want_api != arvargs.work_api:
if api_client is None:
api_client = arvados.safeapi.ThreadSafeApiCache(
api_params={"model": OrderedJsonModel(), "timeout": arvargs.http_timeout},
- keep_params={"num_retries": 4})
+ keep_params={"num_retries": 4},
+ version='v1',
+ )
keep_client = api_client.keep
# Make an API object now so errors are reported early.
api_client.users().current().execute()
if keep_client is None:
- keep_client = arvados.keep.KeepClient(api_client=api_client, num_retries=4)
- executor = ArvCwlExecutor(api_client, arvargs, keep_client=keep_client, num_retries=4)
+ block_cache = arvados.keep.KeepBlockCache(disk_cache=True)
+ keep_client = arvados.keep.KeepClient(api_client=api_client, num_retries=4, block_cache=block_cache)
+ executor = ArvCwlExecutor(api_client, arvargs, keep_client=keep_client, num_retries=4, stdout=stdout)
+ except WorkflowException as e:
+ logger.error(e, exc_info=(sys.exc_info()[1] if arvargs.debug else False))
+ return 1
except Exception:
logger.exception("Error creating the Arvados CWL Executor")
return 1
# Note that unless in debug mode, some stack traces related to user
- # workflow errors may be suppressed. See ArvadosJob.done().
+ # workflow errors may be suppressed.
+
+ # Set the logging on most modules INFO (instead of default which is WARNING)
+ logger.setLevel(logging.INFO)
+ logging.getLogger('arvados').setLevel(logging.INFO)
+ logging.getLogger('arvados.keep').setLevel(logging.WARNING)
+
if arvargs.debug:
logger.setLevel(logging.DEBUG)
logging.getLogger('arvados').setLevel(logging.DEBUG)
else:
arvados.log_handler.setFormatter(logging.Formatter('%(name)s %(levelname)s: %(message)s'))
+ if stdout is sys.stdout:
+ # cwltool.main has code to work around encoding issues with
+ # sys.stdout and unix pipes (they default to ASCII encoding,
+ # we want utf-8), so when stdout is sys.stdout set it to None
+ # to take advantage of that. Don't override it for all cases
+ # since we still want to be able to capture stdout for the
+ # unit tests.
+ stdout = None
+
+ if arvargs.workflow.startswith("arvwf:") or workflow_uuid_pattern.match(arvargs.workflow) or arvargs.workflow.startswith("keep:"):
+ executor.loadingContext.do_validate = False
+ if arvargs.submit:
+ executor.fast_submit = True
+
return cwltool.main.main(args=arvargs,
stdout=stdout,
stderr=stderr,
logger_handler=arvados.log_handler,
custom_schema_callback=add_arv_hints,
loadingContext=executor.loadingContext,
- runtimeContext=executor.runtimeContext)
+ runtimeContext=executor.toplevel_runtimeContext,
+ input_required=not (arvargs.create_workflow or arvargs.update_workflow))