import re
from functools import partial
import time
+import urllib
from cwltool.errors import WorkflowException
import cwltool.workflow
from .fsaccess import CollectionFsAccess, CollectionFetcher, collectionResolver, CollectionCache, pdh_size
from .perf import Perf
from .pathmapper import NoFollowPathMapper
-from .task_queue import TaskQueue
+from cwltool.task_queue import TaskQueue
from .context import ArvLoadingContext, ArvRuntimeContext
from ._version import __version__
from cwltool.process import shortname, UnsupportedRequirement, use_custom_schema
-from cwltool.pathmapper import adjustFileObjs, adjustDirObjs, get_listing, visit_class
+from cwltool.utils import adjustFileObjs, adjustDirObjs, get_listing, visit_class, aslist
from cwltool.command_line_tool import compute_checksums
from cwltool.load_tool import load_tool
arvargs=None,
keep_client=None,
num_retries=4,
- thread_count=4):
+ thread_count=4,
+ stdout=sys.stdout):
if arvargs is None:
arvargs = argparse.Namespace()
self.should_estimate_cache_size = True
self.fs_access = None
self.secret_store = None
+ self.stdout = stdout
if keep_client is not None:
self.keep_client = keep_client
if current is None:
return
runtime_status = current.get('runtime_status', {})
- # In case of status being an error, only report the first one.
- if kind == 'error':
- if not runtime_status.get('error'):
- runtime_status.update({
- 'error': message
- })
- if detail is not None:
- runtime_status.update({
- 'errorDetail': detail
- })
- # Further errors are only mentioned as a count.
- else:
- # Get anything before an optional 'and N more' string.
- try:
- error_msg = re.match(
- r'^(.*?)(?=\s*\(and \d+ more\)|$)', runtime_status.get('error')).groups()[0]
- more_failures = re.match(
- r'.*\(and (\d+) more\)', runtime_status.get('error'))
- except TypeError:
- # Ignore tests stubbing errors
- return
- if more_failures:
- failure_qty = int(more_failures.groups()[0])
- runtime_status.update({
- 'error': "%s (and %d more)" % (error_msg, failure_qty+1)
- })
- else:
- runtime_status.update({
- 'error': "%s (and 1 more)" % error_msg
- })
- elif kind in ['warning', 'activity']:
- # Record the last warning/activity status without regard of
- # previous occurences.
+ if kind in ('error', 'warning'):
+ updatemessage = runtime_status.get(kind, "")
+ if not updatemessage:
+ updatemessage = message
+
+ # Subsequent messages tacked on in detail
+ updatedetail = runtime_status.get(kind+'Detail', "")
+ maxlines = 40
+ if updatedetail.count("\n") < maxlines:
+ if updatedetail:
+ updatedetail += "\n"
+ updatedetail += message + "\n"
+
+ if detail:
+ updatedetail += detail + "\n"
+
+ if updatedetail.count("\n") >= maxlines:
+ updatedetail += "\nSome messages may have been omitted. Check the full log."
+
runtime_status.update({
- kind: message
+ kind: updatemessage,
+ kind+'Detail': updatedetail,
})
- if detail is not None:
- runtime_status.update({
- kind+"Detail": detail
- })
else:
# Ignore any other status kind
return
srccollection = sp[0][5:]
try:
reader = self.collection_cache.get(srccollection)
- srcpath = "/".join(sp[1:]) if len(sp) > 1 else "."
+ srcpath = urllib.parse.unquote("/".join(sp[1:]) if len(sp) > 1 else ".")
final.copy(srcpath, v.target, source_collection=reader, overwrite=False)
except arvados.errors.ArgumentError as e:
logger.error("Creating CollectionReader for '%s' '%s': %s", k, v, e)
}).execute(num_retries=self.num_retries)
except Exception:
logger.exception("Setting container output")
- return
+ raise
def apply_reqs(self, job_order_object, tool):
if "https://w3id.org/cwl/cwl#requirements" in job_order_object:
for req in job_reqs:
tool.requirements.append(req)
- def arv_executor(self, tool, job_order, runtimeContext, logger=None):
+ def arv_executor(self, updated_tool, job_order, runtimeContext, logger=None):
self.debug = runtimeContext.debug
- tool.visit(self.check_features)
+ workbench1 = self.api.config()["Services"]["Workbench1"]["ExternalURL"]
+ workbench2 = self.api.config()["Services"]["Workbench2"]["ExternalURL"]
+ controller = self.api.config()["Services"]["Controller"]["ExternalURL"]
+ logger.info("Using cluster %s (%s)", self.api.config()["ClusterID"], workbench2 or workbench1 or controller)
+
+ updated_tool.visit(self.check_features)
self.project_uuid = runtimeContext.project_uuid
self.pipeline = None
if runtimeContext.submit_request_uuid and self.work_api != "containers":
raise Exception("--submit-request-uuid requires containers API, but using '{}' api".format(self.work_api))
+ default_storage_classes = ",".join([k for k,v in self.api.config().get("StorageClasses", {"default": {"Default": True}}).items() if v.get("Default") is True])
+ if runtimeContext.storage_classes == "default":
+ runtimeContext.storage_classes = default_storage_classes
+ if runtimeContext.intermediate_storage_classes == "default":
+ runtimeContext.intermediate_storage_classes = default_storage_classes
+
if not runtimeContext.name:
- runtimeContext.name = self.name = tool.tool.get("label") or tool.metadata.get("label") or os.path.basename(tool.tool["id"])
+ runtimeContext.name = self.name = updated_tool.tool.get("label") or updated_tool.metadata.get("label") or os.path.basename(updated_tool.tool["id"])
# Upload local file references in the job order.
job_order = upload_job_order(self, "%s input" % runtimeContext.name,
- tool, job_order)
+ updated_tool, job_order)
+
+ # the last clause means: if it is a command line tool, and we
+ # are going to wait for the result, and always_submit_runner
+ # is false, then we don't submit a runner process.
submitting = (runtimeContext.update_workflow or
runtimeContext.create_workflow or
(runtimeContext.submit and not
- (tool.tool["class"] == "CommandLineTool" and
+ (updated_tool.tool["class"] == "CommandLineTool" and
runtimeContext.wait and
not runtimeContext.always_submit_runner)))
loadingContext = self.loadingContext.copy()
loadingContext.do_validate = False
- loadingContext.do_update = False
if submitting:
+ loadingContext.do_update = False
# Document may have been auto-updated. Reload the original
# document with updating disabled because we want to
- # submit the original document, not the auto-updated one.
- tool = load_tool(tool.tool["id"], loadingContext)
+ # submit the document with its original CWL version, not
+ # the auto-updated one.
+ tool = load_tool(updated_tool.tool["id"], loadingContext)
+ else:
+ tool = updated_tool
# Upload direct dependencies of workflow steps, get back mapping of files to keep references.
# Also uploads docker images.
if existing_uuid or runtimeContext.create_workflow:
# Create a pipeline template or workflow record and exit.
if self.work_api == "containers":
- return (upload_workflow(self, tool, job_order,
+ uuid = upload_workflow(self, tool, job_order,
self.project_uuid,
uuid=existing_uuid,
submit_runner_ram=runtimeContext.submit_runner_ram,
name=runtimeContext.name,
- merged_map=merged_map),
- "success")
+ merged_map=merged_map,
+ submit_runner_image=runtimeContext.submit_runner_image)
+ self.stdout.write(uuid + "\n")
+ return (None, "success")
self.apply_reqs(job_order, tool)
if runtimeContext.submit:
# Submit a runner job to run the workflow for us.
if self.work_api == "containers":
- if tool.tool["class"] == "CommandLineTool" and runtimeContext.wait and (not runtimeContext.always_submit_runner):
- runtimeContext.runnerjob = tool.tool["id"]
+ if submitting:
+ tool = RunnerContainer(self, updated_tool,
+ tool, loadingContext, runtimeContext.enable_reuse,
+ self.output_name,
+ self.output_tags,
+ submit_runner_ram=runtimeContext.submit_runner_ram,
+ name=runtimeContext.name,
+ on_error=runtimeContext.on_error,
+ submit_runner_image=runtimeContext.submit_runner_image,
+ intermediate_output_ttl=runtimeContext.intermediate_output_ttl,
+ merged_map=merged_map,
+ priority=runtimeContext.priority,
+ secret_store=self.secret_store,
+ collection_cache_size=runtimeContext.collection_cache_size,
+ collection_cache_is_default=self.should_estimate_cache_size)
else:
- tool = RunnerContainer(self, tool, loadingContext, runtimeContext.enable_reuse,
- self.output_name,
- self.output_tags,
- submit_runner_ram=runtimeContext.submit_runner_ram,
- name=runtimeContext.name,
- on_error=runtimeContext.on_error,
- submit_runner_image=runtimeContext.submit_runner_image,
- intermediate_output_ttl=runtimeContext.intermediate_output_ttl,
- merged_map=merged_map,
- priority=runtimeContext.priority,
- secret_store=self.secret_store,
- collection_cache_size=runtimeContext.collection_cache_size,
- collection_cache_is_default=self.should_estimate_cache_size)
+ runtimeContext.runnerjob = tool.tool["id"]
if runtimeContext.cwl_runner_job is not None:
self.uuid = runtimeContext.cwl_runner_job.get('uuid')
if runtimeContext.submit and not runtimeContext.wait:
runnerjob = next(jobiter)
runnerjob.run(runtimeContext)
- return (runnerjob.uuid, "success")
+ self.stdout.write(runnerjob.uuid+"\n")
+ return (None, "success")
current_container = arvados_cwl.util.get_current_container(self.api, self.num_retries, logger)
if current_container:
if runtimeContext.submit and isinstance(tool, Runner):
logger.info("Final output collection %s", tool.final_output)
+ if workbench2 or workbench1:
+ logger.info("Output at %scollections/%s", workbench2 or workbench1, tool.final_output)
else:
if self.output_name is None:
self.output_name = "Output of %s" % (shortname(tool.tool["id"]))
if self.output_tags is None:
self.output_tags = ""
- storage_classes = runtimeContext.storage_classes.strip().split(",")
+ storage_classes = ""
+ storage_class_req, _ = tool.get_requirement("http://arvados.org/cwl#OutputStorageClass")
+ if storage_class_req and storage_class_req.get("finalStorageClass"):
+ storage_classes = aslist(storage_class_req["finalStorageClass"])
+ else:
+ storage_classes = runtimeContext.storage_classes.strip().split(",")
+
self.final_output, self.final_output_collection = self.make_output_collection(self.output_name, storage_classes, self.output_tags, self.final_output)
self.set_crunch_output()
projects / arvados.git / blobdiff