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.")
+
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.")
self.match_local_docker = False
self.enable_preemptible = None
self.copy_deps = None
+ self.defer_downloads = False
super(ArvRuntimeContext, self).__init__(kwargs)
self.toplevel_runtimeContext.make_fs_access = partial(CollectionFsAccess,
collection_cache=self.collection_cache)
+ self.defer_downloads = arvargs.submit and arvargs.defer_downloads
+
validate_cluster_target(self, self.toplevel_runtimeContext)
raise WorkflowException("Directory literal '%s' is missing `listing`" % src)
elif src.startswith("http:") or src.startswith("https:"):
try:
- keepref = http_to_keep(self.arvrunner.api, self.arvrunner.project_uuid, src)
- logger.info("%s is %s", src, keepref)
- self._pathmap[src] = MapperEnt(keepref, keepref, srcobj["class"], True)
+ if self.arvrunner.defer_downloads:
+ # passthrough, we'll download it later.
+ self._pathmap[src] = MapperEnt(src, src, srcobj["class"], True)
+ else:
+ keepref = http_to_keep(self.arvrunner.api, self.arvrunner.project_uuid, src)
+ logger.info("%s is %s", src, keepref)
+ self._pathmap[src] = MapperEnt(keepref, keepref, srcobj["class"], True)
except Exception as e:
logger.warning(str(e))
else: