Merge branch '17388-arvcopy-storage-classes' into main. Closes #17388

Arvados-DCO-1.1-Signed-off-by: Lucas Di Pentima <lucas.dipentima@curii.com>

diff --git a/doc/user/topics/arv-copy.html.textile.liquid b/doc/user/topics/arv-copy.html.textile.liquid
index d35df4fcec9f92f12e2b9dc3020667be5f4153f0..6e41a4f237d0bcf7d133007c96c742a2c7fb75d9 100644 (file)
--- a/doc/user/topics/arv-copy.html.textile.liquid
+++ b/doc/user/topics/arv-copy.html.textile.liquid
@@ -57,12 +57,14 @@ arvados.arv-copy[1234] INFO: Success: created copy with uuid dstcl-4zz18-xxxxxxx
 
 The output of arv-copy displays the uuid of the collection generated in the destination cluster. By default, the output is placed in your home project in the destination cluster. If you want to place your collection in an existing project, you can specify the project you want it to be in using the tag @--project-uuid@ followed by the project uuid.
 
-For example, this will copy the collection to project dstcl-j7d0g-a894213ukjhal12 in the destination cluster.
+For example, this will copy the collection to project @dstcl-j7d0g-a894213ukjhal12@ in the destination cluster.
 
 <notextile> <pre><code>~$ <span class="userinput">arv-copy --src pirca --dst dstcl --project-uuid dstcl-j7d0g-a894213ukjhal12 jutro-4zz18-tv416l321i4r01e
 </code></pre>
 </notextile>
 
+Additionally, if you need to specify the storage classes where to save the copied data on the destination cluster, you can do that by using the @--storage-classes LIST@ argument, where @LIST@ is a comma-separated list of storage class names.
+
 h3. How to copy a workflow
 
 We will use the uuid @jutro-7fd4e-mkmmq53m1ze6apx@ as an example workflow.

diff --git a/sdk/python/arvados/commands/arv_copy.py b/sdk/python/arvados/commands/arv_copy.py
index 93fd6b598aefab0448e450391beecccbb2419f42..79dabd38b2d847072aa7d8eccb119c0224469244 100755 (executable)
--- a/sdk/python/arvados/commands/arv_copy.py
+++ b/sdk/python/arvados/commands/arv_copy.py
@@ -102,6 +102,9 @@ def main():
     copy_opts.add_argument(
         '--project-uuid', dest='project_uuid',
         help='The UUID of the project at the destination to which the collection or workflow should be copied.')
+    copy_opts.add_argument(
+        '--storage-classes', dest='storage_classes',
+        help='Comma separated list of storage classes to be used when saving data to the destinaton Arvados instance.')
 
     copy_opts.add_argument(
         'object_uuid',
@@ -114,6 +117,9 @@ def main():
         parents=[copy_opts, arv_cmd.retry_opt])
     args = parser.parse_args()
 
+    if args.storage_classes:
+        args.storage_classes = [x for x in args.storage_classes.strip().replace(' ', '').split(',') if x]
+
     if args.verbose:
         logger.setLevel(logging.DEBUG)
     else:
@@ -410,6 +416,9 @@ def create_collection_from(c, src, dst, args):
     if not body["name"]:
         body['name'] = "copied from " + collection_uuid
 
+    if args.storage_classes:
+        body['storage_classes_desired'] = args.storage_classes
+
     body['owner_uuid'] = args.project_uuid
 
     dst_collection = dst.collections().create(body=body, ensure_unique_name=True).execute(num_retries=args.retries)
@@ -563,7 +572,7 @@ def copy_collection(obj_uuid, src, dst, args):
                 if progress_writer:
                     progress_writer.report(obj_uuid, bytes_written, bytes_expected)
                 data = src_keep.get(word)
-                dst_locator = dst_keep.put(data)
+                dst_locator = dst_keep.put(data, classes=(args.storage_classes or []))
                 dst_locators[blockhash] = dst_locator
                 bytes_written += loc.size
             dst_manifest.write(' ')

diff --git a/sdk/python/tests/test_arv_copy.py b/sdk/python/tests/test_arv_copy.py
index 452c2beba2b0639abfdf637e3f503f2f25526f7a..b560018d385bfd3f62f366333527f54a3ec272c2 100644 (file)
--- a/sdk/python/tests/test_arv_copy.py
+++ b/sdk/python/tests/test_arv_copy.py
@@ -42,6 +42,8 @@ class ArvCopyVersionTestCase(run_test_server.TestCaseWithServers, tutil.VersionC
         with c.open('foo', 'wt') as f:
             f.write('foo')
         c.save_new("arv-copy foo collection", owner_uuid=src_proj)
+        coll_record = api.collections().get(uuid=c.manifest_locator()).execute()
+        assert coll_record['storage_classes_desired'] == ['default']
 
         dest_proj = api.groups().create(body={"group": {"name": "arv-copy dest project", "group_class": "project"}}).execute()["uuid"]
 
@@ -60,7 +62,7 @@ class ArvCopyVersionTestCase(run_test_server.TestCaseWithServers, tutil.VersionC
             assert len(contents["items"]) == 0
 
             try:
-                self.run_copy(["--project-uuid", dest_proj, src_proj])
+                self.run_copy(["--project-uuid", dest_proj, "--storage-classes", "foo", src_proj])
             except SystemExit as e:
                 assert e.code == 0
 
@@ -76,6 +78,7 @@ class ArvCopyVersionTestCase(run_test_server.TestCaseWithServers, tutil.VersionC
             assert contents["items"][0]["uuid"] != c.manifest_locator()
             assert contents["items"][0]["name"] == "arv-copy foo collection"
             assert contents["items"][0]["portable_data_hash"] == c.portable_data_hash()
+            assert contents["items"][0]["storage_classes_desired"] == ["foo"]
 
         finally:
             os.environ['HOME'] = home_was