Summary: 179 instances, 51 unique

Text	Count
# TODO refine later	3
# TODO: handle is_deny	1
// TODO: Legacy, not needed anymore. Remove in next major version.	3
# TODO we want to upload to infra node, use a service in a container to serve workers requesting this package.	1
# TODO: deprecate typo "AvaliableJobNum" in legacy code	1
# FIXME JobRestAPIUtils.CloneJob is not implemented	1
# TODO parallelize deleting resource of different nodes	1
# TODO assert job_object is a Job	1
# TODO setup reasonable timeout	1
"""the ip generated for worker / nfs not used for vm creation TODO delete?"""	1
# TODO: Make mountpoints independent of job.get_plugins	1
# TODO it should return only one entry	2
# TODO: This can be made as a separate service to GC DB and orphaned pods	1
# write_nodelist_yaml() TODO verify whether this step is necessary	1
# TODO: Tolerate faults	1
# TODO: Refactor	2
# TODO: Replace joblog manager with elastic search	1
# TODO set the timeout	1
# TODO maintain a data_handler so do not need to init it every time	1
# TODO: Fix the case where CPU worker exists in a GPU pool	1
# TODO: Deprecate resource_gpu in the future	1
# TODO: Tolerate faults	2
# TODO: return 403 error code	1
# TODO instead of delete, we could check update existiong ones. During refactoring, keeping the old way.	1
# TODO: Merge with update_worker_nodes	1
// TODO: remove after dropping support for < 2.0	3
# TODO: Simplify code logic after removing PS	6
# TODO zx: we may need to def get_file_modules_2_copy_by_node_role() to make it more extendable.	1
# TODO: deprecate typo "gpu_avaliable" in legacy code	1
// TODO: This is sample code that needs validation from the WAAD team!	1
# TODO: split into generic + specific node for options.env and worker-kubeconfig.yaml	1
# TODO: Set memory limits when we've profiled the container for large	1
# TODO: Find the proper regex to do this.	1
# FIXME with pod_name, we may can not use blobfuse	1
// TODO: make this comparison case-insensitive on windows?	3
cmd_timeout = 10 # TODO 99th latency is xxx	1
TODO: Should be covered by update_role_nodes in deploy.py V2	3
# TODO currently don't keep history of operation here. or name the bash by time?	1
# TODO: Find a better way to manage system and user resource quota	1
# TODO use cluster_resource.py to simplify code:	1
# TODO: Refactor into mountpoint add	1
# TODO: Deprecate typo "gpu_avaliable" in legacy code	1
# TODO: merge with storage-mount-path when dlts vc migration completes.	1
# TODO we need job["lastUpdated"] for filtering	3
# TODO: Deprecate typo "AvaliableJobNum" in legacy code	1
# TODO try delete with resource delete, if possible, remove this function	1
# TODO ??? when ps/master role "Succeeded", return Succeeded	1
# TODO speed this up, since this is O(n^2)	1
# TODO we don't load and dump here since it would break the orders	1
* @param {anything} params.operationThreading - TODO: ?	108
echo TODO: RUN functional tests!	2