Skip to content

cluster status safeguards #254

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 7, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 18 additions & 5 deletions src/codeflare_sdk/cluster/cluster.py
Original file line number Diff line number Diff line change
Expand Up @@ -176,9 +176,15 @@ def status(
ready = False
status = CodeFlareClusterStatus.FAILED # should deleted be separate
return status, ready # exit early, no need to check ray status
elif appwrapper.status in [AppWrapperStatus.PENDING]:
elif appwrapper.status in [
AppWrapperStatus.PENDING,
AppWrapperStatus.QUEUEING,
]:
ready = False
status = CodeFlareClusterStatus.QUEUED
if appwrapper.status == AppWrapperStatus.PENDING:
status = CodeFlareClusterStatus.QUEUED
else:
status = CodeFlareClusterStatus.QUEUEING
if print_to_console:
pretty_print.print_app_wrappers_status([appwrapper])
return (
Expand Down Expand Up @@ -561,11 +567,18 @@ def _map_to_ray_cluster(rc) -> Optional[RayCluster]:


def _map_to_app_wrapper(aw) -> AppWrapper:
if "status" in aw and "canrun" in aw["status"]:
return AppWrapper(
name=aw["metadata"]["name"],
status=AppWrapperStatus(aw["status"]["state"].lower()),
can_run=aw["status"]["canrun"],
job_state=aw["status"]["queuejobstate"],
)
return AppWrapper(
name=aw["metadata"]["name"],
status=AppWrapperStatus(aw["status"]["state"].lower()),
can_run=aw["status"]["canrun"],
job_state=aw["status"]["queuejobstate"],
status=AppWrapperStatus("queueing"),
can_run=False,
job_state="Still adding to queue",
)


Expand Down
6 changes: 4 additions & 2 deletions src/codeflare_sdk/cluster/model.py
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ class AppWrapperStatus(Enum):
Defines the possible reportable states of an AppWrapper.
"""

QUEUEING = "queueing"
PENDING = "pending"
RUNNING = "running"
FAILED = "failed"
Expand All @@ -55,8 +56,9 @@ class CodeFlareClusterStatus(Enum):
READY = 1
STARTING = 2
QUEUED = 3
FAILED = 4
UNKNOWN = 5
QUEUEING = 4
FAILED = 5
UNKNOWN = 6


@dataclass
Expand Down