Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[Serve] Scale down old terminal replicas #3550

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

[Serve] Scale down old terminal replicas #3550

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2e4d1e0
fix
cblmemo May 14, 2024
eaacd06
revert
cblmemo May 14, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
12 changes: 12 additions & 0 deletions sky/serve/autoscalers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -314,7 +314,19 @@ def select_outdated_replicas_to_scale_down(
self,
replica_infos: List['replica_managers.ReplicaInfo']) -> List[int]:
"""Select outdated replicas to scale down."""
all_replica_ids_to_scale_down = []
for info in replica_infos:
if info.version < self.latest_version and info.is_terminal:
all_replica_ids_to_scale_down.append(info.replica_id)
Comment on lines +319 to +320
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

IIRC the original behavior will terminate the failed replicas already. Is this only for removing the FAILED replica entries in the serve status table? In that case, should we make the sky serve down command able to remove a FAILED entry in the table instead?

I feel keeping the FAILED replicas for the previous version might be still useful.

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, it is only for removing those failed records from a user's request. Agree that adding the ability to remove a record in sky serve down is a better idea. It is implemented in #3179 and I'll take a look soon 🫡

all_replica_ids_to_scale_down.extend(
self._select_outdated_nonterminal_replicas_to_scale_down(
replica_infos))
return all_replica_ids_to_scale_down

def _select_outdated_nonterminal_replicas_to_scale_down(
self,
replica_infos: List['replica_managers.ReplicaInfo']) -> List[int]:
"""Select outdated nonterminal replicas to scale down."""
Comment on lines +321 to +329
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This refactoring seems not necessary.

Suggested change
all_replica_ids_to_scale_down.extend(
self._select_outdated_nonterminal_replicas_to_scale_down(
replica_infos))
return all_replica_ids_to_scale_down
def _select_outdated_nonterminal_replicas_to_scale_down(
self,
replica_infos: List['replica_managers.ReplicaInfo']) -> List[int]:
"""Select outdated nonterminal replicas to scale down."""

if self.update_mode == serve_utils.UpdateMode.ROLLING:
latest_ready_replicas = []
old_nonterminal_replicas = []
Expand Down