From ec55e96a09ac825c84c67d53ed86289759196bfb Mon Sep 17 00:00:00 2001
From: Jason Sollom <jason.sollom@hpe.com>
Date: Tue, 29 Oct 2024 15:47:26 -0500
Subject: [PATCH] Provide an option to control the PCS transition deadline

---
 CHANGELOG.md                            | 4 ++++
 api/openapi.yaml.in                     | 7 +++++++
 src/bos/common/options.py               | 5 +++++
 src/bos/operators/power_off_forceful.py | 2 +-
 src/bos/operators/power_off_graceful.py | 3 ++-
 src/bos/operators/power_on.py           | 3 ++-
 6 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4105b927..56c6a8a7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## Unreleased
+### Added
+- BOS option to control how long a deadline it gives PCS to complete its transition
+
 ## [2.30.5] - 2024-10-15
 ### Fixed
 - Fix per-bootset CFS setting
diff --git a/api/openapi.yaml.in b/api/openapi.yaml.in
index 31475590..b7b96faa 100644
--- a/api/openapi.yaml.in
+++ b/api/openapi.yaml.in
@@ -976,6 +976,13 @@ components:
         Options for the Boot Orchestration Service.
       type: object
       properties:
+        pcs_transition_deadline:
+          type: integer
+          description: |
+            The amount of time (in minutes) to set the deadline for a PCS pcs_transition_deadline
+          example: 1
+          minimum: 1
+          maximum: 1440
         cfs_read_timeout:
           type: integer
           description: |
diff --git a/src/bos/common/options.py b/src/bos/common/options.py
index f01914c6..4d922cd9 100644
--- a/src/bos/common/options.py
+++ b/src/bos/common/options.py
@@ -29,6 +29,7 @@
 # code should either import this dict directly, or (preferably) access
 # its values indirectly using a DefaultOptions object
 DEFAULTS = {
+    'pcs_transition_deadline': 60,
     'cfs_read_timeout': 20,
     'cleanup_completed_session_ttl': "7d",
     'clear_stage': False,
@@ -63,6 +64,10 @@ def get_option(self, key: str) -> Any:
     # All these do is convert the response to the appropriate type for the option,
     # and return it.
 
+    @property
+    def pcs_transition_deadline(self) -> int:
+        return int(self.get_option('pcs_transition_deadline'))
+
     @property
     def cfs_read_timeout(self) -> int:
         return int(self.get_option('cfs_read_timeout'))
diff --git a/src/bos/operators/power_off_forceful.py b/src/bos/operators/power_off_forceful.py
index 5d258b7a..a2ad13ed 100644
--- a/src/bos/operators/power_off_forceful.py
+++ b/src/bos/operators/power_off_forceful.py
@@ -59,7 +59,7 @@ def filters(self):
     def _act(self, components):
         if components:
             component_ids = [component['id'] for component in components]
-            pcs.force_off(nodes=component_ids)
+            pcs.force_off(nodes=component_ids, task_deadline_minutes=options.pcs_transition_deadline)
         return components
 
 
diff --git a/src/bos/operators/power_off_graceful.py b/src/bos/operators/power_off_graceful.py
index 9a925b07..bad62c82 100644
--- a/src/bos/operators/power_off_graceful.py
+++ b/src/bos/operators/power_off_graceful.py
@@ -26,6 +26,7 @@
 
 from bos.common.values import Action, Status
 from bos.operators.utils.clients import pcs
+from bos.operators.utils.clients.bos.options import options
 from bos.operators.base import BaseOperator, main
 from bos.operators.filters import BOSQuery, HSMState
 
@@ -55,7 +56,7 @@ def filters(self):
     def _act(self, components):
         if components:
             component_ids = [component['id'] for component in components]
-            pcs.soft_off(component_ids)
+            pcs.soft_off(component_ids, task_deadline_minutes=options.pcs_transition_deadline)
         return components
 
 
diff --git a/src/bos/operators/power_on.py b/src/bos/operators/power_on.py
index 8b06f84a..7bfe4fe1 100644
--- a/src/bos/operators/power_on.py
+++ b/src/bos/operators/power_on.py
@@ -39,6 +39,7 @@
 from bos.operators.utils.clients import pcs
 from bos.operators.utils.clients.ims import tag_image
 from bos.operators.utils.clients.cfs import set_cfs
+from bos.operators.utils.clients.bos.options import options
 from bos.operators.base import BaseOperator, main
 from bos.operators.filters import BOSQuery, HSMState
 from bos.server.dbs.boot_artifacts import record_boot_artifacts
@@ -88,7 +89,7 @@ def _act(self, components: Union[List[dict],None]):
             raise Exception(f"Error encountered setting CFS information: {e}") from e
         component_ids = [component['id'] for component in components]
         try:
-            pcs.power_on(component_ids)
+            pcs.power_on(component_ids, task_deadline_minutes=options.pcs_transition_deadline)
         except Exception as e:
             raise Exception(f"Error encountered calling CAPMC to power on: {e}") from e
         return components