Adding ceph health check bypass in sat bootsys ncn-power

IM:CRAYSAT-1787
Reviewer:Ryan
Adding ceph health check bypass prompt for the user to decide whether to wait
or proceed with skipping the health check after unfreezing of ceph is done.
As it may take some time and the next steps may not explicitly require, by the
time it comes back it would be good to use.

CHANGELOG.md

@@ -43,6 +43,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   ncn power stage
 - If containers fail to stop, automate the procedure of trying to stop them again
   in the `platform-services` stage.
+- Adding a ceph health check bypass prompt to take input from user and act accordingly.
+  unfreezing of ceph would be done, only the wait period will be skipped if user wishes to.
 
 ### Fixed
 - Updated `sat bootsys` to increase the default management NCN shutdown timeout

sat/cli/bootsys/platform.py

@@ -539,6 +539,34 @@ def do_ceph_freeze():
         raise FatalPlatformError(str(err))
 
 
+def prompt_user_for_health_check():
+    """Prompt the user to decide if they want to skip the Ceph health check.
+
+    Returns:
+        bool: True if the user wants to skip the health check, False otherwise.
+    """
+    while True:
+        response = input("Do you want to skip the Ceph health check after unfreezing? (yes/no): ").strip().lower()
+        if response in ['yes', 'no']:
+            return response == 'yes'
+        else:
+            print("Invalid response. Please enter 'yes' or 'no'.")
+
+
+def prompt_user_for_health_check():
+    """Prompt the user to decide if they want to skip the Ceph health check.
+
+    Returns:
+        bool: True if the user wants to skip the health check, False otherwise.
+    """
+    while True:
+        response = input("Do you want to skip the Ceph health check after unfreezing? (yes/no): ").strip().lower()
+        if response in ['yes', 'no']:
+            return response == 'yes'
+        else:
+            print("Invalid response. Please enter 'yes' or 'no'.")
+
+
 def do_ceph_unfreeze(ncn_groups):
     """Start inactive Ceph services, unfreeze Ceph and wait for it to be healthy.
 
@@ -551,14 +579,20 @@ def do_ceph_unfreeze(ncn_groups):
     except RuntimeError as err:
         raise FatalPlatformError(str(err))
 
-    with BeginEndLogger('wait for ceph health'):
-        ceph_timeout = get_config_value('bootsys.ceph_timeout')
-        LOGGER.info(f'Waiting up to {ceph_timeout} seconds for Ceph to become healthy after unfreeze')
-        ceph_waiter = CephHealthWaiter(ceph_timeout, storage_hosts, retries=1)
-        if not ceph_waiter.wait_for_completion():
-            raise FatalPlatformError(f'Ceph is not healthy. Please correct Ceph health and try again.')
-        else:
-            LOGGER.info('Ceph is healthy.')
+    # Prompt the user to decide if they want to skip the Ceph health check
+    skip_health_check = prompt_user_for_health_check()
+
+    if skip_health_check:
+        LOGGER.info("Skipping Ceph health check as per user's request.")
+    else:
+        with BeginEndLogger('wait for ceph health'):
+            ceph_timeout = get_config_value('bootsys.ceph_timeout')
+            LOGGER.info(f'Waiting up to {ceph_timeout} seconds for Ceph to become healthy after unfreeze')
+            ceph_waiter = CephHealthWaiter(ceph_timeout, storage_hosts, retries=1)
+            if not ceph_waiter.wait_for_completion():
+                raise FatalPlatformError(f'Ceph is not healthy. Please correct Ceph health and try again.')
+            else:
+                LOGGER.info('Ceph is healthy.')
 
 
 def do_etcd_snapshot(ncn_groups):