[DNM]: Revert W/A for devicehealth module ceph health failure during ODF deployment (DFBUGS-6749)

ocs_ci/deployment/deployment.py

@@ -194,7 +194,6 @@
     get_acm_mce_build_tag,
     apply_oadp_workaround,
     mute_mon_netsplit,
-    ceph_health_resolve_devicehealth,
 )
 from ocs_ci.utility.vsphere_nodes import update_ntp_compute_nodes
 from ocs_ci.helpers import helpers
@@ -2272,14 +2271,6 @@ def deploy_ocs(self):
         # https://issues.redhat.com/browse/DFBUGS-4521
         if config.DEPLOYMENT.get("arbiter_deployment"):
             mute_mon_netsplit(namespace=self.namespace)
-
-        # Workaround for DFBUGS-6749: devicehealth module fails when its
-        # pool cannot be created due to a missing default CRUSH rule.
-        try:
-            ceph_health_resolve_devicehealth()
-        except Exception as ex:
-            logger.warning(f"devicehealth workaround failed (may not be needed): {ex}")
-
         # Verify health of ceph cluster
         logger.info("Done creating rook resources, waiting for HEALTH_OK")
         try:

ocs_ci/ocs/resources/storage_cluster.py

@@ -92,7 +92,6 @@
     TimeoutSampler,
     convert_device_size,
     extract_image_urls,
-    ceph_health_resolve_devicehealth,
 )
 from ocs_ci.utility.decorators import switch_to_orig_index_at_last
 from ocs_ci.helpers.helpers import storagecluster_independent_check
@@ -786,12 +785,6 @@ def ocs_install_verification(
 
     # TODO: Enable the check when a solution is identified for tools pod on FaaS consumer
     if not (fusion_aas_consumer or hci_cluster):
-        # Workaround for DFBUGS-6749: devicehealth module fails when its
-        # pool cannot be created due to a missing default CRUSH rule.
-        try:
-            ceph_health_resolve_devicehealth()
-        except Exception as ex:
-            log.warning(f"devicehealth workaround failed (may not be needed): {ex}")
         # Temporarily disable health check for hci until we have enough healthy clusters
         assert utils.ceph_health_check(
             namespace,

ocs_ci/utility/utils.py

@@ -3128,58 +3128,9 @@ def check_ceph_health_not_ok():
     sampler.wait_for_func_status(True)
 
 
-def ceph_health_resolve_devicehealth():
-    """
-    Fix ceph health issue where the devicehealth module fails because
-    its pool cannot be created due to a missing CRUSH rule.
-
-    Workaround:
-        1. Set osd_pool_default_crush_rule to 0 (block pool rule)
-        2. Restart the devicehealth module so it retries pool creation
-        3. Archive any resulting crash reports
-
-    """
-    # importing here to avoid circular import
-    from ocs_ci.ocs.resources.pod import get_ceph_tools_pod
-
-    log.warning(
-        "Trying to fix devicehealth module failure by setting "
-        "default CRUSH rule and restarting the module"
-    )
-    ct_pod = get_ceph_tools_pod()
-
-    ct_pod.exec_ceph_cmd(
-        ceph_cmd="ceph config set mon osd_pool_default_crush_rule 0",
-        format=None,
-        out_yaml_format=False,
-    )
-    log.info("Set osd_pool_default_crush_rule to 0")
-
-    ct_pod.exec_ceph_cmd(
-        ceph_cmd=("ceph mgr module force disable devicehealth --yes-i-really-mean-it"),
-        format=None,
-        out_yaml_format=False,
-    )
-    log.info("Force disabled devicehealth module")
-
-    ct_pod.exec_ceph_cmd(
-        ceph_cmd="ceph mgr module enable devicehealth",
-        format=None,
-        out_yaml_format=False,
-    )
-    log.info("Re-enabled devicehealth module")
-
-    # give time to generate crash
-    time.sleep(180)
-
-    ceph_crash_info_display(ct_pod)
-    archive_ceph_crashes(ct_pod)
-
-
 def ceph_health_resolve_crash():
     """
     Fix ceph health issue with daemon crash
-
     """
     log.warning("Trying to fix the issue with crash by archiving crashes")
     from ocs_ci.ocs.resources.pod import get_ceph_tools_pod
@@ -3298,20 +3249,6 @@ def ceph_health_recover(
 
     """
     ceph_health_fixes = [
-        {
-            "pattern": r"Module 'devicehealth' has failed",
-            "func": ceph_health_resolve_devicehealth,
-            "func_args": [],
-            "func_kwargs": {},
-            "ceph_health_tries": 10,
-            "ceph_health_delay": 30,
-            "known_issues": [
-                {
-                    "issue": "DFBUGS-6749",
-                    "pattern": r"Module 'devicehealth' has failed",
-                },
-            ],
-        },
         {
             "pattern": r"daemons have recently crashed",
             "func": ceph_health_resolve_crash,