mgr/rbd_support: fix recursive locking on CreateSnapshotRequests lock

The MirrorSnapshotScheduleHandler's run thread issues asynchronous
create snapshot requests using a CreateSnapshotRequests instance. When
the thread invokes a CreateSnapshotRequests instance's get_ioctx(),
the instance's class variable lock is acquired. With the class
variable lock held, the garbage collection of a CreateSnapshotRequests
instance may race in the thread. The thread would then call
CreateSnapshotRequests __del__() that tries to acquire the class
variable lock that the thread already holds. Fix this
recursive deadlock by converting the CreateSnapshotRequests lock from
a class variable to an instance variable. There is no need to share
the lock across CreateSnapshotRequests instances.

Also convert MirrorSnapshotScheduleHandler, PerfHandler and
TrashPurgeScheduleHandler class variables to instance variables
that don't need to be shared across the instances.

Fixes: https://tracker.ceph.com/issues/62994
Signed-off-by: Ramana Raja <rraja@redhat.com>
Co-Authored-By: Ilya Dryomov <idryomov@gmail.com>
(cherry picked from commit 4452bc22d1c6c8499cf55d6e39090adf7ae1dcbf)

 Conflicts:
	src/pybind/mgr/rbd_support/mirror_snapshot_schedule.py
	src/pybind/mgr/rbd_support/perf.py
	src/pybind/mgr/rbd_support/trash_purge_schedule.py
 - Above conflicts were due to commit e4a16e2
   ("mgr/rbd_support: add type annotation") not in pacific

diff --git a/src/pybind/mgr/rbd_support/mirror_snapshot_schedule.py b/src/pybind/mgr/rbd_support/mirror_snapshot_schedule.py
index 42ecdbbe0cf309e733c4e673524a6bbb304bde66..69a8f677f862aa621a20a26080a45634f0ef14db 100644 (file)
--- a/src/pybind/mgr/rbd_support/mirror_snapshot_schedule.py
+++ b/src/pybind/mgr/rbd_support/mirror_snapshot_schedule.py
@@ -25,10 +25,9 @@ def image_validator(image):
 
 class CreateSnapshotRequests:
 
-    lock = Lock()
-    condition = Condition(lock)
-
     def __init__(self, handler):
+        self.lock = Lock()
+        self.condition = Condition(self.lock)
         self.handler = handler
         self.rados = handler.module.rados
         self.log = handler.log
@@ -306,10 +305,9 @@ class MirrorSnapshotScheduleHandler:
     SCHEDULE_OID = "rbd_mirror_snapshot_schedule"
     REFRESH_DELAY_SECONDS = 60.0
 
-    lock = Lock()
-    condition = Condition(lock)
-
     def __init__(self, module):
+        self.lock = Lock()
+        self.condition = Condition(self.lock)
         self.module = module
         self.log = module.log
         self.last_refresh_images = datetime(1970, 1, 1)

diff --git a/src/pybind/mgr/rbd_support/perf.py b/src/pybind/mgr/rbd_support/perf.py
index 1a26119b12048b7b3120570d1cdbfd3e6f2a98aa..469309c60f1e997c3ea488e9ac556e33e19bdb1b 100644 (file)
--- a/src/pybind/mgr/rbd_support/perf.py
+++ b/src/pybind/mgr/rbd_support/perf.py
@@ -39,15 +39,6 @@ REPORT_MAX_RESULTS = 64
 
 
 class PerfHandler:
-    user_queries = {}
-    image_cache = {}
-
-    lock = Lock()
-    query_condition = Condition(lock)
-    refresh_condition = Condition(lock)
-
-    image_name_cache = {}
-    image_name_refresh_time = datetime.fromtimestamp(0)
 
     @classmethod
     def prepare_regex(cls, value):
@@ -85,6 +76,16 @@ class PerfHandler:
                 and (pool_key[0] == search_key[0] or not search_key[0]))
 
     def __init__(self, module):
+        self.user_queries = {}
+        self.image_cache = {}
+
+        self.lock = Lock()
+        self.query_condition = Condition(self.lock)
+        self.refresh_condition = Condition(self.lock)
+
+        self.image_name_cache = {}
+        self.image_name_refresh_time = datetime.fromtimestamp(0)
+
         self.module = module
         self.log = module.log
 

diff --git a/src/pybind/mgr/rbd_support/trash_purge_schedule.py b/src/pybind/mgr/rbd_support/trash_purge_schedule.py
index cbbdb1321b2834a94b38f8cffb621445bb3d9a61..9b8e7b9e8c05941264bae88a3646c5b685804ed6 100644 (file)
--- a/src/pybind/mgr/rbd_support/trash_purge_schedule.py
+++ b/src/pybind/mgr/rbd_support/trash_purge_schedule.py
@@ -17,10 +17,9 @@ class TrashPurgeScheduleHandler:
     SCHEDULE_OID = "rbd_trash_purge_schedule"
     REFRESH_DELAY_SECONDS = 60.0
 
-    lock = Lock()
-    condition = Condition(lock)
-
     def __init__(self, module):
+        self.lock = Lock()
+        self.condition = Condition(self.lock)
         self.module = module
         self.log = module.log
         self.last_refresh_pools = datetime(1970, 1, 1)