From ecef670efcfdd4a7101f6e81bd8cd8d71cb542e6 Mon Sep 17 00:00:00 2001
From: Arnaud Morin <arnaud.morin@ovhcloud.com>
Date: Thu, 20 Nov 2025 15:29:52 +0100
Subject: [PATCH] Do not delete queues on error

When a queue is in error, we used to delete the faulty queue.
The problem with that code is that under heavy load, for queues that are
shared accross agents, this could fail in a loop and never recover.

Agent A detect the queue is broken:
it delete the queue and then recreate

In the meantime, Agent B detect the same thing:
it delete the queue and then recreate as well.

Now imagine this with more than 3k agents...

Change-Id: I762bf2839482ee06c5b2fc9fa50f38f5542cbe99
Closes-bug: #2133389
Signed-off-by: Arnaud Morin <arnaud.morin@ovhcloud.com>
---
 oslo_messaging/_drivers/impl_rabbit.py        | 26 -------------------
 ...void-quorum-deletion-ec5fede2d4ecb001.yaml |  5 ++++
 2 files changed, 5 insertions(+), 26 deletions(-)
 create mode 100644 releasenotes/notes/avoid-quorum-deletion-ec5fede2d4ecb001.yaml

diff --git a/oslo_messaging/_drivers/impl_rabbit.py b/oslo_messaging/_drivers/impl_rabbit.py
index 94506dca8..88001e17d 100644
--- a/oslo_messaging/_drivers/impl_rabbit.py
+++ b/oslo_messaging/_drivers/impl_rabbit.py
@@ -558,14 +558,6 @@ class Consumer:
                           'Queue: [%(queue)s], '
                           'error message: [%(err_str)s]', info)
                 time.sleep(interval)
-                if self.queue_arguments.get('x-queue-type') == 'quorum':
-                    # Before re-declare queue, try to delete it
-                    # This is helping with issue #2028384
-                    # NOTE(amorin) we need to make sure the connection is
-                    # established again, because when an error occur, the
-                    # connection is closed.
-                    conn.ensure_connection()
-                    self.queue.delete()
                 self.queue.declare()
             else:
                 raise
@@ -608,24 +600,6 @@ class Consumer:
                                    nowait=self.nowait)
             else:
                 raise
-        except amqp_ex.InternalError as exc:
-            if self.queue_arguments.get('x-queue-type') == 'quorum':
-                # Before re-consume queue, try to delete it
-                # This is helping with issue #2028384
-                if exc.code == 541:
-                    LOG.warning('Queue %s seems broken, will try delete it '
-                                'before starting over.', self.queue.name)
-                    # NOTE(amorin) we need to make sure the connection is
-                    # established again, because when an error occur, the
-                    # connection is closed.
-                    conn.ensure_connection()
-                    self.queue.delete()
-                    self.declare(conn)
-                    self.queue.consume(callback=self._callback,
-                                       consumer_tag=str(tag),
-                                       nowait=self.nowait)
-            else:
-                raise
 
     def cancel(self, tag):
         LOG.trace('ConsumerBase.cancel: canceling %s', tag)
diff --git a/releasenotes/notes/avoid-quorum-deletion-ec5fede2d4ecb001.yaml b/releasenotes/notes/avoid-quorum-deletion-ec5fede2d4ecb001.yaml
new file mode 100644
index 000000000..efe7d4c1e
--- /dev/null
+++ b/releasenotes/notes/avoid-quorum-deletion-ec5fede2d4ecb001.yaml
@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    Avoid deleting RabbitMQ ``quorum`` queues if they are failing on server
+    side with ``Internal Server Error`` (error ``541``).