Project

General

Profile

Bug #57956

Ceph monitors in crash loop

Added by liu jun 3 months ago. Updated 3 months ago.

Status:
New
Priority:
Normal
Assignee:
-
Category:
Monitor
Target version:
% Done:

0%

Source:
Tags:
mon
Backport:
Regression:
No
Severity:
1 - critical
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

Creating a pool causes mon to restart

This is the detailed question:https://github.com/rook/rook/issues/10110

https://github.com/rook/rook/issues/11242
https://github.com/rook/rook/issues/11081

Environment:

OS : Fedora CoreOS 35.20220327.3.0
Kernel : 5.16.16-200.fc35.x86_64
Cloud provider or hardware configuration: Dell FC640/MX740c
Rook version: 1.8.8/1.9.0
Storage backend version : 16.2.7
Kubernetes version : 1.23.5
Kubernetes cluster type: Baremetal (self-managed/vanilla)
Storage backend status : Keeps timings out when mons are crashing and updated with number of mons down

History

#1 Updated by liu jun 3 months ago

liu jun wrote:

Creating a pool causes mon to restart

This is the detailed question:https://github.com/rook/rook/issues/10110

https://github.com/rook/rook/issues/11242
https://github.com/rook/rook/issues/11081

Environment:

OS : Fedora CoreOS 35.20220327.3.0
Kernel : 5.16.16-200.fc35.x86_64
Cloud provider or hardware configuration: Dell FC640/MX740c
Rook version: 1.8.8/1.9.0
Storage backend version : 16.2.7
Kubernetes version : 1.23.5
Kubernetes cluster type: Baremetal (self-managed/vanilla)
Storage backend status : Keeps timings out when mons are crashing and updated with number of mons down

Create 3 mons normally, check the mon node process after initialization, you will find that ms_dispatch and fn_monstore will have cpu 100% problem, and pg pool is being created at this time. Quickly kill these two processes ceph cluster is normal.

Also available in: Atom PDF