Ceph - OSD nodes have 'page allocation failure' messages in system logs and causing slow requests because of heartbeat failures.
Issue
- Ceph - OSD nodes have
page allocation failuremessages in system logs and causing slow requests because of heartbeat failures.
- In dmesg:
[2487558.078129] swapper/2: page allocation failure: order:2, mode:0x104020
[2487558.078471] python: page allocation failure: order:2, mode:0x104020
- In /var/log/messages:
May 11 12:42:55 node01 kernel: kswapd0: page allocation failure: order:2, mode:0x104020
May 11 12:42:55 node01 kernel: CPU: 36 PID: 225 Comm: kswapd0 Tainted: G W ------------ 3.10.0-514.10.2.el7.x86_64 #1
Environment
- Red Hat Enterprise Linux 7.3 - kernel-3.10.0-514.10.2.el7
- Red Hat Ceph Storage 2.2
- Virtual memory kernel tunable -
vm.min_free_kbytes
Subscriber exclusive content
A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.
