Exalogic Compute Nodes Hang When More Than 32 Virtual Machines Are Running
Last updated on MAY 23, 2018
Applies to:Oracle Exalogic Elastic Cloud Software - Version 220.127.116.11.0 to 18.104.22.168.3
Oracle Exalogic Elastic Cloud Software - Version 22.214.171.124.1 to 126.96.36.199.2
This MOS Note Applies To Following Releases:
- Exalogic Virtual Releases 188.8.131.52.x on X4-2 racks
- Exalogic Virtual Releases 184.108.40.206.x on X4-2 and X5-2 racks
In Exalogic X4-2 and X5-2 Virtual racks when running over 32 VM's on a compute node, the following symptoms are observed.
- Guest VM's are all hung or inaccessible on given node
- OCFS timeouts in all compute node logs
- Hung node cannot access NFS or other hosts via infiniband network.
The following errors can also be observed in the compute node /var/log/messages log.
Adding additional virtual machines can trigger this problem.
Sign In with your My Oracle Support account
Don't have a My Oracle Support account? Click to get started
My Oracle Support provides customers with access to over a
Million Knowledge Articles and hundreds of Community platforms