Question & Answer
Question
What are the network best practices required for building a healthy cluster in SSP environment ?
Cause
If a node in the Shared Storage Pool (SSP) cluster is isolated from the rest of cluster, i,e., if a node loses network connectivity, then the leader will expel this node to allow forward progress in the cluster.
Answer
In order to minimize network issues on a node that will lead to its expel and a possible impact on its client LPARs, there are certain best practices that are recommended to be practiced by our development.
1) Synchronize clocks of all VIOS nodes in the cluster using ntpd/xntpd
2) Keep cluster communication on network adapter that is not congested
3) Do not share cluster communication adapter with client partitions. In other words, do not configure IP on a Shared Ethernet Adapter's(SEA) interface and use that IP for cluster communication because an SEA is configured to bridge network traffic to the client LPARs.
4) Do not share cluster communication adapter with storage traffic (FCoE)
5) Redundancy of networking communication:
- Configure ether-channel. Bind logical interface over a channel that has multiple ports, connected over multiple switches.
- Configure multi-path routing
7) If necessary, bring storage pool and VMs down during networking re-configurations.
Related Information
[{"Type":"MASTER","Line of Business":{"code":"LOB57","label":"Power"},"Business Unit":{"code":"BU058","label":"IBM Infrastructure w\/TPS"},"Product":{"code":"SSPHKW","label":"PowerVM Virtual I\/O Server"},"ARM Category":[{"code":"a8m50000000L0KiAAK","label":"PowerVM VIOS-\u003EShared Storage Pool {SSP}"}],"ARM Case Number":"","Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"3.1.2;3.1.3;3.1.4"}]
Was this topic helpful?
Document Information
Modified date:
30 May 2023
UID
isg3T1024628