Stalling I/O triggers HAE Cluster

This document (7010781) is provided subject to the disclaimer at the end of this document.

Environment

SUSE Linux Enterprise High Availability Extension 11 Service Pack 1
SUSE Linux Enterprise High Availability Extension 11 Service Pack 2

Situation

The SuSE HAE Cluster is designed to react to anomalies in the system. If the memory is big and the dirty ratio is relatively high, then the moment the dirty ratio is hit and written to disk this can reduce the I/O drastically. This can trigger the Cluster to react as to an anomaly. In some cases this will trigger a fence of a node.

Resolution

To circumvent this from happening it is best practice to set on HAE Cluster systems with big memory, which can be anything bigger than 8GB in

/etc/sysctl.conf

          vm.dirty_background_bytes = 134217728
          vm.dirty_bytes = 1073741824

and activate with

        sysctl -p

no reboot is necessary for this setting.

Disclaimer

This Support Knowledgebase provides a valuable tool for SUSE customers and parties interested in our products and solutions to acquire information, ideas and learn from one another. Materials are provided for informational, personal or non-commercial use within your organization and are presented "AS IS" WITHOUT WARRANTY OF ANY KIND.