Operational Differences on an SMW HA System

The SMW HA system includes the following operational differences from running a single SMW:

• On an SMW HA system, control the rsms daemon as root rather than as crayadm. In addition, restarting rsms behaves differently than on a system with a single SMW. Running /etc/init.d/rsms restart does not display the expected output, because the HA cluster returns immediately rather than waiting for the HSS daemons to start. To display the daemon status, run /etc/init.d/rsms status.
• Key system services (also called resources) are controlled by the cluster manager (see Cluster Resources). Do not start or stop these services individually. Instead, use cluster management tools to start and stop these services. For more information, see About SMW HA Commands.
• Auto-throttling of applications is likely while an actual SMW failover is taking place. Blades begin to auto-throttle if essential HSS daemons (erd, state-manager, or xtnlrd) are unavailable and lasts until those daemons resume operation on the other SMW. On a single-cabinet system, the throttled period was fairly consistent, lasting 37 seconds. The throttled period may increase for larger systems.
• Because several file systems are shared between the two SMWs, an SMW HA system has a slightly increased risk for double-mount problems. Do not mount the shared file systems from the boot RAID on both SMWs at the same time.