ScaleMP Management & Monitoring

Bright Cluster Manager® — Advanced Edition can aggregate multiple cluster nodes into a single virtual SMP node, using ScaleMP's Versatile SMP™ (vSMP) architecture. Capabilities include on-the-fly deployment, provisioning, configuration, monitoring and management of virtual SMP nodes.

Virtual SMP

Creating one or more virtual SMP nodes using ScaleMP's Versatile SMP architecture is trivial with Bright Cluster Manager. This screenshots shows the Virtual SMP tab in which virtual SMP nodes are created and configured.

Creating one or more virtual SMP nodes using ScaleMP's Versatile SMP architecture is trivial with Bright Cluster Manager.

Virtual SMP technology allows multiple physical x86 servers (nodes) to be aggregated and presented as a single, virtual SMP server (node).

Bright Computing's integration with vSMP Foundation means that creating and dismantling a virtual SMP node can be achieved with just a few clicks within the cluster management GUI. Virtual SMP nodes can even be built and launched automatically on-the-fly using the scripting capabilities of the cluster management shell.

In a Bright Cluster Manager cluster a virtual SMP node behaves like any other node. This means it can be provisioned, monitored, used in the workload management system, have health checks running on it, and so on.

Features

Bright Cluster Manager provides a dashboard-style overview of your virtual SMP node. This screenshot shows overviews of running jobs, disk usage, network interfaces, and health status of virtual SMP node "vnode001".

Bright Cluster Manager provides a dashboard-style overview of your virtual SMP node.

Bright Cluster Manager — Advanced Edition allows the configuration of the virtual SMP node, as well as the underlying physical members of the virtual SMP node.

The configuration is integrated into Bright Cluster Management such that, amongst other features:

• a new virtual SMP node can be created with a few mouse clicks;
• member nodes can be added to or removed from the virtual SMP node as needed;
• a list of physical member nodes used by the virtual SMP node is set;
• the percentage memory used by the OS running on the virtual SMP node can be set, with the remainder used on the node for virtual SMP related optimization purposes;
• the minimal number of active interface boards needed in order for booting to start can be set;
• console redirection can be set to specific serial port(s) of the physical node members;
• the boot device member for the virtual SMP node can be set;
• behavior upon boot failure can be set (for example, to restart or to drop to a menu);
• hyperthreading can be switched on or off, to suit performance needs;
• extended ACPI information can be switched on or off;
• the HCA firmware can be updated;
• a watchdog-style restart can be set in case the virtual SMP node kernel panics.