Two years after we first wrote about the Distributed Management Task Forces SMASH, Version 1.0 of the spec is complete. This is good news for IT managers who have bought SMASH-capable data center hardware, as they will now be able to fully use the out-of-service, out-of-band specifications provided by SMASH 1.0.
SMASH, or Systems Management Architecture for Server Hardware, specifies how IT managers can interact directly with equipment to get standards-formatted data, including enclosure temperatures, fan speeds and power consumption.
SMASH 1.0 also includes Server Management CLP (Command Line Protocol), designed to reduce management complexity in heterogeneous environments; Managed Element Addressing, which makes it easier to leverage the DMTFs CIM (Common Information Model) standard; CLP-to-CIM Mapping, which describes common requirements for mapping Server Management CLP commands to elements of CIM; and Server Management Profiles for addressing specific management domains.
SMASH 1.0 enables IT managers to use industry-standard protocols along with the semantics provided in the specification to facilitate- local and remote system management.
But to what extent will SMASH 1.0 allow IT managers to replace single-vendor system management tools? Most server hardware today comes with capable management tools—usually at no extra cost. The challenge for SMASH, therefore, will be to demonstrate that it can effectively reduce the number of consoles needed to track fault management in the data center.
SMASH 1.0, which was released in December, is supported by most mainstream server hardware manufacturers, including Dell, Hewlett-Packard and IBM.
Technical Director Cameron Sturdevant can be reached at [email protected]
Check out eWEEK.coms for the latest news, views and analysis on servers, switches and networking protocols for the enterprise and small businesses.