Abstract: Techniques are provided herein for optimizing boot order for devices in a data center environment. These techniques may be embodied as a method, apparatus and instructions in a computer-readable storage media to perform the method. A computing apparatus having connectivity to a network receives instructions from a management device in the network. The instructions comprise attributes that are associated with boot devices hosted by the computing apparatus. The attributes are analyzed to determine a priority order for the boot devices. One or more boot devices hosted by the computing apparatus is removed from an initialization process when the one or more boot devices do not match the attributes in the instructions. The remaining boot devices, other than the one or more boot device removed from the initialization process, are initialized in accordance with the priority order.

Abstract: Techniques are provided herein for optimizing boot order for devices in a data center environment. These techniques may be embodied as a method, apparatus and instructions in a computer-readable storage media to perform the method. A computing apparatus having connectivity to a network receives a service profile boot policy from a management device in the network. The service profile boot policy includes attributes identifying boot devices hosted by the computing apparatus. Data representing the service profile boot policy is stored and an order of boot devices hosted by the computing apparatus is generated. The order is generated according to the attributes of the service profile boot policy. Boot devices are excluded from the order according to the attributes of the service profile boot policy.

Abstract: A data center system management device receives power configuration information for one or more power groups. Each power group has one or more servers. The power configuration information has a power group power limit for each power group. The power budgets are sent to server control units within each power group. Messages are received from each of the server control units, the messages including information to indicate whether servers in the power groups have a power deficit or a power surplus, and a number of power units for the power deficit and power surplus for each server. The server power budgets of the one or more servers in each of the one or more power groups based on power deficits and power surpluses within each power group using a priority based reallocation mechanism.

Abstract: Techniques are provided herein for optimizing boot order for devices in a data center environment. These techniques may be embodied as a method, apparatus and instructions in a computer-readable storage media to perform the method. A computing apparatus having connectivity to a network receives a service profile boot policy from a management device in the network. The service profile boot policy includes attributes identifying boot devices hosted by the computing apparatus. Data representing the service profile boot policy is stored and an order of boot devices hosted by the computing apparatus is generated. The order is generated according to the attributes of the service profile boot policy. Boot devices are excluded from the order according to the attributes of the service profile boot policy.

Abstract: A method includes ranking a plurality of servers in a network environment according to power characteristics, and choosing a server from the plurality of servers for placement of a service profile according to at least a priority specified in the service profile and the server's rank. The ranking includes identifying power groups into which the plurality of servers are partitioned, identifying respective power group caps of the power groups, determining respective power ranges and respective power supply multipliers of the plurality of servers, calculating a score of each server in the plurality of servers, and assigning ranks to the scores. Choosing the server includes partitioning the servers into priority sets according to respective ranks of servers, and searching the priority sets beginning with a priority set having the priority specified in the service profile until a suitable server is found.

Abstract: Techniques presented herein provide approaches for managing rack servers. In one embodiment, a message is received from a management controller of a rack server and via a switch port, where the message requests a lease for a network address under a first protocol. Upon determining that the management controller is a supported device, the switch port is configured to allow network traffic under at least a second protocol.

Abstract: Techniques are provided herein for optimizing boot order for devices in a data center environment. These techniques may be embodied as a method, apparatus and instructions in a computer-readable storage media to perform the method. A computing apparatus having connectivity to a network receives instructions from a management device in the network. The instructions comprise attributes that are associated with boot devices hosted by the computing apparatus. The attributes are analyzed to determine a priority order for the boot devices. One or more boot devices hosted by the computing apparatus is removed from an initialization process when the one or more boot devices do not match the attributes in the instructions. The remaining boot devices, other than the one or more boot device removed from the initialization process, are initialized in accordance with the priority order.

Abstract: A method includes ranking a plurality of servers in a network environment according to power characteristics, and choosing a server from the plurality of servers for placement of a service profile according to at least a priority specified in the service profile and the server's rank. The ranking includes identifying power groups into which the plurality of servers are partitioned, identifying respective power group caps of the power groups, determining respective power ranges and respective power supply multipliers of the plurality of servers, calculating a score of each server in the plurality of servers, and assigning ranks to the scores. Choosing the server includes partitioning the servers into priority sets according to respective ranks of servers, and searching the priority sets beginning with a priority set having the priority specified in the service profile until a suitable server is found.

Abstract: A data center system management device receives power configuration information for one or more power groups. Each power group has one or more servers. The power configuration information has a power group power limit for each power group. The power budgets are sent to server control units within each power group. Messages are received from each of the server control units, the messages including information to indicate whether servers in the power groups have a power deficit or a power surplus, and a number of power units for the power deficit and power surplus for each server. The server power budgets of the one or more servers in each of the one or more power groups based on power deficits and power surpluses within each power group using a priority based reallocation mechanism.

Abstract: Techniques are provided for a computer device to receive and store data comprising information configured to indicate boot device parameters for devices to be initialized during a given boot sequence. Those devices that match the device parameters are initialized prior to loading the computer device's operating system. Devices that do not match the boot parameters are masked out by the BIOS, and Option ROM firmware is loaded and executed for those devices that match the boot parameters.

Abstract: Techniques presented herein provide approaches for managing rack servers. In one embodiment, a message is received from a management controller of a rack server and via a switch port, where the message requests a lease for a network address under a first protocol. Upon determining that the management controller is a supported device, the switch port is configured to allow network traffic under at least a second protocol.