Systems and methods for disaggregated power control of a server rack

1 . An Information Handling System (IHS), comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises program instructions stored thereon that, upon execution by the processor, cause the IHS to:

obtain power telemetry, via a network, from a plurality of nodes of a server rack;

obtain power shelf telemetry, via the network, from one or more power shelves of the server rack, wherein the one or more power shelves comprise one or more disaggregated power shelves that provide dynamic keep-alive features via the network-based telemetries to prevent power infrastructure failure for the one or more power shelves, and wherein each of the one or more disaggregated power shelves comprises one or more power supplies;

determine, based at least in part on the power telemetry and the power shelf telemetry, respective power limits for respective individual nodes of the plurality of nodes, including a first power limit for a first node of the plurality of nodes;

determine that each of the individual nodes is either a utilized node or an under-utilized node; and

provide the determined respective power limits to the respective individual nodes of the server rack, including the first power limit to the first node;

wherein to determine the respective power limits for the respective individual nodes, the program instructions further cause the IHS to:

determine that the respective power limits for the utilized nodes comprise a percentage of a thermal design power above 50%; and

determine that the respective power limits for the under-utilized nodes comprise a node lower boundary power which comprises a percentage of a thermal design power at or below 50%.

2 . The IHS of claim 1 , wherein the power telemetry comprises at least one of: power inventory of the plurality of nodes, turbo power of the plurality of nodes, thermal design power of the plurality of nodes, or a power inventory lower boundary of the plurality of nodes.

3 . The IHS of claim 2 , wherein the power shelf telemetry comprises at least one of: power capacity of the one or more power shelves, or power capability of the one or more power shelves.

4 . The IHS of claim 1 , further comprising:

limit, by the first node, the power consumption of the first node to at or below the first power limit.

5 . The IHS of claim 1 , wherein the power telemetry comprises power inventory of the plurality of nodes.

6 . The IHS of claim 1 , wherein the power telemetry comprises thermal design power of the plurality of nodes, or a power inventory lower boundary of the plurality of nodes.

7 . The IHS of claim 2 , wherein the power inventory lower boundary of the plurality of nodes comprises a power that each of the plurality of nodes requires when it is fully throttled.

8 . An Information Handling System (IHS), comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises program instructions stored thereon that, upon execution by the processor, cause the IHS to:

obtain power telemetry, via a network, from a plurality of nodes of a server rack;

obtain power shelf telemetry, via the network, from one or more power shelves of the server rack, wherein the one or more power shelves comprise one or more disaggregated power shelves that provide dynamic keep-alive features via the network-based telemetries to prevent power infrastructure failure for the one or more power shelves, and wherein each of the one or more disaggregated power shelves comprises one or more power supplies;

determine, based at least in part on the power telemetry and the power shelf telemetry, respective power limits for respective individual nodes of the plurality of nodes, including a first power limit for a first node of the plurality of nodes;

determine that each of the individual nodes is either a utilized node or an under-utilized node; and

provide the determined respective power limits to the respective individual nodes of the server rack, including the first power limit to the first node;

wherein to determine the respective power limits for the respective individual nodes, the program instructions further cause the IHS to:

determine that the respective power limits for the utilized nodes comprise a thermal design power; and

determine that the respective power limits for the under-utilized nodes comprise a percentage of the thermal design power above 50%.

9 . An Information Handling System (IHS), comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises program instructions stored thereon that, upon execution by the processor, cause the IHS to:

obtain power telemetry, via a network, from a plurality of nodes of a server rack;

obtain power shelf telemetry, via the network, from one or more power shelves of the server rack, wherein the one or more power shelves comprise one or more disaggregated power shelves that provide dynamic keep-alive features via the network-based telemetries to prevent power infrastructure failure for the one or more power shelves, and wherein each of the one or more disaggregated power shelves comprises one or more power supplies;

determine, based at least in part on the power telemetry and the power shelf telemetry, respective power limits for respective individual nodes of the plurality of nodes, including a first power limit for a first node of the plurality of nodes;

determine that each of the individual nodes is either a utilized node or an under-utilized node; and

provide the determined respective power limits to the respective individual nodes of the server rack, including the first power limit to the first node;

wherein to determine the respective power limits for the respective individual nodes, the program instructions further cause the IHS to:

determine that the respective power limits for the utilized nodes comprise a percentage of a thermal design power above 100%; and

determine that the respective power limits for the under-utilized nodes comprise the thermal design power.