Managing servers using power transmission circuits

Patent metadata

Field	Value
Publication number	US-12436829-B2
Application number	US-202318372227-A
Country	US
Kind code	B2
Filing date	Sep 25, 2023
Priority date	Sep 25, 2023
Publication date	Oct 7, 2025
Grant date	Oct 7, 2025

Abstract

A technique is directed to managing a server cluster that includes multiple servers. The technique involves receiving, from a server in the server cluster, set of heartbeat signals through a power transmission circuit constructed and arranged to deliver power to the server cluster. The technique further involves detecting an interruption in receiving the set of heartbeat signals. The technique further involves, in response to detecting the interruption in receiving the set of heartbeat signals, performing a remedial activity to coordinate input/output (I/O) operations among the multiple servers in the server cluster.

First claim

What is claimed is:

1. A method of managing a server cluster that includes multiple servers, the method comprising:
receiving, from a server in the server cluster, a set of heartbeat signals through a power transmission circuit constructed and arranged to deliver power to the server cluster;
detecting an interruption in receiving the set of heartbeat signals; and
in response to detecting the interruption in receiving the set of heartbeat signals, performing a remedial activity to coordinate input/output (I/O) operations among the multiple servers in the server cluster;

wherein the set of heartbeat signals includes a first identifier of the server in the server cluster;
wherein an identifying device is coupled with the power transmission circuit, the identifying device being constructed and arranged to provide a second set of heartbeat signals through the power transmission circuit, the second set of heartbeat signals including a second identifier of the identifying device, the second identifier being different from the first identifier; and
wherein the method further comprises:
while receiving the set of heartbeat signals from the server through the power transmission circuit, receiving the second set of heartbeat signals from the identifying device through the power transmission circuit.

2. The method of claim 1 wherein the server cluster is constructed and arranged to perform the I/O operations to store host data into and retrieve the host data from a set of storage devices on behalf of a set of host computers; and
wherein receiving the set of heartbeat signals includes:
acquiring the set of heartbeat signals from the server while the I/O operations are performed.

3. The method of claim 1 wherein a computer network couples the multiple servers in the server cluster with each other, the computer network being different from the power transmission circuit; and
wherein the method further comprises:
communicating with the server through the computer network to coordinate performing the I/O operations with the server.

4. The method of claim 3 wherein communicating with the server through the computer network includes:
while receiving the set of heartbeat signals from the server through the power transmission circuit, receiving another set of heartbeat signals from the server through the computer network;

wherein performing the remedial activity to coordinate the I/O operations among the multiple servers is further in response to detecting another interruption in receiving the other set of heartbeat signals through the computer network.

5. The method of claim 4 wherein the server includes a wireless transmitter constructed and arranged to provide signals through the computer network; and
wherein receiving the other set of heartbeat signals from the server through the computer network includes:
acquiring the other set of heartbeat signals wirelessly through the computer network.

6. The method of claim 1 wherein detecting the interruption includes:
detecting a timeout event in which no heartbeat signal is received within a timeout period; and

wherein performing the remedial activity to coordinate the I/O operations among the multiple servers includes:
in response to detecting the timeout event, prohibiting the server from performing further I/O operations.

7. The method of claim 1 , further comprising:
detecting a second interruption in receiving the second set of heartbeat signals from the identifying device while detecting the interruption in receiving the set of heartbeat signals from the server; and

wherein performing the remedial activity to coordinate the I/O operations among the multiple servers includes:
in response to detecting the second interruption in receiving the second set of heartbeat signals from the identifying device while detecting the interruption in receiving the set of heartbeat signals from the server, prohibiting the server from performing further I/O operations.

8. The method of claim 7 wherein another identifying device is coupled with another power transmission circuit constructed and arranged to deliver power to the server cluster, the other identifying device being constructed and arranged to provide a third set of heartbeat signals through the other power transmission circuit, the third set of heartbeat signals including a third identifier of the other identifying device, the third identifier being different from both the first identifier and the second identifier;
wherein the method further comprises:
after prohibiting the server from performing the further I/O operations, receiving the set of heartbeat signals from the server through the other power transmission circuit while receiving the third set of heartbeat signals from the other identifying device through the other power transmission circuit; and

wherein performing the remedial activity further includes:
after receiving the set of heartbeat signals from the server through the other power transmission circuit while receiving the third set of heartbeat signals from the other identifying device through the other power transmission circuit, allowing the server to perform the further I/O operations.

9. The method of claim 1 wherein the server cluster includes a power supply unit (PSU) and a signal adapter coupled with the PSU, the signal adapter being constructed and arranged to acquire the set of heartbeat signals from a power signal provided to the PSU; and
wherein receiving the set of heartbeat signals through the power transmission circuit includes:
receiving the power signal through the power transmission circuit, the power signal including the set of heartbeat signals and providing power to the PSU; and
acquiring the set of heartbeat signals from the power signal.

10. The method of claim 1 wherein the server includes (i) a management controller constructed and arranged to coordinate the I/O operations among the multiple servers in the server cluster and (ii) a processor constructed and arranged to perform the I/O operations;
wherein the set of heartbeat signals includes (i) a first set of signals of the management controller and (ii) a second set of signals of the processor; and
wherein the method further comprises:
after receiving the set of heartbeat signals through the power transmission circuit, identifying the first set of signals and the second set of signals included in the set of heartbeat signals.

11. The method of claim 1 , wherein the identifying device includes a power inlet and a power outlet, the power inlet being coupled with the power transmission circuit, the power outlet providing pass-through power from the power inlet; and
wherein the method further comprises:
receiving the pass-through power via the power outlet of the identifying device along with the second set of heartbeat signals.

12. The method of claim 1 , further comprising:
while the interruption in receiving the set of heartbeat signals is ongoing, continuing to receive the second set of heartbeat signals from the identifying device; and
identifying a first type of failure from a plurality of types of failures based on continuing to receive the second set of heartbeat signals while the interruption is ongoing.

13. A server cluster, comprising:
multiple servers;
memory; and
control circuitry coupled to the memory, the memory storing instructions which, when carried out by the control circuitry, cause the control circuitry to perform a method of:
receiving, from a server in the server cluster, a set of heartbeat signals through a power transmission circuit constructed and arranged to del

Assignees

• Dell Products Lp

Inventors

• Krivenok Dmitry Vladimirovich
• Alkalay Amitai
• Hadav Aric

Classifications

• G06F11/2007

  using redundant communication media · CPC title

• G06F11/2005

  using redundant communication controllers · CPC title

• G06F11/0727

  in a storage system, e.g. in a DASD or network based storage system (drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097) · CPC title

• G06F11/2092

  Techniques of failing over between control units · CPC title

• G06F1/266 Primary

  Arrangements to supply power to external peripherals either directly from the computer or under computer control, e.g. supply of power through the communication port, computer controlled power-strips · CPC title