Memory-driven out-of-band management

• US 10,387,059 B2
• Filed: 01/30/2015
• Issued: 08/20/2019
• Est. Priority Date: 01/30/2015
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Wang, Zhikui, Brown, Andy, Lyle, Stephen B., Milojicic, Dejan S., Venkatraman, Chandrasekar
• Primary Examiner(s): Gu, Shawn X
• Application Number:
  US15/329,936
• Publication Number:
  US 20170262209A1
• Time in Patent Office: 1,663 Days
• CPC Class Codes: G06F 12/084 with a shared cache
• CPC Class Codes: G06F 12/1072 Decentralised address translation, e.g. in distributed shared memory systems
• CPC Class Codes: G06F 13/1663 Access to shared memory
• CPC Class Codes: G06F 15/167 using a common memory, e.g. mailbox
• CPC Class Codes: G06F 3/0604 Improving or facilitating administration, e.g. storage management
• CPC Class Codes: G06F 3/0629 Configuration or reconfiguration of storage systems
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays

Abstract

According to an example, memory-driven OOB management may include OOB management of a computing node of a plurality of computing nodes. The OOB management may be executed independent of an OS of the computing node. A memory fabric may be used to provide for shared access to a plurality of NVM nodes by the plurality of computing nodes.

Claims

1. A method for memory-driven out-of-band (OOB) management, the method comprising:

implementing, by a processor, an OOB management on a first computing node of a plurality of computing nodes, wherein the processor used to implement the OOB management on the first computing node is independent from resources used to run an operating system (OS) of the first computing node;

assigning, by the processor, a memory address to the OOB management on the first computing node to enable the OOB management on the first computing node to operate as a destination of memory read or write operations by other computing nodes of the plurality of computing nodes via a memory fabric, wherein the memory fabric is a fabric via which the plurality of computing nodes is connected to a plurality of non-volatile memory (NVM) nodes for storing and retrieving data;

collecting, by the processor of the first computing node, data related to the OOB management from a sensor device on the first computing node; and

forwarding, by the processor of the first computing node, the collected data from the first computing node to a system manager, which is separate and independent from the NVM nodes, via the memory fabric using the memory address assigned to the OOB management.

2. The method of claim 1, wherein implementing the OOB management on the first computing node of the plurality of computing nodes further comprises:

conducting an inventory of hardware components and an inventory of machine readable instructions components of the plurality of computing nodes.

3. The method of claim 1, wherein implementing the OOB management on the first computing node of the plurality of computing nodes further comprises:

determining logging information from the plurality of computing nodes.

4. The method of claim 1, wherein implementing the OOB management on the first computing node of the plurality of computing nodes further comprises:

determining configuration information of the plurality of computing nodes.

5. The method of claim 1, wherein implementing the OOB management on the first computing node of the plurality of computing nodes further comprises:

monitoring environment information related to each of the plurality of computing nodes.

6. The method of claim 1, further comprising:

receiving, via the memory fabric, instructions to implement a predetermined function related to the OOB management implemented on the first computing node from the system manager.

7. The method of claim 1, further comprising:

forwarding, via the memory fabric, data related to the OOB management from the first computing node to the system manager.

8. The method of claim 1, further comprising:

assigning, by the processor, memory blocks of the NVM nodes to each of the plurality of computing nodes, wherein the assigned memory blocks of the NVM nodes are accessible only via the memory fabric; and

accessing the memory fabric to store the collected data related to the OOB management in the assigned memory blocks of the plurality of NVM nodes.

9. The method of claim 8, further comprising:

utilizing a dedicated memory controller to access the memory fabric to retrieve data stored in the assigned memory blocks of the plurality of NVM nodes.

10. The method of claim 1, wherein collecting data related to the OOB management from the sensor device comprises:

collecting temperature measurements detected by temperature sensors located at the first computing node.

11. A memory-driven out-of-band (OOB) management apparatus comprising:

a processor; and

a memory storing machine readable instructions that when executed by the processor cause the processor to;

implement an OOB management on a first computing node of a plurality of computing nodes, wherein the processor used to implement the OOB management on the first computing node is independent from resources used to operate an operating system (OS) of the first computing node;

assign a memory address to the OOB management on the first computing node to enable the OOB management on the first computing node to operate as a destination of a memory fabric, wherein the memory fabric is a fabric via which the plurality of computing nodes is connected to a plurality of non-volatile memory (NVM) nodes for storing and retrieving data;

collect, at the first computing node, data related to the OOB management from a sensor device on the first computing node; and

forward the collected data from the first computing node to a system manager, which is separate and independent from the NVM nodes, via the memory fabric using the memory address assigned to the OOB management.

12. The memory-driven OOB management apparatus according to claim 11, further comprising machine readable instructions to:

implement the OOB management on the first computing node of the plurality of computing nodes by performing OOB management functions related to the plurality of computing nodes at the first computing node.

13. The memory-driven OOB management apparatus according to claim 11, wherein the machine readable instructions are executable to cause the processor to:

assign memory blocks of the plurality of NVM nodes to each of the plurality of computing nodes upon receipt of a request from the computing node.

14. The memory-driven OOB management apparatus according to claim 11, wherein the machine readable instructions to collect data related to the OOB management from the sensor device comprise machine readable instructions to:

collect temperature measurements detected by temperature sensors located at the first computing node.

15. A non-transitory computer readable medium having stored thereon machine readable instructions to provide memory-driven out-of-band (OOB) management, the machine readable instructions, when executed, cause a processor to:

receive, from a system manager, configuration information related to OOB management of a first computing node of a plurality of computing nodes, wherein the OOB management of the first computing node is executed independently of an operating system (OS) of the first computing node;

implement the OOB management on the first computing node based on the configuration information;

assign a memory address to the OOB management on the first computing node to enable the OOB management on the first computing node to operate as a destination of a memory fabric, wherein the memory fabric is a fabric via which the plurality of computing nodes is connected to a plurality of non-volatile memory (NVM) nodes for storing and retrieving data;

collect, at the first computing node, data related to the OOB management from a sensor device on the first computing node; and

forward the collected data from the first computing node to the system manager, which is separate and independent from the NVM nodes, via the memory fabric using the memory address assigned to the OOB management.

16. The non-transitory computer readable medium according to claim 15, further comprising machine readable instructions to:

assign memory blocks of the NVM nodes to each of the plurality of computing nodes, wherein the assigned memory blocks of the NVM nodes are accessible only via the memory fabric; and

bypass a central processing unit (CPU) of the first computing node to access the assigned memory blocks of the plurality of NVM nodes.

17. The non-transitory computer readable medium according to claim 15, wherein the machine readable instructions to collect data related to the OOB management from the sensor device comprise machine readable instructions to:

collect temperature measurements detected by temperature sensors located at the first computing node.