Job target aliasing in disaggregated computing systems

Patent metadata

Field	Value
Publication number	US-12175292-B2
Application number	US-202117191112-A
Country	US
Kind code	B2
Filing date	Mar 3, 2021
Priority date	Mar 3, 2021
Publication date	Dec 24, 2024
Grant date	Dec 24, 2024

Abstract

Deployment of arrangements of physical computing components coupled over a communication fabric are presented herein. In one example, a method includes presenting, to a workload manager, a target machine capable of receiving execution jobs from the workload manager. The target machine has a network state and comprises a selection of computing components. The method also includes receiving a job issued by the workload manager that is directed to the target machine. Based on properties of the job, the method includes determining resource requirements for handling the job, forming a composed machine comprising physical computing components that support the resource requirements of the job, transferring the network state of the target machine to the composed machine and indicating the network state of the composed machine to the workload manager, and initiating execution of the job on the composed machine.

First claim

What is claimed is:

1. A method comprising:
presenting, to a workload manager, a fictitious set of resources capable of handling execution jobs, the fictitious set of resources comprising a selection of computing components presented as being available to service the execution jobs without regard for a present availability to service the execution jobs;
receiving a job issued by the workload manager and directed to the fictitious set of resources;
based on properties of the job, determining resource requirements for handling the job, and forming a composed machine comprising physical computing components that support the resource requirements of the job;
indicating a network state of the composed machine to the workload manager;
initiating execution of the job on the composed machine; and
responsive to completion of the job, de-composing the composed machine and transferring the network state of the composed machine to be associated with the fictitious set of resources.

2. The method of claim 1 , wherein the fictitious set of resources comprises a placeholder aliased target not corresponding to physically present computing components.

3. The method of claim 1 , wherein responsive to status inquiries about the fictitious set of resources, transferring status responses indicating that the selection of computing components are available for execution of the job regardless of the present availability or physical presence of the selection of computing components.

4. The method of claim 1 , comprising:
responsive to forming the composed machine, transferring a network state associated with the fictitious set of resources to the composed machine to establish the network state of the composed machine; and
wherein the network state comprises a network socket.

5. The method of claim 4 , further comprising:
transferring the network state by at least altering a Media Access Control (MAC) address relationship for an IP address initially corresponding to the fictitious set of resources to instead correspond to a MAC address of the composed machine.

6. The method of claim 1 , wherein the selection of computing components comprises an overprovisioned quantity of computing components having a greater quantity of computing components than are physically present for servicing the execution jobs.

7. The method of claim 1 , further comprising:
selecting the physical computing components from among a pool of physical computing components individually and arbitrarily arrangeable into sets forming composed machines; and
instructing at least a communication fabric that couples the pool of physical computing components to form logical partitioning in the communication fabric to establish the composed machine, wherein the logical partitioning isolates the physical computing components of the composed machine from other physical computing components of the pool of physical computing components.

8. The method of claim 7 , wherein the pool of physical computing components comprises one or more among central processing units (CPUs), co-processing units, graphics processing units (GPUs), tensor processing units (TPUs), field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), storage drives, and network interface controllers (NICs) coupled to at least the communication fabric.

9. An apparatus, comprising:
one or more computer readable storage media; and
program instructions stored on the one or more computer readable storage media that, based on being executed by a processing system, direct the processing system to at least:
present, to a workload manager, a fictitious set of resources capable of handling execution jobs, the fictitious set of resources comprising a selection of computing components presented as being available to service the execution jobs without regard for a present availability to service the execution jobs;
receive a job issued by the workload manager and directed to the fictitious set of resources;
based on properties of the job, determine resource requirements for handling the job, and form a composed machine comprising physical computing components that support the resource requirements of the job;
indicate a network state of the composed machine to the workload manager;
initiate execution of the job on the composed machine; and
responsive to completion of the job, de-compose the composed machine and transfer the network state of the composed machine to be associated with the fictitious set of resources.

10. The apparatus of claim 9 , wherein the fictitious set of resources comprises a placeholder aliased target not corresponding to physically present computing components.

11. The apparatus of claim 9 , comprising program instructions, based on being executed by the processing system, direct the processing system to at least:
responsive to status inquiries about the fictitious set of resources, transfer status responses indicating that the selection of computing components are available for execution of the job regardless of the present availability or physical presence of the selection of computing components.

12. The apparatus of claim 9 , comprising:
responsive to forming the composed machine, transfer a network state associated with the fictitious set of resources to the composed machine to establish the network state of the composed machine; and
wherein the network state comprises a network socket.

13. The apparatus of claim 12 , comprising program instructions, based on being executed by the processing system, direct the processing system to at least:
transfer the network state by at least altering a Media Access Control (MAC) address relationship for an IP address initially corresponding to the fictitious set of resources to instead correspond to a MAC address of the composed machine.

14. The apparatus of claim 9 , wherein the selection of computing components comprises an overprovisioned quantity of computing components having a greater quantity of computing components than are physically present for servicing the execution jobs.

15. The apparatus of claim 9 , comprising program instructions, based on being executed by the processing system, direct the processing system to at least:
select the physical computing components from among a pool of physical computing components individually and arbitrarily arrangeable into sets forming composed machines; and
instruct at least a communication fabric that couples the pool of physical computing components to form logical partitioning in the communication fabric to establish the composed machine, wherein the logical partitioning isolates the physical computing components of the composed machine from other physical computing components of the pool of physical computing components.

16. The apparatus of claim 15 , wherein the pool of physical computing components comprises one or more among central processing units (CPUs), co-processing units, graphics processing units (GPUs), tensor processing units (TPUs), field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), storage drives, and network interface controllers (NICs) coupled to at least the communication fabric.

17. A computing system, comprising:
a job interface configured to:
present computing targets as fictitious targets for job execution, the computing targets each having an associated set of advertised computing components and corresponding network addressing presented as being available to service the jobs without regard for a present availability to service the jobs;
receive a job f

Assignees

• Liqid Inc

Inventors

• Cannata James Scott
• Clark Phillip
• Mcmullen Marshall
• Schramm Bryan

Classifications

• H04L2101/622

  Layer-2 addresses, e.g. medium access control [MAC] addresses · CPC title

• H04L61/103 Primary

  across network layers, e.g. resolution of network layer into physical layer addresses or address resolution protocol [ARP] · CPC title

• G06F2209/503

  Resource availability · CPC title

• G06F9/5027 Primary

  the resource being a machine, e.g. CPUs, Servers, Terminals · CPC title

• G06F2209/5011

  Pool · CPC title