Supercharge Your Innovation With Domain-Expert AI Agents!

System and method for computing resource allocation in distributed computing

A distributed computing and distributed system technology, applied in the field of distributed computing systems, can solve problems such as low scheduling efficiency, time-consuming, and complex workload scheduling.

Active Publication Date: 2021-11-19
HUAWEI CLOUD COMPUTING TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Conflicts between schedulers' needs can be resolved, but result in inefficient scheduling, as a failing scheduler will have to spend extra time trying to find other computing devices or resource servers with available resources that can execute the workload
Inefficient scheduling can negatively impact performance metrics such as workload throughput, resource utilization, and workload runtime
[0006] As distributed computing systems scale and workloads increase, workload scheduling itself becomes a complex and time-consuming process
Efficiently scheduling workloads can be difficult, especially when the total workload approaches or exceeds the computing resources available from computing devices or resource servers
However, as the workload increases, the existing workload scheduling methods tend to reduce efficiency and performance, and resolving conflicts between schedulers will become a bottleneck in system performance

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for computing resource allocation in distributed computing
  • System and method for computing resource allocation in distributed computing
  • System and method for computing resource allocation in distributed computing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] figure 1 is a diagram illustrating an example distributed computing system 100 . In distributed computing system 100 , one or more computing devices 102 may connect directly or indirectly to one or more resource servers 103 to access or utilize one or more resources 150 provided by resource servers 103 .

[0045] Distributed computing system 100 includes hardware and software components. For example, as shown, distributed computing system 100 includes a combination of computing devices 102 , resource server 103 , and resource management system 109 , which are connected by network 107 . As shown, resource server 103 has one or more resources 150 that can be allocated to perform computations on workloads from one or more computing devices 102 . The resource server 103 provides memory (such as random access memory (Random Access Memory, RAM)), processing units such as processors or processor cores, graphics processing units (graphics processing unit, GPU), storage device...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

Disclosed herein are systems and methods for allocating computing resources to execute workloads in a distributed computing system utilizing a resource acquisition cycle and a workload scheduling cycle. One or more resource provisioning managers provide each transmission resource in the one or more schedulers. Each scheduler transmits resource requests and / or resource release requests in response to each resource provisioning manager. After resolving conflicts, each resource provisioning manager calculates the resources allocated to each scheduler and allocates said resources to each scheduler according to the resource allocation decision. The resource acquisition cycle is separate from the workload scheduling cycle.

Description

[0001] Related Applications Cross Application [0002] This application requires the filing of U.S. Patent Application No. 15 / 643,429, filed on July 6, 2017, entitled "Systems and Methods for Allocating Computing Resources in Distributed Computing (SYSTEMS AND METHODS FOR ALLOCATING COMPUTING RESOURCES IN DISTRIBUTEDCOMPUTING)" Priority is given to the earlier application, which is hereby incorporated by reference in its entirety. technical field [0003] The present invention relates to a distributed computing system, and in particular to a system and method for managing the computing resource allocation of a scheduler in the distributed computing system. Background technique [0004] In modern distributed computing systems such as cloud computing systems, many different computing tasks (hereinafter referred to as workloads) are aggregated by computing devices from multiple sources (such as tenants, projects, groups, and workstations). Likewise, computing resources from mu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F9/50H04W72/04
CPCG06F9/5016G06F9/5033G06F9/4881H04L47/83H04L47/827H04L67/10G06F9/5083
Inventor 胡振华柯晓棣卡勒德·齐亚·艾恩赵志罗志刚
Owner HUAWEI CLOUD COMPUTING TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More