Supercharge Your Innovation With Domain-Expert AI Agents!

Scheduling method and device for load balancing and computing equipment

A scheduling method and load balancing technology, which is applied in the direction of multi-program device, program startup/switching, resource allocation, etc., can solve the problems of poor parallel computing performance, slow balancing speed, long load balancing interval, etc., to reduce time overhead , the effect of improving performance

Pending Publication Date: 2022-04-01
UNIONTECH SOFTWARE TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, scenarios such as big data and AI (Artificial Intelligence, artificial intelligence) generally have multi-threaded parallel computing. Therefore, on a NUMA (Non Uniform Memory Access, non-uniform memory access) architecture server, there will be more than ten CPUs on one CPU. In the scenario where the process is running, when relying on the system's load balancing mechanism to migrate the process to other CPUs, each load balancing can only be performed between two CPUs, and when scheduling across NODEs (nodes), the load balancing interval Long time, poor performance
Therefore, the current load balancing scheme has a slow balancing speed, resulting in poor parallel computing performance in a short period of time.

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
  • Scheduling method and device for load balancing and computing equipment
  • Scheduling method and device for load balancing and computing equipment
  • Scheduling method and device for load balancing and computing equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0027] figure 1 It is a schematic diagram of the framework of the NUMA architecture of the embodiment of the present invention; the NUMA architecture includes 16 NODEs, respectively NODE 0-15, and each NODE includes 8 CPUs, respectively CPU 0-7, assuming that the processes P0-P15 run on On CPU0 of NODE 0, other CPUs on NODE 0 are idle, and all CPUs on NODE 15 are idle. The goal of the load balancing mechanism is to balance the pro...

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

The invention discloses a scheduling method and device for load balancing and computing equipment. The method comprises the following steps: determining an emigration process CPU and one or more migration target CPUs at least based on the CPU load size in CPUs of all nodes of the multi-core system; traversing all processes on the emigration process CPU, and determining a to-be-migrated process at least according to the CPU affinity of each process; determining a corresponding relation between the to-be-migrated process and the migration target CPU according to the CPU affinity of the to-be-migrated process; and migrating the process to be migrated to the corresponding migration target CPU according to the corresponding relationship. The invention also discloses a corresponding device and computing equipment.

Description

technical field [0001] The invention relates to the technical field of data scheduling, in particular to a scheduling method, device and computing equipment for load balancing. Background technique [0002] At present, scenarios such as big data and AI (Artificial Intelligence, artificial intelligence) generally have multi-threaded parallel computing. Therefore, on a NUMA (Non Uniform Memory Access, non-uniform memory access) architecture server, there will be more than ten CPUs on one CPU. In the scenario where the process is running, when relying on the system's load balancing mechanism to migrate the process to other CPUs, each load balancing can only be performed between two CPUs, and when scheduling across NODEs (nodes), the load balancing interval Long time, poor performance. Therefore, the current load balancing scheme has a slow balancing speed, resulting in poor performance of short-term parallel computing. [0003] Therefore, for a complex system with multiple la...

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
IPC IPC(8): G06F9/48G06F9/50
Inventor 周鹏叶中玉胡翔余昇锦
Owner UNIONTECH SOFTWARE 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com