Cache service control method and device, storage medium and electronic device

By measuring the task time and throughput of CDN servers and dynamically adjusting the concurrency, the performance issues of CDN caching services under high load were resolved, resulting in improved stability and responsiveness, and optimized resource utilization and system flexibility.

CN122268758APending Publication Date: 2026-06-23TENCENT TECH (BEIJING) CO LTD
View PDF -1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
TENCENT TECH (BEIJING) CO LTD
Filing Date
2024-12-20
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

CDN caching services are unable to respond to request pressure in a timely manner under high load, resulting in performance degradation or service interruption, affecting user experience and system stability. Furthermore, existing control methods are inefficient and increase the burden of operation and maintenance.

Method used

By acquiring the task time, successful request throughput, and coroutine scheduling time of the CDN associated server, the maximum concurrency is dynamically adjusted. Combined with the difference between the preset coroutine scheduling time and the actual time, the concurrency of the target server is adaptively set to optimize system performance and resource utilization.

Benefits of technology

In a high-concurrency environment, ensure the stability and availability of caching services, reduce request waiting time, improve system stability and flexibility, optimize resource utilization, and reduce dependence on origin services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122268758A_ABST
    Figure CN122268758A_ABST
Patent Text Reader

Abstract

This application discloses a control method, apparatus, storage medium, and electronic device for a caching service. The method includes: acquiring the task time, successful request throughput, and coroutine scheduling time generated by a target server associated with a content delivery network executing the caching service; determining a time difference based on a preset coroutine scheduling time and the actual coroutine scheduling time; adaptively determining a maximum concurrency based on the time difference, the preset coroutine scheduling time, the actual coroutine scheduling time, the task time, and the successful request throughput; and setting the target server according to the maximum concurrency, where the maximum concurrency represents the maximum number of task requests allowed to be processed simultaneously on the target server. The time difference is used to indicate the degree of influence of the preset coroutine scheduling time and the actual coroutine scheduling time on the value of the maximum concurrency. This application solves the technical problem of low control efficiency of caching services in related technologies. This application can be applied, but is not limited to, scenarios such as file distribution and server performance testing.
Need to check novelty before this filing date? Find Prior Art