Task stealing method and system based on task stealing algorithm

Abstract

The invention provides a task stealing method and system based on a task stealing algorithm, and the method comprises the steps: 1, enabling all threads in the system to be arranged from small to large according to numbers to form a queue, and enabling the queue to be connected end to end to form a ring; 2, judging the state of the next thread according to the current thread; if the thread is in the overload state, stealing the calculation task from the task queue of the overload thread, and if the thread is in the normal state, executing the step A; 3, locally executing the calculation task stolen in the step 2, then executing the step 2, and continuing to check the state of the next thread of the overload thread; step A, judging whether a queued computing task exists in a local queue ornot, and if the queue is not empty, executing the computing task in a current thread queue; and if the queue is empty, completing the Ring Steering process once. According to the method and the device, the thread in a normal state can share the load pressure of a plurality of overload threads, and the request delay is reduced.

Description

technical field [0001] The present invention relates to the field of multi-thread load balancing, in particular to a task-stealing method and system based on a task-stealing algorithm, and in particular to a task-stealing algorithm based on Work Stealing for low-latency and high-concurrency multi-threaded systems. Background technique [0002] Since the performance improvement of a single CPU core has a serious bottleneck problem, more and more systems have begun to use multiple threads to perform parallel computing to improve the concurrent processing capabilities of the system. This type of high-concurrency request processing system usually receives new requests continuously, and the requests are stored in the task queue. Each request is actually a computing task, and the computing tasks are independent of each other. The system is generally composed of multiple threads, each thread is equipped with a task queue, each thread takes requests from its own task queue, and the...

AI Technical Summary

Problems solved by technology

Therefore, the traditional Work Stealing mechanism is hardly triggered, and cannot solve the problem of high latency caused by some requests being blocked by complex computing tasks in a high-concurrency request processing system

[0008] The traditional Work Stealing technology only steals computing tasks when the task queue is empty, and it is rare for a thread task queue to be empty in a high-concurrency request processing system. Therefore, the traditional Work Stealing algorithm (task stealing algorithm) The load balancing effect is poor in a high-concurrency system

Images