Data processing method, device and equipment and storage medium

Abstract

The method is suitable for the technical field of computers, and provides a data processing method comprising: in response to a plurality of user instructions sent by a plurality of terminal devices,putting the user instructions into a first data queue of a scheduling thread corresponding to a user instruction category, and then putting the user instructions in the first data queue into a seconddata queue of a co-thread corresponding to a user in the scheduling thread; and enabling the scheduling thread to traverse the to-be-scheduled co-thread, if the currently traversed to-be-scheduled co-thread satisfies a call-in condition, a call-in operation is performed on the co-thread, and if the called-in co-thread satisfies a call-out condition, a call-out operation is performed on the co-thread. Through said steps, processor resources can be fully utilized to achieve data processing efficiency close to parallel processing.

Description

technical field [0001] The present application belongs to the field of computer technology, and in particular relates to a data processing method, device, equipment and storage medium. Background technique [0002] In many financial systems, the remote synchronous call mode is very common, that is, the call programming of the request and the response is almost unavoidable, and a long waiting time is often required in the process of waiting for the response. For example, in the development practice of the futures financial trading terminal, the original mature remote call scenario, for example, the online transaction scenario, is a typical situation of synchronous call with a large delay in request response. In this scenario, each user has an exclusive transaction connection and call channel, and the remote round-trip interaction of an ordinary command is at the millisecond level. Under the demands of programmatic transactions, the transaction party needs to simultaneously d...

AI Technical Summary

Problems solved by technology

Considering the real-time requirements of the algorithm, multiple user commands are required to send and interact concurrently. Therefore, the mode of serially sending user commands through a single thread cannot meet the efficiency requirements of the algorithm.

For many software solutions in financial applications, considering the security, stability, novelty and reliability of the system, it is difficult and costly to realize multi-threaded concurrent data processing by reconstructing the communication layer or deeply reconstructing the software parallel processing architecture. Therefore, there is a need for a low-cost solution to parallel processing of multiple user instructions based on the existing system architecture

Images