Message scheduling method and device

Abstract

The embodiment of the invention discloses a message scheduling method and device. The method comprises the steps of monitoring an enqueue state of a queue; when it is determined that the enqueue state represents that a message is enqueued, updating a message tail pointer of the queue, wherein the message tail pointer is used for pointing to the last cell of the last complete message in the queue; calculating a difference value between a scheduling head pointer and a dequeue head pointer of the queue and obtaining a scheduling difference value, wherein the scheduling head pointer is used for pointing to the cell currently requested to be scheduled, and the dequeue head pointer is used for pointing to the cell which is scheduled at the last; and when it is determined that the scheduling difference value is smaller than a preset threshold value and the scheduling head point is smaller than the message tail pointer, scheduling messages in the queue. The continuity of the messages is ensured, and the number of the cells which initiate scheduling requests and are not actually dequeued can be precisely controlled, so the consumption of cache resources can be reduced.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a message scheduling method and device. Background technique [0002] In a computer network, terminals usually buffer messages through queues. The so-called queue in computer science is a first-in-first-out linear table, which only allows deletion operations at the front end of the table to leave the queue, and insertion operations at the back end of the table to enter the queue. [0003] Among them, the end that performs the delete operation is called the head of the team, and the end that performs the insertion operation is called the tail of the team. Each queue forms a linked list, and dynamically manages and caches messages through the linked list, so that the messages in the queue can be scheduled. [0004] refer to Figure 1a As shown in the schematic diagram of the queue, the queue contains several messages, and each message contains several cells (Cells...

AI Technical Summary

Problems solved by technology

[0007] However, in this way, on the one hand, since the tail pointer only points to the latest Cell that has entered the queue, it is not possible to determine whether the last Cell of a message has entered the queue through the tail pointer, and there is a problem of scheduling incomplete messages.

On the other hand, due to a certain delay in the complete scheduling process, there may be multiple Cells that have initiated scheduling requests but have not yet completed the actual dequeue, which will consume a lot of cache resources

Images