Flow control method and system based on service grid, equipment and medium

Abstract

The embodiment of the invention provides a flow control method and system based on a service grid, equipment and a medium. In the embodiment of the invention, the architecture of the service grid is improved, and the processing work of the data surface in the service grid is sunk into a physical network card through a close cooperation mode of software and hardware, so that the processing work of the data surface in the service grid does not need to occupy computing resources on a host machine any more, and the host machine can focus on the micro-service; in addition, the physical network card has higher forwarding performance, so that the network throughput can be effectively improved, the network delay can be reduced, and the inter-service communication performance under the service grid can be ensured.

Description

technical field [0001] The present application relates to the field of cloud network technologies, and in particular to a flow control method, system, device and medium based on a service grid. Background technique [0002] Service mesh: is a dedicated infrastructure layer for handling communication between services. It is responsible for reliably passing requests through complex service topologies that encompass modern cloud-native applications. In practice, service meshes are often implemented through a set of lightweight network proxies that are deployed alongside the application code without being aware of the application itself. [0003] The purpose of the service grid is to realize the governance of service traffic. In the field of cloud native, it usually takes the form of Sidecar. A "Proxy Sidecar" is built into each deployed atomic unit Pod to take over all service traffic entering and leaving the Pod. This requires a lot of memory resources; moreover, it needs to...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the service grid is to realize the governance of service traffic. In the field of cloud native, it usually takes the form of Sidecar. A "Proxy Sidecar" is built into each deployed atomic unit Pod to take over all service traffic entering and leaving the Pod. This requires a lot of memory resources; moreover, it needs to enter and exit the kernel and user mode multiple times to complete flow control, and the processing performance is relatively poor, resulting in poor connection efficiency between services

Images