Mobile distributed computing system and method for storing node fault-tolerant information

Abstract

The invention discloses a mobile distributed computing system and a method for storing node fault-tolerant information. The method comprises steps as follows: (1), a fault-tolerant information management module of a base station records mobility information of a mobile host in a service domain; (2), unrepeated serial numbers of nodes of the mobile host are maintained, and reference time is set; (3), fault-tolerant information of the nodes of the mobile host is synergized, collected and maintained by the base station through the fault-tolerant information management module; (4), the fault-tolerant information management module of the base station stores the collected fault-tolerant information of the nodes in a network sharing and storage device through a high-speed wired network, so that the fault-tolerant information of the nodes of the mobile host are stored and shared. The mobile distributed computing system and method can reduce wireless signal interference produced when the nodes of the mobile host transmit calculation process check points to the local base station, effectively supports a check point rollback recovery mechanism in the mobile distributed computing system and better meets the requirement of the mobile distributed computing system for reliability in various fields.

Description

technical field [0001] The invention belongs to the field of distributed computing fault tolerance, in particular to a mobile distributed computing system and a method for storing node fault tolerance information. Background technique [0002] The mobile distributed computing system has the characteristics of mobility, rapid construction, autonomy, topology changeability and peer-to-peer, and has a wide range of application prospects. Compared with the traditional fixed network distributed computing, the communication bandwidth of the mobile distributed computing system is narrow, the storage capacity of the mobile host node is limited and easy to be lost, the battery power supply capacity is limited, and the mobility of the mobile host node makes it grow with the scale of the system. The growth of the system greatly increases the probability of errors. The error of a single node can lead to the collapse of the entire system and the loss of all previous calculations. The fa...

AI Technical Summary

Problems solved by technology

The method that the process checkpoints are created and transmitted at the same time will cause serious signal interference to each other when each mobile host node transmits the process checkpoints to its base station, which reduces the transmission throughput of the wireless communication of the mobile distributed computing system, and even May affect the normal communication between computing processes of mobile host nodes

Images