Space single event upset autonomous fault tolerance method

Abstract

The invention discloses a space single event upset autonomous fault tolerance method, and relates to the technical field of computers. The method includes: according to the size of data, creating three redundant memory pools for the data, respectively distributing the three redundant memory pools to three partitions of the system; setting one redundant memory pool in the three redundant memory pools as a main data block, and setting the other two redundant memory pools as auxiliary data blocks; obtaining a first auxiliary data block and a second auxiliary data block, and recording the storageaddresses of the data in the three partitions in a variable-address mapping table, writing the data into the data areas of the three partitions in sequence; according to the variable-address mapping table, acquiring data in the main data block; juding whether the EDAC circuit is triggered to check the memory error operation or not; if yes, using the two-out-of-three strategy to process the data inthe three partitions. The address distribution between redundant memory pools and the isolation between the data are guaranteed, the EDAC memory exception capture mechanism is combined and used, thefault-tolerant efficiency is improved, and the fault-tolerant cost is reduced.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an autonomous fault-tolerant method for spatial single-event flipping. Background technique [0002] In the computer system used in the aerospace field, device failure caused by the harsh space environment is one of the root causes of the reliability decline or failure of the computer system. [0003] Radiation in space is formed by particles such as electrons, neutrons, and protons emitted by various radiation sources inside and outside the solar system. These particles usually have very high energy, and the radiation effect produced can not only cause the degradation of electronic devices, but also cause the failure of the system. [0004] There are two main types of radiation produced by various radiation sources inside and outside the solar system: solar radiation and galactic cosmic rays. The radiation received by electronic equipment in space mainly comes from the Earth...

AI Technical Summary

Problems solved by technology

[0013] (1) Low execution efficiency

[0014] Using data redundancy codes such as Hamming codes and cyclic codes to encode and decode key data, and memory redundancy allocation methods for fault tolerance, all have problems of low execution efficiency;

[0015] (2) Insufficient data isolation

[0016] Using redundant memory allocation method for data fault tolerance, there are problems of insufficient isolation between data, including the inability to guarantee the distribution of physical addresses between redundant memory pools, data competition when multiple tasks perform redundant memory allocation at the same time, etc. ;

[0017] (3) High cost of fault tolerance

[0018] EDAC memory error detection and system-level fault tolerance both require increased hardware costs and increased fault tolerance costs

Images