Hardware monitoring and micro-packet protocol-based key data restoration method

Abstract

The invention discloses a hardware monitoring and micro-packet protocol-based key data restoration method in a triple modular redundancy fault-tolerant computer system. The method is characterized by comprising the following steps of: dividing to-be-restored key data into hardware data blocks with equal size and dividing each hardware data block into monitoring packets with the same size; meanwhile, setting a monitor on hardware aiming at each hardware data block, wherein the number of the monitoring packets which can be monitored by the monitor is equal to that of the monitoring packets obtained by dividing each hardware data block; forming a basis for retransmitting a data region of the hardware data block once the condition that the monitoring packet is updated or amended is discovered; and retransmitting data with packet as a unit so as to reduce retransmitted data quantity.

Description

technical field [0001] The invention relates to a key data recovery method in a triple-mode redundant fault-tolerant computer system, in particular to a key data recovery method in a triple-mode redundant fault-tolerant computer system based on hardware monitoring and a micropacket protocol. Background technique [0002] Triple-mode redundant (TMR) fault-tolerant computers are usually used in environments that require high reliability. If one of the machines fails seriously, the system will be downgraded to a dual-level operation mode, and the faulty machine will be restored during the dual-machine operation, and During the recovery process, the normal operation of the system is not interrupted, so that the system can be restored from the dual-computer operation mode to the three-mode operation state, thereby improving the reliability and continuity of the three-mode redundant fault-tolerant computer. . For a repairable TMR fault-tolerant system, recovery is an important pa...

AI Technical Summary

Problems solved by technology

However, the management of memory data and current state is realized by software, which mainly has three deficiencies: First, the key data is managed in queues according to the update frequency in the form of one-way linked list. If the memory data and machine running status are updated, then The user needs to notify the recovery program of the TMR fault-tolerant computer by calling the software program. In most cases, the user will notify the recovery program in a centralized manner. Otherwise, the recovery program needs to be notified in each program branch, and the execution efficiency is low. Secondly, the key data is monitored by a one-way linked list If the key data is updated, the modification flag of the corresponding linked list block data will be reset, and the user's modification cannot be limited to one block, and it is impossible for the entire block of data to be retransmitted and restored. , so the key data management implemented by software leads to insufficient application convenience and monitorability, and the monitoring granularity is large; again, the original recovery method can only use the idle time of periodic tasks, when the amount of data that can be transmitted in idle time is less than each There is a problem when the production volume is changed during the cycle, and seamless recovery cannot be performed

Images