An offline optimal cache replacement device and method for data recovery of a deduplicated system

Abstract

The invention discloses an offline optimal cache replacement device and method for data recovery of a deduplication system. Because logically contiguous data is physically scattered across different disk locations, the performance of system recovery is seriously affected by the debris generated by traditional de-duplication methods. At present, some optimization methods attempt to improve that recovery performance by utilizing the optimize cache replacement strategy, however, when the data locality is not strong, the cache hit rate of these methods is low or the extra computational overhead consumed when calculating the optimal replacement order on line is large, which leads to the problem that the fragmentation can not be effectively resisted on the recovery performance. To solve the above problem, the invention calculates the optimal cache replacement strategy from the offline perspective; moreover, without sacrifice of the system deduplication rate and additional computational overhead, the optimal replacement order can be obtained to effectively improve the recovery performance and throughput. The offline optimal cache replacement strategy can effectively optimize the requiredfile recovery time and meet the requirements of modern data storage.

Description

technical field [0001] The present invention relates to the technical field of data recovery of a deduplication system, in particular to an off-line optimal cache replacement device and method for data recovery of a deduplication backup system. Background technique [0002] With the advent of the era of big data, the rapid growth of data volume has brought great challenges to the limited storage space of data centers. Data deduplication technology greatly reduces the disk overhead required for data storage and the bandwidth required for network transmission, and has gradually become a key data reduction technology for today's backup systems. The purpose of deduplication backup system is to store data for timely recovery in the future. If an enterprise fails to recover data in time when a disaster occurs such as disk failure or database-related file corruption, the losses suffered will be immeasurable, and data backup will also become incalculable. It doesn't make much sense...

AI Technical Summary

Problems solved by technology

Since the logically continuous data is physically dispersed in different disk locations, the fragmentation generated by the traditional deduplication method seriously affects the recovery performance of the system

Some existing optimization methods try to use the optimized cache replacement strategy to improve recovery performance during recovery. However, these methods either have a low hit rate or high additional computing overhead, and cannot effectively resist the impact of fragmentation on recovery performance.

Images