A deduplication of HDFS distributed backup system
Wang Jian-hu · Electronic Design Engineering · 2014
With the speed of electronic of traditional industry gradually accelerating, the amount of data on the computer is growing, challenges in the field of data backup are also growing. Because traditional backup requires a lot of disk arrays as the storage medium, so the cost control has been a problem.For this situation, combined with the low cost of cloud storage platform, scalable and efficient resource utilization, research in HDFS system by adding new data de-duplication technology, and optimize the existing backup strategy, design a cloud-based storage the deduplication backup system. Finally, through the improved scheme system and the traditional backup program backup file with useing less space and time parameters were compared.