Reducing Fragmentation via Exploiting Backup History and Cache Knowledge Granting Security

Abstract

Duplicate chunks are eliminated between multiple backups, the chunks of a backup unfortunately become physically scattered in different containers, which is known as fragmentation in backup systems. We observe that the fragmentation comes in two categories of containers: sparse containers and out-of-order containers, which have different negative impacts and require dedicated solutions. During a restore, a majority of chunks in a sparse container are never accessed, and the chunks in an out-of-order container are accessed intermittently. Both of them hurt the restore performance. Increasing the restore cache size alleviates the negative impacts of out-of-order containers, but it is ineffective for sparse containers because they directly amplify read operations. Additionally, the merging operation is required to reclaim sparse containers in the garbage collection after users delete backups. In order to reduce the fragmentation, we propose History-Aware Rewriting algorithm (HAR) and Cache-Aware Filter (CAF). HAR exploits historical information in backup systems to accurately identify and reduce sparse containers, and CAF exploits restore cache knowledge to identify the out-of-order containers that hurt restore performance. To reduce the metadata overhead of the garbage collection, we further propose a Container-Marker Algorithm (CMA) to identify valid containers instead of valid chunks. Although data deduplication brings a lot of benefits, security and privacy concerns arise as users’ sensitive data are susceptible to both insider and outsider attacks.