SNAP: efficient snapshots for back-in-time execution

Abstract

SNAP is a novel high-performance snapshot system for object storage systems. The goal is to provide a snapshot service that is efficient enough to permit "back-in-time" read-only activities to run against application-specified snapshots. Such activities are often impossible to run against rapidly evolving current state because of interference or because the required activity is determined in retrospect. A key innovation in SNAP is that it provides snapshots that are transactionally consistent, yet non-disruptive. Unlike earlier systems, we use novel in-memory data structures to ensure that frequent snapshots do not block applications from accessing the storage system, and do not cause unnecessary disk operations. SNAP takes a novel approach to dealing with snapshot meta-data using a new technique that supports both incremental meta-data creation and efficient meta-data reconstruction. We have implemented a SNAP prototype and analyzed its performance. Preliminary results show that providing snapshots for back-in-time activities has low impact on system performance even when snapshots are frequent.