Search for: All records

Effectively exploiting emerging far-memory technology requires consideration of operating on richly connected data outside the context of the parent process. Operating-system technology in development offers help by exposing abstractions such as memory objects and globally invariant pointers that can be traversed by devices and newly instantiated compute. Such ideas will allow applications running on future heterogeneous distributed systems with disaggregated memory nodes to exploit near-memory processing for higher performance and to independently scale their memory and compute resources for lower cost.

 

Large-scale distributed storage systems, such as object stores, usually apply hashing-based placement and lookup methods to achieve scalability and resource efficiency. However, when object locations are determined by hash values, placement becomes inflexible, failing to optimize or satisfy application requirements such as load balance, failure tolerance, parallelism, and network/system performance. This work presents a novel solution to achieve the best of two worlds: flexibility while maintaining cost-effectiveness and scalability. The proposed method Smash is an object placement and lookup method that achieves full placement flexibility, balanced load, low resource cost, and short latency. Smash utilizes a recent space-efficient data structure and applies it to object-location lookups. We implement Smash as a prototype system and evaluate it in a public cloud. The analysis and experimental results show that Smash achieves full placement flexibility, fast storage operations, fast recovery from node dynamics, and lower DRAM cost (<60%) compared to existing hash-based solutions such as Ceph and MapX. 

Modern data privacy regulations such as GDPR, CCPA, and CDPA stipulate that data pertaining to a user must be deleted without undue delay upon the user’s request. Existing systems are not designed to comply with these regulations and can leave traces of deleted data for indeterminate periods of time, often as long as months. We developed Lethe to address these problems by providing fine-grained secure deletion on any system and any storage medium, provided that Lethe has access to a fixed, small amount of securely-deletable storage. Lethe achieves this using keyed hash forests (KHFs), extensions of keyed hash trees (KHTs), structured to serve as efficient representations of encryption key hierarchies. By using a KHF as a regulator for data access, Lethe provides its secure deletion not by removing the KHF, but by adding a new KHF that only grants access to still-valid data. Access to the previous KHF is lost, and the data it regulated securely deleted, through the secure deletion of the single key that protected the previous KHF. 

Keeping data safe in the presence of crashes is a fundamental problem.