Utah Scalable Computer Systems Lab



Sandstorm - NSF CAREER CSR-1750558

Businesses are moving data and applications into the cloud, meaning that many applications and data are consolidated efficiently in one place on fewer servers. Cloud storage services must keep the data of thousands of customers separated while also allowing customers to operate on it efficiently. Safely intermixing customer-provided operations over data is problematic. Historically, processor hardware isolates programs, but increasing data access rates make that costly. The goal of this project is to sidestep legacy isolation costs with a new approach to storage that allows safe operation on data without hardware protection using recent advances in programming languages. It combats data movement between disaggregated storage and compute nodes with untrusted tenant extensions pushed to Sandstorm, a new cloud storage system. Sandstorm's insight is that storage extensions can use language-level isolation to eliminate hardware isolation overheads that cannot be avoided today: not with virtual machines, containers, nor serverless Lambdas. Sandstorm also eliminates copying data for safety, so extensions benefit from low-level hardware functionality like zero-copy network transmission. The project will develop multitenant benchmarks, low-cost performance-isolated concurrency mechanisms for multicores, techniques to minimize data movement within servers, storage extensions that demonstrate the benefits, and distributed extensions over clusters. The overall goal is for Sandstorm to enable any cloud developer to accelerate data-intensive applications like real-time social network and natural graph analysis and fine-grained coordination of hundreds of thousands of autonomous vehicles.


Memshare is a drop-in memcached replacment with first class support for multi-tenancy. Memshare's unique combination of in-memory cleaning and online per-tenant hit rate curve profiling give it better hit rates than exsiting caches even while it allows the cache operator to control QoS, sharing, and isolation between applications.


PDF ECHO: A Reliable Distributed Cellular Core Network for Hyper-scale Public Clouds.
Binh Nguyen, Tian Zhang, Bozidar Radunovic, Ryan Stutsman, Thomas Karagiannis, Jakub Kocur, and Jacobus Van Merwe.
Proceedings of the 24th Annual International Conference on Mobile Computing and Networking (Mobicom'18).
PDF Tailwind: Fast and Atomic RDMA-based Replication.
Yacine Taleb, Ryan Stutsman, Gabriel Antoniu, and Toni Cortes.
Proceedings of the 2018 USENIX Annual Technical Conference (USENIX ATC '18).
PDF Towards a Shared-Everything Database on Distributed Log-Structured Storage.
Tao Zhu, Zhuoyue Zhao, Feifei Li, Weining Qian, Aoying Zhou, Dong Xie, Ryan Stutsman, Haining Li, and Huiqi Hu.
Proceedings of the 2018 USENIX Annual Technical Conference (USENIX ATC '18).
PDF Rocksteady: Fast Data Migration for Low-latency In-memory Storage.
Chinmay Kulkarni, Aniraj Kesavan, Tian Zhang, Robert Ricci, and Ryan Stutsman.
Proceedings of the Twenty-Sixth ACM Symposium on Operating Systems Principles (SOSP '17).
PDF Memshare: Memory Resource Sharing in Multi-tenant Web Caches.
Asaf Cidon, Daniel Rushton, Stephen M. Rumble, and Ryan Stutsman.
Proceedings of the 2017 USENIX Conference on Annual Technical Conference (USENIX ATC'17).
PDF JavaScript for Extending Low-latency In-memory Key-value Stores.
Tian Zhang and Ryan Stutsman.
Proceedings of the 9th USENIX Conference on Hot Topics in Cloud Computing (HotCloud'17).
PDF Beyond Simple Request Processing with RAMCloud.
Chinmay Kulkarni, Aniraj Kesavan, Robert Ricci, and Ryan Stutsman.
IEEE Data Engineering Bulletin 40(1).
PDF To Copy or Not to Copy: Making In-Memory Databases Fast on Modern NICs.
Aniraj Kesavan, Robert Ricci, and Ryan Stutsman.
4th Workshop on In-memory Data Management.
PDF Toward Rigorous Design of Domain-Specific Distributed Systems.
Mohammed Al-Mahfoudh, Ganesh Gopalakrishnan, and Ryan Stutsman.
4th IEEE/ACM FME Workshop on Formal Methods in Software Engineering, FormaliSE 2016, Austin, Texas, May 15, 2016.
PDF Toward Bringing Distributed Systems Design Upon Rigorous Footing.
Mohammed Al-Mahfoudh, Ganesh Gopalakrishnan, and Ryan Stutsman.
IEEE Workshop on Formal Methods and Integration (FMi).
PDF Experience with Rules-Based Programming for Distributed, Concurrent, Fault-Tolerant Code.
Ryan Stutsman, Collin Lee, and John Ousterhout.
Proceedings of the 2015 USENIX Conference on Annual Technical Conference (USENIX ATC'15).