Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
View analytic
Monday, September 21 • 3:30pm - 4:25pm
Beyond Consistent Hashing and TCP: Vastly Scalable Load Balanced Storage Clustering

Sign up or log in to save this to your schedule and see who's attending!

Successive generations of storage solutions have increased decentralization. Early NAS systems made all the decisions on a single server, down to sector assignment. Federated NAS enabled dynamic distribution of the namespace across multiple storage serves. The first Object Clusters delegated CRUD-based management of both object metadata and data to OSDs.

Current generation of Object Clusters uses Consistent Hashing to eliminate the need for central metadata. However, Consistent Hashing and its derivatives, combined with the prevalent use of TCP/IP in storage clusters results in performance hot spots and bottlenecks, diminished scale-out capability and dis-balances in resource utilization.

These shortcomings will be demonstrated with a simulation of a large storage cluster. An alternative next generation strategy that simultaneously optimizes available IOPS "budget" of the back-end storage, storage capacity, and network utilization will be explained. Practically unlimited load-balanced scale-out capability using Layer 5 (Replicast) protocol for Multicast Replication within the cluster will be presented.

Learning Objectives

Why neither Consistent Hashing nor TCP/IP scale
How CCOW (Cloud Copy-on-Write) and Replicast provide for infinite scale-out
Impact on IOPS, Storage Capacity and Network utilization
Simulation: queuing and congestion in a 4000 node cluster Actual
Results: measured with a more affordable cluster

Speakers
avatar for Alex Aizman

Alex Aizman

CTO and Founder, Nexenta Systems
Alex is founder and CTO, Nexenta Systems, Inc. Alex created NexentaOS and NexentaStor – the company’s flagship software-only platform, currently at its 5th generation. He co-created iSCSI stack for Linux kernel and its major distributions and co-invented Large Receive Offload (LRO), the broadly adopted method to improve TCP and UDP performance, supported currently in all major operating systems, with and without (LRO) assistance in the... Read More →
avatar for Caitlin Bestler

Caitlin Bestler

Senior Director of Arch, Nexenta Systems
Caitlin Bestler is Sr. Director of Architecture at Nexenta Systems and is the architect of the NexentaEdge product line. Her experience includes not only storage systems but networking (especially RDMA) and Cable TV control systems. The Cable TV control system experience is strangely relevant to modern distributed storage networking. Controlling cable decoders is managing a highly distributed authorization database with very unreliable components... Read More →


Monday September 21, 2015 3:30pm - 4:25pm
Stevens Creek Room

Attendees (7)