Consistent hashing is a central building block in many networking applications, such as maintaining connection affinity of TCP flows. However, current consistent hashing solutions do not ensure full consistency under arbitrary changes or scale poorly in terms of memory footprint, update time and key lookup complexity. We present AnchorHash, a scalable and fully-consistent hashing algorithm. AnchorHash achieves high key lookup rate, low memory footprint and low update time. We formally establish its strong theoretical guarantees, and present an advanced implementation with a memory footprint of only a few bytes per resource. Moreover, evaluations indicate that AnchorHash scales on a single core to 100 million resources while still achieving a key lookup rate of more than 15 million keys per second.

AnchorHash: A Scalable Consistent Hash

Consistent hashing has played an indispensable role in cloud infrastructure, although its load balancing performance is not necessarily perfect. Consistent hashing has long remained the most widely used method despite many methods being proposed to improve load balancing because these methods trade off load balancing against consistency, memory usage, lookup performance, and/or fault-tolerance. This article presents Structured Allocation-based Consistent Hashing (SACH), a cloud-optimized consistent hashing algorithm that overcomes the trade-offs by taking advantage of the characteristics of cloud environments: scaling management and auto-healing. Since scaling can be distinguished from failures, SACH applies two different algorithms to update hashing functions: a fast-update algorithm for unmanaged backend failures to satisfy fault-tolerance with quick response and a slow-update algorithm for managed scaling. Hashing functions are initialized or slow-updated considering the characteristics of the fast-update algorithm to satisfy load balancing and the other properties as far as the number of failed backends is kept small by auto-healing. The experimental results show that SACH outperforms existing algorithms in each aspect. SACH will improve the load balancing of cloud infrastructure components, where the trade-offs have prevented the renewal of hashing functions.

/pdf/structured-allocation-based-consistent-hashing-with-improved-1d0sz445vm.pdf

Structured Allocation-Based Consistent Hashing With Improved Balancing for Cloud Infrastructure

Consistent hashing (CH) is a central building block in many networking applications, from datacenter load-balancing to distributed storage. Unfortunately, state-of-the-art CH solutions cannot ensure full consistency under arbitrary changes and/or cannot scale while maintaining reasonable memory footprints and update times. We present AnchorHash, a scalable and fully-consistent hashing algorithm. AnchorHash achieves high key lookup rates, a low memory footprint, and low update times. We formally establish its strong theoretical guarantees, and present advanced implementations with a memory footprint of only a few bytes per resource. Moreover, extensive evaluations indicate that it outperforms state-of-the-art algorithms, and that it can scale on a single core to 100 million resources while still achieving a key lookup rate of more than 15 million keys per second.

AnchorHash: A Scalable Consistent Hash.

Distributed systems use consistent hashing algorithms to solve load balancing problems because of their good balance, minimal interruptions, and high query rates. However, existing algorithms fail to maintain consistency under changes, require high memory for high query rates, or have poor scaling. Therefore, we propose consistent AreaHash, which virtualizes the hash space into a ring. The logically ordered ring nodes occupy the same area, allowing the AreaHash to expand the nodes without any change. The key calculated using the hashing algorithm can be mapped to a node by a simple shift calculation, reducing memory requirements. We make a reasonable theoretical analysis and perform high-level algorithm implementation with a memory footprint of only a few bytes per node. Experimental results indicate that AreaHash achieves a lookup rate of more than 40 million keys per second, even when the number of nodes on a single CPU exceeds one million. In addition, a lookup rate of more than 20 million keys per second is achieved when more than half of the nodes in the cluster are down.

AreaHash: A Balanced and fully scalable consistency hashing algorithm

Consistent Hashing functions are widely used for load balancing across a variety of applications. However, the original presentation and typical implementations of Consistent Hashing rely on randomised allocation of hash codes to keys which results in a flawed and approximately-uniform allocation of keys to hash codes. We analyse the desired properties and present an algorithm that perfectly achieves them without resorting to any random distributions. The algorithm is simple and adds to our understanding of what is necessary to create a consistent hash function.

Matthew Sackman

Papers

Perfect Consistent Hashing.