LARK -- Linearizability Algorithms for Replicated Keys in Aerospike

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Goodng, Andrew, Porter, Kevin, Lopatic, Thomas, Shinde, Ashish, Sayyaparaju, Sunil, Seshadri, Srinivasan, Srinivasan, V.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915593963175936
author Goodng, Andrew
Porter, Kevin
Lopatic, Thomas
Shinde, Ashish
Sayyaparaju, Sunil
Seshadri, Srinivasan
Srinivasan, V.
author_facet Goodng, Andrew
Porter, Kevin
Lopatic, Thomas
Shinde, Ashish
Sayyaparaju, Sunil
Seshadri, Srinivasan
Srinivasan, V.
contents We present LARK (Linearizability Algorithms for Replicated Keys), a synchronous replication protocol that achieves linearizability while minimizing latency and infrastructure cost, at significantly higher availability than traditional quorum-log consensus. LARK introduces Partition Availability Conditions (PAC) that reason over the entire database cluster rather than fixed replica sets, improving partition availability under independent failures by roughly 3x when tolerating one failure and 10x when tolerating two. Unlike Raft, Paxos, and Viewstamped Replication, LARK eliminates ordered logs, enabling immediate partition readiness after leader changes -- with at most a per-key duplicate-resolution round trip when the new leader lacks the latest copy. Under equal storage budgets -- where both systems maintain only f+1 data copies to tolerate f failures -- LARK continues committing through data-node failures while log-based protocols must pause commits for replica rebuilding. These properties also enable zero-downtime rolling restarts even when maintaining only two copies. We provide formal safety arguments and a TLA+ specification, and we demonstrate through analysis and experiments that LARK achieves significant availability gains.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01843
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LARK -- Linearizability Algorithms for Replicated Keys in Aerospike
Goodng, Andrew
Porter, Kevin
Lopatic, Thomas
Shinde, Ashish
Sayyaparaju, Sunil
Seshadri, Srinivasan
Srinivasan, V.
Distributed, Parallel, and Cluster Computing
Databases
We present LARK (Linearizability Algorithms for Replicated Keys), a synchronous replication protocol that achieves linearizability while minimizing latency and infrastructure cost, at significantly higher availability than traditional quorum-log consensus. LARK introduces Partition Availability Conditions (PAC) that reason over the entire database cluster rather than fixed replica sets, improving partition availability under independent failures by roughly 3x when tolerating one failure and 10x when tolerating two. Unlike Raft, Paxos, and Viewstamped Replication, LARK eliminates ordered logs, enabling immediate partition readiness after leader changes -- with at most a per-key duplicate-resolution round trip when the new leader lacks the latest copy. Under equal storage budgets -- where both systems maintain only f+1 data copies to tolerate f failures -- LARK continues committing through data-node failures while log-based protocols must pause commits for replica rebuilding. These properties also enable zero-downtime rolling restarts even when maintaining only two copies. We provide formal safety arguments and a TLA+ specification, and we demonstrate through analysis and experiments that LARK achieves significant availability gains.
title LARK -- Linearizability Algorithms for Replicated Keys in Aerospike
topic Distributed, Parallel, and Cluster Computing
Databases
url https://arxiv.org/abs/2511.01843