vix.ing · top · new · best · stats · spec

Exploiting Locality in Lease-Based Replicated Transactional Memory via\n Task Migration

2013/08/09 by Danny Hendler, Hendler, Danny, Alex Naiman +9 · 1 citation
Computer Science · Psychology · #Age of Information Optimization #Cognitive Functions and Memory #Databases (cs.DB) #Distributed #Distributed systems and fault tolerance #FOS: Computer and information sciences #Mobile Agent-Based Network Management #Parallel #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.1308.2147

openalex publication_date 2013/08/09 · openalex created_date 2025/10/24 · openalex updated_date 2026/07/28

Abstract

We present Lilac-TM, the first locality-aware Distributed Software\nTransactional Memory (DSTM) implementation. Lilac-TM is a fully decentralized\nlease-based replicated DSTM. It employs a novel self- optimizing lease\ncirculation scheme based on the idea of dynamically determining whether to\nmigrate transactions to the nodes that own the leases required for their\nvalidation, or to demand the acquisition of these leases by the node that\noriginated the transaction. Our experimental evaluation establishes that\nLilac-TM provides significant performance gains for distributed workloads\nexhibiting data locality, while typically incurring no overhead for non-data\nlocal workloads.\n

Citations

Cited by

Related