Distributed Lock Manager

Lock Manager Lock Manager Data

Fast Locks in Distributed Shared Memory Systems

Synchronization and remote memory access delays cause staggering ineeciency in most shared memory programs if run on thousands of processors. This paper introduces eecient lock synchronization using the combination of group write consistency, which guarantees write ordering within groups of processors, and eagersharing distributed memory, which sends newly written data values over fast network ...

A distributed lock manager on fault tolerant MPP

The Distributed L.ock Manager (DLM) is the cornerstone of running the Oracle Parallel Server on a MPP UNIX system. The DLM grants resource locks in NULL, READ, WRITE, and other levels. The DLM is typically implemented either with distributed message passing or in global shared memory, depending on the architecture. Reflective memory on the Encore Infinity 90 architecture permits a shared memory...

The Design and Performance Evaluation of a Lock Manager for a Memory-Resident Database System

In the last fteen years, lock managers for regular disk-based database systems have seen little change. This is not without reason, since traditional memory-resident lock managers have always been much faster than disk-based database storage managers and disk-based database systems had few alternative design options. However, the introduction of memory-resident database systems has created both...

Using RDMA for Lock Management

In this work, we aim to evaluate different Distributed Lock Management service designs with Remote Direct Memory Access (RDMA). In specific, we implement and evaluate the centralized and the RDMAenabled lock manager designs for fast network settings. Experimental results confirms a couple of hypotheses. First, in the traditional centralized lock manager design, CPU is the bottleneck and bypassi...