Shared-disk architecture
A shared-disk architecture (SD) is a distributed computing architecture in which the nodes share same disk devices but each node has its own private memory.[1] The disks have active nodes which all share memory in case of any failures.[2] In this architecture, the disks are accessible from all the cluster nodes. This architecture has quick adaptability to the changing workloads.[3] It uses robust optimization techniques. Multiple processors can access all disks directly via intercommunication network and every processor has local memory.
It contrasts with shared-nothing architecture, in which all nodes have sole access to distinct disks,[4] and with shared-memory, in which they also share memory.
Shared-disk has two advantages over Shared-memory. Firstly, each processor has its own memory, the memory bus is not a bottleneck; secondly, the system offers a simple way to provide a degree of fault tolerance.
References
- ↑ "Difference between Shared Nothing Architecture and Shared Disk Architecture" (in en-US). 2020-05-18. https://www.geeksforgeeks.org/difference-between-shared-nothing-architecture-and-shared-disk-architecture/.
- ↑ Solar: Towards a Shared-Everything Database on Distributed Log-Structured Storage. pp. 13. https://www.cs.utah.edu/~dongx/paper/solar-atc.pdf.
- ↑ Rylan, John (1 April 2018). "Big Database (Part 2): Database Architecture". https://dzone.com/articles/big-database-2-database-architecture.
- ↑ "Shared Nothing v.s. Shared Disk Architectures: An Independent View". November 24, 2009. http://www.benstopford.com/2009/11/24/understanding-the-shared-nothing-architecture/.
 |  |
