Shared-disk architecture: Difference between revisions

Revision as of 08:27, 1 March 2021

Revision as of 04:30, 2 March 2021

Line 1:

{{refimprove|date=November 2012}}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.<ref>{{Cite web|date=2020-05-18|title=Difference between Shared Nothing Architecture and Shared Disk Architecture|url=https://www.geeksforgeeks.org/difference-between-shared-nothing-architecture-and-shared-disk-architecture/|access-date=2021-02-24|website=GeeksforGeeks|language=en-US}}</ref> The disks have active nodes which all share memory in case of any failures.<ref>{{Cite journal|title=Solar: Towards a Shared-Everything Database on Distributed Log-Structured Storage|url=https://www.cs.utah.edu/~dongx/paper/solar-atc.pdf|journal=https://www.cs.utah.edu/~dongx/paper/solar-atc.pdf|pages=13|via=Solar}}</ref> In this architecture the disks are accessible from all the cluster nodes. This architecture has quick adaptability to the changing workloads.<ref>{{Cite web|last=Rylan|first=John|date=1 April 2018|title=Big Database (Part 2): Database Architecture|url=https://dzone.com/articles/big-database-2-database-architecture|url-status=live|website=DZone}}</ref> It uses robust optimization techniques. It contrasts with [[shared nothing architecture]], in which all nodes have sole access to distinct disks.<ref name="stopford">{{cite web|date=November 24, 2009|title=Shared Nothing v.s. Shared Disk Architectures: An Independent View|url=http://www.benstopford.com/2009/11/24/understanding-the-shared-nothing-architecture/|access-date=November 1, 2012}}</ref> Multiple processors can access all disks directly via intercommunication network and every processor has local memory.

Log-Structured Storage|url=https://www.cs.utah.edu/~dongx/paper/solar-atc.pdf|journal=https://www.cs.utah.edu/~dongx/paper/solar-atc.pdf|pages=13|via=Solar}}</ref> In this architecture the disks are accessible from all the cluster nodes. This architecture has quick adaptability to the changing workloads.<ref>{{Cite web|last=Rylan|first=John|date=1 April 2018|title=Big Database (Part 2): Database Architecture|url=https://dzone.com/articles/big-database-2-database-architecture|url-status=live|website=DZone}}</ref> It uses robust optimization techniques. It contrasts with [[shared nothing architecture]], in which all nodes have sole access to distinct disks.<ref name="stopford">{{cite web|date=November 24, 2009|title=Shared Nothing v.s. Shared Disk Architectures: An Independent View|url=http://www.benstopford.com/2009/11/24/understanding-the-shared-nothing-architecture/|accessdate=November 1, 2012}}</ref> Multiple processors can access all disks directly via intercommunication network and every processor has local 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.