Shared-nothing Vs. Single Point of Failure
The failure of disk hardware can create a single point of failure that can result in data loss. To avoid this problem, a shared nothing architecture can be employed. Each storage node communicates changes to other nodes or to a master, for replication purposes. If a single disk fails, other copies can be used to reconstruct or replace it on the fly so "nothing" is lost. To enable this feature, clients must be unaware of the physical location of a file. A single global file system is presented to clients, so the file system itself deals with allocations and low-level failures. Examples of this type of file system are found in products such as Ceph, Lustre, Isilon, IBRIX Fusion, and Hadoop.
Read more about this topic: Clustered File System
Famous quotes containing the words single, point and/or failure:
“Mad about the boy,
I know it’s stupid to be mad about the boy,
I’m so ashamed of it
But must admit
The sleepless nights I’ve had about the boy.
On the Silver Screen
He melts my foolish heart in every single scene.”
—Noël Coward (1899–1973)
“The town is divided into various groups, which form so many little states, each with its own laws and customs, its jargon and its jokes. While the association holds and the fashion lasts, they admit nothing well said or well done except by one of themselves, and they are incapable of appeciating anything from another source, to the point of despising those who are not initiated into their mysteries.”
—Jean De La Bruyère (1645–1696)
“Extemporaneous speaking should be practised and cultivated. It is the lawyer’s avenue to the public.... And yet there is not a more fatal error to young lawyers than relying too much on speechmaking. If any one, upon his rare powers of speaking, shall claim an exemption from the drudgery of the law, his case is a failure in advance.”
—Abraham Lincoln (1809–1865)