If one node fails and the GFS Shared File System is being used from multiple nodes, the other nodes can continue file accesses. The file system data retained by the failing node is automatically recovered in consistency within the GFS Shared File System from the other nodes. In other words, application programs operating on the other nodes can continue without a file system operation error.
See
For more information on the uninterrupted operation function, see "Chapter 3 Failure Recovery."
Figure 1.4 Uninterrupted operation in case of node failure
