Dell Products Inc.

Emc Corporation

Pascal Donette

Ronald Brown

John Bankier

Francois Roche

Philippe Armangau

Frederic Corniquet

John Michael Hayden

Hongmei Wang

Aju John

A system can perform a migration. The system can, in response to receiving a request to perform a file system operation on a destination file system, wherein the request identifies a first source file handle, direct, by a second computer and to a first computer, to perform the file system operation on a source file system with the first source file handle, to produce a second source file handle, convert the first and second source file handles to corresponding first and second components of a destination file handle, perform the file system operation on the destination file system with the first and second components of a destination file handle, respond to the client computer with the second source file handle. The system can re-assign a network address when rolling back the migration, wherein a client is configured to use the second source file handle with the source file system.

Efficient transparent rollback of file system consolidation migrations

A system can migrate a source file system on a first computer to a destination file system on a second computer. The system can receive, at the second computer, a request from a client computer that indicates a file system operation, and that references a source file handle of the source file system that comprises an identifier of the source file system. The system can identify the destination file system based on the identifier of the source file system. The system can determine, from a source inode number of the source file handle, a source inode number segment. The system can determine, from the source inode number segment, a destination inode number segment. The system can determine, from the destination inode number segment, a destination inode number. The system can perform the file system operation on the destination file system using the destination inode number and the identifier of the destination file system.

Efficient transparent switchover of file system consolidation migrations

For disaster recovery of a file server at an active site, the files that define the user environment of the file server are replicated to a virtual server at a disaster recovery site. To switch over user access from the active site to the disaster recovery site, the disaster recovery system determines whether there are sufficient network interfaces and file system mounts at the disaster recovery site. If so, the required resources are reserved, and user access is switched over. If not, an operator is given a list of missing resources or discrepancies, and a choice of termination or forced failover. Interruptions during the failover can be avoided by maintaining a copy of user mappings and a copy of session information at the disaster recovery site, and keeping alive client-server connections and re-directing client requests from the active site to the disaster recovery site.

Internet protocol based disaster recovery of a server

Growing community of inventors

Magny les Hameaux, France

Pascal Donette