Open Invention Network LLC

Intransa, Inc.

Ismail Dalgic

Alan Rowe

Sameer Narkhede

Wing Au

Chandrika Srinivasan

Kadir Ozdemir

Omer Tunali

Robert Eugene Gilligan

F Alan Jones

Michael Syben

Frederic Pont

Jeffrey Henry Raubitschek

Randolph E Harr

David C Lee

Methods, computer media encoding instructions, and systems that receive write requests directed to non-sequential logical block addresses and write the write requests to sequential disk block addresses in a storage system include an overprovision of a storage system to include an increment of additional storage space such that it is more likely a large enough sequential block of storage will be available to accommodate incoming write requests.

Method for achieving sequential I/O performance from a random workload

Methods, computer media encoding instructions, and that receive write requests directed to non-sequential logical block addresses and writing the write requests to sequential disk block addresses in a storage system include an overprovision of a storage system to include an increment of additional storage space such that it is more likely a large enough sequential block of storage will be available to accommodate incoming write requests.

Some embodiments of the present invention provide methods, computer media encoding instructions, and systems for receiving write requests directed to non-sequential logical block addresses and writing the write requests to sequential disk block addresses in a storage system. Some embodiments further include overprovisioning a storage system to include an increment of additional storage space such that it is more likely a large enough sequential block of storage will be available to accommodate incoming write requests.

Method for achieving sequentail I/O performance from a random workload

Method and apparatus for migrating a volume and a virtual disk from a first storage controller to a second storage controller in a distributed storage system having volumes and virtual disks associated with storage controllers. In one embodiment, the virtual disk is migrated to the second storage controller, and requests for data reads/writes associated with the virtual disk are routed to the second controller. Further, in another embodiment, the volume is migrated to the second storage controller, and requests for data reads/writes associated with the volume are routed to the second controller. A contact address may be associated with a plurality of storage controllers and once a session between an application server and a volume is established, the application server may be redirected so as to communicate with the storage controller associated with the volume using the IP address of the storage controller. In this manner, the volumes and the virtual disks may be migrated, independently if desired, to other storage controllers in the network without disrupting the data flow between the application server and the storage controllers.

Method and apparatus for migrating volumes and virtual disks

Apparatus and methods for distributing iSCSI and SCSI targets. The initiator may assist in the distribution and order the SCSI commands. A subset of target storage processors may act as proxies. Target storage processors forward requests to a selected target storage processor which decides whether any and which of the other target storage processors is to process a forwarded request. The target storage processors may act as peers. A target storage processor communicates each received request to all of the other storage processors. Each of the target storage processors determines whether a request it received is to execute. A target storage processors may arrange themselves into layers to divide the SCSI and iSCSI protocol work. A distributed system associates each of multiple egress target storage processors with a respective ingress target storage processor and associates a set of blocks of storage with each of the egress target storage processors.

Distributed iSCSI and SCSI targets

Apparatus and methods for managing storage. A storage system may receive a request from a host, for example, to allocate n blocks of storage. The storage system may allocate m blocks of physical storage, where m<n, and indicate that the request completed successfully. In various embodiments, m>zero (0) or m&equals;zero (0). The storage system may receive a request to access a block j of the requested blocks of storage, m<j<n, and accessing the block j, in response to the request to access. Allocating the physical storage may include allocating m blocks of physical storage encompassing the block j. After the allocating, the storage system may receive a request to access a block j of the requested blocks of storage, m<j<n, access the block j and indicate that the request to access completed successfully.

Growing community of inventors

Sunnyvale, CA, United States of America

Ismail Dalgic