Emc Corporation

Hewlett-packard Development Company, L.p.

Peter Kamvysselis

Dan Arnon

David Meiri

Mark J Halstead

Yuval Ofek

Michael Hirsch

Samuel Krikler

David Shadmon

Zoran Cakeljic

Sharon Galtzur

Yakov Yazlovitsky

Alexander Gutman

Peter Lacey

Emir Barucija-Hodzic

A method for scanning a message-list accessible to a plurality of processors includes retrieving, from a cache associated with a scanning processor from the plurality of processors, information identifying a starting message-slot. This information is then used to begin a scan of the message-list at that starting message-slot. The information indicating the starting message-slot is obtained by identifying, in the message-list, a message-slot containing a message intended for a recipient processor from the plurality of processors and obtaining, from the identified message-slot, information indicative of a location of a succeeding message-slot in the message-list. This information is then cached, for retrieval during a subsequent scan of the message-list.

Scanning a message-list

Transmitting data from a source to a destination, includes receiving the data from the source and providing the data to the destination using a network, where the data is acknowledged to the source as being successfully received at the destination prior to all of the data being provided to the network. The source may be a primary storage device. The destination may be a secondary storage device. The data may be provided from the source in a first format and may be provided to the network in a second format that is different from the first format where the first format may be RDF and the second format may be TCP/IP or UDP. The destination may receive the data in a first format different from a second format used to transmit the data over the network. The first format may be RDF and the second format may be TCP/IP or UDP.

Ordered writes for SRDF assist

Providing multiple jobs for a device associated with a communication device includes providing a plurality of device records, where each of the device records corresponds to a device associated with the communication device, providing a plurality of job records for at least one of the device records, where each of the job records contains at least some information that is also provided in the corresponding one of the device records, and linking the job records and the corresponding device record so that any one of the job records may be accessed by first accessing the corresponding one of the device records. Providing multiple jobs may also include providing one of a plurality of shared pointers in each of the job records and the corresponding one of the device records, where all of the shared pointers point to the corresponding one of the device records. Linking the job records may include providing a forward pointer and a backward pointer for each of the job records. Linking the job records may also include providing a pointer to one of the job records in the corresponding one of the device records.

Multiple jobs per device that are linked via a device record for servicing by different adapters

SRDF assist

Error recovery for SRDF assist

Software behavior is analyzed. A disk drive controller has a processor executing computer software stored in a memory communicating with the processor via a local bus. In the controller, computer executable program code is identified that includes a set of computer executable program instructions for recording analytical data for at least a subset of the computer executable program code. The set of computer executable program instructions is disabled from executing. Without halting execution of the computer executable program code, execution of the set of computer executable program instructions is enabled.

Analyzing software behavior

Shuttle-based mechanism for numbering concurrent chains of independent data transfers

A backup appliance that can be disposed on a computer adapter card mid-plane internal to a data storage system. The appliance includes logic on the computer adapter card. The logic is configured for selectively allowing either directly controlling the robot picker through the fiber channel connection or indirectly controlling the robot picker by communicating with the backup server. The logic is also configured for controlling buffering of data stored in the data storage system and communicating directly with media backup drives for writing the data from buffers in the data storage system onto the backup media drives.

System and method for improving performance of a data backup operation

A mechanism to support remote mirroring of storage devices by data storage systems in a one-to-many switched environment. Each data storage system includes a disk director that is adapted to control at least one device group that is supported in a mirrored configuration with a corresponding device group controlled by one of the other data storage systems. For each device group and corresponding device group, there are first ports associated with the device group and second ports associated with the corresponding device group. A switch element is adapted to connect one of the first ports to at least one of the second ports so that data may be exchanged between the ports for each device group and corresponding device group. The disk director selects which first port is to be connected to which second port via the switch element in the establishment of a logical link. Thus, each port connected to the switch is capable of achieving multiple connections to multiple destinations for increased connectivity, redundancy and performance (load balance) without additional hardware.

Remote mirroring in a switched environment

A data transfer arrangement transfers data from a source device, such as a local mass storage facility, to a destination device, such as a remote storage facility. The data transfer arrangement comprises a source device and a destination device. The source device transfers to the destination device a data block including data and padding along with a source check value that is a function of the data and selectively the padding, and a check indication indicating whether the check value is the function of the data alone, or the data and the padding. The destination device, after receiving the data block, source check value and check indication, generates a destination check value that is the function of the data alone, or the data and the padding, based on the check indication, and uses the source and destination check values to determine whether the data block was correctly received.

System and method for expediting transfer of data from a local storage facility to a remote storage facility

This invention is a system and method for improving performance of a backup operation of data from a data storage system to a media library. In response to a computer system request to backup a slot or track of data, a data engine in communication with the system and a data storage system selectively reads the requested data. Such data engine reads may occur concurrent to host access for I/O operations by employing a protection scheme, e.g. a protection bit. Simultaneously, different backup sessions may read the same track of data that has been read by the data engine. The data slot or track remains in cache memory of the data storage system until all protection bits are reset. A requested slot or track may be moved to a sidefile stored in the cache memory if a host requested to write to it while protection bits are still set and then sent to the Data engine for transfer to a media library.

This invention is a system and method for efficiently carrying out a restore operation in a data storage environment. The present invention is a system and method for restoring data in a manner that reduces wait time of associated resources. Logic, which is part of the invention, determines whether a restore is in progress when an application on a computer system is involved in trying to perform an I/O operation on a track of data. A protective scheme is used to keep such data from being updated while the restore is taking place. Importantly the system resources do not have to wait for the restore to complete to carry out I/O operations, which are accounted for separately from the data itself and then a synchronization occurs following completion of the restore.

System and method for efficiently performing a restore operation in a data storage environment

Transferring data from a local storage device to a remote storage device includes providing a first portion of data to a cache memory of the local storage device, marking the first portion of data as write pending, and, in response to transferring a second portion of data related to the first portion of data prior to the first portion of data being transferred to the remote storage device, transferring the first and second portions of data from the local storage device to the remote storage device. The data may be transferred using RDF format. The first portion of data may be a first block and the second portion of data may be a second block and the first and second blocks may be part of a same sector of data. Transferring the data may also include setting a wpmode flag in response to the first portion of data not being transferred when a request to transfer the second portion of data is made. Transferring the data may also include, in response to the wpmode flag being set, transferring additional data from the local storage device to the remote storage device. The additional data may include data that has also been marked as write pending.

Growing community of inventors

Boston, MA, United States of America

Peter Kamvysselis