Lsi Corporation

Netapp, Inc.

Lsi Logic Corporation

Ross Zwisler

Gerald James Fredin

Andrew J Spry

Kenneth J Gibson

Brian Dennis McKean

Kevin Lee Kidney

Robert L Sheffield

The present invention is a system and method which allows for a VTL system that supports thin provisioning to implicitly unmap unused storage. Such unmap operations may occur even though the VTL system does not receive any explicit unmap requests from its initiators. For example, if a system administrator knows that once a virtual tape drive of the VTL system has been partially overwritten, all previously written data sets on that virtual tape drive will never again be accessed, the system administrator may configure the VTL system so that it unmaps the entire remainder of the virtual tape drive on the first data overwrite.

System and method for providing implicit unmaps in thinly provisioned virtual tape library systems

The method includes receiving a command at a first storage system of a block storage cluster. The command is transmitted by the initiator system to the first storage system via a network and includes a request for data. The method further includes transferring the stored data from the first storage system to the initiator system via the network when data requested in the data request is stored by the first storage system. The method further includes transmitting a referral response from the first storage system to the initiator system when a portion of the data requested in the data request is not stored by the first storage system, but is stored by a second storage. system of the block storage cluster.

Small computer system interface input output (SCSI IO) referral

The present invention is a method for providing multi-pathing via Small Computer System Interface Input/Output (SCSI I/O) referral between an initiator and a storage cluster which are communicatively coupled via a network. The method includes receiving an input/output (I/O) at a first target device from the initiator via the network. The I/O includes a data request. The method further includes transmitting a SCSI I/O referral list to the initiator when data included in the data request is not stored on the first target device, but is stored on a second target device. The referral list includes first and second port identifiers for identifying first and second ports of the second target device respectively. The first and second ports of the target device are identified as access ports for accessing the data requested in the data request.

Transport agnostic SCSI I/O referrals

A first Network Interface Controller operates in a low power mode. The first Network Interface Controller transitions from low power mode to a power-up sequence if a sleep packet in not received from a second Network Interface Controller at the first Network Interface Controller within a predetermined time threshold.

Implementing sleep lines in commodity ethernet hardware

The present disclosure is directed to a method for communication between an initiator system and a block storage cluster. The method may comprise initiating an input/output (I/O) request from the initiator system to a first storage system included in a plurality of storage systems of the block storage cluster, each of the plurality of storage systems comprising a plurality of data segments; receiving a referral response from the first storage system, the referral response providing information describing a layout of data requested in the I/O request; obtaining a virtual disk count, a segment size, and at least one indexed port identifier based on the referral response; and directing the I/O request from the initiator system to the block storage cluster based on the virtual disk count, the segment size, and the at least one indexed port identifier.

Striping with SCSI I/O referrals

A method and/or system may be configured to receive an input/output (I/O) request from an initiator system, add priority information to a multiple path referral for each port on which data can be accessed, selectively omit ports on which data may be accessed, transmit the multiple path referral from the target to the initiator, and/or choose a path on the initiator with the highest performance.

Load balancing with SCSI I/O referrals

A method for communication between an initiator system and a block storage cluster may include receiving a first command at a first storage system included in a plurality of storage systems of the block storage cluster. The method may also include transmitting a referral response from the first storage system to the initiator system when at least a portion of the data associated in the first command is stored by a second storage system. The method may further include obtaining a segment start value and a corresponding port identifier based on the referral response, and directing a second command to at least a second storage system included in the plurality of storage systems of the block cluster.

Explicit data segment boundaries with SCSI I/O referrals

A system and method for root booting includes a plurality of computing devices that each boot from a read-only base volume of an attached storage device that includes data common to the computing devices. The attached storage device also includes a plurality of volumes, each dedicated to one of the computing devices, which are redirect on write snapshots of the read-only base volume including unique items for the respective computing device. The read-only base volume may be stored in one or more solid state drives which may be configured as a RAID (redundant array of independent disks) and/or mirrored with one or more other storage drives. The plurality of volumes may each be stored in one or more hard disk drives which may be configured as a RAID. The attached storage device may be operable to add common data to the read-only base volume.

Efficient root booting with solid state drives and redirect on write snapshots

Contentual metadata of an extended cache is stored within the extended cache. The contentual metadata of the extended cache is approximated utilizing a counting Bloom filter. The counting Bloom filter is stored within a primary cache. Contentual metadata of the primary cache is stored within the primary cache. One of a data read or a data write is executed without accessing the contentual metadata of the extended cache stored within the extended cache.

Managing extended RAID caches using counting bloom filters

A method for communication between an initiator system and a block storage cluster may include receiving a first input/output (I/O) request from the initiator system. The method may also include sending a referral response from a first storage system included in a plurality of storage systems of the block storage cluster to the initiator system when data associated with the first I/O request is stored in more than one storage system of the plurality of storage systems of the block storage cluster. Additionally, the method may include directing a referral I/O to the first storage system and the second storage system for transferring data to or transferring data from the first storage system and the second storage system, and transferring data associated with the referral I/O to or transferring data associated with the referral I/O from the first storage system and the second storage system.

Method and system for implementing parallelism with SCSI I/O referrals

The present invention is a method for communication between an initiator system and a block storage cluster. The method includes receiving a command at a first storage system of a block storage cluster. The command is transmitted by the initiator system to the first storage system via a network and includes a request for data. The method further includes transferring the stored data from the first storage system to the initiator system via the network when data requested in the data request is stored by the first storage system. The method further includes transmitting a referral response from the first storage system to the initiator system when a portion of the data requested in the data request is not stored by the first storage system, but is stored by a second storage system of the block storage cluster. The referral response indicates to the initiator system that: a) not all of the requested data was transferred; and b) that the second storage system stores the portion of the requested data.

The present invention is a method for providing multi-pathing via Small Computer System Interface Input/Output (SCSI I/O) referral between an initiator and a storage cluster which are communicatively coupled via a network, the storage cluster including at least a first target device and a second target device. The method includes receiving an input/output (I/O) at the first target device from the initiator via the network. The I/O includes a data request. The method further includes transmitting a SCSI I/O referral list to the initiator when data included in the data request is not stored on the first target device, but is stored on the second target device. The referral list includes first and second port identifiers for identifying first and second ports of the second target device respectively. The first and second ports of the target device are identified as access ports for accessing the data requested in the data request.

Multi-pathing with SCSI I/O referrals

The present invention is a method for drive management and data placement in an archival storage system having a set of drives. The method includes mapping redundant data stripes onto the drives. A first active data stripe, located on a first subset of the drives, is then selected from the mapped data stripes. The first subset is placed into a normal power state and a second subset of the drives is placed into a low power state. Data is then written to the first active data stripe. Before the first active data stripe is fully used, the method includes selecting a next active/second active data stripe from the mapped data stripes, the second active data stripe being at least partially located on the second subset. The method may be performed by a system which implements MAID techniques for drive management and CRUSH for data placement.

Method for optimizing performance and power usage in an archival storage system by utilizing massive array of independent disks (MAID) techniques and controlled replication under scalable hashing (CRUSH)

A command is issued to a first data storage system for addressing a set of data and at least one of a first referral response including a referral to at least a second data storage system or at least a first subset of the set of data and the first referral response including the referral to the at least the second data storage system. The at least one of a first referral response is accessed. A command is issued to the second data storage system for addressing the set of data and a second referral response including a referral to at least one of the first data storage system and a third data storage system, the second data storage system including at least a second subset of the set of data. The second subset of the set of data and the second referral response including the referral to the at least one of the first data storage system or the third data storage system is accessed.

Growing community of inventors

Lafayette, CO, United States of America

Ross Zwisler