Hewlett-packard Development Company, L.P.

Robert Alan Cochran

Marcel Duvekot

David A Robinson

David E Oseto

Ayman Abouelwafa

Joseph Algieri

Titus E Davis

Harald Burose

Woodson B Long

Matthias Popp

Mathias Popp

The Thanh Phan

Erik A Lipps

Richard S Wilkins

Jay Schultz

An exemplary storage network and methods of operation are disclosed. The exemplary storage network comprises a plurality of storage cells. At least one storage cell comprises physical storage media and a storage media controller that controls data transfer operations with the storage media. The exemplary storage network further comprises a plurality of host computers configurable to execute write operations to at least one storage cell, at least one write control server that regulates the write operations of one or more host computers, and a communication network that provides communication connections between the storage cells, the host computers, and the write control server. In exemplary methods of operation the write control server regulates write access by the host computers. In another exemplary method of operation the write control server broadcasts a write failure signal to one or more host computers in the network.

Write operation control in storage networks

A data synchronization method (for a redundant data storage arrangement in which there are at least a primary storage entity and mirroring first and second remote storage entities in communication therewith, respectively, writes to the first and second remote storage entities being tracked via respective first and second sidefiles, the first and second storage entities having different levels of write-currency relative to each other) may include: comparing the first sidefile with the second sidefile; and updating writes stored at the second remote storage entity based upon the comparison of the first and second sidefiles.

Data synchronization for two data mirrors with sidefiles

A mirroring device includes an interface capable of coupling a primary storage array and a secondary storage array to a network. The interface further includes a logic that monitors traffic for a network packet destined for the primary storage array and selectively identifies a storage array write operation and associated data in the network packet, constructs a network packet targeted to the secondary storage array, and transmits the packet to the primary storage array and the secondary storage array.

Mirroring storage interface

An apparatus and communication method that provide for communicating information on a standardized link compliant with a published standard and communicating information on a private link capable of operation at a throughput higher than maximum throughput of the published standard. The apparatus and method further provide for monitoring private link performance and increasing information throughput on the private link above the maximum standard throughput by an amount determined by the monitored private link performance.

Link throughput enhancer

Embodiments include methods, apparatus, and systems for enabling and disabling cache in storage systems. One embodiment includes a method that changes a time period for delaying host requests received at a cache of a storage device and converts the storage device from a cache enabled state to a cache disabled state while the storage device is online.

Enabling and disabling cache in storage systems

Embodiments include methods, apparatus, and systems for replication in storage systems. One embodiment includes a method that uses a target port on a storage array to function as an initiator port on a host in a storage area network (SAN). The target port discovers storage arrays in the SAN and mimics an initiator port to transmit input/output (I/O) requests.

Replication in storage systems using a target port mimicking a host initiator port

In one embodiment, a storage controller comprises a first I/O port that provides an interface to a host computer, a second I/O port that provides an interface to a storage device, a processor that receives I/O requests generated by the host computer and, in response to the I/O requests, generates and transmits I/O requests to the storage device, and a memory module communicatively connected to the processor. The memory module comprises logic instructions which, when executed by the processor, configure the processor to collect performance data and availability data for a plurality of logical devices (LDEVS) managed by the storage controller, and present the performance data and availability data to a reporting interface.

Intelligent logical unit provisioning

Various method and system embodiments of the present invention employ enhanced journal-based resynchronization for resynchronization of a primary volume to a remote secondary volume following restoration of a communications link or another event. Enhanced journal-based resynchronization involves maintaining a filled journal after the primary component system has resorted to bitmap-based journaling. Following communications-link restoration, or another event, enhanced resynchronization analyzes various values maintained by the primary component system to characterize the journaling state in order to determine whether or not to first merge the filled journal with the track-based bitmap before carrying out bit-map-based resynchronization, or to instead unspool the filled journal and transmit the unspooled WRITE requests to the second component system prior to separately carrying out bit-map-based resynchronization.

Method and system for efficient journal-based resynchronization

A storage system including journaling comprises a controller capable of coupling to at least one storage device and to at least one journaling device, and a process executable on the controller. The executable process comprises a resolve utility capable of determining logical unit, track, and sector identification for a selected file on the at least one storage device, a user interface enabling a user to select tracks and sectors on the at least one storage device for restoration to a predetermined point in time, and a restoration utility. The restoration utility accesses data corresponding to the selected tracks and sectors from the journaling device and restores the data to the track and sector locations of the storage device to the predetermined point in time.

Storage system with journaling

A storage system comprises an interface capable of interconnecting a network infrastructure via a plurality of communication links. The plurality of communication links has a diversity of data-carrying capacity and performance. The storage system further comprises a controller coupled to the interface that assigns the plurality of communication links into at least one link affinity group based on performance criteria and controls link selection based on link affinity group assignment.

Storage system with link selection control

Described herein are exemplary storage network architectures and methods for block size allocation in copy operations. A copy operation from a first storage cell to a second storage cell is initiated. The copy operation initially utilizes a first write block size. The write block size is changed to utilize a second write block size, different from the first write block size, and a performance parameter is measured at the second write block size. The second write block size is maintained if the performance parameter exceeds a threshold.

Block size allocation in copy operations

A disk array having an internal mirror architecture may include: a plurality of disk drives configured to provide a primary logical storage device (LDEV), a first instance of an internally-mirroring secondary LDEV and a second instance of an internally-mirroring secondary LDEV.

Internal disk array mirror architecture

A storage system with primary mirror shadow comprises a storage array, and a controller. The controller is capable of predefining storage array volumes as a primary volume that is subsequently paired with a secondary volume, emulating a primary logical device and a plurality of secondary logical devices including a shadow logical device, tracking volumes and logical devices using a pointer, and instantaneously evoking a volume copy by a pointer exchange.

Storage system with primary mirror shadow

On a dominant logical unit provided by a mass-storage device, hot spare disks are employed to create a much larger, disk-based time-ordered WRITE-request buffer that spans, in one embodiment, both electronic memory and hot spare disks. The much larger time-ordered WRITE-request buffer in the modified dominant logical unit allows for storing WRITE requests in time order for a much longer period of time during communications failure between the dominant logical unit and remote-mirror logical unit than in the current techniques that employ only an electronic-memory-based time-ordered WRITE-request buffer. On the remote-mirror logical unit, mass-storage space is provided for an alternate logical unit that can be resynchronized with the dominant logical unit following restoration of communications between the dominant logical unit and remote-mirror logical unit. When resynchronization is complete, a simple logical-unit-pointer switch operation can be employed to designate the alternate logical unit as the new remote-mirror logical unit, and the previous remote-mirror logical unit as the alternate logical unit.

Method and system for reliable remote-mirror resynchronization in disk arrays and other mass storage devices

A database system is capable of executing a database application that transfers a logical object in multiple fragments. The database system comprises a main storage site, a remote storage site, a main protocol executable on the main storage site, and a remote protocol executable on the remote storage site. The remote storage site is capable of linking to the main storage site and mirroring information stored in the main storage site. The remote storage site includes a storage and a cache sidefile divided into a plurality of array sidefile recordsets. The main protocol is capable of including information indicative of logical object fragment commencement and completion in the multiple fragment database application transfer. The remote protocol is capable of controlling the cache sidefile to cache the multiple fragments as received and to enable destaging of the logical object to the storage on receipt of all fragments.

Growing community of inventors

Sacramento, CA, United States of America

Robert Alan Cochran