Lsi Logic Corporation

Lsi Corporation

Magnachip Semiconductor, Inc.

Rodney A DeKoning

William Patrick Delaney

Ray M Jantz

Dennis E Gates

William V Courtright, Ii

John R Kloeppner

Bret S Weber

Donald Roman Humlicek

Timothy E Hoglund

Charles D Binford

Keith W Holt

Thomas L Langford, Ii

Matthew A Markus

Scott E Greenfield

Robin Huber

Michael J Gallagher

A system for updating management entities or devices in a computer system network with configuration change information from the devices being managed. The management entities are configured to discover, monitor and configure managed devices, such as storage systems, connected to the network. Preferably, the managed devices include a comparator which can track changes made to the managed device configuration or properties and report that change back to the various management entities. In this way, the management entities can keep track of the configurations of the various devices that they manage, even though they might not be responsible for issuing the configuration change. This can be accomplished even when managed devices developed by different manufacturers according to different standards or protocols are involved.

Methods and apparatus for issuing updates to multiple management entities

A parity assist circuit that provides multiple XOR calculations using a scatter-gather list is disclosed. The parity assist circuit includes a control circuit that obtains a plurality of source operands in response to a scatter-gather list, and an XOR engine that provides a plurality of XOR products computed from the supplied source operands. Destination and length parameters in the scatter-gather list are used by the XOR engine to store the XOR computation product and to determine the length of the data in the source and destination blocks to be computed. Preferably, the parity assist circuit is part of a RAID controller that includes a processor and a cache memory. The parity assist circuit preferably utilizes the scatter-gather list to gather required source operands from a memory and to scatter multiple XOR products to the memory before sending an interrupt to the processor or receiving additional setup instructions from the processor, thereby providing rapid and efficient parity calculations and improving overall system performance of the RAID storage subsystem.

Disk array storage subsystem with parity assist circuit that uses scatter-gather list

In a storage area network having a host device and a consolidated storage array (CSA), one of the storage arrays of the CSA acts as a primary device of the CSA to form logical data volumes across one or more of the total storage arrays of the CSA. The logical data volumes typically have performance requirements that cannot be met by a single storage array. Upon receipt of a command from the host device to create one of the logical data volumes, the CSA primary device analyzes the storage arrays to determine a combination thereof, across which the logical data volume will be striped, that best satisfies the performance requirements. The CSA primary device configures these storage arrays to form the logical data volume and sends striping information, which defines the logical data volume, to the host device. Striping software based on the host device responds to the striping information to access the logical data volume. The CSA primary device also manages the storage arrays and the logical data volume by monitoring the storage arrays to determine whether any of the storage arrays is about to reach its saturation point, typically due to changing performance requirements of all of the logical data volumes on the storage arrays. The CSA primary device then migrates a portion of one of the logical data volumes from one storage array to another to balance the data transfer loads on the storage arrays.

Configuring and monitoring data volumes in a consolidated storage array using one storage array to configure the other storage arrays

This invention presents a method and system to emulate logging or journaling file systems by means of a snapshot mechanism. Use of the snapshot mechanism reduces the number of system bus calls during log or journal updates and recalls in case of file recovery. The snapshot mechanism is implemented in hardware to provide for speedy and reliable data transfers. Overall system performance thereby is improved with an average reduced number of calls to the system memory bus. The present invention offers a cost effective way of retrofitting existing file systems with a journaling or logging capability.

Method for the acceleration and simplification of file system logging techniques using storage device snapshots

A shared resource manager circuit for use in conjunction with multiple processors to manage allocation and deallocation of a shared resource. The shared resource manager allocates and deallocates software resources for utilization by the processors in response to allocation and deallocation requests by the processors. The shared resource manager may include a bus arbitrator as required in a particular application for interfacing with a system bus coupled to the processors to provide mutual exclusion in access to the shared resource manager among the multiple processors. The shared resource manager may manage a memory block (FIFO queue) with multiple resource control blocks. A system may advantageously apply a plurality of shared resource managers coupled to a plurality of processors via a common interface bus. Each shared resource manager device may then be associated with management of one particular shared resource.

Shared resource manager for multiprocessor computer system

A system for monitoring and managing devices on network comprising one or more managed devices connected to the network and storage means for storing a device management application program associated with each of the managed devices. The system further includes a management station which is in communication with each of the managed devices across the network, and the management station is in communication with the storage means. When a user wishes to monitor, configure, or manage one of the managed devices on the network, the user preferably selects the managed device to be managed and the management station retrieves from the storage means the device management application program associated with the selected managed device. By the management station processing the management application program for the selected managed device, the management station allows the user to monitor the status of the managed device, as well as change the configuration of and fix errors with the managed device.

Methods and apparatus for managing heterogeneous storage devices

Devices (e.g. &ldquo;servers&rdquo;) in a data storage system access data contained in logical volumes contained in a plurality of storage devices or storage arrays. The servers issue access requests through any available transfer path from the servers to the storage devices or storage arrays. I/O (input/output) devices control access between the servers and devices that control access to the data (e.g. &ldquo;array controllers&rdquo;), so that the access requests from the servers are uniformly routed to the preferred array controllers independently of the transfer paths through which the servers issue the access requests.

Uniform routing of storage access requests through redundant array controllers

An array controller of a data storage system initiates a test of another array controller of the data storage system to determine the operational condition of the controller under test (CUT) as well as an array of storage devices to which the CUT is connected and a network fabric over which the CUT receives commands from host devices of the data storage system. If the CUT or devices connected thereto are not functioning properly, the controller initiating the test can diagnose the problem. The controller initiating the test instructs the CUT to perform certain normal operating functions, e.g. data read and write functions, and checks whether the functions are completed correctly. Additionally, a loopback test checks the operation of the network fabric, and the read and write functions also check the operation of the storage devices.

Testing components of a computerized storage network system having a storage unit with multiple controllers

A mirrored data storage system utilizes a first host device and a local storage device for primary data storage and a second host device and a remote storage device for mirrored, fail-over storage on behalf of client devices. At periodic intervals (called checkpoints), the first host device initiates data synchronization between itself and the two storage devices and issues checkpoint information to ensure that each device maintains information for a common stable storage state. The local storage device synchronizes its stored data and forwards the checkpoint information to the remote storage device. The remote storage device maintains a copy (called a snapshot) of the data at the common stable storage state. Given the snapshot and the checkpoint information, the remote storage device can restore itself to the common stable storage state in the event of a failure of the first host device and/or the local storage device. Upon failure of the first host device and/or the local storage device, the second host device is instructed to initiate a switch, or fail-over, to serving as the primary data storage on behalf of the client devices.

Data storage with host-initiated synchronization and fail-over of remote mirror

In a storage environment or storage area network having multiple host devices and at least one storage array, the host devices access logical data volumes stored on the storage array through array controllers disposed in the storage array. Multiple host devices can request access to shared ones of the logical data volumes through multiple paths to multiple array controllers, but each logical data volume is controlled or owned by only one array controller at a time. Thus, ownership of shared logical data volumes is transferred between the array controllers as necessary on behalf of the requesting host devices. To prevent ownership transfers from occurring too often, however, ownership of the logical data volumes is made exclusive, or &ldquo;sticky,&rdquo; for a period of time after each transfer. During the exclusive ownership period of time, the ownership cannot be transferred. After expiration of the exclusive ownership period of time, ownership of the affected logical data volume is transferred if the transfer does not cause another host device to lose access to the same logical data volume, unless priorities between competing host devices permit one host device to take access away from the other host device.

Method and apparatus for handling transfers of data volumes between controllers in a storage environment having multiple paths to the data volumes

A system and method for dynamically generating the topology of a storage array network by linking information concerning hosts and clusters along with information about host port adapters. Namely, each host identifies itself to all controllers and provides information in a command that allows the controller to know which host and cluster, if applicable, is associated with the host port adapter through which the command was issued. In addition, the topology is automatically updated anytime there is a change on the network such as a new device was added or a host port adapter was replaced.

Method and system for determining and displaying the topology of a storage array network having multiple hosts and computer readable medium for generating the topology

A data structure contains sequence number metadata which identifies an input/output (I/O) operation such as a full stripe write on a redundant array of independent disks (RAID) mass storage system, and also contains revision number metadata which identifies a subsequent I/O operation such as a read modify write on only a fractional component of the entire user data. The sequence number and revision number metadata are used in an error detection and correction technique, along with parity metadata, to detect and correct silent errors arising from inadvertent data path and drive data corruption. An error to a portion of the stripe is detected by a difference in sequence numbers for all of the components of data. An error arising after an I/O operation is detected by a revision number which is different from the correct revision number. The errors in both cases are corrected by using the parity metadata for the entire collection of user data and the correct information from the other components of the user data and metadata, and applying this information to an error correcting algorithm. The technique may be executed in conjunction with a read I/O operation without incurring a substantial processing overhead penalty.

Data structures containing sequence and revision number metadata used in mass storage data integrity-assuring technique

In a storage system, such as a storage area network, a snapshot volume or one or more checkpoint volumes are formed from the same base volume using a single repository containing multiple images of data stored in the base volume. The first image is started with the formation of the snapshot volume or the first checkpoint volume and is filled with blocks of data copied from the base volume, thereby increasing in size within the repository, until the first image is stopped and the next image is started. The next image is then filled with blocks of data copied from the base volume until stopped. Thus, the blocks of data are copied only into the most recently created image within the repository. With the creation of each checkpoint volume, a new image is concurrently started in the same repository. Each checkpoint volume is dependent on the image that was created concurrently plus any images created thereafter.

Managing a snapshot volume or one or more checkpoint volumes with multiple point-in-time images in a single repository

A client machine ( ) is connected to a network medium ( ) for use in managing the operation of a plurality of subsystems ( ) that are also coupled to the network medium ( ). The client machine ( ) includes a cache memory ( ) for storing management-related objects that have been retrieved by the client machine ( ) from the individual subsystems ( ). When called upon to manage a particular subsystem, the client machine ( ) first determines which management related objects will be required to manage the subsystem. The client machine ( ) then checks the cache memory ( ) to determine whether any of the required objects are located therein before requesting the objects from the associated subsystem. In this manner, only objects that are not available locally are requested from the subsystem, thereby reducing management-related information traffic in the network ( ).

Method and apparatus for caching objects in a disparate management environment

A method of configuring a plurality of managed devices. The method preferably includes selecting a source managed device, obtaining a source configuration description from the source managed device, selecting one or more destination managed devices to be configured, issuing a configuration change command to each of the selected destination managed devices and applying the source configuration description selected from the source managed device to each of the selected destination managed devices. In addition, the method may further include the step of editing the source configuration description before issuing the configuration change commands to the one or more destination managed devices.

Growing community of inventors

Augusta, KS, United States of America

Rodney A DeKoning