Seagate Technology Incorporated

Hewlett-packard Development Company, L.p.

Compaq Computer Corporation, Inc.

Michael D Walker

Susan Gaye Elkington

Stephen J Sicola

Clark Edward Lubbers

James Edwin Pherson

Paul D Guttormson

Richard Franklin Lary

James Francis McCarty

Roger Oakey

Diana Shen

Randall L Hess

Randy L Roberson

David Peter DeCenzo

Robert S Gittins

Robert Charles Swindler, Jr

Jason Richard Huddleston

Method and apparatus for aligning addresses of resource sets in a memory space used by a software system. The resource sets are accessed by multiple layers of a software system and are each provided with a respective alignment requirement preferably comprising a power of two. A table preferably includes entries for each of the resource sets, and the table is sorted to provide a decreasing sequence beginning with the resource set having the greatest alignment requirement and ending with the resource set having the smallest alignment requirement. The resource sets are thereafter placed in the memory space in accordance with the decreasing sequence at localized addresses that align with the respective alignment requirements of the resource sets. Each resource within each resource set uses a localized, base address. The actual address within the memory space is preferably stored at a specified offset within a global structure.

Address aligned resource set allocation in a memory space

Method and apparatus for adaptive arrangement of data on storage media, such as in a multi-device storage array across which data are stored. A virtual hot space is formed to store frequently accessed data. The virtual hot space comprises at least one hot data zone which extends across storage media of a plurality of arrayed storage devices over a selected seek range less than an overall radial width of the media. The frequently accessed data are stored to the hot data zone(s) in response to a host level request, such as from a host level operating system (OS) or by a user which identifies the data as frequently accessed data. Alternatively or additionally, access statistics are accumulated and frequently accessed data are migrated to the hot data zone(s) in relation thereto. Lower accessed data sets are further preferably migrated from the hot data zone(s) to another location of the media.

Hot data zones

Method and apparatus for flushing cached writeback data to a storage array. Sets of writeback data are accumulated in a cache memory in an array with a view toward maintaining a substantially uniform distribution of the data across different locations of the storage array. The arrayed sets of data are thereafter transferred from the cache memory to the storage array substantially at a rate at which additional sets of writeback data are provided to the cache memory by a host. Each set of writeback data preferably comprises a plurality of contiguous data blocks, and are preferably written (flushed) to the storage in conjunction with the operation of a separate access command within a selected proximity range of the data with respect to the storage array. A stripe data descriptor (SDD) is preferably maintained for each set of writeback data in the array.

Dynamic adaptive flushing of cached data

Method and apparatus for managing the storage of data in a cache memory by placing pending read requests for sequential data in a dedicated read ahead stream control (RASC) data structure, and further configured for dynamically switching both ways, in response to data stored in the RASC, between speculative non-requested read ahead data streaming to read behind stream locking on the read requests in the RASC.

Read ahead storage control

Method and apparatus for allocating system resources for use by software processes in a computer-based system, such as a wide area network (WAN) comprising a data storage array. A first memory space provides a first bit indicator to indicate whether at least one system resource is available for use. A second memory space provides a second bit indicator to indicate whether a pending software process awaits availability of the system resource. The resource is allocated for use by the process in relation to a combinatorial operation upon the first and second bit indicators, preferably comprising a logical AND operation. The first and second memory spaces are preferably characterized as multi-bit registers. A free resource stack identifies available resources, and a process queue identifies pending processes waiting for released processes. The statuses of the respective stack and queue are reflected in the bits in the multi-bit registers.

Resource allocation in a computer-based system

A dual ported active-active array controller apparatus is provided having a first policy processor partnered with a first ISP having a first plurality of dedicated purpose FCs, a second policy processor partnered with a second ISP having a second plurality of dedicated purpose FCs, a communication bus interconnecting the ISPs, and programming instructions stored in memory and executed by the array controller to maintain the first policy processor in top level control of transaction requests from both the first plurality of FCs and the second plurality of FCs that are associated with network input/output (I/O) commands directed to a storage logical unit number (LUN) which the first ISP is a logical unit master of.

Processing wrong side I/O commands

Method and apparatus for wave flushing cached writeback data to a storage array. A cache manager operates to initiate a wave flushing operation whereby sets of writeback data in a cache memory are sequentially written to each of a plurality of logical groups radially concentric with respect to the storage medium. During the wave flushing operation, a write transducer is radially advanced across the medium in a single radial direction across boundaries between immediately adjacent groups. The write operations thus form a traveling wave across the medium, analogous to a wave in a sports stadium formed by spectators standing up and sitting down in turn. Each logical group preferably corresponds to a selected transducer seek range, such as an associated RAID stripe. Seeks are preferably bi-directional within each group, and uni-directional between adjacent groups. A dwell time (service time interval) for each group can be constant, or adaptively adjusted.

Wave flushing of cached writeback data to a storage array

Method and apparatus for caching and retaining non-requested speculative data from a storage array in an effort to accommodate future requests for such data. A cache manager stores requested readback data from the storage array to a cache memory, and selectively transfers speculative non-requested readback data to the cache memory in relation to a time parameter and a locality parameter associated with a data structure of which the requested readback data forms a part. The locality parameter preferably comprises a stream count as an incremented count of consecutive read requests for a contiguous data range of the storage array, and the time parameter preferably indicates a time range over which said read requests have been issued. The speculative readback data are transferred when both said parameters fall within a selected threshold range. The data structure preferably comprises a RAID stripe on a selected storage device of the array.

Predicting accesses to non-requested data

A method of managing critical resource usage comprises monitoring queue depth in at least one critical resource queue for a high level of resource consumption and preventing subsequent commands of a client/server combination in response to a command that increases resource consumption to the high level. The method further comprises queuing an identifier of the client/server combination on a waiting queue, removing the client/server combination identifier from the waiting queue in queuing order as resource consumption declines, and enabling commands of the client/server combination.

Resource management system

Method and apparatus for caching readback data in a cache memory. Upon a transfer of cached readback data to a host device, a cache manager operates to force a retention of the readback data in the cache memory in relation to a time parameter and a locality parameter associated with said data. In this way, the readback data are either retained in hopes of satisfying a subsequent cache hit, or not retained to accommodate subsequently cached data. Preferably, the cache manager compares the time parameter to a time threshold and the locality parameter to a locality threshold, and forces said retention of the readback data if both said thresholds are met. The readback data is preferably associated with a data structure such as a RAID stripe, the time parameter preferably indicates elapsed time since last access to the structure and the locality parameter preferably indicates accesses to the structure.

2D dynamic adaptive data caching

A format is provided for a command signal from a target device comprising a bit field adapted for communicating a unit attention signal from the target device following a status changing event. A method is provided for managing a unit attention signal from a target device in a distributed network, comprising: setting an indicator bit in a bit field of a command signal from the target device to a signaling value when a predetermined condition warrants an associated unit attention signal; detecting the indicator bit; and indexing a table in relation to the indicator bit to send the unit attention signal.

Managing multiple unit attentions

Method and apparatus for logging and analyzing event flows associated with execution of a service request in a software system, such as a computer-based system comprising a multi-disc data storage array. Execution of the service request results in a plurality of events carried out by multiple layers of the software system. A global event log accumulates a corresponding plurality of entries which associates each of the events carried out by the multiple layers. An event trace facility preferably accesses the global event log to provide a sequence of the entries corresponding to the service request, such as in a tree structure or time sequence order displayed by a graphical user interface. A log manager preferably controls operation of the global event log. Entries in the global event log are preferably entered sequentially for each ongoing process, and each entry preferably includes an identifier that identifies the associated service request.

Event logging and analysis in a software system

A data storage system is provided with a pair of controllers and circuitry configured for failing back from a single active write back mode to a dual active write back mode by copying cached data directly from a cache of a survivor controller of the pair of controllers to a cache of the other controller. A method is provided for failing over from a dual active mode of first and second controllers to a single active mode of the first controller by relying on previously mirrored cache data by the second controller; reinitializing the second controller; and failing back to the dual active mode by copying cached data directly from the first controller to the second controller.

Failover and failback of write cache data in dual active controllers

A method for implementing security management in a storage area network by controlling access to network resources. Initially, a resource provider communicates with potential resource users, such as host computers, servers, and workstations, to allow the users to discover the resources available on the storage area network. Resource users that have not previously logged in to a particular resource supply identification information to the resource provider, which places the information in a 'not yet approved entity' table. The 'not yet approved entity' table is made available to a management station. An administrator, using the management station, then determines whether to authorize use of resources. If access to the requested resource is allowed, the resource user identification information is stored in an &#x2018;approved entity&#x2019; table. A login is then allowed by the resource user to the selected resource. Once a resource user has initially logged in, connection information is maintained in the &#x2018;approved entity&#x2019; table facilitating subsequent log-in attempts by the resource user.

File security management

A disaster-tolerant data backup and remote copy system which is implemented as a controller-based replication of one or more LUNs (logical units) between two remotely separated pairs of array controllers connected by redundant links. In the situation wherein an array controller fails during an asynchronous copy operation, the partner array controller uses a 'micro log' stored in mirrored cache memory to recover transactions, in order, which were 'missed' by the backup storage array when the array controller failure occurred.

Growing community of inventors

Colorado Springs, CO, United States of America

Michael D Walker