International Business Machines Corporation

Other

Oded Cohn

Yoram Novick

William Frank Micka

Kenneth M Nagin

Alexander Winokur

Michael Howard Hartung

Claus William Mikkelsen

Alex Winokur

Efraim Zeidner

Kenneth Nagin

Michael Rodeh

John N McCauley, Jr

Jaishankar Moothedath Menon

James T Brady

Norman Ken Ouchi

John Norbert McCauley

Yosef Moatti

Dafna Sheinwald

Joe-Ming Cheng

Eliezer Dekel

James W Eldridge

Danit Segev

Richard Lewis Mattson

Shmuel Gal

Nimrod Rotics

Udi N Rotics

Yona Hollander

Efaim Zeidner

A cache control system is disclosed for use with data storage apparatus having a movably mounted storage element, such as a magnetic or optical disk and solid-state cache memory, in which the storage element is not at operating speed when data access has not occurred during a predetermined time period, comprising means arranged to access data stored on the storage element if a read or write request cannot be satisfied via access to the cache memory and a cache replacement mechanism for transferring data between the cache memory and the storage element to maintain consistency of data therebetween. The system is characterized in that the cache replacement mechanism performs data transfers between the cache memory and the storage element only while the storage element is at operating speed after a read or write request has given rise to an access to the storage element.

Cache control system

A method and system are disclosed for enhanced efficiency of backup copying of designated datasets stored within a plurality of storage devices coupled to the data processing system via a storage subsystem control unit having subsystem memory therein. Application execution within the data processing system is temporarily suspended long enough to form a dataset logical-to-physical system address concordance to be utilized to administer copying of the designated dataset. Thereafter, application initiated updates to uncopied portions of the designated datasets are temporarily deferred until sidefiles of the affected portions of the designated datasets are written to subsystem memory. The updates are then written to the storage subsystem. Portions of the designated datasets are then accessed and copied from the storage subsystem on a scheduled or opportunistic basis utilizing selected data retrieval command sequences. A sidefile status query is appended to selected data retrieval command sequences and the presence of data within the subsystem memory is determined without the necessity of additional communications between the data processing system and the storage subsystem. The sidefiles are then accessed and copied. Copied portions of the designated datasets and sidefiles are then copied to alternate storage locations in a backup copy order defined by the address concordance.

Method and system for sidefile status polling in a time zero backup copy process

A log-structured array (LSA) includes a relatively large, non-volatile cache memory as well as a memory segment write buffer. The LSA cache memory contains both updated logical tracks received from the host system and also clean logical tracks read from direct access storage devices of the array. When the fraction of updated tracks in the cache memory exceeds a threshold value, updated tracks are moved from the LSA cache memory to the memory segment. With each modified track to be moved, adjacent modified tracks also are moved. The updated tracks are moved regardless of their location in the updated LRU list. Clean tracks in the LSA cache memory are moved into the memory segment as well, when additional clean tracks are needed in the cache memory. The clean tracks are selected from the bottom of the LSA cache clean track LRU list. Checking for adjacency also can occur at garbage collection time, performed in a background mode. The criterion for determining logical adjacency can use information from the host computer and can be changed dynamically to optimize performance.

Log-structured disk array with garbage collection regrouping of tracks

A data storage disk device for a RAID disk array is disclosed, comprising a rotatably mounted disk having a data storage surface; a first head for reading data from and writing data to the data storage surface; with a second head for reading data from the data storage surface; and control means for executing a write operation to a sector, said write operation including reading the contents of the sector via the second head for subsequent processing and writing new data to the sector via the first head, the first and second heads being arranged with respect to the data storage surface so that the new data can be written to the sector on the same revolution of the disk as the reading operation. The addition of a second head to the disk storage device improves performance of the disk device for RAID applications.

Data storage apparatus for disk array

A method for operating a data storage system that is comprised of at least one disk. The method includes a step of partitioning a data compression unit into n basic compression units, where n is greater than one. Each data compression unit is comprised of a plurality of disk sectors and each of n basic compression units begins with a different initial sector. A next step partitions the data compression unit into X intervals, where X is less than n. Each of the X intervals begins with a different initial sector and within one of the n basic compression units. Further steps of the method include storing, external to the at least one disk, a plurality of first pointers each of which points to the initial sector of one of the n basic compression units wherein the 1/X, 2/X, . . . , (X-1)/X intervals begin; storing, within each of the initial sectors of the individual ones of the n basic compression units wherein the 1/X, 2/X, . . . , (X-1)/X intervals begin, a second pointer to the initial sector of the interval that begins within the basic compression unit; and, in response to a disk read operation that reads a compressed data unit that begins with one of the sectors that is located within one of the X intervals, accessing the beginning sector of the compressed data unit in accordance with one of the first pointers and one of the second pointers. The step of allocating includes a step of determining an actual compression ratio for the record, determining a value of a longest run of identical characters within the record, and adjusting the actual compression ratio based on the value of the longest run of identical characters. The step of allocating also includes a step of adding at least one additional sector to the estimated number to enable the compressed record to be subsequently updated in place.

System for storing pointers to initial sectors of variable length n

A method and apparatus for improving storage controller throughput and reducing unit control block contention when selecting a Utility Volume for servicing non-specific read requests. Throughput is increased by enabling the storage controller to service non-specific read requests issued against a Utility Volume which is not the same as the device associated with the data that the non-specific read is requesting. The Utility Volume is dynamically selected by considering the current loads on the available devices for both specific and non-specific processing. A Penalty Index is assigned to each volume, wherein the Penalty Index is a weighted average of the specific and non-specific processing. The device having the lowest Penalty Index is selected as the Utility Volume for a session. A Penalty Index evaluation is made at a Reference Point which is further enabled by a random clock to ensure that sessions do not likely pick the same Utility Volume.

Method for optimal retrieval of non-volume-specific data

A backup method for a computer database system comprising maintaining a mirrored copy of the database at a remote location is characterized in that updates to the remote database data are delayed for a delay time greater than or equal to the upper limit on the data communication delay between the local location and the remote location and updates to a remote log for the database are executed after corresponding updates to a local log without said delay. In this way a consistent copy of the database may be recovered from the mirrored copy of the database and the remote log after destruction of the database system.

System and method for providing a backup copy of a database

A method and apparatus for improving storage controller throughput when servicing non-specific read requests. Throughput is increased by enabling the storage controller to service non-specific read requests issued against a device address which is not the same as the device address associated with the data that the non-specific read is requesting. The device address associated with the data is thus free to be used for another I/O operation. When the device address used by the non-specific read is a non-busy type (that is, the device and/or data is not locked) then the throughput improvement is obtained by increasing the number of data requests that may be concurrently handled by the storage controller.

Locking a non-busy device for accessing a data record stored on another

A computer implemented method for speeding up the recursive most significant digit radix sorting of a set of record keys in which the keys are scanned for a shared or common prefix, coded according to the point in the key where they differ and the value of the differing digit, and processed such that during each dispersion phase the code words are used to speed processing by avoiding comparison matching of the prefixes, the recursive dispersion and collection phases continuing until singletons are reached. In the absence of shared prefixes the keys are normally recursively radix sorted.

Radix sorting method and means for minimizing movement of elements

A data backup copying session on a data processing system is secured responsive to initiation of the data backup session by an application executing on a processing unit by generating a unique identifier for the data backup session. Thereafter, all member paths of a group of paths designated by the processing unit for communication between itself and the first storage subsystem are identified and associated with the data backup session. Access to the session is thereafter allowed only along a member path of the group of paths associated with the data backup session. The system and method of the invention further provide for fault recovery and protection against excessive demand on storage control unit memory.

Method and system for time zero backup session security

A method and system for efficiently accessing desired datasets among multiple datasets which are stored at specific data addresses within multiple storage subsystems which are coupled to a host system via a storage subsystem controller and a data channel. A data request is transmitted from the host system to the storage subsystems via the data channel. The data request specifies non-address attributes for desired datasets, such as boundary addresses for large data extents including many datasets or a request for all datasets modified since the occurrence of a specified event. The data request is then processed at the storage subsystem controller to determine a data address for each dataset within the storage subsystem which possess the desired attributes. Thereafter, the desired datasets are transmitted via the data channel to the host system in association with a specific address for each dataset. A selected status message is transmitted from the storage subsystem controller when no more datasets are located which possess the desired attributes. In this manner, the retrieval of data from a storage subsystem is greatly enhanced.

Method and system for non-specific address data retrieval in a data

A method and system are disclosed for permitting high concurrency of access during backup copying of designated data stored within a storage subsystem which includes multiple storage devices coupled to the data processing system via a storage subsystem control unit having subsystem memory therein. Data within each storage device is accessed utilizing a Unique Control Block (UCB), which identifies a selected storage device, and an associated data retrieval command sequence which identifies the data to be accessed. Portions of the data copied to subsystem memory within the subsystem storage control unit as sidefiles from a first storage device may be accessed utilizing a Unique Control Block (UCB) associated with an alternate storage device by associating a selected data retrieval command sequence therewith which identifies the data as stored within the subsystem memory. In this manner, data from a first storage device may be accessed utilizing an alternate Unique Control Block (UCB), permitting concurrent access of data utilizing the Unique Control Block (UCB) associated with the first storage device.

Growing community of inventors

Haifa, Israel

Oded Cohn