Storage Technology Corporation

Other

Jay S Belsan

George A Rudeseal

Charles Allen Milligan

John Timothy O'Brien

Henry S Ludlam

Mogens H Pedersen

Michael Steven Milillo

Robert F Walsh

Patrick James Tomsula

Robert J Raicer

Charles Patrick Schafer

Jeffrey Steven Laughlin

Alan R Permut

John F Kitchen

Barbara L Steele

Bruce A Mork

Robert C Lynn

The present data file storage management system for snapshot copy operations maintains a two level mapping table which enables the data files to be copied using the snapshot copy process and only having to update a single corresponding mapping table entry when the physical location of the data file is changed. The snapshot copy updates to the contents of the first level of the two level mapping table are stored on the backend data storage devices to provide a record of the snapshot copy operation which can be used to recover the correct contents of the mapping table. This record of the snapshot copy operations remains valid even though the physical location of a copied data file instance is subsequently changed. Furthermore, the physical storage space holding the updated portions of the first level of the two level mapping table can be managed using techniques like those used to manage the physical storage space holding data file instances. Mapping table updates resulting from the snapshot copy operation are delayed until all mapping table updates resulting from earlier data file write operations have been completed and any attempt to update the mapping table to reflect data written to the original data file or the copy data file that occurs after initiation of the copy must wait until the first set of mapping table pointers have been copied.

Data file storage management system for snapshot copy operations

One or more background processes that references data storage volumes and cylinders that are to be scrubbed to ensure the integrity of the data stored thereon. A priority scrubbing process is also available to note data storage volumes that have recently had data written thereon by the host processor and which require a more timely review of the data than less frequently used volumes.

Disk scrubbing system

A data storage subsystem dynamically maps a virtual data storage device image presented to associated processors to physical data storage devices used to implement the data storage subsystem. Multiple destage memory elements are concurrently active to increase an aggregate destage data transfer rate and to allow data to be stored on various memory elements appropriate to the type of data contained in each stored virtual object. An open logical cylinder list is used to maintain data integrity among multiple open destage memory elements. Memory elements are also selected to function as archive memory. The data storage subsystem includes a plurality of data storage elements configured into at least two redundancy groups, each redundancy group including n+m of the data storage elements, and a cache memory connected to the redundancy groups and a host processor interface. The data storage subsystem stores data indicative of the amount of available memory space on each of the open logical cylinders and little used data records are migrated or transferred from other memory elements to the archive memory elements to maintain sufficient available memory space.

Dynamically mapped data storage subsystem having multiple open destage

The data storage subsystem is implemented using an array of data storage elements which vary in data storage characteristics and/or data storage capacity. Control apparatus automatically compensates for any nonuniformity among the data storage elements by selecting a set of physical characteristics that define a common data storage element format. The selected set of physical characteristics may not match any of the disk drives but each disk drive can emulate these selected characteristics. This capability enables the disk drives in the data storage subsystem to be replaced by nonidentical disk drives in a nondisruptive manner to provide continuous data availability.

Disk drive array memory system using nonuniform disk drives

The disk drive array data storage subsystem maps between virtual and physical data storage devices and schedules the writing of data to these devices. The data storage subsystem functions as a conventional large form factor disk drive memory, using an array of redundancy groups, each containing N+M disk drives. This system copies data records by simply creating a duplicate data record pointer in a virtual track directory to reference the original data record. This enables the host processor to access the data record via two virtual addresses while only a single physical copy of the data record resides in the data storage subsystem.

Data record copy system for a disk drive array data storage subsystem

This file server system appears to the host computer to be a plurality of data storage devices which are directly addressable by the host computer using the native data management and access structures of the host computer. The file server however is an intelligent data storage subsystem that defines, manages and accesses synchronized sets of data and maintains these synchronized sets of data external from the host computer system's data management facilities in a manner that is completely transparent to the host computer. This is accomplished by the use of the snapshot application data group that extends the traditional sequential data set processing concept of generation data groups.

File server having snapshot application data groups

The disk drive array data storage subsystem maps between virtual and physical data storage devices and schedules the writing of data to these devices. The data storage subsystem functions as a conventional large form factor disk drive memory, using a plurality of redundancy groups, each containing N+M disk drives. A performance improvement is obtained by eliminating the disk formatting delays found in the prior art. In order to accommodate the need to format virtual volumes to be compatible with the form and format of the data records to be transmitted by the host processor, the present disk drive array memory system stores format information in a virtual track directory which controls the mapping of the virtual cylinders defined by the host processor into the physical elements of the disk drive array. Therefore, not only the cylinders are mapped from virtual to physical but the format of these cylinders is also mapped from the virtual format defined by the host processor to the physical configuration used by the disk drive array memory. The disk drive array memory system does not physically format the cylinders and tracks of the disk drives contained therein in response to a format command from the host processor but simply emulates this operation by writing the format data into the virtual track directory.

Disk drive array memory system having instant format capability

The data record copy apparatus for a virtual memory system instantaneously makes a copy of a selected data record by simply generating a new set of pointers to reference the same physical memory location as the original reference pointer. All the pointers referencing the same physical memory space are stored in the virtual memory mapping tables to record all the virtual addresses of the data record. When the original data record is staged to an associated cache memory or a copy of the data record is in cache memory, the consistency of the data record is maintained by loading all the virtual addresses of the data record from the mapping tables to the hash table and collision list of the cache memory. Thus, any access of one of these virtual addresses will result in the virtual memory system locating the single data record instance in cache memory. If an associated host processor attempts to update the data record at one of these virtual addresses, the virtual memory system copies the data record to a new cache memory location so that a unique instance of the data record is available for update while the remaining virtual addresses still point to the original data record in cache memory.

Method and apparatus to access data records in a cache memory by

The interprocess message queue operates in a multiprocessing environment to ensure that interprocess messages sent from an originating task do not overflow the destination task resource pipe. To prevent message overflow, the destination task creates a message queue when a communication session is originated and populates this message queue with n message reserved for the originating task. Each time the originating task wishes to send a message to the destination task, the originating task first retrieves one of the reserved messages from the destination task message queue. Once the message is retrieved from the message queue, the originating task is assured that memory space is available in the resource pipe to send a message. When the destination task receives the message, the destination task reads the message and flags the message as old, thereby allowing another message to be sent, since the originating task can now remove this old message from the message queue to make room for a new message. In this way, the destination task resource pipe never overflows.

Interprocess message queue

The multiple step data read apparatus provides a buffer memory (108-0) for each read/write head (110-0) in the rotating media (111-0) data storage system that can store up to the entire track (400) of data that includes the requested data (Sectors 2-6). The data is fragmented such that the data transferred into the read/write head buffer first is transmitted to the control unit first whether or not that data is at the beginning of the data requested by the control unit. The data is further fragmented such that critical portions of the data are available to the control unit to satisfy the host request as soon as the data is read from the device. This fragmenting results in the data becoming available to the control unit in the minimum time possible and the performance of the subsystem being the maximum possible. In addition each data fragment transfer to the control unit (104) is initiated a predetermined time before the end of the fragment of data such that the read/write head (110-0) reaches the end of the fragment the same time that the last sector of the fragment is transmitted to the control unit (104).

System for retrieval of a data record by buffering the record in

This apparatus makes use of a disk drive array to store data records for an associated host processor. This disk drive array emulates the operation of a large form factor disk drive by using a plurality of interconnected small form factor disk drives. These small form factor disk drives are configured into redundancy groups, each of which contains n+m disk drives for storing data records and redundancy information thereon. The use of this configuration is significantly more reliable than a large form factor disk drive. However, in order to maintain compatibility with host processors that request the duplex copy group feature, the phantom duplex copy group apparatus of the present invention mimics the creation of a duplex copy group in this dynamically mapped data storage subsystem using a disk array and a phantom set of pointers that mimic the data storage devices on which the data records are stored.

Phantom duplex copy group apparatus for a disk drive array data storge

The parallel disk drive array data storage subsystem dynamically maps between virtual and physical data storage devices and schedules the writing of data to these devices. The data storage subsystem functions as a conventional large form factor disk drive memory, using an array of redundancy groups, each containing N+M disk drives. The data storage subsystem does not modify data stored in a redundancy group but simply writes the modified data as a new record in available memory space on another redundancy group. The original data is flagged as obsolete. A mapping table is maintained to identify portions of these redundancy groups which contain newly written or modified virtual track instances. These marked virtual track instances are written to backup medium as a background process and the mapping table is updated to clear the flags that identify these virtual track instances as having been modified.

Incremental disk backup system for a dynamically mapped data storage

The deleted dataset space release system provides facilities in a dynamically mapped virtual memory data storage subsystem to immediately release the physical space occupied by a deleted dataset for use by the data storage subsystem to store subsequently received data files. This system also provides data security by preventing the unauthorized access to the data of scratched data files, both in cache memory and on the data storage devices. The deleted dataset space release system utilizes a user exit in the host processor data file scratch routine to transmit information to the data storage subsystem indicative of the host processor data file scratch activity. Existing channel command words are used in a manner that is transparent to the host processor. The data storage subsystem thereby immediately receives an indication that the host processor is scratching a data file from the volume table of contents of a virtual volume. The data storage subsystem can then concurrently scratch this data file from the virtual track directory contained in the data storage subsystem and thereby release the physical storage space occupied by this scratched data file.

Deleted data file space release system for a dynamically mapped virtual

The disk drive array data storage subsystem functions as a conventional large form factor disk drive memory, using an array of redundancy groups, each containing N+M disk drives. The data storage subsystem does not modify data stored in a redundancy group but simply writes the modified data as a new record in available memory space on another redundancy group. The original data is flagged as obsolete. Virtual tracks that are least used are migrated as part of a free space collection process to low access cylinders, which are, in turn, migrated to secondary media, such as magnetic tape. The migration process is either periodic or demand driven to automatically archive little used data records.

Multilevel, hierarchical, dynamically mapped data storage subsystem

A method and apparatus for effecting a transfer of data between different areas of a memory. Memory reading circuitry and memory writing circuitry are both connected to loopback switching apparatus. The loopback switching apparatus is controllably operable to interconnect the read circuitry with the write circuitry. This permits the data read out of a first memory area to be extended to the write circuitry for entry into a second memory area.

Growing community of inventors

Nederland, CO, United States of America

Jay S Belsan