Abstract: A customizable cache discard policy is provided which reduces adverse consequences of conventional discard policies. In a data processing system, a cache controller invokes a cache data discard policy as the cache approaches its capacity. Using one possible policy, data having the shortest retrieval (fetch) time is discarded before data having longer retrieval times. In an alternative policy, data may be discarded based upon its source. Weightings may be applied based upon the distance from each source to the cache, may be based upon priorities assigned to each source, or may be based upon the type of each source.

Abstract: A high density storage enclosure houses first and second pluralities of hard disk drives (HDDs). The enclosure may be partitioned into a plurality of virtual enclosures, the first plurality of HDDs being associated with a first virtual enclosure and the second plurality of HDDs being associated with a second virtual enclosure. In the event of a failure within one of the virtual enclosures, an SES in the failed virtual enclosure is isolated from the rest of the virtual enclosure. Then, an inter-enclosure link may be enabled between the failed virtual enclosure and another virtual enclosure. The isolated SES processor may then be accessed to obtain data associated with the failure and to execute commands associated with a recovery process.

Abstract: A storage system includes a RAID adapter, disk array switches, sub-processors, and hard disk drives. A disk-related operation is initiated in the RAID adapter which dispatches a command to a disk array processor (or sub-processor) in an enclosure for the processor to perform the operation on one or more drives. The adapter may dispatch the command to a processor in a single enclosure through a disk array switch or to processors in multiple enclosures through switches in upstream enclosures. The adapter is then free to perform other functions. The processor commences the specified operation on one or more selected drives. Upon completion of the operation, the results are transmitted by the processor and received by the adapter. Offloading the task to the distributed sub-processors reduces the burden on the RAID adapter, reduces system bandwidth usage, and enables access to other drives to be maintained.

Abstract: In an automated library, data cartridges, such as magnetic tape cartridges, are stored in storage cells and accessed by data storage drives. An accessor with a gripper transports cartridges between storage cells and storage drives. Cartridges are prioritized according to their relative importance. A processor manages the placement of the cartridges in cells by having higher priority cartridges stored closer to the front of multi-cartridge cells than cartridges with a lower priority. Cartridges with a higher priority may also be stored closer to a storage drive than cartridges with a lower priority. A pusher may be used to push cartridges towards the front of multi-cartridge cells with an empty position to enable the gripper to reach the front cartridge.

Abstract: A high density storage enclosure houses first and second pluralities of hard disk drives (HDDs). The enclosure may be partitioned into a plurality of virtual enclosures, the first plurality of HDDs being associated with a first virtual enclosure and the second plurality of HDDs being associated with a second virtual enclosure. Configuration of the storage enclosure is performed by an SES processor in the storage enclosure accessing configuration parameters received from an external configuration unit coupled to the storage enclosure. The virtual enclosures may be configured as two (or more) independent virtual enclosures on two (or more) independent fabrics or may be configured in a trunked manner. Power supplies and cooling blowers in the storage enclosure may also be partitioned and assigned to be managed by SES processors in the virtual enclosures.

Abstract: Policy based data shredding is provided to be executed in a storage controller. A logical volume stored on media, such as magnetic disk drives, may be assigned one or more possible shredding policies. Storing and executing the policies in the controller is more efficient than performing host-based shredding and requires the use of less valuable bandwidth between the host and the controller. In addition, the controller is aware of failures, degradation and offline status of each drive in an array, and is able to thereby terminate or modify a shredding operation if necessary. Each policy includes the number of write passes to be performed on the media location in which the volume is stored and the pattern to write on the media location. The policy may also indicate whether to update a parity area during each of a plurality of write passes or only on the first.

Abstract: An automated data storage library accesses data stored on storage media contained in cartridges in response to commands from an external host. The cartridges include cartridge memory and a component in the library includes a cartridge memory interface for reading data from and/or writing data to the cartridge memory. When a cartridge is to be stored in the library, the library modifies the contents of the cartridge memory such that the data stored on the cartridge becomes inaccessible, thereby preventing access to the data outside of the library. To perform an authorized access, the library restores the contents of the cartridge memory or provides a correction or correction algorithm to allow access to the data without removing the access protection of the storage media. The cartridge memory may also or alternatively include an identifier which permits access to the data only by the identified physical and/or logical library(s).

Abstract: To improve reliability for multi-layer media, a data stream U is received for recording to a multi-layer rotating storage medium, the data stream U comprising a sequence of data bits. Each data bit U(J) is encoded into X representation bits. A first representation bit B(1,J) is recorded onto a first layer of the storage media, the second representation bit B(2,J) is recorded onto a second layer of the storage media, etc. When a request to read the recorded data U from the storage media is subsequently received, a plurality of the X representation bits are read back from the storage media and are decoded into the original data bit U(J). One embodiment employs a convolution encoding algorithm and PRML decoding algorithm. Another embodiment employs Reed Solomon encoding/decoding.

Abstract: Methods and apparatus are provided for dynamically compressing categories in a data storage library. In one embodiment, the method includes retrieving an identification of a first category in the data storage library, the first category being a last-compressed category. Next, an identification number of a first order of the first category is retrieved, the first order being a last compressed order. Compression is resumed of orders in the first category with an order next following the first order and continued with additional orders in the first category. If a predetermined amount of time has elapsed, the identification of the first category and the identification number of the order of the first category being compressed are stored. If, however, the predetermined amount of time has not elapsed and compression of the first category is complete, compression of a second category is begun.

Abstract: When data is stored in many storage subsystems, metadata, such as a sequence number, is also generated and stored with the data. When the data is accessed, the metadata is checked to ensure that the desired data element has been accessed. In conventional storage subsystems, data elements, such as logical blocks, are stored sequentially in logical pages of each logical volume. Consequently, sequence numbers closely correlate with block positions within the physical pages and sequence number/position patterns tend to repeat frequently and access errors may not be detected. Algorithms are provided to calculate new, offset, physical block positions which reduce the close association of sequence numbers and physical positions, thereby reducing such aliasing. The algorithms incorporate the logical volume number, the logical page number, or both, in addition to the logical block number. As a result, detection of access errors becomes more likely.

Abstract: An unencoded m-bit data input sequence is divided into a block of n bits and a block of m?n bits. The block of n bits is divided into a first set of n+1 encoded bits, wherein at least one of P1 subblocks of the first set satisfies a G, M and I constraints. The first set of n+1 encoded bits is mapped into a second set of n+1 encoded bits wherein at least one of P2 subblocks of the second set gives rise to at least Q1 transitions after 1/(1+D2) precoding. A second set of n+1 encoded bits is divided into P3 encoded subblocks and the P3 encoded subblocks are interleaved among (m?n)/s unencoded symbols so as to form a (m+1)-bit output sequence codeword which is then stored on a data storage medium.

Abstract: In controlled mechanical hardware, such as servo-controlled hardware, data from the control algorithm is obtained and logged for possible later analysis. Loss-less compression is provided without increasing the size of the storage memory. Instead of continuously storing the complete (absolute) value of a monitored control parameter, an absolute value is stored in an absolute entry and one or more values of the parameter which are relative to each preceding value are stored in a sequence of associated relative entries. The space required to store a relative value is less than the space required to store an absolute value. Updated absolute values and groups of associated relative values may also be recorded periodically or when a relative value is too large for the allotted space. The size of relative values may be variable and appropriate information data entries may be generated to indicate the size of associated relative entries.

Abstract: Apparatus and computer program products are provided to monitor and report performance data of a device such as a data storage drive. A plurality of quantitative values are obtained from feedback and measurement mechanisms in a data storage device of a first model during operation of the storage device. The plurality of quantitative values are normalized. Then, one or more qualitative values are generated from one or more normalized quantitative values and evaluated against corresponding baseline performance values established for the first model.

Abstract: A method of verifying the passage of a data write across a bus is provided including sending the data write from an originator across the bus to a target, counting the number of data entries received at the target with a counter, and transmitting a return echo write from the target across the bus to a return address. The method further includes attaching the counter value to other data associated with the return echo write and polling the return address. The method allows determination of the completion of a data write by comparing the number of data entries included in the data write with the counter value polled from the return address. Alternatively, in a data streaming environment the progress of a data write may be determined by comparing the number of data entries included in the data write at a select point in time with the counter value polled from the return address. Typical data entries which are counted may include, but are not limited to, bytes, words, double words, or similar data quantities.

Abstract: An increase in the efficiency of copy operations in a data storage system is provided. A host device directs that a volume of customer data be stored through one of two virtual storage servers on media in an associated library. An initiating controller queues a request to copy the volume to a second library. If the request is not processed by the initiating controller within a predetermined period, the initiating controller broadcasts the copy request to other controllers, each of which queues the request. After one of the controllers processes the request and the volume has been copied to the second library, the processing controller broadcasts a message to the other controllers which then dequeue the copy request from their respective copy queues. Upon receipt of such message, the initiating controller transmits a message to the host device that the volume was successfully stored and copied.

Abstract: Noise in a same-gap, frequency-based servo tape system is reduced by applying correlated noise factors, generated during calibration, to filtered data write signals. The resulting noise values are subtracted from filtered servo signals, at frequencies F1 and F2, to generate first and second noise-compensated servo signals at frequencies F1 and F2. In one embodiment, the F1 and F2 data signals are filtered through two SOBP filters which output the magnitudes of the signals. The F1 and F2 servo signals are similarly filtered. In another embodiment, the F1 and F2 data signals are filtered through two Goertzel filters which output the real and imaginary components of the signals and the F1 and F2 servo signals are similarly filtered through two other Goertzel filters. Correlated noise factors are applied to the outputs of the write data Goertzel filters and the results subtracted from the corresponding outputs of the servo Goertzel filters.

Abstract: Because cable length affects signal quality, amplifying signals differently to account for cable length (“tuning”) becomes especially important when high speed signals are used. Cable length information may be stored in a non-volatile memory which may be integrated into a cable assembly or may be a discrete component between the cable and an interface. Rather than using a dedicated data line to the memory component a ground line may be connected to the memory component and multiplexed. During normal operation the selected line is grounded through a switching device. When a cable is detected, a management controller changes the state of the switching device to decouple the selected line from ground to allow the management controller access to the data stored in the memory component, including cable length information. The selected line is then re-coupled to ground and interface circuits may be tuned for the cable length.

Abstract: Methods, system and computer program product are provided to improve the efficiency of data transfers in a PPRC environment. Any or all of three features may be implemented, each of which reduces the number of round trips required for the exchange of handshaking, data and control information. A first feature includes disabling the “transfer ready” acknowledgment which normally occurs between a primary storage controller and a secondary storage controller. A second feature includes pre-allocating payload and data buffers in the secondary storage controller. A third feature includes packaging write control information with a write command in an extended command descriptor block (CDB). Such a step eliminated the need for a separate transmission of the write control information. The CDB is transmitted along with a data block from the primary storage controller to the secondary storage controller and placed in the respective, pre-allocated buffers. Data may also be pipelined to the secondary.

Abstract: A simplified digital implementation of a fourth order Linkwitz-Riley crossover network is provided using approximations and transformations of the classical form. The approximation is particularly beneficial when the crossover frequency is low relative to the digital sampling rate, such as when an audio stream is split between bass and treble at about 30-300 Hz and the sampling frequency is about 100 times the cutoff frequency or higher. Rather than merely cascading two sets of second order filters, such as Butterworth filters, a fourth order transfer function is more directly implemented. Conventional transfer functions are simplified through approximations resulting in the elimination of all except one parameter, c, which is a linear function of the cutoff frequency. Additionally, multipliers are moved in line with the integrator elements.

Abstract: A two-phase process FlashCopy operation is provided that can be used to aid in the formation of consistency groups across multiple storage control units. In the first phase, preparations to create a new consistency group are made “revertible” by write-inhibiting the source volumes through “Establish-FlashCopy-revertible” commands. If the preparation of any volume within the consistency group fails, a “Withdraw-FlashCopy-revert” command may be executed, thereby causing a retention of the prior FlashCopy point-in-time copy. In the second phase, executed if all preparations are successful, a “Withdraw-FlashCopy-commit” command may be executed to remove all write-inhibit indicators, complete the creation of the new FlashCopy point-in-time copy and secure the new consistency group. Write requests to the FlashCopy source volumes may then be received and processed without risking corruption of the new consistency group on the Flashcopy target volumes.