Abstract: When data in one semiconductor memory device is corrupted during a padding process by a padding unit and the data cannot be recovered even by using an error correcting code for correcting a data error, a storage control device issues a data recovery request to a data recovery device. The data recovery device reads the data from other semiconductor memory device in response to the data recovery request to recover the data, and returns a recovery result to the padding unit in the storage control device to perform the padding process.

Abstract: A controller stores therein a sector address set indicating logical storage positions within a nonvolatile-memory storage area; page addresses indicating, in units of pages, physical storage positions within the nonvolatile-memory storage area; and pieces of management information each indicating whether one or more special sectors each being either a bad sector or a trimmed sector trimmed by a TRIM command are present in the corresponding page, while associating them with each other. When an access to a specified sector address is requested, the device refers to the piece of management information and judges whether any special sector is present in the page identified by the page address corresponding to the sector address. The device generates predetermined response data if the page contains one or more special sectors and accesses the nonvolatile-memory storage position corresponding to the sector address if the page contains no special sector.

Abstract: A volatile management memory stores management information for managing a use state of a storage medium. A management information storing unit divides the management information into plural division pieces and individually stores them in the storage medium. A main controller receives a command from a host device while the division pieces are being stored, performs data processing for the storage medium in response to the command between each division piece is stored, updates the management information divided into the division pieces according to the data processing content, and creates a log representing an update content of the management information. A log storing unit stores the log in the storage medium. A restoring unit reads the division pieces stored in the storage medium to the management memory as the management information, updates the management information according to the log stored in the storage medium, and restores the updated management information.

Abstract: A high availability system includes a first server computer for a first virtual computer and a first hypervisor and a second server computer for a second virtual computer and a second hypervisor. The first virtual computer executes a processing and the second virtual computer executes the processing behind from the first virtual computer. Information associated with an event is transmitted. The event provides an input to the first virtual computer. In the second hypervisor, a control unit performs, control based on the information to match the execution state of the second virtual computer and that of the first virtual computer, and control associated with the information, when the event associated with the information is predetermined one of an I/O completion interrupt from the first virtual storage and an interrupt handler call corresponding to the interrupt, after the interrupt from the second virtual storage corresponding to the interrupt is caught.

Abstract: A semiconductor storage includes a receiver configured to receive a write request from a host device; a storage unit configured to hold redundancy data generation/non-generation information; a writing unit configured to write data in a semiconductor memory array and write redundancy data generation/non-generation information of the written data in the storage unit; a first data extracting unit configured to extract data whose redundancy data is not generated from among the data held by the semiconductor memory array; a first redundancy data generating unit configured to generate redundancy data; a first redundancy data writing unit configured to write the generated redundancy data in the semiconductor memory array; and a first redundancy data generation/non-generation information updating unit configured to update the redundancy data generation/non-generation information of the data whose redundancy data held by the storage unit is generated.

Abstract: A high availability system includes a first server computer for a first virtual computer and a first hypervisor and a second server computer for a second virtual computer and a second hypervisor. The first virtual computer executes a processing and the second virtual computer executes the processing behind from the first virtual computer. Information associated with an event is transmitted. The event provides an input to the first virtual computer. In the second hypervisor, a control unit performs, control based on the information to match the execution state of the second virtual computer and that of the first virtual computer, and control associated with the information, when the event associated with the information is predetermined one of an I/O completion interrupt from the first virtual storage and an interrupt handler call corresponding to the interrupt, after the interrupt from the second virtual storage corresponding to the interrupt is caught.

Abstract: A data control apparatus includes a mapping-table managing unit that manages a mapping table that is associated with a corrupted-data recovery function of recording data and error correcting code data as redundant data that is given separately from the data, distributed and stored in units of stripe blocks in the plural nonvolatile semiconductor memory devices, the mapping table containing arrangement information of the data and the error correcting code data; a determining unit that determines whether to differentiate frequencies of writing the data into the semiconductor memory devices; and a changing unit that changes the arrangement information by switching the data stored in units of the stripe blocks managed using the mapping table to differentiate the frequencies of writing the data into the semiconductor memory devices, when the determining unit determines that the frequencies of writing the data into the semiconductor memory devices are to be differentiated.

Abstract: When data in one semiconductor memory device is corrupted during a padding process by a padding unit and the data cannot be recovered even by using an error correcting code for correcting a data error, a storage control device issues a data recovery request to a data recovery device. The data recovery device reads the data from other semiconductor memory device in response to the data recovery request to recover the data, and returns a recovery result to the padding unit in the storage control device to perform the padding process.

Abstract: A size storage unit stores therein a block size of a memory element. A buffering unit executes buffer processing configured to store data received from a RAID (Redundant Arrays of Inexpensive/Independent Disks) controller into a buffer, and to write the data stored in the buffer into the memory element. A stripe-size receiving unit receives a stripe size that indicates a size of a unit of access at time of access to the memory element by the RAID controller. Writing processing is configured to write data received from the RAID controller into the memory element without executing the buffer processing by the buffering unit, when the stripe size is n times of the block size (n is a positive integer).

Abstract: A RAID is configured using plural nonvolatile semiconductor memory devices to enable recovery of data stored in the nonvolatile semiconductor memory devices, and data is read from the nonvolatile semiconductor memory device included in the RAID in response to a data reading request inputted from outside. When an error occurs during the reading, data for which the reading error occurs is recovered, and rewritten into an area of the nonvolatile semiconductor memory device in which the reading error occurs.