摘要:
A method for dynamically enabling and disabling use of XFR_RDY is disclosed herein. In one embodiment of the invention, such a method includes receiving a write command at a target and determining whether XFR_RDY is enabled or disabled for the write command. In the event XFR_RDY is disabled, the method determines whether one or more buffers are available at the target. If at least one buffer is available, the method processes the write command by writing data associated with the write command to the one or more buffers. The method then returns information indicating the number of buffers that are still available at the target after completing the write command. A corresponding apparatus and computer program product are also disclosed and claimed herein.
摘要:
Various embodiments provide systems and methods for migrating data. One system includes a small computer system interface logical unit number (SCSI LUN) configured to store protected data, a processor, and memory configured to store a peer-to-peer remote copy (PPRC) application. The processor is configured to execute the PPRC application to modify the protection in transmitted data and received data. One method includes receiving unprotected data, utilizing a PPRC application to add protection to the data to generate protected data, and storing the protected data in a protected SCSI LUN. Another method includes receiving, at a protected SCSI LUN, a request to transmit protected data, utilizing a PPRC application to strip the protection from the protected data to generate unprotected data, and transmitting the unprotected data to an unprotected SCSI LUN.
摘要:
A method to maintain write operation atomicity where a write operation crosses a data storage medium track boundary. The method supplies a storage controller comprising a host adapter, a processor, and a NVS. The host adapter receives from a host computer a write request and data. The method determines if the write request will cross a data storage medium track boundary. If the write request will cross a data storage medium track boundary, the method indicates to the host adapter that the write request comprises a two-track transfer, and writes the data to the NVS as the data is received. If the host computer fails prior to providing all the data to the storage controller, the method discards the data written to the NVS to ensure write operation atomicity.
摘要:
A method, system, and computer program product to preserve data integrity in a mirror and copy environment is disclosed herein. In one embodiment, a method may include receiving a write command and data from a host device. The method may further include writing the data to a primary storage device and attaching a primary sequence number associated with the primary storage device to the write command, thereby providing a numbered write command with a command sequence number. The numbered write command may then be transmitted to a secondary storage device. The method may further include comparing the command sequence number to a secondary sequence number associated with the secondary storage device. If the command sequence number matches the secondary sequence number, then the command may be executed. Otherwise, it may be ignored.
摘要:
A first device determines a possibility of an invalidation of a second device, wherein the first device is coupled to the second device via a fabric. A query is sent from the first device to validate the second device, in response to determining the possibility of the invalidation of the second device. A determination is made, at the first device, whether to continue I/O operations from the first device to the second device based on receiving a response to the query within a time period.
摘要:
Provided are a method, system, and article of manufacture, wherein a determination is made that a first data array in a plurality of data arrays has to be repaired to replace a failed storage device within the first data array. A storage device is selected from a selected data array of the plurality of data arrays to replace the failed storage device, wherein a data value corresponding to the selected data array is less than the data value corresponding to the first data array.
摘要:
Provided are a method, system, and article of manufacture for verifying a record as part of an operation to modify the record, A search request is received to determine whether a record matches a value. A first component executes the search request to determine if the record matches the value. The first component sends a verify request to a second component that did not execute the search request to execute the search request to determine whether the record matches the value. A result of the first and second components executing the search request is logged.
摘要:
A plurality of storage devices of a plurality of types is provided. A plurality of criteria is associated for each of the plurality of storage devices, based on characteristics of the plurality of storage devices, wherein the plurality of criteria can be used to determine whether a selected storage device is a compatibility spare for a storage device in a storage device array, and whether the selected storage device is an availability spare for the storage device in the storage device array. A determination is made by a spare management application, based on at least the plurality of criteria and at least one optimality condition, of a first set of storage devices selected from the plurality of storage devices to be allocated to a plurality of storage device arrays, and of a second set of storage devices selected from the plurality of storage devices to be allocated as spares for the plurality of storage device arrays. An allocation is made of the first set of storage devices to the plurality of storage device arrays. An allocation made of the second set of storage devices as spares for the plurality of storage device array.
摘要:
A method for facilitating input/output (I/O) communication for a processing operation is provided. An interrogate command is obtained by an I/O communications adapter. The interrogate command queries for status information of the processing operation to be provided in an interrogate response. A fixed number of resources and a time allocated to the interrogate command is throttled by pre-allocating the fixed number of resources needed for the interrogate command, and maintaining a timestamp for a interrogate message. The interrogate message is forwarded from the I/O communications adapter to a control unit. If the interrogate response is not received by the I/O communications adapter within a limited timeout period as measured by the timestamp, or if the interrogate message is received while the fixed number of pre-allocated resources are in use, the I/O communications adapter returns a busy response indicating the control unit is busy to prevent overrunning the control unit.
摘要:
A first unit and a second unit are provided in a multi-layer computing system, wherein the first unit is at a higher layer than the second unit in the multi-layer computing system, and wherein the first unit is a higher level unit and the second unit is a lower level unit. The higher level unit sends to the lower level unit, information to adjust a threshold for failure of components coupled to the lower level unit, wherein the higher level unit has more information on a degree of redundancy in the multi-layer computing system than the lower level unit. The lower level unit adjusts the threshold for the failure of the components, by using the information sent from the higher level unit.