摘要:
A RAID system performs host I/O processing during RAID formatting of a plurality of physical disk drives. The controller executes sequential format processing and one-point format processing. A RAID format writing size (SFS) for sequential format processing is set larger than a RAID format writing size (OFS) for one-point format processing. Delay of host I/O processing is reduced, so that the time required for RAID formatting can be shortened.
摘要:
According to an aspect of an embodiment, a method of storing user data (UD) with parity data (PD) for correcting the UD in a storage apparatus comprising disk units, each of the disk units storing data in data blocks(DBs), each of the DBs storing the UD or associated PD and position information(PI) indicative of the location of the DBs, comprising: obtaining the UD, dividing the UD into UD blocks (UDBs) which are adapted to be stored in the DBs, and determining which UDBs are to be stored into which DBs, respectively; determining PI of the DBs for storing the UDBs; generating PD for a group of UDBs and associated PI by parity operation using a weighting function to the UDBs and the PI; determining PI for the PD for said group by modifying a part of the PD; and storing the group of the UDBs, associated PI, and the PD.
摘要:
A system creates a configuration definition table to be used for accessing a physical disk according to a host I/O request, to decrease a memory size of the configuration definition table even if common firmware is used for models with different scales. For this, a model correspondence table to show the definition of each model is provided in a configuration setup processing module, the maximum values of this model are recorded in a memory based on this content, and a memory area for each item is secured. And the actual content of the configuration definition is developed on the secured memory. Therefore even for a diversity of models, the memory size of the configuration definition table can be decreased to a size matching the model, with common firmware regardless the model.
摘要:
A RAID-group converting apparatus converts two RAID groups into one RAID group. The RAID-group converting apparatus includes: a data-reading unit that reads at least non-parity data from data including the non-parity data and parity data, for each stripe from a plurality of recording media belonging to the two RAID groups; a parity-generating unit that generates two parities using the data belonging to a same stripe read by the data-reading unit; and a parity-writing unit that writes the two parities generated by the parity-generating unit into a parity storage area belonging to the same stripe.
摘要:
When receiving a notification of an error detected by patrol processing of the device adaptor for a secondary disk apparatus, a first recovery processing unit reads out data corresponding to the error location from a normal primary disk apparatus and writes the data into the error disk apparatus to eliminate the error. If it is determined that the content of the error notification is abnormality of the block ID which is an identifier of the order of writing data, a second recovery processing unit retrieves a correct write address indicated by the identifier, compares data of the error disk apparatus with that of the normal disk apparatus, determines that a lost write exists in the case of mismatch, and eliminates the lost write by writing the data read out from the normal disk apparatus into the error disk apparatus.
摘要:
A storage system prevents a time out error of the host I/O caused by a stagnation of command processing in the storage system for accessing a disk device according to the host I/O request and internal I/O request. In DTC, counters for managing the requests in-process for host I/Os (host read) and internal I/Os (pre-fetch, write back) individually are provided, and the number of processing requests to be issued to a virtual disk (RLU) is limited individually. By assigning priority to the host I/Os, the load balance of the host I/Os and internal I/Os can be controlled. For rebuild/copy back, a dedicated load control mechanism is disposed where the load adjustment between ordinary I/Os and rebuild/copy back is performed.
摘要:
An input/output device includes a creating unit that creates a first data pattern that is different from a second data pattern created last time, a writing unit that writes the first data pattern as a written data pattern, and a judging unit that reads out a data pattern written in the input/output device as a read data pattern and judges whether the written data pattern and the read data pattern coincide with each other.
摘要:
According to an aspect of an embodiment, a method of storing user data (UD) with parity data (PD) for correcting the UD in a storage apparatus comprising disk units, each of the disk units storing data in data blocks(DBs), each of the DBs storing the UD or associated PD and position information(PI) indicative of the location of the DBs, comprising: obtaining the UD, dividing the UD into UD blocks (UDBs) which are adapted to be stored in the DBs, and determining which UDBs are to be stored into which DBs, respectively; determining PI of the DBs for storing the UDBs; generating PD for a group of UDBs and associated PI by parity operation using a weighting function to the UDBs and the PI; determining PI for the PD for said group by modifying a part of the PD; and storing the group of the UDBs, associated PI, and the PD.
摘要:
A system creates a configuration definition table to be used for accessing a physical disk according to a host I/O request, to decrease a memory size of the configuration definition table even if common firmware is used for models with different scales. For this, a model correspondence table to show the definition of each model is provided in a configuration setup processing module, the maximum values of this model are recorded in a memory based on this content, and a memory area for each item is secured. And the actual content of the configuration definition is developed on the secured memory. Therefore even for a diversity of models, the memory size of the configuration definition table can be decreased to a size matching the model, with common firmware regardless the model.
摘要:
A RAID device changes the redundancy of the RAID configuration, while allows various RAID level conversions and capacity increase. Using new and old RAID configuration definition information which define at least a RAID level and a number of logical devices, the control unit performs RLU mapping based on the respective RAID configuration definition information, and performs staging and write back to change the RAID configuration. Therefore various RAID level conversions and capacity increase can be implemented.