摘要:
An embodiment of this invention divides a cache memory of a storage system into a plurality of partitions and information in one or more of the partitions is composed of data different from user data and including control information. The storage system dynamically swaps data between an LU storing control information and a cache partition. Through this configuration, in a storage system having an upper limit in the capacity of the cache memory, a large amount of control information can be used while access performance to control information is kept.
摘要:
To extend endurance and reduce bit cost, a method and a storage apparatus are provided, which storage apparatus includes a controller and a semiconductor storage media that includes a first storage device and a second storage device having an upper limit of an erase count of data smaller than the first storage device. Area conversion information includes correspondence of a first address to be specified as a data storage destination and a second address of an area in which data is to be stored. A rewrite frequency of stored data is recorded for each area. The controller selects an area corresponding to the first address, determines whether or not the rewrite frequency of the selected area is equal to or larger than a first threshold value, when the rewrite frequency is equal to or larger than the threshold value, selects an area to be provided by the first storage device, and when the rewrite frequency is smaller than the threshold value, selects an area to be provided by the second storage device and maps the address of the selected area to the first address.
摘要:
An embodiment of this invention divides a cache memory of a storage system into a plurality of partitions and information in one or more of the partitions is composed of data different from user data and including control information. The storage system dynamically swaps data between an LU storing control information and a cache partition. Through this configuration, in a storage system having an upper limit in the capacity of the cache memory, a large amount of control information can be used while access performance to control information is kept.
摘要:
With respect to a storage system in which quick formatting and sequential formatting can be run concurrently, the time it takes to process an access request from a host is prevented from becoming prolonged even when a normal sequential formatting process is executed with respect to a storage volume which frequently incurs I/O penalties. The storage device measures the load from the host per configurational unit (storage medium) of LUs, and divides the LUs into a group of LUs whose load per storage medium is low, and a group of LUs whose load per storage medium is high. Further, the density per unit of LU capacity of I/O penalties incurred in a storage volume for which quick formatting is being executed is calculated. Sequential formatting is then executed, with priority, with respect to the LUs belonging to the group with low loads and in order of descending density of incurred I/O penalties.
摘要:
To extend endurance and reduce bit cost, a storage apparatus includes a controller and a first storage device and a second storage device having a smaller erase count upper limit than the first storage device. Area conversion information includes correspondence of a first address of a data storage destination and a second address of a data storage area The controller selects an area corresponding to the first address, determines whether a rewrite frequency of the selected area is equal to or larger than a first threshold and, when the rewrite frequency is equal to or larger than the threshold, selects an area of the first storage device, and, when the rewrite frequency is smaller than the threshold, selects an area of the second storage device and maps the address of the selected area to the first address.
摘要:
With respect to a storage system in which quick formatting and sequential formatting can be run concurrently, the time it takes to process an access request from a host is prevented from becoming prolonged even when a normal sequential formatting process is executed with respect to a storage volume which frequently incurs I/O penalties. The storage device measures the load from the host per configurational unit (storage medium) of LUs, and divides the LUs into a group of LUs whose load per storage medium is low, and a group of LUs whose load per storage medium is high. Further, the density per unit of LU capacity of I/O penalties incurred in a storage volume for which quick formatting is being executed is calculated. Sequential formatting is then executed, with priority, with respect to the LUs belonging to the group with low loads and in order of descending density of incurred I/O penalties.
摘要:
Disclosed is a storage apparatus that extends endurance and reduces bit cost. A storage apparatus includes a controller and a semiconductor storage media that has a plurality of storage devices. The plurality of storage devices include a first storage device and a second storage device having an upper limit of an erase count of data smaller than that of the first storage device. Area conversion information includes correspondence of a first address to be specified as a data storage destination and a second address of an area in which data is to be stored. A rewrite frequency of stored data is recorded for each area. The controller selects an area corresponding to the first address, determines whether or not the rewrite frequency of the selected area is equal to or larger than a first threshold value, when the rewrite frequency is equal to or larger than the threshold value, selects an area to be provided by the first storage device, and when the rewrite frequency is smaller than the threshold value, selects an area to be provided by the second storage device and maps the address of the selected area to the first address.
摘要:
The present invention provides high-speed copying of a compressed data volume.The control unit of the storage apparatus divides the pool into a plurality of chunks comprising a plurality of pages storing data, compresses data which is written to the logical volume by the host and assigns one of the plurality of chunks to a compressed data logical volume which stores the compressed data, and, when the compressed data logical volume is copied, the control unit makes the page length of the chunk which is assigned to the compressed data logical volume which is the copy source the same as the page length of the chunk which is assigned to the compressed data logical volume which is the copy destination.
摘要:
Efficient leveling among a plurality of FMPKs 130 including a newly added or replaced FMPK 130. When a storage controller 110 lacks free blocks in real FMPKs 130 and any FMPK 130 of the real FMPKs 130 and an added substitute FMPK 130 are selected as leveling object devices, if the attribute of a block in the real FMPK 130 belonging to the leveling object devices is “Hot,” data larger than a threshold value from among data belonging to that block is migrated to a block in the substitute FMPK 130; or if the attribute of a block in the real FMPK 130 belonging to the leveling object devices is “Cold,” data smaller than the threshold value from among data belonging to that block is migrated to a block in the substitute FMPK 130.
摘要:
A spark ignition control system distinguishes engine operating condition between low engine load range where acceleration shock tends to be created and high engine load range where acceleration shock to be created is small and better acceleration characteristics is required. The spark ignition timing control system performs spark advance retarding control while the engine is in the low engine load range and in response to acceleration demand. On the other hand, the spark advance retarding control is disabled in the high engine load range.