摘要:
The present invention comprises a memory, a plurality of access portions for accessing the memory, a memory adapter for controlling access to the memory from the plurality of access portions, and a response-type path (R path) and a throughput-type path (T path) which communicatively connect the respective access portions, and the memory adapter. The amount of information capable of being transferred by the R path within the same period of time is smaller than that of the T path, but the length of time from the sending of information until the receipt of a response thereto is shorter for the R path than for the T path. The length of time from the sending of information until the receipt of a response thereto is longer for the T path than for the R path, but the amount of information capable of being transferred by the T path within the same period of time is greater than that of the R path. The memory adapter preferentially allows access to the memory via the R path than access to memory via the T path.
摘要:
A controller and one or more intermediate devices that are connected to a plurality of processors and this controller so that communications are possible are provided. A first access message including a designated value designated by the processor is transmitted to the controller by a first intermediate device connected to the processor. The controller specifies a local memory address corresponding to the designated value included in the first access message, and transmits a second access message including this specified local memory address to two or more other processors. The two or more other processors or second intermediate devices that are connected to these processors access local memory regions of two or more local memories respectively corresponding to two or more other processors, which are local memory regions corresponding to the local memory addresses included in the second access message.
摘要:
A controller and one or more intermediate devices that are connected to a plurality of processors and this controller so that communications are possible are provided. A first access message including a designated value designated by the processor is transmitted to the controller by a first intermediate device connected to the processor. The controller specifies a local memory address corresponding to the designated value included in the first access message, and transmits a second access message including this specified local memory address to two or more other processors. The two or more other processors or second intermediate devices that are connected to these processors access local memory regions of two or more local memories respectively corresponding to two or more other processors, which are local memory regions corresponding to the local memory addresses included in the second access message.
摘要:
This invention relates to a disk array controller. There has been demand for a large scale memory device system operable without interruption. Further, in order to cope with the recent trend toward open systems, scalability of performance and capacity in such systems is needed. Conventionally, internal buses such as ones which connect the channel interface section to the shared memory section, and the disk interface section to the shared memory section, have been mounted on one platter, and the channel interface and other packages have been mounted thereon. If the internal buses have failed, the operation of the whole system must be stopped. There has been another problem that the performance of the internal buses is fixed. A disk array controller according to this invention comprises an interface platter on which a channel interface section and a disk interface section are mounted, a memory platter on which a shared memory section is mounted, and a cable which connects the interface platter to the memory platter in order to solve the above problems.
摘要:
An apparatus for use in a storage device having at least two clusters, each including a disk control device having a plurality of channel controllers that send and receive commands and data to and from an upper system, a plurality of disk controllers that control disk units, and a cache that temporarily stores data between the upper system and the disk units. The apparatus includes a first bus included in a first cluster. The first bus is connected to the channel controller, the disk controller and the cache of the first cluster. A second bus is included in a second cluster. The second bus is connected to the channel controller, the disk controller and the cache of the second cluster. A common resource is connected to the first bus of the first cluster and the second bus of the second cluster. The common resource includes a specified set of data which is commonly accessible from each of the channel controllers or the disk controllers of the clusters.
摘要:
The disk array controller includes a plurality of interfaces with respective processors for connecting with a host computer or disk devices, duplicated shared memories connected in a one to one ratio between each interface and respective access paths, a selector connected to the plurality of interfaces, and a cache memory connected to the selector. The number of access paths between the selector and the plurality of interfaces is greater than the number of access paths between the cache memory and the selector. Each processor performs dual writing in the duplicated shared memories.
摘要:
A disk array control device which includes a plurality of channel interface (IF) units, a plurality of disk IF units, a cache memory unit, and a shared memory unit. The connection system between the plurality of channel IF units and plurality of disk IF units and the cache memory unit is different from the connection system between the plurality of channel IF units and plurality of disk IF units and the shared memory unit. In the invention the plurality of channel IF units and the plurality of disk IF units are connected via a selector to the cache memory unit, whereas the plurality of channel IF units and the plurality of disk IF units are directly connected to the shared memory unit with no selectors.
摘要:
Provided is a storage subsystem capable of maintaining the reliability of I/O processing to a host apparatus, even if there is an unauthorized access from a processor core to a switch circuit, by applying a multi-core system to a processor. A multi-core processor is applied to a second logical address space that is different from a first logical address space to be commonly applied to multiple controlled units such as a host interface to be accessed by the processor. The switch circuit determines the processor core that issued an access based on an address belonging to a second address space, and maps an address containing in an access from the processor core to an address of a first address space.
摘要:
According to the present invention, in cases where a CHA function and a DKA function are mounted within a single package, a battery power supply that is used during the occurrence of power supply trouble is effectively utilized so that the supply of power can be separately controlled for each function. A CHA part and DKA part are disposed in a single control package. When trouble such as a power outage is detected, the CHA part blocks access requests from the host, and initiates end processing. When the end processing of the CHA part is completed, the package internal power supply control part stops the clock supply to the CHA part. Then, when the DKA part completes destage processing, the package internal power supply control part stops the supply of power to the DKA part. The power consumption of the package is lowered in stages in accordance with the progress of the end processing.
摘要:
A PLD is interposed on the communication route between a microprocessor (hereinbelow called MP) and boot memories. The boot memories store MP start-up data needed to start up the MP and start-up protection code constituting protection code for the MP start-up data. The PLD reads the MP start-up data and the start-up protection code thereof from the boot memories, performs, in hardware fashion, a check of the validity of the MP start-up data using this start-up protection code and, if a negative check result is obtained, resets the MP and if a positive check result is obtained, inputs the start-up data that is thus read to the MP.