摘要:
In a storage system which includes a plurality of microprocessors, it is desired to prevent delay in I/O responses due to synchronous processing waiting for asynchronous processing, while still ensuring the throughput of asynchronous processing. In a plurality of microprocessors possessed by a controller, synchronous processors and asynchronous processors are mixed together. The synchronous processors are microprocessors whose duty is to perform synchronous processing and not to perform asynchronous processing. And the asynchronous processors are microprocessors whose duty is to perform asynchronous processing and not to perform synchronous processing.
摘要:
In a storage system which includes a plurality of microprocessors, it is desired to prevent delay in I/O responses due to synchronous' processing waiting for asynchronous processing, while still ensuring the throughput of asynchronous processing. In a plurality of microprocessors possessed by a controller, synchronous processors and asynchronous processors are mixed together. The synchronous processors are microprocessors whose duty is to perform synchronous processing and not to perform asynchronous processing. And the asynchronous processors are microprocessors whose duty is to perform asynchronous processing and not to perform synchronous processing.
摘要:
Among a plurality of microprocessors 12, 32, when the load on a microprocessor 12 which performs I/O task processing of received I/O requests is equal to or greater than a first load, the microprocessor assigns at least an I/O task portion of the I/O task processing to another microprocessor 12 or 32, and the other microprocessor 12 or 32 executes at least the I/O task portion. The I/O task portion is a task processing portion comprising cache control processing, comprising the securing in cache memory 20 of a cache area, which is one area in cache memory 20, for storage of data.
摘要:
Among a plurality of microprocessors 12, 32, when the load on a microprocessor 12 which performs I/O task processing of received I/O requests is equal to or greater than a first load, the microprocessor assigns at least an I/O task portion of the I/O task processing to another microprocessor 12 or 32, and the other microprocessor 12 or 32 executes at least the I/O task portion. The I/O task portion is a task processing portion comprising cache control processing, comprising the securing in cache memory 20 of a cache area, which is one area in cache memory 20, for storage of data.
摘要:
Among a plurality of microprocessors 12, 32, when the load on a microprocessor 12 which performs I/O task processing of received I/O requests is equal to or greater than a first load, the microprocessor assigns at least an I/O task portion of the I/O task processing to another microprocessor 12 or 32, and the other microprocessor 12 or 32 executes at least the I/O task portion. The I/O task portion is a task processing portion comprising cache control processing, comprising the securing in cache memory 20 of a cache area, which is one area in cache memory 20, for storage of data.
摘要:
There are a loose coupling and a tight coupling as the coupling configurations for a first module and a second module. The loose coupling is a coupling configuration in which the first and second modules are coupled together by way of a front-end path, and the first module is not able to access a second storage resource. The tight coupling is a coupling configuration in which the first and second modules are coupled together by way of a back-end path, and the first module is able to access the second storage resource. A switch from the loose coupling to the tight coupling is performed using the following processing flow without the first and second modules being partitioned into respectively independent storage modules. Specifically, first, the first and second modules are coupled together by way of the back-end path, and next, the first module merges information denoted by second management information from the second storage resource with first management information via the back-end path.
摘要:
There are a loose coupling and a tight coupling as the coupling configurations for a first module and a second module. The loose coupling is a coupling configuration in which the first and second modules are coupled together by way of a front-end path, and the first module is not able to access a second storage resource. The tight coupling is a coupling configuration in which the first and second modules are coupled together by way of a back-end path, and the first module is able to access the second storage resource. A switch from the loose coupling to the tight coupling is performed using the following processing flow without the first and second modules being partitioned into respectively independent storage modules. Specifically, first, the first and second modules are coupled together by way of the back-end path, and next, the first module merges information denoted by second management information from the second storage resource with first management information via the back-end path.
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 computer system having a plurality of controllers for data input/output control is provided, wherein even if a control authority of a processor is transferred to another processor and the computer system migrates control information necessary for a controller to execute data input/output processing, from a shared memory to a local memory for the relevant controller, the computer system prevents the occurrence of unbalanced allocation of a control function necessary for data input/output control between the plurality of controllers; and a load equalization method for such a computer system is also provided.
摘要:
A computer system having a plurality of controllers for data input/output control is provided, wherein even if a control authority of a processor is transferred to another processor and the computer system migrates control information necessary for a controller to execute data input/output processing, from a shared memory to a local memory for the relevant controller, the computer system prevents the occurrence of unbalanced allocation of a control function necessary for data input/output control between the plurality of controllers; and a load equalization method for such a computer system is also provided.