摘要:
A high availability system includes a first server computer for a first virtual computer and a first hypervisor and a second server computer for a second virtual computer and a second hypervisor. The first virtual computer executes a processing and the second virtual computer executes the processing behind from the first virtual computer. Information associated with an event is transmitted. The event provides an input to the first virtual computer. In the second hypervisor, a control unit performs, control based on the information to match the execution state of the second virtual computer and that of the first virtual computer, and control associated with the information, when the event associated with the information is predetermined one of an I/O completion interrupt from the first virtual storage and an interrupt handler call corresponding to the interrupt, after the interrupt from the second virtual storage corresponding to the interrupt is caught.
摘要:
A controller stores therein a sector address set indicating logical storage positions within a nonvolatile-memory storage area; page addresses indicating, in units of pages, physical storage positions within the nonvolatile-memory storage area; and pieces of management information each indicating whether one or more special sectors each being either a bad sector or a trimmed sector trimmed by a TRIM command are present in the corresponding page, while associating them with each other. When an access to a specified sector address is requested, the device refers to the piece of management information and judges whether any special sector is present in the page identified by the page address corresponding to the sector address. The device generates predetermined response data if the page contains one or more special sectors and accesses the nonvolatile-memory storage position corresponding to the sector address if the page contains no special sector.
摘要:
A high availability system includes a first server computer for a first virtual computer and a first hypervisor and a second server computer for a second virtual computer and a second hypervisor. The first virtual computer executes a processing and the second virtual computer executes the processing behind from the first virtual computer. Information associated with an event is transmitted. The event provides an input to the first virtual computer. In the second hypervisor, a control unit performs, control based on the information to match the execution state of the second virtual computer and that of the first virtual computer, and control associated with the information, when the event associated with the information is predetermined one of an I/O completion interrupt from the first virtual storage and an interrupt handler call corresponding to the interrupt, after the interrupt from the second virtual storage corresponding to the interrupt is caught.
摘要:
According to an embodiment, a control system includes a processing device; a main storage device to store the data; a cache memory to store part of the data stored; a prefetch unit to predict data highly likely to be accessed and execute prefetch, reading out data in advance onto the cache memory; and a power supply unit. The system further includes: a detecting unit to detect whether the processing device is in an idle state; a determining unit that determines whether to stop the supply of power to the cache memory in accordance with the state of the prefetch when determined as idle state; and a power supply control unit that controls the power supply unit so as to stop the supply of power, or controls the power supply unit so as to continue the supply of power.
摘要:
A high availability system includes a first computer on which a first virtual computer and a first hypervisor managing the first virtual computer operate, and a second computer on which a second virtual computer and a second hypervisor managing the second virtual computer operate. The first hypervisor includes an acquisition unit which acquires synchronization information associated with an event, wherein the event has occurred in the first virtual computer and accompanies an input to the first virtual computer, and a transmission unit which transmits the acquired synchronization information to the second hypervisor. The second hypervisor includes a reception unit which receives the synchronization information from the first hypervisor, and a control unit which performs control to match an input to the second virtual computer with an input to the first virtual computer in accordance with the received synchronization information.
摘要:
According to one embodiment, an information processing apparatus includes an auxiliary storage unit, a non-volatile main storage unit, a secondary cell, a first writing unit, and a second writing unit. The non-volatile main storage unit includes a cache area to temporarily store therein data that is to be stored in the auxiliary storage unit. The first writing unit writes the data into the cache area. The second writing unit writes the data written in the cache area into the auxiliary storage unit when an amount of power in the secondary cell is greater than a predetermined first threshold.
摘要:
In an information processing apparatus, a program processing unit executes a program described as an object-oriented language executed by a platform-independent machine language. A monitor unit monitors a change of a network address of the information processing apparatus. A reference provision unit provides a new network address of the information processing apparatus for another information processing apparatus when said monitor unit detects the change of the network address of the information processing apparatus.
摘要:
According to an aspect of the present invention, in a virtual space unit area, a message is distributed among computers using a physical topology based on a physical network. This avoids delaying operations in a computer which are related to those in another computer on a virtual space and taking a roundabout route on the physical network for distribution. On the other hand, outside the virtual space unit area, a message is distributed among computers using a virtual topology based on a virtual space. Consequently, the computers forming the physical topology can be limited to those present in the virtual space unit area. It is thus possible to reduce the amount of communication required to measure physical network distances.
摘要:
A write control method of exclusively controlling write requests from a plurality of user terminals to an identical structured document is disclosed. The identical structured document includes a plurality of elements each containing document content. A monitor field is set in units of the elements within the identical structured document. Upon accepting one write request from one user terminal, it is determined if the one write request is directed to the document content under monitoring by referral to the monitor field. Then, the one write request is handled to reject overwriting of the document content despite the one write request if the document content has been rewritten by another write request from another user terminal in advance.
摘要:
A single virtual space management scheme suitable for a distributed system. The single virtual space for arranging programs and/or data among a plurality of computers forming the distributed system are divided into a plurality of regions called memory chapters, and a part of the single virtual space to be managed independently by each computer is requested from each computer in units of these memory chapters. Then, a server allocates one of the memory chapters to each computer in response to each request from each computer, while managing allocations of the memory chapters to the plurality of computers so as not to allocate each one of the memory chapters to more than one computers. Each memory chapter allocated to each computer is independently managed by further dividing each memory chapter into a plurality of sub-regions called memory sections, and carrying out an access protection in units of these memory sections at each computer.