摘要:
Disclosed herewith is a composite type computer system that can assure that a PCI tree to be allocated to a computer is configured completely before the computer is powered. The composite type computer system includes a PCI switch that connects plural computers through PCI interfaces; plural PCI devices connected to the PCI switch; a system controller that controls the computers; and a PCI manager that controls allocation of the PCI devices to the computers. The system controller carries out processings in the steps of (a) powering an object computer to start up its OS; (b) acquiring the identifier of a PCI tree allocated by the system controller to the computer and PCI tree management information denoting the status of the PCI tree; (c) retrying the powering or canceling the powering of the computer if the acquired PCI tree management information denotes the status “not initialized”; and (d) carrying out the powering for the computer if the acquired PCI management information denotes the status “initialized”.
摘要:
To improve throughput in data transfer in a remote I/O system, this invention provides a computer system including: a host computer; a device which communicates with the host computer; and a network which connects the host computer and the device, in which the device is coupled to the network via a device bridge including a bridge memory, and the host computer includes a host memory and a device driver. The device driver writes, when at least one of data and an address is written in the host memory, in the bridge memory the at least one of the data and address stored through the writing in the host memory; and sends a data transfer request to the device bridge, and the device bridge reads, upon reception of the data transfer request, an address from a predetermined area; and reads data from an area that is indicated by the read address.
摘要:
There is a need for applying an appropriate QoS setting to a complex information platform apparatus capable of flexibly changing an apparatus configuration so as to ensure an intra-apparatus communication band and realize management communication independence. Multiple processing modules are combined to construct one or more processing units with different apparatus types. An apparatus template management table prepares multiple levels of setting specifications with different ensured bands for intra-apparatus communication corresponding to each apparatus type. One set of setting specification is selected from multiple levels of setting specifications prepared for an apparatus type settled at the time of configuration setting. A QoS setting management table is generated based on the selected setting specification. When the configuration is set or changed, setting verification means verifies whether or not a total of ensured bands associated with each adapter is within an allowable range. When a result is negative, the setting specification is automatically changed to another provided with a smaller ensured band. A verified setting is distributed from the QoS setting management table to an IO switch and each adapter.
摘要:
A method for moving files between network storages in a virtualized network storage system having multiple network storages and rebalancing the free disk spaces. It periodically judges whether to start rebalancing. Two different conditions are adopted for the determination of start: (a) an imbalance of free disk spaces and the minimum value of the free disk spaces is less than a threshold and (b) an imbalance of free disk spaces and the frequency of accesses to the system is less than a threshold. Rebalancing is performed until the difference in free disk spaces falls below the threshold without exceeding the maximum execution time of rebalancing. If a request to write into a file which is being moved from a client takes place during a file moving step, the movement of the file is aborted and the file is deleted from the destination.
摘要:
There are a large number of operation workload reallocating plans, but in terms of a required calculation resource, it is undesirable to, in each case, derive power consumption required for a cooling apparatus, select and control operation workload deployment for minimizing a total value of the derived power consumption and server power. The present invention derives a rule about the IT workload allocation in advance from configuration information (static information) including position information of facilities including an air conditioner of the data center and the IT equipment items, changes priority of an applied rule on the basis of dynamic information including ambient temperature, and changes the IT workload allocation, thereby reducing the power consumption of the air conditioner.
摘要:
The physical server includes a hypervisor for managing an association between the virtual server and the I/O device allocated to the virtual server. The I/O switch includes: a setting register for retaining a request to inhibit a transaction from being issued from the I/O device to the virtual server; a Tx inhibition control module for performing an inhibition of the transaction from the I/O device to the virtual server, and guaranteeing a completion of a transaction from the I/O device issued before the inhibition; a virtualization assist module for converting an address of the virtual server into an address within a memory of the physical server; and a switch management module for managing a configuration of the I/O switch.
摘要:
Module combination candidates which compose an information platform, to reduce human error when a platform is composed, and to permit automatic configuration changes. There is therefore provided a compound information platform comprising information platforms combining one or more universal processing modules and dedicated processing modules, wherein a management module has a means which computes processing module combination candidates when newly composing the information platform, computes the sum total value of the maximum guaranteed communication bandwidth of an IO protocol interface for each physical interconnection PL using an interface setting management information, adding an additional maximum guaranteed communication bandwidth due to a processing module combination candidate, and determining whether this is a possible module combination candidate by comparing the addition result with the maximum permitted communication bandwidth of each physical interconnection.
摘要:
An IO adapter for guaranteeing the data transfer bandwidth on each capsule interface when multiple capsule interfaces jointly share the DMA engine of the IO adapter. An IO driver containing a capsule interface information table including bandwidth information and for setting the forming status of a pair of capsule interfaces and, during data transfer subdivides the descriptors for the capsule interfaces into multiple groups for each data buffer size satisfying the preset bandwidth information and, copies one group at each fixed sample time set by the descriptor registration means, into the descriptor ring and performs DMA transfer. To control this copy information, the IO driver contains a ring scheduler information table for managing the number of descriptor entries for the capsule interface cycle time and, a ring scheduler cancel means for renewing the entries in the ring scheduler information table each time one transmission of the descriptor group ends.
摘要:
The physical server includes a hypervisor for managing an association between the virtual server and the I/O device allocated to the virtual server. The I/O switch includes: a setting register for retaining a request to inhibit a transaction from being issued from the I/O device to the virtual server; a Tx inhibition control module for performing an inhibition of the transaction from the I/O device to the virtual server, and guaranteeing a completion of a transaction from the I/O device issued before the inhibition; a virtualization assist module for converting an address of the virtual server into an address within a memory of the physical server; and a switch management module for managing a configuration of the I/O switch.
摘要:
A system includes at least a user and a file system connected to the user through a network. An estimated write size of a write operation of the user into the file system is managed as an accumulated value. The timing of judging the limit of the disk usage amount is specified from the accumulated value and a predetermined threshold value, and the limit of the disk usage amount is judged at the specified timing, so that disk usage amount by a user may be limited and managed.