Abstract: A shared-nothing database management system employs a method of adding and removing a database server without significantly affecting the processing performance for accessing a table from a user or an application. A scheduler module creates a schedule which separately handles the addition of a CPU resource and the addition of a storage I/O resource, and a server is added in accordance with the created schedule. A common disk is used to remove a disk at an arbitrary timing. Further, a data region is previously subdivided on the common disk to eliminate a movement of data associated with the addition of a server.

Abstract: A shared-nothing database management system employs a method of adding and removing a database server without significantly affecting the processing performance for accessing a table from a user or an application. A scheduler module creates a schedule which separately handles the addition of a CPU resource and the addition of a storage I/O resource, and a server is added in accordance with the created schedule. A common disk is used to remove a disk at an arbitrary timing. Further, a data region is previously subdivided on the common disk to eliminate a movement of data associated with the addition of a server.

Abstract: A shared-nothing database management system employs a method of adding and removing a database server without significantly affecting the processing performance for accessing a table from a user or an application. A scheduler module creates a schedule which separately handles the addition of a CPU resource and the addition of a storage I/O resource, and a server is added in accordance with the created schedule. A common disk is used to remove a disk at an arbitrary timing. Further, a data region is previously subdivided on the common disk to eliminate a movement of data associated with the addition of a server.

Abstract: The present invention improves input/output speed by multiplexing/demultiplexing data and also reducing the processing time required for interrupt handling. The present invention involves a process which requests input/output operation; an adapter which performs input/output operation based on the request from the process; and a scheduler which keeps the process in wait state while the adapter is performing input/output operation. When the input/output operation of the adapter is completed, the state of the process waiting for the completion of the operation is changed into “runnable” by the adapter, and the execution of the process which requested input/output operation is thereby restarted.

Abstract: A computer controls I/O allocation for partitions independently of CPU allocation and, in each I/O adapter and partition, the computer has a scheduling means controlling allocation for partitions of the I/O adapter by time sharing, a means to allocate the I/O adapter to partitions by space sharing and a means to dynamically change said allocation made by a partition-control program. Further, the computer has a means to monitor input/output performance of each partition, and a means to maintain SLA of a user program according to performance of each partition.

Abstract: A storage comprising an object access module for the shared part for implementing advanced I/O provides an interface (121) for registering and deleting object description data declaring how to store objects within a second storage, in order to reduce the development cost of modules for implementing functions. Also, in order to reduce the total cost of ownership, modules are transferred to the storage through a management computer. The present invention allows the storage for contiguously providing functions effective to a vast range of applications to be provided with lower development cost as well as lower total cost of ownership.

Abstract: The present invention aims to dynamically re-configure hosts and storage in a shared-nothing database. In the shared-nothing database, processes 24 to 29 executed in the hosts 11 to 14 access data of a storage device 30. A system manager 70 and a database manager 10 manage the hosts 11 to 14 and the storage device 30. The processes 24 to 29 access one or more disks 51 to 54 of the storage device. To add or reduce the number of the hosts, the processes 24 to 29 are reassigned among the hosts 11 to 14.

Abstract: A storage apparatus and a storage method for decreasing the number of storage devices shared by a plurality of servers for reduced size and power consumption and for updating storage contents by preventing services from being degraded. A first virtual volume includes a plurality of storage devices and saves the same data in part or all of the storage devices. A virtualization engine detaches a storage device from the first virtual volume and generates a second virtual volume from the detached storage device. The virtualization engine further detaches a storage device from the first virtual volume and moves the detached storage device to the second virtual volume. The virtualization engine writes the difference between data saved in the first and second virtual volumes to the moved storage device.

Abstract: When a load of a user is fluctuated, a data center dynamically changes resource allocation to the user according to the load and holds security for each user. A control program on a data center managing server creates a VLAN configuration table so as to allocate a user-dedicated VLAN including plural network switches for each user company, thereby configuring the ports of a load balancer and network switches allocated to a user to the user-dedicated VLAN. A VPN is configured from the user to the data center, whereby a VLAN tagging technique is used to hold security of the user from the user to the data center. The control program compares a user condition setting table created along the service level agreement for each user with the monitoring result of the computer operating state (the CPU utilization history in a VLAN operation table) to dynamically change the computer allocation and VLAN configuration at unsatisfied agreement.

Abstract: In order to execute a flow control and a congestion control in a hop-by-hop manner in a data communication among computers connected to different networks, in a data communication between a client A1 and a remote server B, a communication proxy of the remote server B is located in a local server A in an LAN to which the client A belongs. A communication packet to be routed to the remote server B is stolen (received) and passed to a transport layer. A TCP communication between the client A1 and the remote server B is divided into two; a communication between the client A1 and the communication proxy of the remote server B and a communication between the communication proxy of the remote server B and the remote server B.

Abstract: In a communicating method between data processing apparatuses using the Sockets API or the MPI API, the apparatus on the receiving side informs the apparatus on the sending side of a data length threshold, which makes the apparatus on the sending side to decide between sending data to a pre-registered pre-allocated buffer on the apparatus on the receiving side, or having the memory region that is the final destination of the data transfer registered and then sending the data to this memory region. When the length of the data to be sent does not exceed the threshold, sending to the pre-allocated buffer is selected, and the data transfer operation is completed by copying the received data from the pre-allocated buffer to the final destination of this transfer. In case the length of the data to be sent exceeds the threshold, the data is sent directly to the final destination of this transfer.

Abstract: To provide a method for managing data processing devices, in which the misidentification of a management target can be prevented. The method for managing data processing devices is applied to a system in which a plurality of container mechanisms are provided each of which contains a plurality of data processing devices and a management unit is provided which monitors each data processing device to collect information concerning the state of the data processing devices and orders management operations to be performed on the data processing devices based on the collected information, this method for managing data processing devices including: specifying a container mechanism containing a data processing device on which a management operation needs to be performed; and displaying information about the management operation on a specified container mechanism side.

Abstract: The present invention improves input/output speed by multiplexing/demultiplexing data and also reducing the processing time required for interrupt handling. The present invention involves a process which requests input/output operation; an adapter which performs input/output operation based on the request from the process; and a scheduler which keeps the process in wait state while the adapter is performing input/output operation. When the input/output operation of the adapter is completed, the state of the process waiting for the completion of the operation is changed into “runnable” by the adapter, and the execution of the process which requested input/output operation is thereby restarted.

Abstract: A storage apparatus and a storage method for decreasing the number of storage devices shared by a plurality of servers for reduced size and power consumption and for updating storage contents by preventing services from being degraded. A first virtual volume includes a plurality of storage devices and saves the same data in part or all of the storage devices. A virtualization engine detaches a storage device from the first virtual volume and generates a second virtual volume from the detached storage device. The virtualization engine further detaches a storage device from the first virtual volume and moves the detached storage device to the second virtual volume. The virtualization engine writes the difference between data saved in the first and second virtual volumes to the moved storage device.

Abstract: At a data center, operation for security management, such as tampering checks, is automatically implemented for a server allocated to one user of the data center without declining the user task processing performance of the servers in the data center. If control is exerted to deallocate one of the severs out of the user tasks, a server is deallocated such that no new load is assigned to the server to be checked for security management. At user-specified time intervals at which such operation is to be performed for one of the servers allocated to a user, judgment is made regarding whether an idle server is available. If available, the idle server is allocated to the user to resume the work load of the server to be checked for security management. If it is determined that no idle server is available, the load on the server to be checked for security management is reduced so as to perform the check for security management on the server.

Abstract: An information processing system having a plurality of address translators between an external network and an internal network to which a plurality of servers are connected, and a controller for switching an access route to a specific server from a route of a first address translator to a route of a second address translator. The controller instructs the second address translator to store received packets destined for the specific server, instructs the first and second address translators to switch a control parameter so that packets for the specific server are received by the second address translator in place of the first address translator, and shifts a control information entry to be used for address translation of packets destined to the specific server from the first address translator to the second address translator.

Abstract: When a load of a user is fluctuated, a data center dynamically changes resource allocation to the user according to the load and holds security for each user.

Abstract: A computer controls I/O allocation for partitions independently of CPU allocation and, in each I/O adapter and partition, the computer has a scheduling means controlling allocation for partitions of the I/O adapter by time sharing, a means to allocate the I/O adapter to partitions by space sharing and a means to dynamically change said allocation made by a partition-control program. Further, the computer has a means to monitor input/output performance of each partition, and a means to maintain SLA of a user program according to performance of each partition.

Abstract: In a communicating method between data processing apparatuses using the Sockets API or the MPI API, the apparatus on the receiving side informs the apparatus on the sending side of a data length threshold, which makes the apparatus on the sending side to decide between sending data to a pre-registered pre-allocated buffer on the apparatus on the receiving side, or having the memory region that is the final destination of the data transfer registered and then sending the data to this memory region. When the length of the data to be sent does not exceed the threshold, sending to the pre-allocated buffer is selected, and the data transfer operation is completed by copying the received data from the pre-allocated buffer to the final destination of this transfer. In case the length of the data to be sent exceeds the threshold, the data is sent directly to the final destination of this transfer.

Abstract: In order to execute a flow control and a congestion control in a hop-by-hop manner in a data communication among computers connected to different networks, in a data communication between a client A1 and a remote server B, a communication proxy of the remote server B is located in a local server A in an LAN to which the client A belongs. A communication packet to be routed to the remote server B is stolen (received) and passed to a transport layer. A TCP communication between the client A1 and the remote server B is divided into two; a communication between the client A1 and the communication proxy of the remote server B and a communication between the communication proxy of the remote server B and the remote server B.