摘要:
A sorting method used with a distributed database having a plurality of first processors for holding partial records of a database that is divided into a plurality of portions and a host processor for accessing to each of the first processors. The method comprises the steps of: assigning a plurality of sections into which the distribution range of key values of records of the database is partitioned to a plurality of second processors in the first processors, and information for representing storage positions of the records to the second processors to which the sections of the key values, to which the records belong, are assigned; and sorting the plurality of key values, which have been received, in the second processors to produce key tables in which the information for representing the storage positions of the records which has been received is registrated together with the sorted key values, as the sorting result.
摘要:
A parallel database processing system a global database processing unit, a plurality of local database processing units, and a network interconnecting the global database processing unit and a plurality of local database processing units, wherein one table containing a number of records is partitioned into local tables, each local table being provided in a corresponding one of the local database processing units, secondary key indexes representing correspondence between the values of secondary keys for all records in the table and access information to the records corresponding to the secondary keys, are partitioned on the basis of the values into local secondary key indexes, each set of the local secondary key indexes being provided in a corresponding one of the local database processing units, and an identifying unit is provided in the global database processing unit, the identifying unit responsive to a retrieval request with the secondary key identifying the local database processing unit having the local secondary key index corresponding to the secondary key. At the global database processing unit, the retrieval request with the secondary key is received, the identifying unit identifies the local database processing unit having the local secondary key index corresponding to the secondary key, and the retrieval request with the secondary key is transferred to the identified local database processing unit. At the identified local database processing unit, its own local secondary key indexes are referred to obtain access information corresponding to the transferred retrieval request with the secondary key, and the retrieval request with the secondary key is processed by using the access information so that the local table corresponding to the retrieval request with the secondary key is accessed.
摘要:
A hierarchical network hierarchically connects a plurality of networks whose nodes are mutually connected by connection paths as a p-array n-dimensional cube to configure a single network. A plurality of nodes are selected from lower layer p-array n-dimensional cubes, and the selected gate nodes are mutually connected as a p-array m-dimensional cube to configure a p-array m-dimensional network on the next layer. Similarly, gate nodes are selected from a plurality of next-layer p-array m-dimensional networks, and mutually connected as a p-array l-dimensional cube to configure a p-array l-dimensional network in a further upper layer, thereby configuring a single hierarchical network as a whole.
摘要:
A packet forwarding device changes packet transfer performance according to a packet load, and ensures communication quality of an important packet while transfer performance is made minimum to suppress power consumption. The packet forwarding device includes a measuring section to measure the packet load for each packet importance degree, an estimation section to estimate a future packet load for each importance degree based on the measurement result, a performance determination section to determine performance for an operation based on the estimated load, which are provided in, for example, a traffic estimation/performance determination section. Reduction in the power consumption and assurance of the communication quality of the important packet are realized by a minimum performance determination based on an important packet estimation load in the performance determination section and a preferential process of the important packet in the packet forwarding device.
摘要:
A packet switch identifies a communication flow carried across an IP network, observes the communication flow, and acquires statistics data thereof, such as the number of packets that passed through the switch, the number of discarded packets, time at which the packets arrived at the switch, and time at which the packets were sent out from the switch. The packet switch continues to acquire the statistics data on the communication flow while the communication flow continues. If the packet switch performs a relay function, it sends the locally obtained statistics data to the adjoining packet switch placed downstream. If the packet switch is a node placed on either end edge of the network, it gathers the statistics data obtained by and delivered from other switches in the network and sends the gathered statistics data to the network management system.
摘要:
A data processor for latching in a floating point register floating point data having exponent parts of fixed and variable lengths, which are transferred from a main storage or an arithmetic unit as they are, but are not converted to another data expression type. When the data of the two representation types are to be input for computations from the floating point register or storage to the arithmetic unit, there is provided circuitry for controlling the data to be computed after that data has been converted into data having an exponent part of fixed length representation, in the arithmetic case of data having an exponent part of the variable length representation, and data to be computed without any data conversion in the arithmetic case of data having an exponent part of the fixed length representation. By thus controlling the two computations discriminatively, it is possible to realize the processing time periods matching the respective data widths.
摘要:
A display apparatus including: a collecting unit that collects power consumption information, wherein the power consumption information shows power consumption of a connecting device, and the connecting device interconnects a plurality of communication paths in a computer network; and a display unit that displays power consumption of the computer network, based on the power consumption information and constituent units based on a virtual network which is configured virtually on the computer network.
摘要:
In a conventional “distributed” integrated network node architecture, specific judgment processes cannot be executed in any routing and transferring unit. The routing and transferring unit is required to share judgment process related information with an enhanced processing unit or other routing and transferring units. Thus, when using enhanced processing units, manufacturing costs increase, while processing speed decreases when routing and transferring units cooperate. If any flow is disposed during a transfer from a packet transferring unit in a routing and transferring unit to a processing unit, the packet is disposed regardless of packet priority. In the present invention, a packet related to a specific judgment process is always transmitted to a specific routing and transferring unit from a line interface unit. If an inputted flow is over the transferring capacity, the line interface unit analyzes the packet header and determines the type, transport priority, and disposal priority of the packet.
摘要:
A network switching device includes multiple ports, multiple switching processors, and a table manager. The switching processors respectively have an address table, a output port specification module, an update requirement determination module, and a table update module. The output port specification module refers to a destination address in received data and the address table and specifies a output port for sending the data among the multiple ports. The update requirement determination module determines requirement for update of the address table with regard to a source address in the data. The table manager has an update detail acquisition module and an update request module. Upon determination of the requirement for update of the address table, the update detail acquisition module obtains an update detail of the address table from one of the switching processors. The update request module sends an update request to the switching processors, based on the update detail.
摘要:
A communication statistic information collection apparatus comprises a unit for searching a flow table for a flow entry corresponding to a searching key, a unit for collecting statistics information for each of flows, a unit for generating a packet for notifying a collector apparatus of stored statistics information, a unit for updating the flow table in accordance with statistics control information shown by a statistics control entry found as a result of searching the flow table, and a unit for generating a sample packet to be transferred to the collect or apparatus at a specified sampling rate in accordance with the statistics control information shown by a specified entry found from the flow table.