Fujitsu Corporation

Tsuyoshi Hashimoto

Atsushi Nukariya

Naoki Hayashi

Kazuhiro Matsuyama

Mio Nakagawa

Tsutomu Ueno

Takeshi Suzuki

Akira Sugawara

Haruhiko Ueno

Hideyuki Akimoto

Masahiko Yamada

Masato Fukumori

Jumpei Kubota

Yoshihisa Chujo

Atsushi Takami

Hiroki Yokota

Takahiro Kagami

Yoshihiro Matsuyama

Ryosuke Kokubo

Masaaki Fushimi

Reiji Masaki

Lei Zhang

Taku Komorida

Ryo Kanbayashi

Shunsuke Tanii

Akio Houjyo

Hisashi Kanda

Yukio Kozawa

Yuta Higuchi

David Campbell

Koichiro Harada

A parallel processing apparatus includes: a memory; and a processor coupled to the memory, the processor is configured to: acquire a first time and a second time; divide a plurality of nodes into a plurality of groups; generate a plurality of schedule candidates each which assigns time zones corresponding to a length of time used to perform a maintenance operation at one or more nodes included in the plurality of groups in a time period from the first time to the second time to the plurality of groups such that no overlap occurs among the plurality of groups; evaluate the plurality of schedule candidates based on one or more process execution schedules of the one or more nodes in the time period; and output one schedule candidate of the plurality of schedule candidates based on a result of the evaluation.

Parallel processing apparatus, and method of maintaining parallel processing apparatus

A parallel processing apparatus includes a memory and a processor. The memory stores a program and the processor is coupled to the memory. The processor calculates, based on a number of nodes to be used in execution of respective jobs that are waiting to be executed and a scheduled execution time period for execution of the respective jobs, an execution scale of the respective jobs and allocates the respective jobs to an area in which a number of problem nodes that have a high failure possibility is small from among a plurality of areas into which a region in which a plurality of nodes are disposed is partitioned and divided. The allocation of the jobs is performed in descending order of the execution scale beginning with the job whose execution scale is the largest.

Parallel processing apparatus to allocate job using execution scale, job management method to allocate job using execution scale, and recording medium recording job management program to allocate job using execution scale

A processor-fault reproduction method includes: determining a heating time of a processor taken using a heating program which heats the processor to a fault occurrence temperature when a fault occurs from a current temperature based on first information regarding the current temperature of the processor, second information regarding a power consumption value and a temperature of the processor before the fault occurs and a refrigerant temperature of a cooling medium to cool the processor, third information regarding the fault occurrence temperature, and fourth information regarding a power consumption value of the processor during execution of the heating program; determining an execution time by adding a fault reproduction time taken by a fault reproducing program which reproduces a state of the processor when the fault occurs to the heating time; and reporting the execution time to a job scheduler with a request to execute the heating and fault reproducing programs.

Processor-fault reproduction method, information processing apparatus, and recording medium recording execution-time reporting program

A start test method executed by a system including a calculation device and a management device that manages failure information on the calculation device, the start test method includes storing, by a first processor included in the management device, a failure rate that has been calculated for each of parts of the calculation device based on the failure information received from the calculation device as performance information, associating with time information and a part of the calculation device; obtaining a failure rate of each of the parts at a time of start of the calculation device based on the performance information and a time when the calculation device is to be started; notifying the calculation device of the obtained failure rate; and executing, by a second processor included in the calculation device, a start test of the calculation device in accordance with the notified failure rate.

Start test method, system, and recording medium

An information processing apparatus includes: a processor performs a scheduling process of scheduling a job for nodes and including: calculating, when one node executes a first job, a job execution end time when execution of the first job is completed by referring an execution history in which an execution time of a job is recorded; acquiring, from a load management node that manages a load of a metadata-process execution node which performing metadata processing to access metadata of a file among the nodes, the load of the metadata-process execution node at the job execution end time; and generating, when the load is equal to or more than a threshold, schedule data to cause a staging execution node which performs the metadata processing produced by staging, at the job execution end time, the metadata processing based on staging to a file having an execution result of the first job.

Information processing apparatus, stage-out processing method and recording medium recording job management program

An information processing apparatus is configured to receive a request for communication between a first node and a second node included in a parallel calculation system, acquire job execution information relating a job to be executed by the parallel calculation system, generate connected graph information based on first information on the first node, second information on the second node, the job execution information, and topology information indicating a topology of the plurality of nodes, generate, based on the connected graph information, route information indicating a plurality of routes used when the communication between the first node and the second node is executed, specify, based on the route information, a route having the lowest passing cost among the plurality of routes; and specify a node included in the specified route as a relay node based on positions of the plurality of nodes in the specified route.

Information processing apparatus, method and non-transitory computer-readable storage medium

A log management apparatus includes a memory configured to store log information and identification information in association with each other, and a processor configured to store, in association with first identification information in the memory, first log information output, before a semaphore returns to an initial value but after the semaphore decreases from the initial value, from a program employing the semaphore, associate the first identification information with information relative to deletion of the log information when the semaphore has returned to the initial value, and perform deletion of the first log information among the log information stored in the memory in accordance with the first identification information associated with the information.

Log management apparatus and log management method

An information processing method for a computer having a memory and a processor coupled to the memory, and the computer is coupled between a plurality of transmission nodes and a reception node. The method including: calculating coefficients of an equation, the coefficients corresponding to a number of transmission nodes having an abnormality among a plurality of transmission nodes, based on a numeric value including state information of transmission nodes having the abnormality and identification information for identifying the transmission nodes having the abnormality; and transmitting the coefficients to a reception node that extracts the numeric value from a solution of the equation using the coefficients.

Calculation device, program, and information processing method

A storage control apparatus configured to control a storage apparatus accessed by an information processing apparatus when the information processing apparatus executes a job, the storage control apparatus includes a memory configured to store plan information that indicates a plan in which the information processing apparatus executes the job and history information that indicates an history of access from the information processing apparatus to the storage apparatus when the information processing apparatus executes the job, and a processor coupled to the memory and configured to perform, based on the plan information and the history information, a prediction of whether the information processing apparatus accesses the storage apparatus in a certain time segment, and control power supply to the storage apparatus based on the prediction.

Storage control apparatus and method of controlling a storage apparatus based on prediction of storage access

A parallel processing system creates a list when determining a start and an end times of processings for nodes and one or more of the nodes used by the processings, the list indicating an order of executing the processings and a number and positions of nodes used by the processings on coordinate axes, nodes included in the nodes and adjacent to each other in coordinate axis directions on the coordinate axes being coupled to each other, identifies a number of unused nodes on the coordinate axes at a time when the execution of a processing ends before an end time of the processing, and determines, based on the number and the list, a processing, a start time of which is to be advanced, from the processings at a time when the execution of the one of the processings ends before the end time of the one of the processings.

Parallel processing system, method, and storage medium

An information processing apparatus, among a plurality of information processing apparatuses that performs parallel computing processing in a parallel computer system, including a memory and a processor coupled to the memory and configured to execute a process including: calculating a centroid position of the information processing apparatuses based on a data length of data for which subsequent reading or writing from or to a file server is requested by the information processing apparatuses and position information on each of the information processing apparatuses; determining a first information processing apparatus that performs data relay according to the calculated centroid position; and collectively receiving or transmitting, when the determined first information processing apparatus that performs data relay is the information processing apparatus, the data for two or more of the information processing apparatuses.

Information processing apparatus, parallel computer system, and file server communication program

Computers are connected via multidimensional mesh or torus connection in a network. In response to a request for executing maintenance processing on computers in the network, an apparatus detects execution-scheduled jobs to be executed after an execution start time of the maintenance processing, based on execution-scheduled start times of jobs to be executed by the computers. The apparatus calculates, for each execution-scheduled job, a characteristic value of an axial length of an execution-scheduled job area in each axial direction of multidimensional axes in the network, where the execution-scheduled job area includes a group of computers to execute the each execution-scheduled job. The apparatus determines a maintenance area in the network on which the maintenance processing is to be executed, based on the characteristic values of the axial lengths of the execution-scheduled job areas, and executes the maintenance processing on computers in the maintenance area.

Apparatus and method for executing maintenance processing on computers coupled via a multidimensional mesh or torus connection in a network

A first node determines a second node belonging to the same first group as the first node, and creates a first receive buffer corresponding to the second node in a memory. The first node determines a third and a fourth node belonging to a second group, and creates a second receive buffer corresponding to the third node in the memory, without creating a receive buffer corresponding to the fourth node. The first node uses the first receive buffer to receive messages when communicating with the second node, uses the second receive buffer to receive messages when communicating with the third node, and uses the first receive buffer or the second receive buffer to receive messages when communicating with the fourth node.

Parallel processing apparatus and inter-node communication method

A computer system includes: a reference point determining unit that sets node allocation reference points for the job in association with job attribute information of the job, to node coordinate spaces where the plurality of computation nodes are arranged; and a node set searching unit that searches for a computation node set that is a set of computation nodes satisfying a predetermined condition related to a remote degree that is an estimate index of a communication time from the node allocation reference point in the node coordinate space.

Computer system, processing method, and computer-readable recording medium having job processing program

An apparatus includes nodes each configured to relay data between the nodes. When a failure occurs in a first-node, a management-node determines, based on power consumption and/or memory usage of the nodes, a collection-node that transmits an instruction in first direction approaching the first-node and a second direction approaching a storage-node, respectively. A second-node that is neither an adjacent-node adjacent to the first-node nor the storage-node, upon receiving data including the instruction, transmit data obtained by adding an evaluation value for the second-node to the received data, in the first or second direction. Each of the adjacent-node and the storage-node, upon receiving data including the instruction, transmit data including an evaluation value for another node included in the received data and an evaluation value for the each node, to the collection-node which determines transmission routes between the collection-node and the first-node, and between the collection-node and the storage-node.

Growing community of inventors

Kawasaki, Japan

Tsuyoshi Hashimoto