Fujitsu Corporation

Yuichi Tsuchimoto

Toshihiro Shimizu

Hidekazu Takahashi

Miho Murata

Hiromichi Kobashi

Nobutaka Imamura

Toshiaki Saeki

Yasuo Yamane

Hiroki Moue

Soichi Shigeta

An operation unit updates grouping information about grouping of data sets stored in a storage device, based on access information about access to data stored in the storage device and memory loading information about data loaded and held in a memory according to access to data stored in the storage device. The operation unit updates data arrangement in the storage device according to the updating of the grouping information. In the updating of the grouping information, the operation unit updates the grouping information based on relationship information between data sets according to the access information.

Data arrangement control method and data arrangement control apparatus

A computer-readable non-transitory recording medium having stored therein a data analyzing program that causes a computer to execute a process. The process includes acquiring a transition matrix of data access based on a data access record of the data access; calculating an entropy rate for each of transition counts by using the transition matrix; determining mutual relevance of the data access based on the entropy rate; and storing data related to the data access on a disk, allocation of the data on the disk being determined by the mutual relevance of the data access.

Data access analysis using entropy rate

There is provided an information processing device includes a task executor and a controller. The task executor executes one or more second tasks that are generated by execution of a first task. The controller that controls the task executor such that the number of tasks to be executed in parallel is adjusted on the basis of a usage degree representing a degree of usage of resource in the information processing device.

Information processing device, method for processing information, and non-transitory computer-readable recording medium having stored therein information processing program

An information processing apparatus includes a first storage device that stores in a first storage area a first data group that includes a first plurality of data to be processed successively, and stores in a second storage area a second data group that includes a second plurality of data to be processed successively, a second storage device that includes a third storage area that stores a command to access data stored in the first storage area and a fourth storage area that stores a command to access data stored in the second storage area, and a processor configured to store, in a corresponding storage area of the third storage area and the fourth storage area, a received command, select one of the third storage area and the fourth storage area, and process one or more command stored in a selected storage area.

Information processing apparatus, computer-readable recording medium, and information processing method

A computer-readable recording medium storing a program causing a processor to execute an operation, the operation includes associating a mathematical function of which a domain includes a key to uniquely specify data to be stored, with each node; associating an index value indicating an amount of the data, with each node; substituting the key in the mathematical function to calculate a value of the mathematical function; substituting the value of the mathematical function and the index value in a weighting function, of which a domain includes the value of the mathematical function and the index value, and in which a size relationship of values of the weighting function is defined in a range of the weighting function, to calculate a value of the weighting function for every node; determining a node in which the data is to be stored, based on the size relationship; and outputting the node.

Node determining program, node determining apparatus, and node determining method

Each of plurality of nodes connected to each other via a network includes a local instance processor and a user application processor. The local instance processor executes a data sharing method for accessing shared data. The data sharing method includes: storing a value of first shared data with a function identifier of an update function upon receiving a registration request, wherein the update function is commutative and idempotent; updating the stored value of the first shared data to a first update value in accordance with an execution result of the update function upon receiving an update request; returning a completion message upon updating the stored value of the first shared data stored in the first node; and transmitting a first reflection request to a second node upon updating the stored value of the first shared data stored in the first node.

Computer-readable medium storing data sharing program, data sharing method, and data sharing processor

A computer-readable recording medium stores a program for causing an apparatus to execute a procedure. The procedure includes: regarding each data in a data set having a key and a value corresponding to the key, calculating a key characteristic value of the data as an index value indicating an existence of the key in the data and another key included in the value based on the value of the key and the value of the other key included in the value; generating a segment in which data blocks of which the calculated key characteristic values are similar to each other are grouped in one group; and setting a storage destination of the data in the generated segment.

Generating method, generating system, and recording medium

A clock determination method executed by a first one of apparatuses included in a system includes receiving a list including first definite clock values of respective apparatuses, the list being circulated among the apparatuses; determining the first clock value of the first apparatus at a point in time based on a smallest of logical clock values regarding corresponding commands on which processing is not completed, the commands being included in commands received by the first apparatus and the logical clock values being obtained at a time of receiving the corresponding commands and being stored, and updating the first clock value, the updated first clock value being included in the list, by using the determined first clock value; specifying, as a second clock value for the system, a smallest of the first clock values included in the updated list; and transmitting the updated list to a second one of the apparatuses.

Method for determining definite clock and node apparatus

A first node apparatus included in a distributed data store acquires first operation information and a first timestamp corresponding to target data. The first operation information specifies a first operation to be executed on the target data. The first timestamp indicates a first receipt time of the first operation information. The first node apparatus determines whether the first receipt time is earlier than some of second receipt times on the basis of second timestamps and the acquired first timestamp. The second timestamp indicates the second receipt time of second operation information. The second operation information specifies a second operation executed on the target data. The first node apparatus re-executes the second operations together with the first operation on the target data in the order of the receipt time when it is determined that the first receipt time is earlier than some of the second receipt times.

Growing community of inventors

Kawasaki, Japan

Yuichi Tsuchimoto