Hitachi, Ltd.

Tomohiro Hanai

Satoru Watanabe

Akira Shimizu

Hideo Aoki

Kazuhiko Mogi

Tsuyoshi Tanaka

Norifumi Nishikawa

Norihiro Hara

Takao Sakurai

Tsunehiko Baba

Atsushi Tomoda

Noriaki Takahashi

Takahiro Yokoyama

Kazutomo Ushijima

Tomohiro Nakamura

Akihiko Sakaguchi

Katsuro Kikuchi

Yuuya Isoda

Shinji Hamada

Kazuho Tanaka

Atsuro Handa

Kenji Kushi

A computer system according to the present invention has a plurality of processor cores that execute a plurality of threads in a parallel manner. When one of the threads updates a database (DB) region that is among a plurality of database regions associated with a database (DB), and that cannot be updated by more than one thread, the computer system selects one of one or more dedicated log buffers as a log buffer to which a log relating to the update of the database region is to be written. In contrast, when one of the threads updates a database region that is among the plurality of database regions, and that can be updated by more than one thread, the computer system selects one of one or more shared log buffers as a log buffer to which a log relating to the update of the database region is to be written. Each dedicated log buffer is a log buffer that can store one or more logs associated with only one thread and that cannot store two or more logs associate with two or more threads. Each shared log buffer is a log buffer that can store two or more logs associated with two or more threads.

Computer system and database management method

A shared resource update apparatus includes: a processor unit including at least one processor having a plurality of processor cores that respectively execute a plurality of threads; and a storage unit storing a program that executes conflict avoidance control by being executed by the processor unit. A shared resource for the plurality of threads comprises a plurality of shared resource parts which are logically or physically partitioned. Each first thread among the plurality of threads is an update thread which updates an allocated shared resource part in response to an update request. Each second thread among the plurality of threads is a reference thread which issues an update request and references a shared resource part. Conflict avoidance control includes allocation of different shared resource parts to different update threads at a ratio of 1:n or 1:1, where n is an integer equal to or larger than 2.

Shared resource update apparatus and shared resource update method

An index tree search method, by a computer, for searching an index tree included in a database provided by the computer which includes processors executing a plurality of threads and a memory, the index tree search method comprising: a first step of allocating, by the computer, search ranges in the index tree to the plurality of threads; a second step of receiving, by the computer, a search key; a third step of selecting, by the computer, a thread corresponding to the received search key; and a fourth step of searching, by the computer, the index tree with the selected thread using the received search key.

Index tree search method and computer

A computer for executing processing through use of a database, the computer comprising: a processor including a cache memory; and a non-volatile memory coupled to the processor, the non-volatile memory having the database constructed thereon. The computer comprises: a database management module configured to execute processing on the database; and a write processing module configured to write data stored in the cache memory into the database. The write processing module writes data that is operated in the transaction processing into the database among data stored in the cache memory, in a case of receiving a commit request for transaction processing that uses the database.

Computer

An object is to improve detection accuracy of unfair use when a task system is used by using a mobile terminal. There is provided a method for detecting unfair use including: recording a plurality of operation feature quantities which are calculated from an operation log of a user and weights for the plurality of operation feature quantities of the user which are calculated by using a plurality of operation feature quantities of other users, obtaining an operation log of the user of a terminal device, calculating a plurality of operation feature quantities from the operation log, calculating similarity between the calculated plurality of operation feature quantities and the recorded plurality of operation feature quantities of the user in advance, by using the weights for the plurality of operation feature quantities, and detecting unfair use of the terminal device.

Method for detecting unfair use and device for detecting unfair use

The present invention is a stream data anomaly detection method for detecting an anomaly in input data received by a computer. The computer has: an input module for receiving the input data; an anomaly detection unit for detecting an anomaly in the input data; and an index management unit for calculating an index for the detection of an anomaly in the input data. The anomaly detection unit compares the received input data with the index and detects an anomaly in the input data when the difference between the value of the input data and the index satisfies a predetermined condition. The index management unit determines whether or not the index should be recalculated, and, when the index is determined to be recalculated, the index management unit recalculates a new index on the basis of the input data and substitutes the index with the calculated index.

Stream data anomaly detection method and device

A method and device for guaranteeing performance of stream data processing wherein a latency guarantee and a processing accuracy guarantee are possible while ensuring a real-time property. An execution system determination unit evaluates an amount of data currently present in a queue of an input data reception unit, calculation time, and the processing accuracy. Then, during a query process, if the amount of data in the queue increases for some reason, and is likely to be larger than the requested latency, the execution system determination unit changes the system to a calculation system by which the latency can be reduced within a range that a final quality can be allowed, on the basis of the evaluation result. Under the condition that the accuracy is reduced, if the latency is likely to be greatly lower than the requested latency, the system changes to a calculation system having a higher processing accuracy.

Method and device for guaranteeing performance in stream data processing

A stream data generating method for a computer system for generating stream data having time information applied thereto in a time series order and processing the generated stream data on the basis of a registered query. The computer system includes a storage for storing therein query information indicative of a plurality of sorts of constituent elements forming stream data corresponding to the query on the basis of the query and a stream definition indicative of the plurality of constituent elements, a data generator for generating and transmitting stream data; and a stream data processor for processing the stream data transmitted from the data generator. The data generator a less quantity of stream data to be transmitted to the stream data processor on the basis of the query information.

Stream data generating method, stream data generating device and a recording medium storing stream data generating program

Provided is a failure recovery method for switching to a standby system if a failure occurs in an active system, which allows reduction of loads on the standby system and a network. A computer system, which receives data to which timestamp information is appended in a chronological order and processes the received data by registered queries, includes the active system for processing the received data and the standby system for processing the received data instead of the active system upon occurrence of a failure. The active system processes the received data by the respective queries according to a predefined sequence, and transmits results obtained from the received data by the respective queries to the standby system as intermediate data on a query basis at a predetermined timing. The standby system restores the data by processing the received data and the intermediate data if a failure occurs in the active system.

Failure recovery method, computer system, and storage medium recorded failure recovery program for a stream data processing system

A computer for the stream data processing system includes a query recovery point management table. A recovery point management section determines a recovery point for the stream data processing system by identifying an oldest one of input tuples used for generating output tuples, which are managed, or an earlier tuple through the use of a query recovery point stored in the query recovery point management table, and transmits the determined recovery point for the stream data processing system to an additional computer. The additional computer stores the last-received recovery point for the stream data processing system in a checkpoint file. When the computer for the stream data processing system recovers from a fault, the additional computer transmits the data succeeding the stored recovery point to the computer for the stream data processing system.

Processing method, and computer for fault recovery

There is provided a method of adding a new computer as a standby computer to a computer system that includes an active computer for performing service processing and a standby computer for storing replica of data stored in the active computer. The replica of the data stored in the standby computer is updated when the data stored in the active computer is updated. The method comprising the steps of: selecting the standby computer from the computer system; transferring the replica of the data stored in the selected standby computer to the new computer; and transferring update information on data updated in the active computer after the transferring the replica of the data is started, to the new computer.

System and method for adding a standby computer into clustered computer system

Provided is a data replication method capable of reducing the number of communication times when a processing result of an active system is replicated to a standby system. The data replication method, in which a first computer receives a first message containing a first processing request, and a plurality of second computers replicates the first message, includes the steps of: sending, by a third computer, the first message to the first computer and the second computers; sending, by each of the second computers, a message receive notification of the first message to the first computer; sending, by the first computer, after reception of the message receive notification from the second computers, the message receive notification of the first message to the third computer; and sending, by the first computer, a notification indicating that the first processing request becomes executable by the first computer to the second computers.

Data replication method

A method of data exchange between volumes without using any unnecessary resource in a storage system includes allocating cache areas for data exchange on a memory, determining the location of data to be exchanged, reading out data from the determined location in source and destination volumes and storing data in their respective caches, and writing data stored in the cache to thus determined location of the volume different from the one that the data was read out.

Growing community of inventors

Tokyo, Japan

Tomohiro Hanai