Hitachi, Ltd.

The University of Tokyo

Hideomi Idei

Kazuhiko Mogi

Norifumi Nishikawa

Masaru Kitsuregawa

Kazuo Goda

Toyohiro Nomoto

Yoshiaki Eguchi

Shinji Fujiwara

Hiroshi Furukawa

Shigeru Miyake

Satoru Tezuka

Kenichi Kihara

Chiho Kitahara

Shihoko Taguchi

Hikari Namba

Alberto Suzano

Yasutomo Yamamoto

Akira Shimizu

Takashi Oeda

Nobuo Kawamura

Yuto Hayamizu

Masashi Toyoda

A database system includes a plurality of DBMSs included in a plurality of nodes. Each DBMS is a first or a second DBMS. The first DBMS transfers a search query and does not execute data retrieval, and the second DBMS executes data retrieval. The plurality of nodes configure one or more node groups. Each node group includes a first node and one or more second nodes. In each node group, the first node is a logical computer that provides a first storage area and executes a first DBMS and the second node is a logical computer that provides a second storage area and executes a second DBMS, each node in the node group stores the same database therein, and data retrieval from the database in the node group is executed by one or more second DBMSs in the node group.

Database system and query execution method

As an I/O method of issuing an I/O request, there are a synchronous I/O method, in which a task is in a waiting state until an I/O response to the I/O request is returned and an asynchronous I/O method, in which another task can be executed before an I/O response to the I/O request is returned. When issuing an I/O request in execution of a task, a DBMS selects any one of the synchronous I/O method and the asynchronous I/O method, based on an I/O response speed of an I/O destination storage device and issues an I/O request according to the selected I/O method.

Database management system, computer, and database management method

There is a storage apparatus which provides a storage area, comprises a cache memory, reads data into the cache memory from the storage area according to a read request and sends the data from the cache memory, and a computer is coupled to the storage apparatus. The computer receives a data processing request, determines an access usage based on the data processing request (or, the information relating to an access usage of the data processing request), selects a logical device corresponding to the determined access usage from a plurality of logical devices which are allocated to the storage area and issues a read request to the selected logical device.

Computer and data read method

A management system manages a plurality of data units constituting schemas of a database in a storage device, which includes a plurality of first storage device sets having a plurality of storage areas. An ordered schema constituted of the plurality of data units having order properties defining respective orders is included in the schemas. When a second storage device set, which is a set of one or more second storage devices and in which each of the storage areas is a free storage area, is added to the first storage device set, the management system migrates two or more data units not consecutive in the order among a plurality of data units stored in the plurality of storage areas in the first storage device set respectively from at least the one first storage device set to the free storage areas of the second storage device set.

Management system and management method for managing data units constituting schemas of a database

This analysis system analyzes the behavior of a DBMS in a computer system having a computer which executes tasks in parallel and reads data from a database (DB) when executing a query. This analysis system acquires the number of selected rows corresponding to a key value of an index key used in the query, and calculates a model-based predicted degree of processing parallelism of the processing corresponding to the query. The system acquires, from the storage device, event information on an input-output event with respect to the storage medium when the processing corresponding to the query is executed actually, calculates a measured degree of processing parallelism when the processing corresponding to the query is executed actually, based on the event information, and displays information based on the model-based predicted degree of processing parallelism and the measured degree of processing parallelism.

Analysis system, computer system, and analysis method for analyzing behavior of database management system

A disk rotation control part for controlling the rotations of a plurality of disk devices is provided. The configuration is such that a disk of a disk device for which an access will not be generated is rotated at a second rate of speed, which is faster than 0, and slower than a first rate of speed, which is the rotation speed at access time. DB management information comprises information denoting which DB schema inside a DB is stored in which location. The disk rotation control part, based on a query plan of a query received by the DBMS, and DB management information, specifies the storage location of a DB schema to be accessed when this query is processed, and rotates a disk of the disk device comprising the specified storage location at a first rate of speed.

Computer system and method for reducing power consumption of storage system

Provided is a computer system including: a computer running as a DB server; a storage system including a plurality of disk drives for storing data; and a management module, in which: at least one of the plurality of disk drives stores data of a DB schema written by the computer; the management module specifies the DB schema to be accessed based on a received query, transmits, to the storage system, an instruction to copy at least a portion of the data of the specified DB schema from the disk drive to a memory, and transmits, to the storage system, an instruction to control an rpm of the disk drive that stores the data of the specified DB schema; and the storage system controls the rpm of the disk drive based on the instruction. Accordingly, power consumption of the storage system can be reduced even if installed disks increase in number.

Method of reducing storage power consumption by use of prefetch and computer system using the same

A pre-fetch server, which is connected to a DB server running a DBMS and to a storage apparatus storing DB data, stores information required for judging whether or not a pre-fetch is effective. Judgment on whether or not the pre-fetch will be effective is performed when a pre-fetch I/O is issued. If the pre-fetch server judges that the pre-fetch will be effective, it issues the pre-fetch I/O to the storage apparatus.

Computer system and database management method using the same

In a computer system with a DBMS running thereon, management of the performance of a storage apparatus is executed by using a performance indicator provided by a user job so as to simplify the management of the performance. For this reason, a management server employed in the computer system monitors an operating state of each system element, a response time onto a job and other information. A method for estimating a processing time is given to the management server, which issues a setting modification command based on an estimated processing time.

Computer system for managing performances of storage apparatus and performance management method of the computer system

A database system includes a center server and local servers. The center server includes a replication requesting unit, a data consolidating unit including a center DB freeze requesting unit and a center DB freeze release requesting unit, a replication source managing table and a data consolidation completion notifying unit. Each of the local servers includes a local DB freeze requesting unit, a remote volume split requesting unit, a remote volume split completion notifying unit and a local DB freeze release requesting unit. The center server permits replications of local DB's in local storage subsystems to be created in the center storage subsystem and accesses shadow images of the replications to give a consolidated access to the plurality of local DB's.

Database system including center server and local servers

In a system in which a DB is built in a virtualization environment, a management server obtains DB processing information such as a DB processing execution plan and a degree of processing priority from a DBMS, predicts data to be accessed in the near future and the order of such accesses based on the information, instructs to read into caches of storage devices data to be accessed in the near future based on the prediction results, and reads the data that will be accessed in the nearest future into a cache memory within the management server.

Prefetch appliance server

A database (DB) server in which a database management system (DBMS) operates and a prefetch server connected to a storage device storing DB data are provided with an acquiring unit for acquiring information on a storage location on the storage device of a DB schema managed by the DBMS, information on DB processing executed by the DBMS, and information on an access to DB data made when the DBMS executes the DB processing, from the DB server, a predictor for predicting data to be read out on the basis of the acquired information, and a prefetch instructing unit for providing the storage device with an instruction to prefetch the corresponding data. Having received the prefetch instruction, the storage device reads out specified data onto a cache memory.

Pre-fetch computer system

In the present invention, there is provided means which sets priorities of DB data for each management unit, means which copies data from a primary site to a secondary site in an order of the data priorities, and means which, when a disaster has occurred in the primary site and recovery of a DB is performed in the secondary site, performs recovery of data in the order of the data priorities to sequentially bring the data to a usable state.

Computer system for recovering data based on priority of the data

A data conversion job used for data conversion is separated into a data conversion server job for executing conversion processing on a data conversion server and a storage job for instructing a copy of a table on a storage device. Then, the storage job is executed to instruct the storage device to copy the table. The data conversion server job is executed only for fields that need to be converted, and thereby data conversion is performed for the copied table. This makes it possible to reduce a load of the data conversion server when converting data of a database, and also to enable a designer of a data conversion job to easily design the data conversion job.

Growing community of inventors

Yokohama, Japan

Hideomi Idei