Fujitsu Corporation

Yoshihiro Tsuchiya

Yasuo Noguchi

Takashi Watanabe

Masahisa Tamura

Kazutaka Ogihara

Tetsutaro Maruyama

Tatsuo Kumano

Kazuichi Oe

Riichiro Take

Toshihiro Ozawa

Shigeyuki Miyamoto

Minoru Kamoshida

Yoshitake Shinkai

Minoru Kamosida

Yuzi Kanazawa

Seiji Toda

Hideki Sakurai

Kazutaka Ogiwara

A storage control apparatus includes a plurality of MBFs for managing pieces of data stored in a storage by storage region, caches some of the MBFs on a RAM, and determines the presence or absence of redundancy on a basis of the MBFs on the RAM alone. The storage control apparatus performs redundancy elimination on the pieces of data already stored in the storage on the basis of how the MBFs are used such that the contents of a hash log for an MBF higher in frequency of use are maintained.

Storage control apparatus and storage control method

A storage control apparatus includes a memory, and a processor. The memory is configured to retain associative relation information for managing an associative relation between a hash value associated with a first address being inputted and a second address as an address of the storage device, filter information containing Bloom filters, and overlap count management information. The processor executes a process that causes the storage control apparatus to perform first storing the storage target data in the storage device without being registered in the filter information, second storing the storage target data in the storage device as well as registering the storage target data in the filter information, performing neither registering the storage target data in the filter information nor storing the storage target data in the storage device and deleting deletable data from the storage device.

Storage control apparatus and control method of storage control apparatus

A deduplicate device includes: a first through N-th (N&#x2267;3) bloom filters; a counting unit that performs a process of judging whether information indicating that a duplicate data of a storing-target data exists in a storage device is registered in each bloom filter sequentially until an unregistered bloom filter in which the information is not registered is found or that the information is registered in the N-th bloom filter is found, and registers, when the unregistered bloom filter is found, the information indicating that the duplicate data exists into the unregistered bloom filter; and a deduplicating unit that stores the storing-target data in the storage device when the counting unit finds the unregistered bloom filter, and stores index information relating the duplicate data in the storage device with the storing-target data when the counting unit finds that the information is registered in the N-th bloom filter.

Deduplication device and deduplication method

A computer-readable recording medium stores a program that causes a computer to execute a writing control process that includes receiving a writing request to write a first data to a first storage apparatus; determining a second data from among a series of data and based on a writing sequence of the series of data written to the computer and a count of storage areas at a second storage apparatus that sequentially selects from among the storage areas when data is received, a storage area to be over written by the received data, where the second data is written to the first storage apparatus and is identical to data that is stored in the storage area to be selected next at the second storage apparatus; and transmitting copy data of the first data to the second storage apparatus, when the second data has been written to the first storage apparatus.

Computer product, writing control method, writing control apparatus, and system

A data existence judging device includes: L number of first storage areas each associated with one of L hash values; M number of second storage areas each associated with some of the L hash values; an information setting part, for each data in a data set, to calculate k hash values about the data, and, for each calculated hash value, when a count value in the first storage area associated with the calculated hash value is less than 2&#x2212;1, to count up the count value, whereas when the count value is 2&#x2212;1, to set 1 into the first storage area associated with the calculated hash value; and a judging part to calculate k hash values about an input data, and to judge that the input data is a new data when a count value in the first storage area associated with the input data is 0.

Data existence judging device and data existence judging method

An access method includes: obtaining, by a computer, a result of monitoring a busy rate and a number of access operations per unit time of a storage device, the storage device having a first storage area and a second storage area; calculating a characteristic of correlation between the busy rate and the number of access operations per unit time based on the result; calculating a second number of access operations per unit time based on the characteristic of the correlation such that a sum of a first busy rate corresponding to a first number of access operations per unit time and a second busy rate corresponding to a second number of access operations per unit time becomes equal to or lower than a given busy rate; and controlling a number of operations to access the second storage area per unit time based on the second number of access operations.

Access method, computer and recording medium

An information processing apparatus includes a first storage unit and a processor. The first storage unit includes a first storage area. The processor receives a first request to write first data into the first storage area. The processor requests an external apparatus to write the first data into a second storage area in a second storage unit included in the external apparatus. The processor determines whether a first response has been received from the external apparatus. The first response indicates that the first data has been written into the second storage area. The processor writes the first data into the first storage area when the first response has been received. The processor requests, without writing the first data into the first storage area, the external apparatus to write second data stored in the first storage area into the second storage area when the first response has not been received.

Information processing apparatus and storage control method

Nodes respectively store a multilayer transposed Bloom filter. A client selects a node Nfrom among the group of nodes and transmits a search request to the node N. Upon receiving a reply from the node N, the client determines whether the received search result indicates 'positive'. If the search result is not positive, the client selects in order of node number, a node Nand transmits a search request to the node N. Upon receiving a reply from the node N, the client determines whether the received search result indicates 'positive'. Upon determining that the search result is positive, the client outputs the search result and ends the search notification process.

Computer product, search method, search apparatus, and node

A method of managing storage implemented in a storage management device that manages storage to which access for information is made by a requesting processing apparatus, including randomly obtaining a prescribed number of data units from among data units that constitute the information from the storage, calculating a sample unit duplication ratio, which is a ratio at which the obtained data units duplicate each other, estimating an overall data unit duplication ratio, which is a ratio at which all data units stored in the storage duplicate each other, by using a prescribed function that utilizes the calculated sample unit duplication ratio, and outputting the estimated overall data unit duplication ratio to an output device.

Duplication elimination in a storage service

A non-transitory computer-readable recording medium stores therein a charge calculating program that causes a computer that manages a database of different data items to execute recording for each data item, information indicating the number of clients that receive the data item; extracting from the information recorded at the recording and for each data item to be received by a given client, information indicating the number of clients receiving the data item; calculating charges for the given client, based on the extracted information; and outputting the calculated charges.

Computer product, charge calculating apparatus, and charge calculating method

An information processing device is provided that provides service by executing a service provider program in a cluster system. The device includes a program information transmission unit that transmits to a monitoring node that monitors the cluster system, a node list information reception unit that receives node list information, an update target selection unit that determines which of the other information processing devices which are not yet updated with the service provider program by referring to the program information in the node list information, a command timing determination unit that determines a time after a lapse of the standby time found in the first update timing information as a command timing of the update command, an update timing information generation unit that generates second update timing information and an update command transmission unit that transmits the update command about the service provider program and the second update timing information.

Computer-readable recording medium storing software update command program, software update command method, and information processing device

A file server has a conversion table that stores therein, in a corresponding manner, logical addresses specified by a higher-level layer and physical addresses specified by a disk driver that are address information indicative of a storage area in a disk device. The file server accesses the disk device with a storage area indicated by a physical address as an access destination and counts up the number of access requests to each storage area in a given period of time for each of the logical addresses. The file server then updates the conversion table such that the physical addresses are lined up in a descending order of the logical addresses of a higher number of the access requests counted. Thereafter, the file server changes storage areas of data stored in the storage device based on the conversion table updated.

Non-transitory medium, access control method, and information processing apparatus

A computer-readable, non-transitory medium stores therein a search program that causes a computer having access to a data block set that includes data groups respectively registered in data blocks, and a Bloom filter row of n Bloom filters that each have m bits indicating negativity in a given number of the data blocks, to execute a process that includes receiving a transposition request for the Bloom filter row; transposing the Bloom filter row into a transposed Bloom filter row of m transposed Bloom filters respectively of n bits gathered from the Bloom filters according to arrangement position in the Bloom filters; and storing the transposed Bloom filter row to a storage device, if a transposition request has been received at the receiving.

Computer product, search apparatus, management apparatus, search method, and management method

In a computer for executing processing based on a storage management program, a management information storing unit designates, from the data blocks having the same content, main-data used as an access destination and sub-data used as a backup, and stores management information that registers storage nodes as allocation destinations of the respective main-data and sub-data; a load information collecting unit continuously collects load information on the storage nodes; a replacement object detecting unit detects a pair of the main-data and the sub-data having the same content and having a predetermined condition such that a load difference between the allocation destination of the main-data and that of the sub-data exceeds a predetermined allowable value; and a management information updating unit replaces roles of the main-data and the sub-data between the detected pair of data blocks.

Program, apparatus and method for managing data allocation of distributed storage system including storage nodes

In a distributed storage system, client terminals make access to virtual storage areas provided as logical segments of a storage volume. Those logical segments are associated with physical segments that serve as real data storage areas. A management data storage unit stores management data describing the association between such logical segments and physical segments. Upon receipt of access requests directed to a specific access range, a segment identification unit consults the management data to identify logical segments in the specified access range and their associated physical segments. A remapping unit subdivides the identified logical segments and physical segments into logical sub-segments and physical sub-segments, respectively, and remaps the logical sub-segments to the physical sub-segments according to a predetermined remapping algorithm. A data access unit executes the access requests based on the remapped logical sub-segments and physical sub-segments.

Growing community of inventors

Kawasaki, Japan

Yoshihiro Tsuchiya