WO2011099099A1 - ストレージ装置 - Google Patents
ストレージ装置 Download PDFInfo
- Publication number
- WO2011099099A1 WO2011099099A1 PCT/JP2010/006171 JP2010006171W WO2011099099A1 WO 2011099099 A1 WO2011099099 A1 WO 2011099099A1 JP 2010006171 W JP2010006171 W JP 2010006171W WO 2011099099 A1 WO2011099099 A1 WO 2011099099A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- separation
- marker
- file
- stored
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0608—Saving storage space on storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0655—Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
- G06F3/0659—Command handling arrangements, e.g. command buffers, queues, command scheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
- G06F3/0689—Disk arrays, e.g. RAID, JBOD
Definitions
- the present invention relates to a storage apparatus, and more particularly to a storage apparatus that eliminates redundant storage of data having the same content.
- a content address storage system has been developed in recent years as shown in Patent Document 1.
- data is distributed and stored in a plurality of storage devices, and the storage location where the data is stored is specified by a unique content address specified according to the content of the data.
- predetermined data is divided into a plurality of fragments, and a fragment that becomes redundant data is further added, and the plurality of fragments are respectively stored in a plurality of storage devices.
- the content address uses, for example, a hash value of data generated so as to be unique according to the content of the data. For this reason, if it is duplicate data, the data of the same content can be acquired by referring to the data at the same storage position. Therefore, it is not necessary to store the duplicate data separately, and duplicate recording can be eliminated and the data capacity can be reduced.
- a tree type file system is used.
- a content address that refers to stored data is referred to by a content address located in a higher hierarchy, and the content address is stored in a tree structure. Accordingly, the target storage data can be accessed by tracing the reference destination of the content address from the upper hierarchy to the lower hierarchy.
- FIG. 1 shows a general structure type file.
- a file is divided into fragments for each deduplication group (hereinafter, storage unit) and stored.
- storage unit data strings such as archive files and communication data are attached to the data with attached information called headers and trailers, and can be separated as a single piece of data (hereinafter referred to as a separation unit).
- an object of the present invention is to solve the decrease in data storage efficiency, which is the above-described problem.
- a storage apparatus provides: A temporary buffer for temporarily storing data that constitutes a file of a predetermined capacity requested for writing every time it is received from outside, The data stored in the temporary buffer is immediately separated into mutually corresponding data parts and marker parts classified according to preset criteria, and the data parts and marker parts are associated with each other to store data.
- the configuration is as follows.
- the program which is the other form of this invention is: To an information processing apparatus having a temporary buffer for temporarily storing data that constitutes a file of a predetermined capacity requested for writing every time it is received from the outside, The data stored in the temporary buffer is immediately separated into mutually corresponding data parts and marker parts classified according to preset criteria, and the data parts and marker parts are associated with each other to store data.
- the pre-separation data writing means for storing in the pre-separation data storage means,
- the data stored in the pre-separation data storage means is separated into the data part and the marker part corresponding to each other in accordance with a preset standard, and the data part and the marker part are associated with each other and the data Re-separation processing means for storing in the storage means and deleting from the pre-separation data storage means; It is a program for realizing.
- a data processing method includes: Each time data that constitutes a file of a predetermined capacity requested for writing is received from the outside, it is temporarily stored in a temporary buffer sequentially. The data stored in the temporary buffer is immediately separated into mutually corresponding data parts and marker parts classified according to preset criteria, and the data parts and marker parts are associated with each other to store data.
- the data stored in the pre-separation data storage means is separated into the data part and the marker part corresponding to each other in accordance with a preset standard, and the data part and the marker part are associated with each other and the data Storing in the storage means and deleting from the pre-separation data storage means,
- the configuration is as follows.
- the present invention can improve the data storage efficiency by being configured as described above.
- FIG. 1 is a block diagram showing a configuration of an entire system including a storage system in Embodiment 1 of the present invention.
- 1 is a block diagram showing an outline of the configuration of a storage system in Embodiment 1 of the present invention.
- 1 is a functional block diagram showing a configuration of a storage system in Embodiment 1 of the present invention.
- FIG. 5 is an explanatory diagram for explaining a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 4 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing and reading processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state when a file is received in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- FIG. 5 is an explanatory diagram illustrating a state of data storage processing in the storage system disclosed in FIG. 4.
- 5 is a flowchart showing an operation of data storage processing in the storage system disclosed in FIG. 4.
- 5 is a flowchart showing an operation of data storage processing in the storage system disclosed in FIG. 4.
- 2 is a functional block diagram illustrating a configuration of a storage system according to attachment 1.
- FIG. 2 is a block diagram showing the configuration of the entire system.
- FIG. 3 is a block diagram showing an outline of the storage system, and
- FIG. 4 is a functional block diagram showing the configuration.
- 5 to 12 are explanatory diagrams for explaining the operation of data storage processing in the storage system.
- 13 to 14 are flowcharts showing the operation of the storage system.
- the present embodiment shows a specific example of a storage device or the like described in an appendix to be described later.
- the storage system is configured by connecting a plurality of server computers.
- the storage system according to the present invention is not limited to being configured by a plurality of computers, and may be configured by a single computer.
- the storage system 100 is connected via a network N to a backup system 110 that controls backup processing. Then, the backup system 110 acquires backup target data (file) stored in the backup target device 120 connected via the network N and requests the storage system 100 to store it. As a result, the storage system 100 stores the backup target data requested to be stored for backup.
- the backup system 110 acquires backup target data (file) stored in the backup target device 120 connected via the network N and requests the storage system 100 to store it.
- the storage system 100 stores the backup target data requested to be stored for backup.
- the storage system 100 in the present embodiment is configured by connecting a plurality of server computers.
- the storage system 100 includes an accelerator node 101 that is a server computer that controls storage and reproduction operations in the storage system 100 itself, and a storage node 102 that is a server computer including a storage device that stores data. Yes.
- the number of accelerator nodes 101 and the number of storage nodes 102 are not limited to those shown in FIG. 3, and more nodes 101 and 102 may be connected.
- the storage system 100 divides and redundantly stores the data, distributes and stores the data in a plurality of storage devices, and stores the data according to a unique content address set according to the content of the stored data. It is a content address storage system for specifying a stored location. This content address storage system will be described in detail later.
- the storage system 100 is one system, the configuration and functions of the storage system 100 will be described. That is, the configuration and function of the storage system 100 described below may be provided in either the accelerator node 101 or the storage node 102. As shown in FIG. 3, the storage system 100 is not necessarily limited to including the accelerator node 101 and the storage node 102, and may have any configuration, for example, a single computer. May be. Furthermore, the storage system 100 is not limited to being a content address storage system.
- FIG. 4 shows the configuration of the storage system 10 in this embodiment.
- the storage system 10 is connected to the user application 1 corresponding to the backup target device 120 and the backup system 110 described above, and stores a file in response to a request from the user application 1. , A process of reading.
- the storage system 10 includes a data storage unit 31 and a pre-separation data storage unit 32 which are storage devices such as a hard disk drive for storing data.
- the storage system 10 also includes an arrival waiting buffer 30 that is a temporary storage device such as a flash memory.
- the storage system 10 includes a write processing unit 11, a read processing unit 12, a data / marker search unit 13, and a data / marker separation unit 14 that are constructed by incorporating a program into the arithmetic device provided.
- the storage system 10 described above includes a plurality of arithmetic devices and storage devices such as CPUs (Central Processing Unit) included in the accelerator node 101 and the storage node 102 illustrated in FIG. Has been.
- CPUs Central Processing Unit
- the storage system 10 in the present embodiment is a content address storage system. Therefore, the data storage unit 31 described above is a storage unit that stores data using content addresses, and the data writing unit 24, the marker writing unit 25, and the index writing unit 26 are as follows. The data is divided and distributed, the storage location is specified by the content address, and the data is stored.
- data storage processing using content addresses in the storage system 10 will be described with reference to FIGS.
- the file A is stored in a predetermined capacity (shown by an arrow Y2 in FIGS. 5 and 6). For example, it is divided into 64 KB) block data D. Based on the data contents of the block data D, a unique hash value H representing the data contents is calculated (arrow Y3). For example, the hash value H is calculated from the data content of the block data D using a preset hash function.
- the block data D that has already been stored has its hash value H and the content address CA representing the storage position associated with each other and registered in an MFI (Main Fragment Index) file. Therefore, when the hash value H of the block data D calculated before storage exists in the MFI file, it can be determined that the same block data D has already been stored (arrow Y4 in FIG. 6). In this case, the content address CA associated with the hash value H in the MFI that matches the hash value H of the block data D before storage is acquired from the MFI file.
- MFI Main Fragment Index
- this content address CA is returned as the content address CA of the block data D requested to be written.
- the already stored data referred to by the content address CA is used as the block data D requested to be written, and there is no need to store the block data D related to the write request.
- the block data D is compressed, and a plurality of pieces of fragment data having a predetermined capacity as shown by an arrow Y5 in FIG. Divide into For example, as shown by symbols D1 to D9 in FIG. 5, the data is divided into nine fragment data (divided data 41). Further, even if some of the divided fragment data is missing, redundant data is generated so that the original block data can be restored and added to the divided fragment data 41. For example, three pieces of fragment data (redundant data 42) are added as indicated by reference numerals D10 to D12 in FIG. As a result, a data set 40 composed of twelve fragment data composed of nine divided data 41 and three redundant data is generated.
- each fragment data constituting the data set generated as described above is distributed and stored in each storage area formed in the storage device. For example, as shown in FIG. 5, when 12 pieces of fragment data D1 to D12 are generated, each piece of fragment data D1 to D12 is stored in a data storage file formed in each of a plurality of storage devices. (See arrow Y6 in FIG. 6).
- the storage system 10 generates a content address CA indicating the storage position of the fragment data D1 to D12 stored as described above, that is, the storage position of the block data D restored by the fragment data D1 to D12.
- a content address CA indicating the storage position of the fragment data D1 to D12 stored as described above, that is, the storage position of the block data D restored by the fragment data D1 to D12.
- a part of the hash value H short hash
- information indicating the logical storage position Are combined to generate a content address CA.
- this content address CA is returned to the file system in the storage system 10 (arrow Y7 in FIG. 6).
- the storage system 10 manages identification information such as the file name of the backup target data and the content address CA in association with the file system.
- each storage node 102 manages the content address CA of the block data D and the hash value H of the block data D by using the MFI file.
- the content address CA is stored in the storage device of the accelerator node 101 or the storage node 102 in association with the information specifying the file, the hash value H, or the like.
- the storage system 10 controls to read out the stored file as described above. For example, when a read request is made by designating a specific file from the user application 1 to the storage system 10, first, based on the file system, a short which is a part of the hash value corresponding to the file related to the read request. A content address CA consisting of hash and logical position information is designated. Then, it is checked whether or not the content address CA is registered in the MFI file. If it is not registered, the requested data is not stored and an error is returned.
- the storage location specified by the content address CA is specified, and each fragment data stored in the specified storage location is read. Read as requested data.
- the storage position of other fragment data can be specified from the same storage position. .
- the block data D is restored from each fragment data read in response to the read request. Further, a plurality of restored block data D are concatenated, restored to a group of data such as file A, and returned.
- the storage system 10 in this embodiment eliminates duplication of data, but has a configuration for further enhancing data storage efficiency. This configuration will be described in detail.
- the storage system 10 in this embodiment includes the data marker separation unit 14 as described above.
- This data / marker separation unit 14 is an actual data portion of a file, and a “data” portion whose value does not change depending on a generated time, the number of updates, and the like, a time stamp, a serial number, etc. It is separated into a “marker” portion whose value changes depending on the difference. Then, the data / marker separation unit 14 separates partial data constituting the file requested to be written from the user application 1 into a “data” portion and a “marker” portion at a predetermined timing.
- the separation unit 14 reads out from either one according to the situation and separates into a “data” portion and a “marker” portion.
- the basic operation of the data separation processing by the data marker separation unit 14 will be described.
- the configuration of the file system constructed in the storage system 10 is referred to by, for example, a general UNIX (registered trademark) file system UFS1 (UFS: Unix File System) that stores data files before separation and an index.
- UFS1 Unix File System
- Content address file system CAFS1 CAFS: Content Address File System
- virtual FS1 that enables indirect reference to files stored in these two file systems
- Consists of Under the virtual FS1 (FS: File System)
- FS File System
- a write access to the file 1 indicates a write request from the user application 1.
- the name of the file system and the mounting location are not limited to those described above.
- the reference destination may be implemented in the same way as the symbolic link file, or may be implemented by calculating using a unique value such as an i-node number.
- the virtual file system may be realized by changing the OS (Operating System) kernel or adding a kernel module, or by using a technology that creates a file system in user space represented by FUSE (Filesystem in User Space).
- the configuration of the present invention is not limited by these techniques.
- FIG. 7 shows a state in which part of data constituting the file 1 stored in the arrival waiting buffer 30 is separated into a “data” portion and a “marker” portion.
- the storage system 10 sequentially receives a part of the data constituting the file 1 and stores it in the arrival waiting buffer 30, but the data marker separating unit 14 stores the data stored in the arrival waiting buffer 30.
- the copy data is stored in the arrival waiting buffer 30, it is separated into a “data” portion and a “marker” portion.
- Such separation processing is referred to as “inline method”.
- part of the data constituting the file is added with index information so that the separated “data” part and “marker” part can be combined at the time of reading, and linked from the index information as shown in the lower diagram of FIG.
- the data file and the marker file are separately stored (see FIG. 9).
- the reference destination of the file 1 is directed to the index file.
- the data file can be expected to have deduplication effect, and the index file and marker file cannot be expected to have much deduplication effect. For this reason, it is most efficient to store only the data file in the data storage unit 31 that stores the content file using the content address.
- the index file and the marker file may also be stored in the data storage unit 31 using the content address.
- the file reference from the user application 1 can be performed via the read processing unit 12.
- the index information, data, and marker corresponding to the file 1 on the virtual file system are read from the user application 1 and combined (see FIG. 9), so that the file 1 is restored and passed to the user application 1.
- FIG. 8 shows a process of separating some data stored in the pre-separation data storage unit 32 by the data / marker separation unit 14. Such separation processing is referred to as an “offline method”.
- the file 1 is stored as the pre-separation data file 1 in the pre-separation data storage unit 32 as shown in the lower diagram of FIG.
- the file 1 on the virtual file system (virtual FS) 1 does not have an entity but only a reference destination thereof. This may be implemented, for example, as a symbolic link file, or may be a method of obtaining a reference destination by calculation using the i-node number of the file.
- the pre-separation data storage unit 32 as a reference destination is preferably a normal file system, not a content address storage system. This is because a marker is included in the file 1 at this time, and it is difficult to deduplicate such a file and data.
- the data / marker separation unit 14 converts the partial data stored in the pre-separation data storage unit 32 into a “data” portion and a “marker” portion. And to separate. At this time, index information is added so that it can be combined in preparation for later reading.
- the index information is separated into three files, a data file and a marker file, which are stored in the data storage unit 31 using the content address. The At this time, the reference destination of the file 1 is directed to the index file.
- the file stored in the pre-separation data storage unit 32 may be deleted immediately, or if there is sufficient free space, leave it. You can leave it. Further, in order to deal with the shortage of free space, for example, the LRU (Least Recently Used) control may be deleted in order from the least frequently used. This is because when a file is updated or added, a file image is created again in the pre-separation data storage unit 32 and then used as a cache image when data and markers are separated again. .
- LRU Least Recently Used
- reading of the file 1 described above can also be performed from the pre-separation data storage unit 32.
- reading from the user application 1 to the file 1 on the virtual file system means that the target file is in the pre-separation data storage unit 32 or the data storage unit 31 from the reference destination of the file 1. Judging.
- the contents of the file 1 are acquired from the pre-separation data storage unit 32.
- the index information is acquired as described above, and the data linked by the index information and the marker are combined (see FIG. 9). Will be restored to the file.
- the multiplicity of communication may be increased in order to improve the speed when writing via a network.
- a device for increasing the bandwidth is performed by increasing the multiplicity and performing window control.
- a part of the file may not arrive.
- NFS Network File System
- NFS Network File System
- the offset can be shifted and written.
- the marker when data and markers are stored separately, the marker generally indicates the next marker, and therefore has a structure in which scanning is performed in order from the beginning of the file. For this reason, when a part of the data has not arrived, it is necessary to buffer and scan until the data is aligned.
- a method of not returning a response to the arrival of data or a method of returning a retry may be used to wait for unarrived portions to be aligned.
- the time until the completion of the storage of all data is increased, and the throughput is lowered.
- separation of subsequent data and markers can be given up, but in such a case, the deduplication rate becomes low.
- the means for separating the data and the marker in the offline method temporarily stores everything in the pre-division data storage unit and then performs the separation process in a lump, so writing with offsets can be processed without any problem. Additional storage capacity is required, and it takes time to complete data storage.
- the storage system 10 has the following configuration in order to suppress the additional storage capacity while further improving the deduplication efficiency.
- the write processing unit 11 receives a write request from the user application 1. Then, the data / marker search unit 13 temporarily stores in the arrival waiting buffer 30 (temporary buffer) a part of the data constituting the sequentially received file requested by the user application 1. At this time, the data / marker search unit 13 immediately searches whether there is a “data” portion and a “marker” portion corresponding to each other in the partial data stored in the arrival waiting buffer 30.
- the search for the “data” part and the “marker” part corresponding to each other in the partial data constituting the file is performed in order to distinguish the “data” part from the “marker” part in advance from the predetermined data.
- a reference is set, and a location corresponding to the reference is specified as a “data” portion and a “marker” portion corresponding to each other. For example, if a specific data format for determining the “marker” portion is set in advance and this data format portion exists in the search range, the portion is determined to be the “marker” portion. To do. Based on the data content of the “marker” portion, the “data” portion associated with the “marker” portion is determined as the “data” portion and the “marker” portion corresponding to each other.
- the “data” portion is, for example, data corresponding to the data content of the file, that is, data that does not change depending on the storage status, such as a time stamp.
- the “marker” portion is data that changes according to the situation when the file is saved, for example, data whose value changes depending on the time or the number of updates, such as a time stamp or a passing plate.
- the data marker search unit 13 searches for the “data” portion and the “marker” portion corresponding to each other, the data / marker search portion 13 passes the data in this range to the data marker separation portion 14. At this time, the data in the range passed to the data / marker separation unit 14 is deleted from the arrival waiting buffer 30.
- the data marker separation unit 14 Upon receiving this, the data marker separation unit 14 immediately separates the data in the range passed from the data marker separation unit 14 into a “data” portion and a “marker” portion. At this time, as described above, the “data” portion and the “marker” portion are separated based on a preset reference. Then, as described above, in the data writing unit 24, the marker writing unit 25, and the index writing unit 26, the “data” portion, the “marker” portion, and the “index” that links them are used as the content address. And stored in the data storage unit 31 in a distributed manner.
- the storage system 10 in this embodiment has the following data writing function (data writing means) based on the inline method.
- data writing function data writing means
- a part of data constituting the file 1 requested to be written by the user application 1 is sequentially stored in the arrival waiting buffer 30 every time it is received.
- data that is classified into a data part and a marker part corresponding to each other in accordance with a preset criterion exists in the partial data stored in the arrival waiting buffer 30, sequentially, these are separated.
- the data is stored in the data storage unit 31 and is deleted from the arrival waiting buffer 30. That is, data that cannot be separated into the “data” portion and the “marker” portion corresponding to each other among the partial data constituting the file 1 requested to be written remains in the arrival waiting buffer 30.
- the data marker search unit 13 in the present embodiment receives the partial data constituting the file 1 and determines that there is no more space in the arrival waiting buffer 30 for storing the partial data
- the data marker search unit 13 All the partial data stored in the waiting buffer 30 is transferred to the pre-separation data writing unit 21. Further, the partial data received from the user application 1 is sequentially transferred to the pre-separation data writing unit 21.
- the pre-separation data writing unit 21 stores the data passed from the data marker searching unit 13 in the pre-separation data storage unit 32. That is, the temporary data constituting the file 1 that cannot be separated stored in the arrival waiting buffer 30 and the remaining partial data constituting the file 1 received from the user application 1 after the arrival waiting buffer 30 runs out of free space Are stored in the pre-separation data storage unit 32.
- the pre-separation data writing unit 21 stores “effective length information” indicating the amount of partial data stored in the pre-separation data storage unit 32 from the arrival waiting buffer 30 in the storage system 10. Store in the device. For example, a part stored in the pre-separation data storage unit 32 by subtracting the offset on the file corresponding to the head from the offset on the file 1 corresponding to the tail of the temporary data stored in the waiting buffer 30 Store as effective length information of data. Further, the pre-separation data writing unit 21 receives the effective amount of the partial data constituting the file 1 received from the user application 1 and stored in the pre-separation data storage unit 32, that is, the offset on the file 1 as well. The effective length information is updated by adding to the length information.
- the reprocessing unit 23 receives the pre-separation data after the file processing of the file 1 requested to be written by the user application 1 is closed, that is, after the write processing unit 11 receives all the partial data constituting the file 1.
- the separation process of the data stored in the storage unit 32 is started. Specifically, the reprocessing unit 23 passes the data stored in the pre-separation data storage unit 32 to the data / marker separation unit 14. At this time, the reprocessing unit 23 deletes the data passed to the data / marker separation unit 14 from the pre-separation data storage unit 32.
- the data / marker separation unit 14 converts the data stored in the pre-separation data storage unit 32 into a “data” portion and a “marker” portion corresponding to each other according to a preset criterion. And stored in the data storage unit 31 using the content address.
- the reprocessing unit 23 separates the data stored in the pre-separation data storage unit 32 by the data / marker separation unit 14, and then the value of the separated data amount is stored in the stored effective length. Subtract from information.
- the storage system 10 has the following data writing function (pre-separation data writing means, re-separation processing means) based on the following offline method.
- the data in the buffer 30 is stored in the pre-separation data storage unit 32, and the remaining part of the data constituting the file received from the user application 1 is also stored in the arrival waiting buffer.
- the data is stored in the pre-separation data storage 32 sequentially without being stored in the data 30.
- the file 1 requested to be written by the user application 1 is closed, the data stored in the pre-separation data storage unit 32 is separated into the “data” part and the “marker” part corresponding to each other.
- the data address is stored in the data storage unit 31 using the content address.
- the data marker searching unit 13 described above is configured so that when the “effective length information” becomes “0”, that is, after all the partial data stored in the pre-separation data storage unit 32 is separated, Again, partial data of the file related to the write request received from the user application 1 is sequentially stored in the arrival waiting buffer 30. Then, as described above, separation processing by the inline method is executed until the arrival waiting buffer 30 is full.
- the read processing unit 12 (data reading unit) receives a file read request from the user application 1
- the target file is stored in either the pre-separation data storage unit 32 or the data storage unit 31.
- the temporary data constituting the file is read from the stored storage unit.
- the data is stored in the pre-separation data storage unit 32
- the data is read via the pre-separation data reading unit 22.
- the “data” portion and the “marker” are read from the data storage unit 31 via the index reading unit 27, the data reading unit 28, and the marker reading unit 29. "Portion is read and combined by the data / marker combining unit 15 to restore and read the file.
- the data marker searching unit 13 performs the processing in an inline manner because the effective length of the reference destination 2 is “0” (step S1: No). Specifically, the empty space in the arrival waiting buffer is confirmed. If there is an empty space (step S2: Yes), the partial data of the file 1 received from the user application 1 is sequentially stored in the arrival waiting buffer 30 ( Step S3).
- the data marker search unit 13 reads the separable data.
- the separation range is sequentially designated and transferred to the data / marker separation unit 14 and deleted from the arrival waiting buffer 30 (step S5).
- a plurality of separable data are found, they are all transferred to the data marker separation unit 14 and deleted from the arrival waiting buffer 30.
- the data marker separating unit 14 sequentially separates the data stored in the arrival waiting buffer 30 passed from the data marker searching unit 13 into a “data” portion and a “marker” portion corresponding to each other. . Then, as shown in FIGS. 11 and 12, the “data” portion and the “marker” portion are linked with the index data in the data storage unit 31 and stored using the content address. At this time, the reference destination of the file 1 is directed to the index file.
- step S2 data that cannot be separated remains among the partial data constituting the file 1 in the arrival waiting buffer 30, and then the arrival waiting buffer 30 is not empty (step S2: No). ).
- the data marker search unit 13 creates the pre-separation data file 1 in the pre-separation data storage unit 32, and “reference destination 2” indicates this ( Step S6).
- all the data in the arrival waiting buffer 30 is written to the pre-separation data file 1 in the pre-separation data storage unit 32.
- step S1: No the operation is performed by the offline method.
- step S1: No the storage system 10 converts the partial data constituting the file received from the user application 1 into the pre-separation data file in the pre-separation data storage unit 32. 1 is written in addition (step S8).
- the “reference destination 2 effective length” is updated.
- a part of data that has not arrived which is a corresponding missing part, arrives between the data received so far on the file, it is treated as a file update, and the effective length is not updated.
- step S11: Yes valid data is stored in “reference destination 2”, and “reference destination 2 effective length” is not “0”
- step S12: Yes it is checked whether there is data that can be separated from the data in the data file 1 before separation.
- the reprocessing unit 23 converts the data of the separation unit from the pre-separation data file 1 stored in the pre-separation data storage unit 32 to the data marker separation unit 14. And the corresponding part is deleted from the reference destination 2 (step S13).
- the data / marker separation unit 14 separates the passed data into a “data” portion and a “marker” portion corresponding to each other as described above. Then, as shown in FIG. 11 and FIG. 12, the data storage unit 31 is linked with index data and stored using a content address. At this time, the reference destination of the file 1 is directed to the index file.
- the reprocessing unit 23 subtracts the “reference destination 2 effective length” by the separated amount (step S14). In this way, reprocessing is performed until there is no separation, that is, until “reference destination 2 effective length” becomes “0”. As a result, the file is finally stored in the data storage unit 31 using the content address.
- the “marker” portion is extracted from the file and stored separately in the “data” portion and the “marker” portion. Duplication of stored data can be eliminated.
- the separation of the “data” part and the “marker” part by the inline method and the offline method is switched when the buffer amount exceeds a certain amount, so that the storage capacity can be suppressed while increasing the throughput. it can.
- the data stored in the temporary buffer 51 is immediately separated into mutually corresponding data parts and marker parts classified according to preset criteria, and the data parts are associated with the marker parts and stored.
- Data writing means 52 for storing in means 61 and deleting from said temporary buffer;
- the pre-separation data writing means 53 for storing in the pre-separation data storage means 62 the data that cannot be separated into the data part and the marker part corresponding to each other;
- the data stored in the pre-separation data storage means 62 is separated into the data part and the marker part corresponding to each other according to a preset criterion, and the data part and the marker part are associated with each other.
- Re-separation processing means 54 for storing in the data storage means 61 and deleting from the pre-separation data storage means 62, Storage device 50.
- the pre-separation data writing means stores the data stored in the temporary buffer in the pre-separation data storage means when the temporary buffer is full, and receives the data received from the outside, Each time it is received, it is sequentially stored in the pre-separation data storage means. Storage device.
- the storage device (Appendix 4) The storage device according to any one of appendices 1 to 3,
- the pre-separation data writing means stores effective length information indicating the data amount of the data stored in the pre-separation data storage means. Storage device.
- the storage device according to any one of appendices 1 to 6, In response to a request for reading the file from the outside, the data constituting the file includes data reading means for reading from the data storage means in which the data is stored or the data storage means before separation. Storage device.
- the storage device according to any one of appendices 1 to 7,
- the data portion is data corresponding to the data content of the file,
- the marker part is data that changes according to the situation when the file is saved. Storage device.
- Data writing means for storing and deleting from the temporary buffer;
- the pre-separation data writing means for storing in the pre-separation data storage means,
- the data stored in the pre-separation data storage means is separated into the data part and the marker part corresponding to each other in accordance with a preset standard, and the data part and the marker part are associated with each other and the data Re-separation processing means for storing in the storage means and deleting from the pre-separation data storage means;
- the pre-separation data writing means stores the data stored in the temporary buffer in the pre-separation data storage means when the temporary buffer is full, and receives the data received from the outside, Each time it is received, it is sequentially stored in the pre-separation data storage means. program.
- the data stored in the pre-separation data storage means is separated into the data part and the marker part corresponding to each other in accordance with a preset standard, and the data part and the marker part are associated with each other and the data Storing in the storage means and deleting from the pre-separation data storage means; Data processing method.
- Storage System 11 Write Processing Unit 12 Read Processing Unit 13 Data Marker Search Unit 14 Data Marker Separation Unit 15 Data Marker Combining Unit 21 Pre-separation Data Writing Unit 22 Pre-separation Data Reading Unit 23 Reprocessing Unit 24 Data Writing Loading unit 25 Marker writing unit 26 Index writing unit 27 Index reading unit 28 Data reading unit 29 Marker reading unit 30 Arrival waiting buffer 31 Data storage unit 32 Pre-separation data storage unit 40 Data set 41 Division data 42 Redundant data 50 Storage device 51 Temporary buffer 52 Data writing means 53 Pre-separation data writing means 54 Re-separation processing means 61 Data storage means 62 Pre-separation data storage means 100 Storage system 101 Accelerator node 102 Storage node 110 Backup system 12 Backup target device
Abstract
Description
書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時的に格納する一時バッファと、
上記一時バッファに格納された上記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、上記一時バッファから削除するデータ書込手段と、
上記一時バッファに格納された上記データのうち、相互に対応する上記データ部分と上記マーカ部分とに分離できない上記データを、分離前データ格納手段に格納する分離前データ書込手段と、
上記分離前データ格納手段に格納された上記データを、予め設定された基準に従って、相互に対応する上記データ部分と上記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて上記データ格納手段に記憶すると共に、上記分離前データ格納手段から削除する再分離処理手段と、を備えた、
という構成をとる。
書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時的に格納する一時バッファを備えた情報処理装置に、
上記一時バッファに格納された上記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、上記一時バッファから削除するデータ書込手段と、
上記一時バッファに格納された上記データのうち、相互に対応する上記データ部分と上記マーカ部分とに分離できない上記データを、分離前データ格納手段に格納する分離前データ書込手段と、
上記分離前データ格納手段に格納された上記データを、予め設定された基準に従って、相互に対応する上記データ部分と上記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて上記データ格納手段に記憶すると共に、上記分離前データ格納手段から削除する再分離処理手段と、
を実現させるためのプログラムである。
書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時バッファに一時的に格納し、
上記一時バッファに格納された上記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、上記一時バッファから削除し、
上記一時バッファに格納された上記データのうち、相互に対応する上記データ部分と上記マーカ部分とに分離できない上記データを、分離前データ格納手段に格納し、
上記分離前データ格納手段に格納された上記データを、予め設定された基準に従って、相互に対応する上記データ部分と上記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて上記データ格納手段に記憶すると共に、上記分離前データ格納手段から削除する、
という構成をとる。
本発明の第1の実施形態を、図2乃至図14を参照して説明する。図2は、システム全体の構成を示すブロック図である。図3は、ストレージシステムの概略を示すブロック図であり、図4は、構成を示す機能ブロック図である。図5乃至図12は、ストレージシステムにおけるデータ記憶処理の動作を説明するための説明図である。図13乃至図14は、ストレージシステムの動作を示すフローチャートである。
図2に示すように、本発明におけるストレージシステム100は、ネットワークNを介してバックアップ処理を制御するバックアップシステム110に接続している。そして、バックアップシステム110は、ネットワークNを介して接続されたバックアップ対象装置120に格納されているバックアップ対象データ(ファイル)を取得し、ストレージシステム100に対して記憶するよう要求する。これにより、ストレージシステム100は、記憶要求されたバックアップ対象データをバックアップ用に記憶する。
次に、上述したストレージシステム10の動作を、図11乃至図14を参照して説明する。まず、ユーザアプリケーション1からの書き込み要求により、仮想ファイルシステムにファイル1が作成されると、図12に示すように、データファイル1、マーカファイル1、インデックスファイル1が準備される。このとき、図12に示す参照先1、参照先2有効長(有効長情報)、参照先2が初期化される。ここで、参照先2有効長は、「0」で初期化する。また、参照先1は、インデックスファイルを示し、参照先2は、後ほど用意するためブランクとする。
上記実施形態の一部又は全部は、以下の付記のようにも記載されうる。以下、本発明におけるストレージ装置50の構成の概略について図15を参照して説明する。また、本発明における、プログラム、データ処理方法の構成について説明する。但し、本発明は、以下の構成に限定されない。
書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時的に格納する一時バッファ51と、
前記一時バッファ51に格納された前記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段61に記憶すると共に、前記一時バッファから削除するデータ書込手段52と、
前記一時バッファ51に格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、分離前データ格納手段62に格納する分離前データ書込手段53と、
前記分離前データ格納手段62に格納された前記データを、予め設定された基準に従って、相互に対応する前記データ部分と前記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて前記データ格納手段61に記憶すると共に、前記分離前データ格納手段62から削除する再分離処理手段54と、を備えた、
ストレージ装置50。
付記1に記載のストレージ装置であって、
前記分離前データ書込手段は、前記一時バッファの空きがなくなったときに、当該一時バッファに格納されている前記データを前記分離前データ格納手段に格納すると共に、外部から受信した前記データを、受信するごとに順次、前記分離前データ格納手段に格納する、
ストレージ装置。
付記2に記載のストレージ装置であって、
前記再分離処理手段は、前記ファイルを構成する前記データを全て外部から受信した後に作動する、
ストレージ装置。
付記1乃至3のいずれかに記載のストレージ装置であって、
前記分離前データ書込手段は、前記分離前データ格納手段に格納した前記データのデータ量を表す有効長情報を記憶する、
ストレージ装置。
付記4に記載のストレージ装置であって、
前記再分離処理手段は、前記分離前データ格納手段に格納された前記データを前記データ格納手段に記憶したときに、当該データのデータ量の値を前記有効長情報から減算し、
前記有効長情報の値に応じて、前記一時バッファは、外部から受信するデータを、順次、一時的に格納する、
ストレージ装置。
付記5に記載のストレージ装置であって、
前記有効長情報の値が0である場合に、前記一時バッファは、外部から受信するデータを、順次、一時的に格納する、
ストレージ装置。
付記1乃至6のいずれかに記載のストレージ装置であって、
外部からの前記ファイルの読み込み要求に応じて、当該ファイルを構成する前記データを、当該データが格納されている前記データ格納手段あるいは前記分離前データ格納手段から読み込むデータ読込手段を備えた、
ストレージ装置。
付記1乃至7のいずれかに記載のストレージ装置であって、
前記データ部分は、前記ファイルのデータ内容に応じたデータであり、
前記マーカ部分は、前記ファイルの保存時の状況に応じて変化するデータである、
ストレージ装置。
書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時的に格納する一時バッファを備えた情報処理装置に、
前記一時バッファに格納された前記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、前記一時バッファから削除するデータ書込手段と、
前記一時バッファに格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、分離前データ格納手段に格納する分離前データ書込手段と、
前記分離前データ格納手段に格納された前記データを、予め設定された基準に従って、相互に対応する前記データ部分と前記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて前記データ格納手段に記憶すると共に、前記分離前データ格納手段から削除する再分離処理手段と、
を実現させるためのプログラム。
付記9に記載のプログラムであって、
前記分離前データ書込手段は、前記一時バッファの空きがなくなったときに、当該一時バッファに格納されている前記データを前記分離前データ格納手段に格納すると共に、外部から受信した前記データを、受信するごとに順次、前記分離前データ格納手段に格納する、
プログラム。
書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時バッファに一時的に格納し、
前記一時バッファに格納された前記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、前記一時バッファから削除し、
前記一時バッファに格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、分離前データ格納手段に格納し、
前記分離前データ格納手段に格納された前記データを、予め設定された基準に従って、相互に対応する前記データ部分と前記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて前記データ格納手段に記憶すると共に、前記分離前データ格納手段から削除する、
データ処理方法。
付記11に記載のデータ処理方法であって、
前記一時バッファの空きがなくなったときに、当該一時バッファに格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、前記分離前データ格納手段に格納すると共に、外部から受信した前記データを、受信するごとに順次、前記分離前データ格納手段に格納する、
データ処理方法。
11 書込処理部
12 読込処理部
13 データ・マーカ検索部
14 データ・マーカ分離部
15 データ・マーカ結合部
21 分離前データ書込部
22 分離前データ読込部
23 再処理部
24 データ書込部
25 マーカ書込部
26 インデックス書込部
27 インデックス読込部
28 データ読込部
29 マーカ読込部
30 到着待ちバッファ
31 データ格納部
32 分離前データ格納部
40 データセット
41 分割データ
42 冗長データ
50 ストレージ装置
51 一時バッファ
52 データ書込手段
53 分離前データ書込手段
54 再分離処理手段
61 データ格納手段
62 分離前データ格納手段
100 ストレージシステム
101 アクセラレータノード
102 ストレージノード
110 バックアップシステム
120 バックアップ対象装置
Claims (10)
- 書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時的に格納する一時バッファと、
前記一時バッファに格納された前記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、前記一時バッファから削除するデータ書込手段と、
前記一時バッファに格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、分離前データ格納手段に格納する分離前データ書込手段と、
前記分離前データ格納手段に格納された前記データを、予め設定された基準に従って、相互に対応する前記データ部分と前記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて前記データ格納手段に記憶すると共に、前記分離前データ格納手段から削除する再分離処理手段と、を備えた、
ストレージ装置。 - 請求項1に記載のストレージ装置であって、
前記分離前データ書込手段は、前記一時バッファの空きがなくなったときに、当該一時バッファに格納されている前記データを前記分離前データ格納手段に格納すると共に、外部から受信した前記データを、受信するごとに順次、前記分離前データ格納手段に格納する、
ストレージ装置。 - 請求項2に記載のストレージ装置であって、
前記再分離処理手段は、前記ファイルを構成する前記データを全て外部から受信した後に作動する、
ストレージ装置。 - 請求項1乃至3のいずれか一項に記載のストレージ装置であって、
前記分離前データ書込手段は、前記分離前データ格納手段に格納した前記データのデータ量を表す有効長情報を記憶する、
ストレージ装置。 - 請求項4に記載のストレージ装置であって、
前記再分離処理手段は、前記分離前データ格納手段に格納された前記データを前記データ格納手段に記憶したときに、当該データのデータ量の値を前記有効長情報から減算し、
前記有効長情報の値に応じて、前記一時バッファは、外部から受信するデータを、順次、一時的に格納する、
ストレージ装置。 - 請求項5に記載のストレージ装置であって、
前記有効長情報の値が0である場合に、前記一時バッファは、外部から受信するデータを、順次、一時的に格納する、
ストレージ装置。 - 請求項1乃至6のいずれか一項に記載のストレージ装置であって、
外部からの前記ファイルの読み込み要求に応じて、当該ファイルを構成する前記データを、当該データが格納されている前記データ格納手段あるいは前記分離前データ格納手段から読み込むデータ読込手段を備えた、
ストレージ装置。 - 請求項1乃至7のいずれか一項に記載のストレージ装置であって、
前記データ部分は、前記ファイルのデータ内容に応じたデータであり、
前記マーカ部分は、前記ファイルの保存時の状況に応じて変化するデータである、
ストレージ装置。 - 書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時的に格納する一時バッファを備えた情報処理装置に、
前記一時バッファに格納された前記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、前記一時バッファから削除するデータ書込手段と、
前記一時バッファに格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、分離前データ格納手段に格納する分離前データ書込手段と、
前記分離前データ格納手段に格納された前記データを、予め設定された基準に従って、相互に対応する前記データ部分と前記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて前記データ格納手段に記憶すると共に、前記分離前データ格納手段から削除する再分離処理手段と、
を実現させるためのプログラム。 - 書き込み要求された所定容量のファイルを構成するデータを、外部から受信するごとに、順次、一時バッファに一時的に格納し、
前記一時バッファに格納された前記データを、直ちに、予め設定された基準に従って分類される相互に対応するデータ部分とマーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けてデータ格納手段に記憶すると共に、前記一時バッファから削除し、
前記一時バッファに格納された前記データのうち、相互に対応する前記データ部分と前記マーカ部分とに分離できない前記データを、分離前データ格納手段に格納し、
前記分離前データ格納手段に格納された前記データを、予め設定された基準に従って、相互に対応する前記データ部分と前記マーカ部分とに分離して、当該データ部分とマーカ部分とを関連付けて前記データ格納手段に記憶すると共に、前記分離前データ格納手段から削除する、
データ処理方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011553663A JP5533888B2 (ja) | 2010-02-10 | 2010-10-19 | ストレージ装置 |
US13/577,862 US9021230B2 (en) | 2010-02-10 | 2010-10-19 | Storage device |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010-027125 | 2010-02-10 | ||
JP2010027125 | 2010-02-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011099099A1 true WO2011099099A1 (ja) | 2011-08-18 |
Family
ID=44367413
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/006171 WO2011099099A1 (ja) | 2010-02-10 | 2010-10-19 | ストレージ装置 |
Country Status (3)
Country | Link |
---|---|
US (1) | US9021230B2 (ja) |
JP (1) | JP5533888B2 (ja) |
WO (1) | WO2011099099A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013047933A (ja) * | 2011-08-29 | 2013-03-07 | Hitachi Ltd | 階層ストレージシステムの重複排除効率の向上 |
JP2014191405A (ja) * | 2013-03-26 | 2014-10-06 | Nec Corp | 仮想化システム、仮想サーバ、ファイル書き込み方法、及びファイル書き込みプログラム |
WO2015033416A1 (ja) * | 2013-09-05 | 2015-03-12 | 株式会社日立製作所 | 情報処理システム及びそのデータ処理方法 |
JP2020140647A (ja) * | 2019-03-01 | 2020-09-03 | Necソリューションイノベータ株式会社 | 情報処理方法 |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014174380A2 (en) * | 2013-04-22 | 2014-10-30 | Bacula Systems Sa | Creating a universally deduplicatable archive volume |
US10692529B2 (en) * | 2018-07-23 | 2020-06-23 | Wasabi Technologies, Inc. | Systems and methods and systems for reading data sequentially on a media |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0258768A (ja) * | 1988-08-23 | 1990-02-27 | Toshiba Corp | ディスク制御装置 |
JP2009070361A (ja) * | 2007-09-11 | 2009-04-02 | Hitachi Ltd | コンピュータストレージシステムにおいてデータ圧縮並びに整合性を管理する方法および装置 |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4412285A (en) * | 1981-04-01 | 1983-10-25 | Teradata Corporation | Multiprocessor intercommunication system and method |
JP2504843B2 (ja) | 1989-09-06 | 1996-06-05 | シャープ株式会社 | バッファ拡張装置 |
US5396635A (en) * | 1990-06-01 | 1995-03-07 | Vadem Corporation | Power conservation apparatus having multiple power reduction levels dependent upon the activity of the computer system |
US20040052501A1 (en) * | 2002-09-12 | 2004-03-18 | Tam Eddy C. | Video event capturing system and method |
US20050195975A1 (en) * | 2003-01-21 | 2005-09-08 | Kevin Kawakita | Digital media distribution cryptography using media ticket smart cards |
JP3934569B2 (ja) * | 2003-03-12 | 2007-06-20 | 株式会社東芝 | 信号処理装置、プリフェッチ命令方法及びプリフェッチ命令プログラム |
JP3857995B2 (ja) * | 2003-03-24 | 2006-12-13 | 三洋電機株式会社 | コンテンツ記録再生装置 |
US7444389B2 (en) | 2003-12-09 | 2008-10-28 | Emc Corporation | Methods and apparatus for generating a content address to indicate data units written to a storage system proximate in time |
US7200626B1 (en) * | 2004-01-22 | 2007-04-03 | Unisys Corporation | System and method for verification of a quiesced database copy |
US7222133B1 (en) * | 2004-02-05 | 2007-05-22 | Unisys Corporation | Method for reducing database recovery time |
JP4453915B2 (ja) * | 2005-03-18 | 2010-04-21 | 富士通株式会社 | クロスバー装置、制御方法及びプログラム |
US7822700B2 (en) * | 2006-12-29 | 2010-10-26 | Brooks Roger K | Method for using lengths of data paths in assessing the morphological similarity of sets of data by using equivalence signatures |
JP4913085B2 (ja) | 2008-03-04 | 2012-04-11 | オリンパスイメージング株式会社 | マルチ画像ファイル編集装置、マルチ画像ファイル編集プログラム、マルチ画像ファイル編集方法 |
CN101582064B (zh) | 2008-05-15 | 2011-12-21 | 阿里巴巴集团控股有限公司 | 一种大数据量数据处理方法及系统 |
-
2010
- 2010-10-19 JP JP2011553663A patent/JP5533888B2/ja active Active
- 2010-10-19 WO PCT/JP2010/006171 patent/WO2011099099A1/ja active Application Filing
- 2010-10-19 US US13/577,862 patent/US9021230B2/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0258768A (ja) * | 1988-08-23 | 1990-02-27 | Toshiba Corp | ディスク制御装置 |
JP2009070361A (ja) * | 2007-09-11 | 2009-04-02 | Hitachi Ltd | コンピュータストレージシステムにおいてデータ圧縮並びに整合性を管理する方法および装置 |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013047933A (ja) * | 2011-08-29 | 2013-03-07 | Hitachi Ltd | 階層ストレージシステムの重複排除効率の向上 |
JP2014191405A (ja) * | 2013-03-26 | 2014-10-06 | Nec Corp | 仮想化システム、仮想サーバ、ファイル書き込み方法、及びファイル書き込みプログラム |
WO2015033416A1 (ja) * | 2013-09-05 | 2015-03-12 | 株式会社日立製作所 | 情報処理システム及びそのデータ処理方法 |
JP2020140647A (ja) * | 2019-03-01 | 2020-09-03 | Necソリューションイノベータ株式会社 | 情報処理方法 |
JP7456601B2 (ja) | 2019-03-01 | 2024-03-27 | Necソリューションイノベータ株式会社 | 情報処理方法 |
Also Published As
Publication number | Publication date |
---|---|
US9021230B2 (en) | 2015-04-28 |
JP5533888B2 (ja) | 2014-06-25 |
US20120311294A1 (en) | 2012-12-06 |
JPWO2011099099A1 (ja) | 2013-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8386733B1 (en) | Method and apparatus for performing file-level restoration from a block-based backup file stored on a sequential storage device | |
US7827368B2 (en) | Snapshot format conversion method and apparatus | |
JP5533888B2 (ja) | ストレージ装置 | |
JP5339432B2 (ja) | ストレージシステム | |
JP5485866B2 (ja) | 情報管理方法、及び情報提供用計算機 | |
US20100082529A1 (en) | Log Structured Content Addressable Deduplicating Storage | |
JP2006268829A (ja) | ストレージシステム間でオブジェクトをミラー化する方法と装置 | |
JP5464269B2 (ja) | ファイルストレージ装置、データ格納方法およびデータ格納プログラム | |
US20110099343A1 (en) | Self-Adjusting Change Tracking for Fast Resynchronization | |
US20080320062A1 (en) | Method of transferring file system, file system transference program, and file system transference device | |
JP5391705B2 (ja) | ストレージシステム | |
US8612717B2 (en) | Storage system | |
EP2669806B1 (en) | Storage system | |
JP5517224B2 (ja) | ストレージ装置 | |
US20220244856A1 (en) | Technique for replicating oplog index among nodes of a cluster | |
JP5660617B2 (ja) | ストレージ装置 | |
JP5459388B2 (ja) | ストレージ装置 | |
JP2009151397A (ja) | 階層記憶制御装置、階層記憶制御システム及びそれらに用いる階層記憶制御方法及びそのプログラム | |
JP6413792B2 (ja) | ストレージシステム | |
US10712941B2 (en) | Leveraging temporal locality to link files together and bypass accessing a central inode list | |
KR101086392B1 (ko) | Wal 기법에서 대용량 객체의 파손 회복 방법 | |
JP6201340B2 (ja) | レプリケーションシステム | |
US20110004750A1 (en) | Hierarchical skipping method for optimizing data transfer through retrieval and identification of non-redundant components | |
JP6343952B2 (ja) | ストレージシステム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10845704 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2011553663 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13577862 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 10845704 Country of ref document: EP Kind code of ref document: A1 |