KR101893566B1 - Data distribution storage apparatus and method using cyclic difference family - Google Patents

Abstract

Disclosed is a data distribution storage apparatus and method utilizing a cyclic difference family. A method for distributing a plurality of messages to a plurality of data stores, the method comprising: distributing the plurality of messages using only a minimum of data stores, selecting only a minimum data store among the data stores, So that the plurality of messages can be loaded so as to prevent data loss for the plurality of messages and to enable fast data loading from the data stores.

Description

TECHNICAL FIELD [0001] The present invention relates to a data distribution storage apparatus and a data distribution method using circulation tiles,

The present invention relates to a technique for distributing and storing a plurality of messages in a plurality of data stores so as to facilitate recovery of data when data loss occurs.

Recently, as the spread of the Internet becomes active, a variety of Internet service providers are emerging. These Internet service providers provide e-mail services, or provide various services such as blogs, cafes, and cloud data storage services.

Especially, as the popularity of social network services has increased recently, a lot of Internet service providers providing social network services are also increasing in number.

These Internet service providers need to store a large amount of data uploaded from a large number of client terminals in their own data storage to provide an e-mail service, a blog, a cafe, a cloud service, a social network service, If it is lost in the store, it is trying to prevent loss of data because it does not provide normal service to customers.

One such effort is introducing a way to back up user messages that need to be stored in a data store to multiple data stores. Such a data backup method is one of the most ideal methods for coping with data loss in that the original message can be replaced by using a backup message even if the original message is lost.

In this way, when one original message is stored in a plurality of data stores at a plurality of times, when a data load command for the original message is applied, Since the message corresponding to the original message is immediately loaded from the data storage, it is possible to provide a faster speed of data loading than a method of storing the original message in one data storage.

However, in the existing data backup method, only a method of distributing a copy message for an original message to a plurality of data stores is adopted, and therefore, from the viewpoint of Internet service providers who need to store a large number of messages in a data store, A problem may arise in that a large amount of data storage capacity is required because copy messages for each of a plurality of messages are generated and distributedly stored in the respective data stores.

Accordingly, in a method of distributing a plurality of messages to a plurality of data stores, a method of distributing a plurality of messages using only a minimum number of data stores and selecting and accessing only a minimum data store among the data stores There is a need for research on a technique for preventing data loss for the plurality of messages and enabling quick data loading from the data stores by loading all of the plurality of messages.

A method for distributing a plurality of messages to a plurality of data stores, the method comprising: distributing the plurality of messages using only a minimum of data stores, selecting only a minimum data store among the data stores, So that the plurality of messages can be loaded so as to prevent data loss for the plurality of messages and to enable fast data loading from the data stores.

In the data distributed storage apparatus using the circulation system according to the embodiment of the present invention, N - N is a natural number satisfying the condition of N = tv, and v satisfies the condition of v = k (k-1) t + 1 , K is a natural number greater than or equal to 2, t is a natural number greater than or equal to 1, - distributed messages to v data stores for the messages are applied, v message distributions corresponding to the v data stores Tk - tk is a product of t and k - distributed allocation of v messages, - distributed allocation of v message distribution groups, The message distribution schemes and the t message messages allocated to each of the v message distribution groups may be transmitted to the v data stores And a data storage unit for separately storing the data in the data repository corresponding to each message distribution group.

In the data distribution storage method using the cyclic shift according to an embodiment of the present invention, N - N is a natural number satisfying the condition of N = tv, and v is a condition of v = k (k-1) t + 1 , K is a natural number equal to or greater than 2, and t is a natural number equal to or greater than 1. When a distributed storage command is applied to v data stores for messages, v data corresponding to the v data stores Tk - tk means a product of t and k - distributedly allocated - distributedly distributed among the v message distribution groups - message distribution groups - Messages may be duplicated to each other, transmitting tk messages allocated to each of the v message distribution groups to the message distribution groups of the v data stores, In a data repository corresponding to < RTI ID = 0.0 > a < / RTI >

A method for distributing a plurality of messages to a plurality of data stores, the method comprising: distributing the plurality of messages using only a minimum of data stores, selecting only a minimum data store among the data stores, A plurality of messages can be loaded so as to prevent data loss for the plurality of messages and to provide a technique for enabling fast data loading from data stores.

1 is a diagram illustrating a structure of a data distribution storage apparatus utilizing a cyclic difference family according to an embodiment of the present invention.
FIG. 2 is a view for explaining the operation of a data distribution storage apparatus using a cyclic shift according to an embodiment of the present invention.
FIG. 3 is a flowchart illustrating a data distribution storage method using a cyclic shift according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. It is to be understood that the description is not intended to limit the invention to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals in the drawings are used for similar elements and, unless otherwise defined, all terms used in the specification, including technical and scientific terms, are to be construed in a manner that is familiar to those skilled in the art. It has the same meaning as commonly understood by those who have it.

1 is a diagram illustrating a structure of a data distribution storage apparatus utilizing a cyclic difference family according to an embodiment of the present invention.

Referring to FIG. 1, a data distribution storage apparatus 110 using a circulation system according to an embodiment of the present invention includes a distribution group generation unit 111, a message distribution assignment unit 112, and a data storage unit 113 .

The distribution group generation unit 111 generates a distribution group for the v messages corresponding to the v data stores 101, 102, and 103 when the distributed storage command to the v data stores 101, 102, Message distribution groups.

Here, N is a natural number satisfying the condition of N = tv, v is a natural number satisfying the condition of v = k (k-1) t + 1, k is a natural number of 2 or more, and t is a natural number of 1 or more.

A message is a kind of data symbol to be stored in v data stores 101, 102 and 103, and the N messages are different data symbols.

The message distribution assigning unit 112 distributes the N messages tk (tk is a product of t and k) to each of the v message distribution groups.

 At this time, messages distributedly allocated to the v message distribution groups may overlap each other.

The data storage unit 113 stores tk messages allocated to the v message distribution groups into each message distribution group among the v message distribution groups and v data stores 101, And stores them separately in the corresponding data repository.

In this case, according to an embodiment of the present invention, the message distribution assignment unit 112 includes a circulation order confirmation unit 114, a first sequence generation unit 115, a second sequence generation unit 116, a sequence matching unit 117 And an assigning unit 118. [0050]

The cyclic shift confirmation unit 114 has k elements (hereinafter, referred to as " k elements ") for Z _v (the number of elements contained in Z _v is an integer of _v) including integers from "0" , Each of all the differences between two different elements among the k elements included in each of the plurality of subsets includes the elements other than "0" in the elements included in the Z _v And t subsets identified as matching only one other element (the collection of t subsets is defined as a circle with parameters of (v, k, 1)).

The first sequence generator 115 generates, for each of the t subsets, the values of "0" to "v" included in the Z _v based on k elements included in each of the t subsets Quot; 1 " and " 0 "code values by assigning code values of" 1 "and" 0 "from" 0 "to" v- (N = tv, wherein v for each of the t subsets is "1 "," 1 " and " 0 "are generated by combining the t partial sequences generated by assigning the code values of " ).

At this time, the first sequence generation unit 115 in respect to each of the two said t subsets, each of the t partial set of integer from "0" contained in the Z _v to "v-1", respectively Assigns a code value of "1 " to integers corresponding to the k elements contained therein, and assigns a code value of" 0 " to the remaining constants that do not match k elements contained in each of the t subsets Quot; and "0" by assigning a code value of " 1 "

The second sequence generator 116 performs a cyclic shift operation in a predetermined direction on each of the t partial sequences composed of the v code values of "1" and "0 & v-1 times, and generates a second sequence by combining the t partial sequences that have undergone the cyclic shift operation each time each cyclic shift operation is performed, thereby generating a total of v-1 second sequences.

Here, the Cyclic Difference Family will be described as follows.

라고 하면, 상기 복수의 부분 집합들 B_i 중, 각 부분 집합에 포함되어 있는 k개의 원소들 중에서 서로 다른 두 원소 간의 모든 차들 각각이 상기 Z_v에 포함되어 있는 원소들에서 "0"을 제외한 서로 다른 λ개의 원소와 일치하는 것으로 연산되는 부분 집합들의 모임을 (v, k, λ)의 파라미터를 갖는 순환 차족이라고 한다.When there is Z _{v which} is an aggregate containing integers from "0" to "v-1" as elements, a plurality of subsets having k elements for Z _v

, Each of all the differences between two different elements among the k elements included in each subset among the plurality of subsets B _i is different from each other in the elements included in the Z _v except for "0" A collection of subsets that are calculated to match the other λ elements is called a circles group with parameters of (v, k, λ).

Here, if all the differences between two different elements among the k elements included in each of the plurality of subsets B _i are denoted by D, D is calculated according to the following equation (1). If the difference between the two different elements is a negative value, the difference between the two different elements may be a residual value obtained by dividing the negative value by v according to the following equation (1).

At this time, the cyclic shift having the parameters of (v, k, 1) means a plurality of subsets having k elements for Z _v , which is an aggregate containing integers from "0" to "v- wherein, except for "0" in the element that is included in which the Z _v all cars each between two other elements that are calculated according to the equation (1) from among the k number of elements included in each of the plurality of the subset A collection of subsets that are found to match only one different element can be defined as a circle with parameters of (v, k, 1).

At this time, when v satisfies the condition of "v = k (k-1) t + 1", there may be a total of t subsets included in the circles having the parameters of (v, k, 1) .

For example, suppose that t = 2, k = 3, v = 13, and the element containing "0,1,2,3,4,5,6,7,8,9,10,11,12" When there is a set Z _v , there may be a plurality of subsets of Z _v containing three elements. Since the plurality of subsets such comprise three elements, each difference between the two different elements included in each subset may be present in a total of six, with the difference between these six two elements included in the Z _v " A set of subsets that are found to match only one integer except for "0" among 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, (13, 3, 1).

In this regard, there may be a subset contained in the circles having parameters of (13, 3, 1) "{0, 1, 4}", "{0, 2, 7}". In the case of "{0,1,4}", "1, 3, 4, 9, 10, 12" can be obtained by calculating the difference between two different elements according to Equation 1, , {3, 4, 9, 10, 12} each correspond only to one of the constants contained in Z _v , so "{0, 1, 4} Or a subset included in one of the circles. In the case of "{0, 2, 7}", the difference between two different elements may be "2, 5, 6, 7, 8, 11" , {5, 6, 7, 8, 11} each correspond only to one of the constants contained in Z _v , so "{0, 2, 7} Or a subset included in one of the circles.

When v satisfies the condition of "v = k (k-1) t + 1 ", when there are t subsets included in the circles having the parameters of (v, k, with respect to t of a subset each, of the integer of the integer from "0" contained in the Z _v to "v-1 'matching the k-element that is included in each of the t partial set Quot; 0 "is assigned to the remaining integers that do not match the k elements contained in each of the t subsets, v" 1 "and" 0 "code values.

If the t sequences are referred to as t partial sequences and the t partial sequences are arranged in a row and combined with each other, a total of N (N = tv) code values of "1" and "0" ≪ / RTI > can be obtained.

Then, a cyclic shift operation is performed v-1 times in a predetermined direction for each of the t partial sequences composed of the v number of code values of "1" and "0", and each time each cyclic shift operation is performed When the second sequence is generated by arranging and arranging the t partial sequences having completed the cyclic shift operation in a row, a total of v-1 second sequences can be additionally obtained.

개 이상이 되고, "0"의 코드 값의 개수는 항상

개 이하가 되는 특징을 가지게 된다.At this time, the number of code values of "1" existing in the first sequence and the second sequence is always constant at tk, and v satisfies the condition of "v = k (k-1) t + , If all the tk sequences randomly selected from among the first sequence and the second sequence are randomly selected and then all the sequences of tk selected randomly are ORed, The number of code values of "1"

, And the number of code values of "0"

Or less.

For example, suppose that k = 3 and t = 2 and v is 13, assuming that v = k (k-1) t + 1, then 0,1,2,3,4,5,6 , The subsets contained in the cyclic series with parameters of (13, 3, 1) at Z _v , which contain the elements 7, 8, 9, 10, } "And" {0, 2, 7} "exist.

Is included in each of the two subsets "{0, 1, 4}", "{0, 2, 7}" of integers from "0" to "12" included in the Z _v Code values of " 1 "are assigned to integers corresponding to the three elements of " {0,1,4} "," {0,1,2,7} "Quot; 0 "is assigned to the remaining integers that do not coincide with the three elements that are present, the two partial sequences" 1100100000000 "and" 1010000100000 "

At this time, if two partial sequences of "1100100000000" and "1010000100000" are arranged in a line and combined, a first sequence of "11001000000001010000100000" composed of 26 code values of "1" and "0" .

The two partial sequences "1100100000000" and "1010000100000" are subjected to a cyclic shift operation 12 times in the right direction, and each time each cyclic shift operation is performed, the two partial sequences having completed the cyclic shift operation are divided into a series , A total of 12 second sequences can be additionally obtained.

In this regard, if one circular shift operation is performed rightward for the two partial sequences "1100100000000" and "1010000100000", two additional partial sequences "0110010000000" and "0101000010000" can be obtained Quot; 0110010000000 "and" 0101000010000 "are combined and arranged in a line, an additional sequence" 01100100000000101000010000 " In this manner, if a cyclic shift operation is performed 12 times in the right direction with respect to two partial sequences and an additional sequence is obtained, a total of 12 sequences can be obtained since 12 cyclic shift operations are performed.

In this way, when a sequence is generated, a total of thirteen sequences can be finally generated, wherein the number of code values of "1" existing in each sequence is constant at six, and the 13 sequences The number of code values of "1" existing in the result of performing the "OR" operation is always 21 , And the number of code values of "0 " is always 5 or less.

According to the above-described sequence generation process using the cyclic shift, the cyclic shift confirmation unit 114 determines whether or not N satisfies the condition of v = k (k-1) t + 1 where N is a natural number satisfying the condition of N = tv Having a k number of elements with respect to Z _v , which is a set of natural numbers satisfying k, a natural number of 2 or more, and t is a natural number of 1 or more and containing integers from "0" to "v- Among all the k elements included in each of the plurality of subsets, each of all the differences between two different elements is different from the elements included in the Z _v by 1 T subsets (the collection of t subsets is defined as a circle with parameters of (v, k, 1)) that are found to match only the elements.

When confirmation of the t subsets included in the cyclic series having parameters of (v, k, 1) is completed, the first sequence generator 115 generates, for each of the t subsets, a code value of "1" for integers that are consistent with the k number of elements in one of an integer from "0" contained in the Z _v to "v-1" included in each of the t partial set And assigning code values of "0" to the remaining constants that do not match the k elements contained in each of the t subsets, so that v code values of "1" and "0"Lt; RTI ID = 0.0 > t < / RTI >

The first sequence generator 115 may then combine the t partial sequences to generate a first sequence consisting of a total of N (N = tv) code values of "1" and "0" .

The second sequence generator 116 performs the cyclic shift operation v-1 times in the predetermined direction for each of the t partial sequences composed of the v code values of "1" and "0 & And each time each cyclic shift operation is performed, combining the t partial sequences that have completed the cyclic shift operation to generate a second sequence, thereby generating a total of v-1 second sequences.

When the first sequence and the v-1 second sequences are generated, the sequence matching unit 117 may combine the first sequence and the v-1 second sequences with respect to each of the v message distribution groups Match one by one.

For each of the v message distribution groups, the allocating unit 118 allocates the N messages to the v message distribution groups in units of tk based on N code values constituting each sequence matched to each of the v message distribution groups. Distributed allocation.

In this case, according to an embodiment of the present invention, the message distribution assigning unit 112 may further include an index assigning unit 119 for assigning an index value associated with the order information to each of the N messages.

At this time, for each of the v message distribution groups, the allocation unit 118 determines an arrangement order of N code values constituting each sequence matched to each of the v message distribution groups, and an arrangement order of N messages And distribute the N messages by tk based on the code value of the array order that matches the index value assigned to the N messages.

In this case, according to an embodiment of the present invention, the assigning unit 118 assigns, for each of the v message distribution groups, N code values constituting each sequence matched to each of the v message distribution groups After confirming the code value of "1" existing at tk, an index value corresponding to the code value of the "1" code value among the N messages is allocated to each of the v message distribution groups Tk messages can be distributed.

According to an exemplary embodiment of the present invention, the data distribution storage apparatus 110 using the cyclic shift may further include a storage message extracting unit 120 and a data loading unit 121.

The stored message extractor 120 may store the N messages in the v data stores 101, 102, and 103 in a distributed manner, and if a load command for the N messages is received, Randomly selecting tk data stores of the v data stores (101, 102, 103) based on the tk data store and storing tk stored messages in each of the tk data stores from each of the tk data stores .

The data loading unit 121 loads the storage messages extracted by each tk from the tk data stores into the data according to the load command for the N messages.

In this case, according to an embodiment of the present invention, the N messages may be Maximum Distance Separable (MDS) codes capable of recovering lost messages based on remaining messages when loss of some messages occurs .

Here, the MDS code is a code that can recover some messages lost based on remaining messages when a loss of some messages among a plurality of messages occurs, thereby performing MDS coding on a predetermined original message, Code can be used to recover lost messages when some of the messages changed to MDS code are lost. At this time, if the original message is to be generated again from the MDS code, MDS decoding can be performed to restore the original message. Therefore, when storing important messages, the MDS code is changed and stored, so that a case of loss of a message can be prepared in advance.

At this time, if tk storing messages are extracted from each of the tk data stores, the data load unit 121 compares an index value assigned to the extracted stored messages with an index value assigned to the N messages If it is determined that there is a remaining message that is not included in the extracted stored messages among the N messages, restores the remaining message based on the extracted stored messages, And load the remaining messages into the data according to the load command for the N messages.

Hereinafter, the operation of the data distribution storage apparatus 110 using the circulation system according to the present invention will be described in detail with reference to FIG. 2, for example.

FIG. 2 is a view for explaining the operation of the data distribution storage device 110 that utilizes the cyclic shift according to an embodiment of the present invention.

Assuming that k = 3 and t = 2 and v = 13 and N = tv according to v = k (k-1) t + 1, 2, data storage 1 (201), data storage 2 (202), data storage 3 (203), data storage 4 (204), data storage 5 (205) A data store 720, a data store 720, a data store 820, a data store 920, a data store 1010, a data store 11 211, a data store 12 212, And the data stores 13 to 213 exist in the data stores 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212 and 213) It is assumed that the number of messages to be stored is 26.

At this time, the distribution group generation unit 111 generates the distribution to the data stores 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213) The message distribution groups 401, 402, and 404 corresponding to the data stores 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413.

The index assigning unit 119 included in the message distribution assigning unit 112 may assign an index value associated with the order information to the 26 messages. When the index assigning unit 119 assigns the 26 messages s when they assign an index value from 1 to 26 in order for the 26 messages _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ "

1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12 because k = 3, t = 2, v = Among all of the three elements included in each of the plurality of subsets, among all of the plurality of subsets having three elements for Z _v , which is the set containing Z It is possible to identify two subsets that are found to match only one different element except for "0 " in the elements included in Z _v .

At this time, the group of the two subsets is defined as a circle having parameters of (13, 3, 1).

At this time, the first sequence generator 115 generates, for each of the two subsets included in the cyclic series having the parameters of (13, 3, 1), three Quot; 1 " and "0" are assigned in the order of "0" to "12" for integers from "0" to "12" included in the Z _v , Two partial sequences composed of code values of "1" and "0 " are generated, and the two partial sequences are combined to generate a first sequence consisting of a total of 26 code values of" 1 & have.

In relation to this, the first sequence generation unit 115 sets the two subsets of the circulation order having the parameters of (13, 3, 1) as "{0,1,4}", "{0,2,7} ".

At this time, the first sequence generation unit 115 is the integer of the two subsets of up to the Z _v "12" from "0" included in "{0, 1, 4}", "{0, For each of the three elements contained in each of the two subsets "{0, 1, 4}", "{0, 2, 7} Assigns a code value of "1 ", and the remaining constants that do not match the three elements contained in each of the two subsets" {0,1,4} ","{0,2,7}Quot; 1100100000000 "and" 1010000100000 "by assigning a code value of" 0 "

Then, the first sequence generator 115 combines the partial sequences "1100100000000" and "1010000100000" by arranging them in a line, thereby generating 11001000000101010000100000 (301 ) ≪ / RTI >

The second sequence generator 116 performs a cyclic shift operation 12 times in either the right or left predetermined direction for the two partial sequences "1100100000000" and "1010000100000" (in this embodiment, And a second sequence is generated by arranging and arranging the two partial sequences that have undergone the cyclic shift operation in a row every time each cyclic shift operation is performed, thereby generating a total of twelve 01100100000000101000010000 (302) , 00110010000000010100001000 303, 00011001000000001010000100 304, 00001100100000000101000010 305, 00000110010000000010100001 306, 00000011001001000001010000 307, 00000001100100100000101000 308, 00000000110010010000010100 309, 10000000011000001000001010 310, 01000000001100000100000101 311, 00100000000111000010000010 312 , 10010000000010100001000001 (313).

The first sequence 11001000000001010000100000 (301) and the 12 second sequences 01100100000000101000010000 (302), 00110010000000010100001000 (303), 0001100100000000100100100 (304), 000011001000000101000010 (305), 000001100100000010100001 (306), 00000011001001000001010000 (307), 00000001100100100101000 (308) 00000000110010010000010100 (309), 10000000011000001000001010 (310), 01000000001100000100000101 (311), 001000000111000010000010 (312), 10010000000010100001000001 313 will always have a code value of tk "1" The code value of "1" contained in each of the 13 sequences 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313, Is always six.

개 이상이 되고, "0"의 코드 값은 항상

개 이하가 되기 때문에 본 실시예에서는 t=2, k=3이라고 가정하였으므로, 13개의 시퀀스들(301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313) 중 어느 6개의 시퀀스들 간에 "OR" 논리 연산이 수행되면, 그 연산 결과 값에 포함되어 있는 "1"의 코드 값은 항상 21개 이상이 되고, "0"의 코드 값은 항상 5개 이하가 된다.If the "OR" logic operation is performed between the tk sequences of the first sequence and the second sequence, the code value of "1" included in the result of the logical operation is always

, And the code value of "0 "

30, 309, 310, 311, 312, 313, 313, 313, 313, 313, ), The code value of "1" included in the operation result value is always 21 or more, and the code value of "0 " is always 5 or less .

When 13 sequences (301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313) are generated, the sequence matching unit 117 acquires 402, 403, 404, 405, 406, 407 (corresponding to the message distribution groups 401, 402, 403, 404, 405, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, 313) for each of the first, second, third, .

2, the sequence matching unit 117 may match 11001000000001010000100000 (301) for the message distribution group 1 401 and 01100100000000101000010000 (302) for the message distribution group 2 402. [ Match 00011001000000001010000100 (304) for message distribution group 4 404, match message distribution group 5 405 (405) to message distribution group 3 403, match message distribution group 3 403 to 00110010000000010100001000 , Match 0000110010000000010100001 (306) to message distribution group 6 406, match 00000011001001000001010000 (307) to message distribution group 7 407, and match 00001100100000000101000010 (305) , Match 00000001100100100000101000 (308) to message distribution group 8 (408), match 00000000110010010000010100 (309) to message distribution group 9 (409) It is possible to match 10000000011000001000001010 (310) to the mountain group 10 (410), match 01000000001100000100000101 (311) to the message distribution group 11 (411), 00100000000111000010000010 (312) to the message distribution group 12 And can match 10010000000010100001000001 (313) to the message distribution group 13 (413)

The assigning unit 118 then allocates 13 messages for each of the 13 message distribution groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, Based on the 26 code values constituting each sequence matched to each of the groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, which are _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 16, quot; m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ ". The assigning unit 118 includes thirteen message distribution groups 401 The sequence of 26 code values constituting each sequence matched with each of the 26 messages, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, _{1, m 2, m 3,} m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 16, m 17, m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m _{2 5,} m ₂₆ "compares the index value assigned to each of the 26 messages, which _{are" m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m _{10, m 11, m 12,} m 13, m 14, m 15, m 16, m 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, m 26 " on the basis of the code values of the collating sequence matching the index values which are assigned to which are the 26 message _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ To the 13 message distribution groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413.

At this time, the allocation unit 118 constructs each sequence matched to each of the 13 message distribution groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, M ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , and m _{9, m 10, m 11,} m 12, m 13, m 14, m 15, m 16, m 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, s m ₂₆ "of" 1 ", the code value is an index value assigned to match the arrangement order of the six message 13 message distribution groups for the (401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, and 413, respectively.

For example, with respect to the message distribution group 1 (401) the sequence of 11001000000001010000100000 301 are matched because assignment unit 118, which are of the 26 message after checking the code of "1" from 11001000000001010000100000 301 "m ₁ m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m _{18, m 19, m 20,} m 21, m 22, m 23, m 24, m 25, m 26 " from among" 1 "is the index value to correspond with the arrangement order of the code value assigned to the six messages in the Message distribution group 1 (401).

Since the code values of "1" are arranged at positions 1, 2, 5, 14, 16 and 21 in the 11001000000001010000100000 (301) M ₁ , m ₂ , m ₅ , and m ₁₄ , to which index values corresponding to positions 1, 2, 5, 14, 16, and 21 are assigned to message distribution group 1 401 , m ₁₆ , m ₂₁ ".

In this manner, the assigning unit 118 assigns to each of the 13 message distribution groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, Based on each of the sequences matched to the respective message distribution groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, _{m 1, m 2, m 3} , m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 16, m 17 m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ ".

The above-mentioned 26 messages "m ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ and m ₂₆ "are all 13 message distribution groups 401, The data storage unit 113 stores 13 message distribution groups 401, 402, 403, 403, 403, 403, 403, 403, 405, 406, 407, 408, 409, 410, 411, 402, 403, 404, 405, 406, 407, 406, 407, 406, 407, 406, 407, 406, 407, 408, 409, 410, 411, (202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213) for each of the message stores 1 to 13 In a data repository corresponding to < RTI ID = 0.0 >

For example, the data storage unit 113 stores the six messages "m ₁ , m ₂ , m ₅ , m ₁₄ , m ₁₆ , m ₂₁ " assigned to the message distribution group 1 401 as data Storage 1 (201).

In this way, the data storage unit 113 stores 6 messages allocated to each of the 13 message distribution groups 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, (201, 202, 203, 204) for each of the 13 message distribution groups (401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413) , 205, 206, 207, 208, 209, 210, 211, 212, 213).

The above-mentioned 26 messages "m ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , _{m 15, m 16, m 17} , m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, m 26 " the data store 1 to 13 (201, 202, 203, 204 , 205, 206, 207, 208, 209, 210, 211, 212, 213) when the distributed storage is complete, which are of the 26 subsequent message _{"m 1, m 2, m} 3, m 4, m 5, m 6 m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m _{23, m 24, m 25,} m 26 " , which are of the 26 message as a data load command is _{for" m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, _{m 9, m 10, m 11} , m 12, m 13, m 14, m 15, m 16, m 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25 , m ₂₆ ", data of any one of six data out of data stores 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, Save Only when after an access to extract the message that is stored in only the six data storage, the which are 26 message _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8 m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , and m ₂₆ ", at least 21 messages are extracted.

Because each of the sequences 301, 302, 303, 304, 305, and 306 is stored in the data storage 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, M ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , and m ₇ according to the code value of "1" m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , and m ₂₆ "are distributed and stored, and on the characteristics of each of the sequences 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, When performing an "OR" logical operation between any six sequences of the sequences 301, 302, 303, 304, 305, 306, 307, 308, 309, 310, 311, 312, and 313, Since there are always 21 or more code values, there are six random data stores among the data stores 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, Extract all 6 messages from each , The which are 26 message _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14 when it _{, m 15, m 16, m} 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, m 26 , at least 21 or more messages from the "are intended to be the all secure.

Therefore, the 26 messages "m ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m _{14 , m 15, m 16, m} 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, m 26 " the data store 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213) "m 1, which are of the 26 message after the distributed storage is completed in _{m 2, m 3, m 4} , m 5, m 6 m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m _23, m _24, m _25, when the load instruction for m ₂₆ "is applied, the store message extracting unit 120 is the data store 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209 , 210, 211, 212, and 213, the data load unit 121 can extract six pieces of data stored in six data storage units at random by selecting only six data storage units having the lowest data traffic. The six data stores M ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m _{12 , m 13, m 14, m} 15, m 16, m 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, m 26 " the total of 21 or more messages of Can be loaded quickly.

At this time, if the 26 messages, which are _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14 _{, m 15, m 16, m} 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, m 26 " a, which are any of the 26 message only of 21 messages of" _{m 1, m 2, m 3} , m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 16, m 17 (26, 21) MDS code configured to be able to restore all of the m, m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ " ) Extracts six stored messages from six randomly selected data stores among the data stores 1 to 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212 and 213) , the index values which are assigned to the stored message extracted and which includes the 26 message "m _1, m _2, when _{m 3, m 4, m 5} , m 6, m 7, m 8, m 9, m 10 m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m _{18, m 19, m 20,} m 21, m 22, m 23, m 24, m 25, m 26 " , which are of the 26 message by comparing the index value assigned to _{the" m 1, m 2, m} 3, m _{4, m 5, m 6,} m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 16, m 17, m 18, m 19, m 20, if it is determined that there is a remaining message that is not included in the extracted stored messages among the m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , and m ₂₆ ' a recover the message and the with the extracted storage message recover residual message which includes the 26 message _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m 9, m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ "To < / RTI >

The data storage 2 (202), the data storage 5 (205), the data storage 7 (207), the data storage 8 (208), the data storage 10 (210), the data storage 13 213, when called, stores the message extraction unit 120 may extract the _{"m 2, m 3, m} 6, m 15, m 17, m 22" from the data storage 2 (202), the data storage 5 ( from _{205) "m 5, m 6} , m 9, m 18, m 20, m 25" a can be extracted from the data store _{7 (207) "m 7,} m 8, m 11, m 14, m 20 , m ₂₂ "from the data store 8 (208) and extract" m ₈ , m ₉ , m ₁₂ , m ₁₅ , m ₂₁ , m ₂₃ " _{m 1, m 10, m 11} , m 17, m 23, m 25 " a may extract, from the data storage _{13 (213)" m 1,} m 4, m 13, m 15, m 20, m 26 " Can be extracted.

Accordingly, the stored message extracting unit 120 eventually obtains the data storage 2 202, the data storage 5 205, the data storage 7 207, the data storage 8 208, the data storage 10 210, from _{13 (213) "m 2,} m 3, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 17, m 18 , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₅ , m ₂₆ "can be extracted.

At this time, the data load unit 121 receives the 26 messages "m ₁ , m ₂ , m ₃ , m ₄ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m _{12 , m 13, m 14, m} 15, m 16, m 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, and the index value assigned to the m ₂₆ " the extracted _{"m 2, m 3, m} 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 17, m 18, m _{20, m 21, m 22,} m 23, m 25, m 26 " , which are of the 26 messages is the index value are compared with each other, which is assigned to _{the" m 1, m 2, m} 3, m 4, m 5, m 6 m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ , m ₁₃ , m ₁₄ , m ₁₅ , m ₁₆ , m ₁₇ , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m _{23, m 24, m 25,} m 26 " the extracted from _{the" m 2, m 3, m} 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m ₁₄ , m ₁₅ , m ₁₇ , m ₁₈ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₅ , m ₂₆ ".

In connection, in the present embodiment, _{"m 1, m 4, m} 16, m 19, m 24" is because the remaining message data load unit 121 _{"m 1, m 4, m} 16, m 19, m 24 M ₂ , m ₃ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ , m ₁₁ , m ₁₂ and m ₁₃ , which are MDS-coded _{, m 14, m 15, m} 17, m 18, m 20, m 21, m 22, m 23, m 25, m " _{from" 26 m 1, m 4,} m 16, m 19, m 24 " to restore I can do it.

Consequently, the data loading unit 121 stores the restored "m ₁ , m ₄ , m ₁₆ , m ₁₉ , m ₂₄ " and the data storage 2 202, the data storage 5 205, M ₂ , m ₃ , m ₅ , m ₆ , m ₇ , m ₈ , m ₉ , m ₁₀ extracted from the data storage 8 (207), the data storage 8 (208) _{, m 11, m 12, m} 13, m 14, m 15, m 17, m 18, m 20, m 21, m 22, m 23, m 25, m 26 " , which are, of the 26 message by loading the" _{m 1, m 2, m 3} , m 4, m 5, m 6, m 7, m 8, m 9, m 10, m 11, m 12, m 13, m 14, m 15, m 16, m 17 , m ₁₈ , m ₁₉ , m ₂₀ , m ₂₁ , m ₂₂ , m ₂₃ , m ₂₄ , m ₂₅ , m ₂₆ ".

As a result, a distribution of data storage devices 110 utilize a circulation chajok according to the invention which are of the 26 message _{"m 1, m 2, m} 3, m 4, m 5, m 6, m 7, m 8, m _{9, m 10, m 11,} m 12, m 13, m 14, m 15, m 16, m 17, m 18, m 19, m 20, m 21, m 22, m 23, m 24, m 25, the first sequence and the second data storage 1 according to the second sequence and 13 (201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211 created on the basis of the m ₂₆ "in rotation chajok , 212, and 213, the data can be restored by accessing only six data stores when the data is loaded at a later time. Therefore, efficiency of system resource utilization in the distributed message storage system can be improved .

According to another embodiment of the present invention, the data distribution storage apparatus 110 using the circulation system may be configured such that the number of messages to be stored exceeds N and the number of the data stores 101, 102, If the number of messages can be increased by the number of messages, the first sequence is generated by checking t subsets belonging to the Perfect Difference Family among the circles with parameters of (v, k, 1) By generating the first sequence and the second sequences by further inserting a code value of "0" in the code value constituting the sequence by an excessive number of messages to be stored, 103 may increase the number of messages to be stored.

For example, when the number of messages to be stored is N + ta, and the number of data stores 101, 102, and 103 is v + a, v, k, 1), and generates the first sequence composed of N code values of "0" and "1 " to form the first sequence 0 "code value for each of the t partial sequences, changing the first sequence into a sequence of N + ta code values of" 0 "and" 1 " A-1) second sequences by performing a cyclic shift operation of v + a-1 times in the predetermined direction with respect to the partial sequences constituting the first sequence.

Then, the data distribution storage device 110 utilizing the cyclic shifts the N + ta messages using the first sequence and the v + a-1 second sequences to v + a data stores 101, 102, and 103, respectively.

In this way, the data distribution storage device 110 utilizing the cyclic shift according to the present invention can freely increase the number of stored messages by increasing the length of the first sequence.

가 있고, B_i가

를 만족할 때,

에 대하여 B_i에 포함되어 있는 원소들 중 tk(k-1)/2개의 서로 다른 원소들 간 차(

)들의 집합이

가 된다면 그 순환 차족은 (v, k, 1) 파라미터를 갖는 완전 차족이라 정의할 수 있다.Hereinafter, a description will be given of the perfect phase. The (v, k, 1) cyclic phase given by v = k (k-1) t +

And B _i is

Lt; / RTI >

(K-1) of the elements contained in B _i / the difference between two different elements

)

, Then the circulation can be defined as a full scale with (v, k, 1) parameters.

FIG. 3 is a flowchart illustrating a data distribution storage method using a cyclic shift according to an embodiment of the present invention.

In step S31, N (N is a natural number satisfying the condition of N = tv, v is a natural number satisfying the condition of v = k (k-1) t + 1, k is a natural number of 2 or more, When a distributed storage command to v data stores is applied to messages of 1 or more natural numbers, v message distribution groups corresponding to the v data stores are generated.

In step S32, the N messages are distributedly allocated to each of the v message distribution groups by tk (tk is a product of t and k) (messages distributed to v message distribution groups are allocated to each other May be duplicated).

In step S33, tk messages allocated to the v message distribution groups are separately stored in the data repository corresponding to each message distribution group among the v message distribution groups and stored in the v data repository do.

At this time, according to an embodiment of the present invention, in step S32, a set Z _v (the number of elements included in the Z _v includes integers from "0" to "v-1" v Games) element contained in said Z _v all cars respectively between the two elements different from the one of the plurality of the subset having the k elements, k of elements included in each of the plurality of the subset of the T subsets (the collection of t subsets is defined as a circle with parameters of (v, k, 1)) that are found to match only one different element except for "0 " From "0" to "v-1" contained in the Z _v , based on k elements contained in each of the t subsets, for each of the t subsets 1 "and" 0 "in the order of" 0 &Quot; 1 "and "0" code values by combining the t partial sequences with the code values of " And combining the t partial sequences generated by assigning code values of "1" and "0 " for each of the t subsets to v for a first sequence (N = tv, Code value of " 1 " and "0" constituting the first sequence is total N) By performing a cyclic shift operation v-1 times in a predetermined direction with respect to each of the sequences, combining the t partial sequences that have completed the cyclic shift operation each time each cyclic shift operation is performed, thereby generating a second sequence generating v-1 second sequences, Matching the first sequence and the v-1 second sequences one by one for each of the v message distribution groups, and for each of the v message distribution groups, matching each of the v message distribution groups And distributing the N messages by tk based on N code values constituting each sequence.

In this case, according to an embodiment of the present invention, the step of generating the first sequence may include, for each of the t subsets, integers from "0" to "v-1" included in the Z _v A code value of "1 " is assigned to integers corresponding to the k elements included in each of the t subsets, and a code value corresponding to k elements included in each of the t subsets By assigning a code value of "0 " to the remaining constants that do not belong to the same sequence, the t partial sequences consisting of the code values of v" 1 "and" 0 ".

According to an embodiment of the present invention, the step S32 may further comprise the step of assigning an index value associated with the order information to each of the N messages.

At this time, the step of distributing the N messages by tk based on the N code values constitutes each sequence matched to each of the v message distribution groups for each of the v message distribution groups The N number of messages is compared with the index value assigned to each of the N messages, and the N number of messages are compared with the index values assigned to the N messages, Tk < / RTI >

According to an embodiment of the present invention, the step of distributing the N messages by tk on the basis of the N code values may further include, for each of the v message distribution groups, 1 "existing in tk among N code values constituting each sequence matched with the code value of " 1 ", and for each of the v message distribution groups, Tk messages to which an index value corresponding to an array order for a code value is allocated can be distributedly allocated.

According to another embodiment of the present invention, there is provided a method of distributing data using circulation, the method comprising: storing N messages in the v data stores in tk distributions; Randomly selects tk data stores out of the v data stores based on the load command and extracts tk stored messages from each of the tk data stores from each of the tk data stores And loading the stored messages extracted from each of the tk data stores into tk data according to a load command for the N messages.

According to an embodiment of the present invention, the N messages are MDS codes capable of recovering lost messages based on remaining messages when a loss of some messages occurs, And stores index values assigned to the extracted stored messages and an index value assigned to the N messages to be included in the extracted stored messages among the N messages, If it is determined that there is a remaining message that is not yet available, restores the remaining message based on the extracted stored messages, and stores the extracted stored messages and the restored remaining message according to a load command for the N messages You can load it as data.

Hereinbefore, the data distribution storage method using the cyclic shift according to the embodiment of the present invention has been described with reference to FIG. Here, the data distribution storage method using the circulation tile according to an embodiment of the present invention may correspond to the configuration of the operation of the data distribution storage apparatus 110 using the circulation tile described with reference to FIGS. 1 and 2 Therefore, a detailed description thereof will be omitted.

The method for storing and distributing data using circulation according to an embodiment of the present invention may be implemented by a computer program stored in a storage medium for execution through a combination with a computer.

In addition, the data distribution storing method using the circulation method according to an embodiment of the present invention may be implemented in a form of a program command that can be executed through various computer means and recorded in a computer readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape; optical media such as CD-ROMs and DVDs; magnetic media such as floppy disks; Magneto-optical media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

As described above, the present invention has been described with reference to particular embodiments, such as specific elements, and specific embodiments and drawings. However, it should be understood that the present invention is not limited to the above- And various modifications and changes may be made thereto by those skilled in the art to which the present invention pertains.

Accordingly, the spirit of the present invention should not be construed as being limited to the embodiments described, and all of the equivalents or equivalents of the claims, as well as the following claims, belong to the scope of the present invention .

110: Distributed data storage using circulation
111: distributed group generation unit 112: message distribution assignment unit
113: Data storage unit 114: Circulation check unit
115: first sequence generator 116: second sequence generator
117: Sequence matching unit 118: Assignment unit
119: Index assigning unit 120: Store message extracting unit
121: Data load unit
101, 102, 103: v data stores

Claims (16)

N is a natural number satisfying the condition of N = tv, v is a natural number satisfying the condition of v = k (k-1) t + 1, k is a natural number of 2 or more, t is natural number of 1 or more, A distributed group generation unit for generating v message distribution groups corresponding to the v data stores when a distributed storage command to v data stores is applied to the messages;
Tk - tk denotes a multiplication of t and k for each of the v message distribution groups, - distributed allocation of messages, - messages distributed over v message distribution groups may overlap each other, A message distribution allocation unit; And
A data storage unit for separating and storing tk messages allocated to each of the v message distribution groups in the v data distribution groups corresponding to v message distribution groups,
Lt; / RTI >
The message distribution assignment unit
Z _v which is an aggregate containing integers from "0" to "v-1", Z _v - the number of elements contained in Z _v is equal to _v - , Each of all the differences between two different elements among the k elements included in each of the plurality of subsets corresponds to only one element other than "0 " in the elements included in the Z _v T subsequences identified as a cyclic shift confirmation, wherein the collection of t subsets is defined as a Cyclic Difference Family with parameters of (v, k, 1);
For each of the t subsets, for integers from "0" to "v-1" contained in the Z _v based on k elements contained in each of the t subsets 1 "and" 0 "code values by assigning code values of" 1 "and" 0 "from" 0 "to" v-1 " A first sequence consisting of a total of N "1" and "0" code values in combination of partial sequences - N = tv and a code value of "1" and "0" for each of the t subsets, The first sequence is generated by combining the t partial sequences generated by assigning the first sequence to the first sequence, and thus the code values of "1" and "0" constituting the first sequence are total N, Generating unit;
Performing a cyclic shift operation in a predetermined direction v-1 times for each of the t partial sequences composed of v code values of "1" and "0 " while performing each cyclic shift operation A second sequence generator for generating a total of v-1 second sequences by generating a second sequence by combining the t partial sequences having completed the cyclic shift operation;
A sequence matching unit for matching the first sequence and the v-1 second sequences one by one for each of the v message distribution groups; And
For each of the v message distribution groups, an allocation unit for allocating tk of the N messages based on N code values constituting each sequence matched to each of the v message distribution groups,
And a data distribution storage apparatus using the circulation system. delete The method according to claim 1,
The first sequence generator
Constant, consistent with the k elements in one of the integer for each of the t of the subset, from "0" contained in the Z _v to "v-1" included in each of the t partial set By allocating a code value of "1" to all of the t subsets and assigning a code value of "0 " to remaining integers not matching k elements contained in each of the t subsets, And generates the t partial sequences composed of code values of "1" and "0 ". The method of claim 3,
The message distribution assignment unit
An index assigning unit for assigning an index value associated with the order information to each of the N messages,
Further comprising:
The assigning unit
For each of the v message distribution groups, an arrangement order of N code values constituting each sequence matched to each of the v message distribution groups is compared with an index value assigned to each of the N messages. And allocates the N messages by tk based on a code value of an array order that matches an index value assigned to the N messages. 5. The method of claim 4,
The assigning unit
For each of the v message distribution groups, a code value of "1" existing in tk among N code values constituting each sequence matched to each of the v message distribution groups is checked, For each of the message distribution groups, distributes tk messages to which an index value corresponding to the code value of the "1" of the N messages is allocated, . 6. The method of claim 5,
When a load command for the N messages is applied after the N messages are distributedly distributed in the v data stores, the tk data among the v data stores based on the load command, A storage message extractor for randomly selecting tanks and extracting tk stored messages stored in each of the tk data stores from each of the tk data stores; And
A data load unit for loading storage messages extracted by each tk of the tk data stores into data corresponding to a load instruction for the N messages,
And a data distribution storage apparatus using the circulation system. The method according to claim 6,
The N messages are Maximum Distance Separable (MDS) codes capable of recovering lost messages based on remaining messages when loss of some messages occurs,
The data loading unit
Wherein when the stored messages are extracted from each of the tk data stores, the index value assigned to the extracted stored messages is compared with the index value assigned to the N messages, Recovering the stored messages based on the extracted stored messages and storing the extracted stored messages and the recovered residual messages in the N messages To load data according to a load command for the data storage device. A method of distributing data using circulation performed by a computer,
N is a natural number satisfying the condition of N = tv, v is a natural number satisfying the condition of v = k (k-1) t + 1, k is a natural number of 2 or more, t is natural number of 1 or more, Generating v message distribution groups corresponding to the v data stores if a distributed store instruction to v data stores is granted for the messages;
Tk - tk denotes a multiplication of t and k for each of the v message distribution groups, - distributed allocation of messages, - messages distributed over v message distribution groups may overlap each other, ; And
Separating and storing tk messages allocated to each of the v message distribution groups in the v message distribution groups and in a data repository corresponding to each message distribution group among the v data stores,
Lt; / RTI >
The step of distributing the N messages by tk for each of the v message distribution groups
Z _v which is an aggregate containing integers from "0" to "v-1", Z _v - the number of elements contained in Z _v is equal to _v - , Each of all the differences between two different elements among the k elements included in each of the plurality of subsets corresponds to only one element other than "0 " in the elements included in the Z _v T subsets identified as a cyclic difference family with a parameter of (v, k, 1);
For each of the t subsets, for integers from "0" to "v-1" contained in the Z _v based on k elements contained in each of the t subsets 1 "and" 0 "code values by assigning code values of" 1 "and" 0 "from" 0 "to" v-1 " A first sequence consisting of a total of N "1" and "0" code values in combination of partial sequences - N = tv and a code value of "1" and "0" for each of the t subsets, Generating the first sequence by combining the t partial sequences generated by assigning the first sequence to the first sequence, and generating code values of "1" and "0" constituting the first sequence in total N;
Performing a cyclic shift operation in a predetermined direction v-1 times for each of the t partial sequences composed of v code values of "1" and "0 " while performing each cyclic shift operation Generating a total of v-1 second sequences by combining the t partial sequences having completed the cyclic shift operation to generate a second sequence;
Matching the first sequence and the v-1 second sequences one by one for each of the v message distribution groups; And
For each of the v message distribution groups, distributing the N messages by tk based on N code values constituting each sequence matched to each of the v message distribution groups
And a data distribution storing method using the circulating series. delete 9. The method of claim 8,
The step of generating the first sequence
Constant, consistent with the k elements in one of the integer for each of the t of the subset, from "0" contained in the Z _v to "v-1" included in each of the t partial set By allocating a code value of "1" to all of the t subsets and assigning a code value of "0 " to remaining integers not matching k elements contained in each of the t subsets, And generating the t partial sequences composed of code values of "1" and "0 ". 11. The method of claim 10,
The step of distributing the N messages by tk for each of the v message distribution groups
Assigning an index value associated with the order information to each of the N messages
Further comprising:
The step of distributing the N messages by tk based on the N code values
For each of the v message distribution groups, an arrangement order of N code values constituting each sequence matched to each of the v message distribution groups is compared with an index value assigned to each of the N messages. And distributing the N messages by tk based on a code value of an array order corresponding to an index value assigned to the N messages. 12. The method of claim 11,
The step of distributing the N messages by tk based on the N code values
For each of the v message distribution groups, a code value of "1" existing in tk among N code values constituting each sequence matched to each of the v message distribution groups is checked, For each of the message distribution groups, tk messages to which an index value corresponding to the code value of the "1" of the N messages is allocated is distributed and distributed. . 13. The method of claim 12,
When a load command for the N messages is applied after the N messages are distributedly distributed in the v data stores, the tk data among the v data stores based on the load command, Randomly selecting the tanks and extracting tk stored messages from each of the tk data stores from each of the tk data stores; And
Loading the stored messages extracted by each tk from each of the tk data stores into data according to a load command for the N messages,
And storing the data in the storage unit. 14. The method of claim 13,
The N messages are Maximum Distance Separable (MDS) codes capable of recovering lost messages based on remaining messages when loss of some messages occurs,
The loading step
Wherein when the stored messages are extracted from each of the tk data stores, the index value assigned to the extracted stored messages is compared with the index value assigned to the N messages, Recovering the stored messages based on the extracted stored messages and storing the extracted stored messages and the recovered residual messages in the N messages To load the data according to the load command for the data. A computer-readable recording medium recording a program for performing the method of any one of claims 8, 10, 11, 12, 13, A computer program stored in a storage medium for executing the method of any one of claims 8, 10, 11, 12, 13 or 14 in combination with a computer.

Images