CN110275873A - File memory method, device, storage management apparatus and storage medium - Google Patents
File memory method, device, storage management apparatus and storage medium Download PDFInfo
- Publication number
- CN110275873A CN110275873A CN201910582756.4A CN201910582756A CN110275873A CN 110275873 A CN110275873 A CN 110275873A CN 201910582756 A CN201910582756 A CN 201910582756A CN 110275873 A CN110275873 A CN 110275873A
- Authority
- CN
- China
- Prior art keywords
- mark
- capacity
- file
- target
- stored
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/17—Details of further file system functions
- G06F16/172—Caching, prefetching or hoarding of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure provides a kind of file memory method, device, storage management apparatus and storage medium, is related to technical field of data processing.This method passes through the corresponding DN mark of the file identification and each DN that obtain file to be stored, Hash hash is carried out to file identification, obtain corresponding cryptographic Hash, according to cryptographic Hash, target DN mark is determined from the corresponding DN mark of each DN, allow to the file identification according to file to be stored, obtain the corresponding target DN mark of file to be stored, file to be stored is sent to the corresponding target DN of target DN mark to store, it can make when being stored to file to be stored, the rapidity that can be hashed based on Hash, file to be stored is distributed to rapidly unique DN corresponding to it by realization, it is also based on the randomness of Hash hash, file to be stored is more equally distributed in each DN, and then reduce the problem of file is unevenly distributed weighing apparatus in each DN, to balance the load of each DN.
Description
Technical field
This disclosure relates to technical field of data storage, in particular to a kind of file memory method, device, storage tube
Manage equipment and storage medium.
Background technique
It is logical based on real-time multimedia with broadband network, the high speed development of digital compression technology and massive store technology
The network service trade of letter is also rapidly developed.For example, can use internet basic arrangement transmission in Video Supervision Technique
Network video, and it is widely used in the fields such as industrial production, traffic, electric power, bank, intelligent building.But it is used in part
Under the biggish application environment of the quantity of family and monitoring point, video monitoring system often will appear bandwidth and processing capacity is insufficient asks
Topic.
To solve the above problems, being proposed in the prior art by introducing the distribution server, video monitoring file is carried out
The method of distributed storage.In this method, the physical memory resources of file system management are not necessarily connected directly between local node
On, but be connected by computer network from different memory nodes, to be realized by multiple memory nodes to video monitoring file
Distributed storage.
But in above-mentioned existing distributed storage method, the memory space situation of different nodes is not considered,
During actual storage, often there is the non-uniform problem of the storage condition of each memory node, lead to each memory node
File distribution is unbalanced.
Summary of the invention
The purpose of the present disclosure is to provide a kind of file memory method, device, storage management apparatus and storage mediums, use
The storage condition of each memory node present in the existing distributed storage method of solution is uneven, leads to each memory node
The unbalanced problem of file distribution.
To achieve the above object, technical solution used by the embodiment of the present disclosure is as follows:
In a first aspect, the embodiment of the present disclosure provides a kind of file memory method, this method is applied to distributed memory system
In centralized storage management equipment CM, distributed memory system includes: CM and multiple back end DN;This method comprises:
Obtain the file identification and the corresponding DN mark of each DN of file to be stored;
Hash hash is carried out to file identification, obtains corresponding cryptographic Hash;
According to cryptographic Hash, target DN mark is determined from the corresponding DN mark of each DN;
File to be stored is sent to the corresponding target DN of target DN mark to store.
Optionally, the corresponding DN mark of each DN of above-mentioned acquisition, comprising:
Obtain the minimum capacity in the capacity of each DN and the capacity of each DN;
For any one DN:
According to the capacity and minimum capacity of DN, n DN mark is created for DN, wherein n is the integer greater than 0.
Optionally, above-mentioned capacity and minimum capacity according to DN creates n DN mark for DN, comprising:
The quotient that the capacity of DN is removed by minimum capacity is calculated, calculated result is obtained;
Calculated result is rounded, n is obtained;
N DN mark is created for DN.
Optionally, the corresponding DN mark of each DN of above-mentioned acquisition, comprising:
Obtain the capacity and preset capacity of each DN;
For any one DN:
Judge whether the capacity of DN is greater than preset capacity;
If more than preset capacity, then according to the capacity of DN and preset capacity, n DN mark is created for DN, wherein n is big
In 0 integer;
Otherwise, 1 DN mark is created for DN.
Optionally, above-mentioned according to cryptographic Hash, target DN mark is determined from the corresponding DN mark of each DN, comprising:
The corresponding DN mark of each DN is ranked up, obtains identifying queue by the DN that m DN mark forms, wherein DN mark
Each DN mark in knowledge queue all has corresponding sequence number and sequence number is less than or equal to m;
According to cryptographic Hash and m, target sequence number is calculated;
From DN mark queue, chooses the corresponding DN mark of target sequence number and identified as target DN.
Optionally, above-mentioned according to cryptographic Hash and m, calculate target sequence number, comprising:
According to cryptographic Hash to m remainder, target sequence number is obtained.
Optionally, above-mentioned file to be stored is sent to target DN to identify before corresponding target DN stored, the party
Method further include:
Judge that target DN identifies the residual capacity of corresponding target DN and whether is greater than default residual capacity threshold value;
If the residual capacity of target DN is greater than default residual capacity threshold value, file to be stored is sent to target DN and is carried out
Storage.
As described above, if the residual capacity of target DN, which is less than or equal to, presets residual capacity threshold value, in delete target DN
Meet the storage file of preset requirement.
Optionally, the storage file of preset requirement is met in above-mentioned delete target DN, comprising:
According to the corresponding storage time of storage file in target DN, by the storage text of storage time within a preset period of time
Part is deleted.
Second aspect, the embodiment of the present disclosure provide a kind of file storage device, which is applied to distributed memory system
In centralized storage management equipment CM, distributed memory system includes: CM and multiple back end DN;The device includes:
Module is obtained, the corresponding DN mark of the file identification and each DN for obtaining file to be stored;
Hash module obtains corresponding cryptographic Hash for carrying out Hash hash to file identification;
Determining module, for determining target DN mark from the corresponding DN mark of each DN according to cryptographic Hash;
Sending module is stored for file to be stored to be sent to the corresponding target DN of target DN mark.
Optionally, obtaining module includes:
First acquisition submodule, for obtaining the minimum capacity in the capacity of each DN and the capacity of each DN;
First creation submodule, for for any one DN: according to the capacity and minimum capacity of DN, creating n for DN
DN mark, wherein n is the integer greater than 0.
Optionally, the first creation submodule is specifically used for, and calculates the quotient that the capacity of DN is removed by minimum capacity, is calculated
As a result;Calculated result is rounded, n is obtained;N DN mark is created for DN.
Optionally, obtaining module includes:
Second acquisition submodule, for obtaining the capacity and preset capacity of each DN;
Second creation submodule, for for any one DN: judging whether the capacity of DN is greater than preset capacity;If more than
Preset capacity creates n DN mark then according to the capacity of DN and preset capacity for DN, wherein n is the integer greater than 0;Otherwise,
1 DN mark is created for DN.
Optionally it is determined that module, comprising:
Sorting sub-module obtains the DN mark being made of m DN mark for the corresponding DN mark of each DN to be ranked up
Queue, wherein each DN mark in DN mark queue all has corresponding sequence number and sequence number is less than or equal to m;
Computational submodule, for calculating target sequence number according to cryptographic Hash and m;
Submodule is chosen, is marked for from DN mark queue, choosing the corresponding DN mark of target sequence number as target DN
Know.
Optionally, computational submodule is specifically used for obtaining target sequence number to m remainder according to cryptographic Hash.
Optionally, this document storage device further include:
Whether judgment module is greater than default residual capacity for judging that target DN identifies the residual capacity of corresponding target DN
Threshold value;
Sending module is used to send file to be stored when the residual capacity of target DN is greater than default residual capacity threshold value
It is stored to target DN.
Optionally, this document storage device further include:
Removing module is less than or equal to default residual capacity threshold value, delete target DN for the residual capacity in target DN
The middle storage file for meeting preset requirement.
Optionally, removing module, specifically for according to the corresponding storage time of storage file in target DN, when by storing
Between storage file within a preset period of time deleted.
The third aspect, the embodiment of the present disclosure provide a kind of storage management apparatus, storage management apparatus and multiple back end
DN forms distributed memory system;Storage management apparatus includes: processor and memory, and being stored in memory can be in processor
The computer program of operation, processor realize file memory method as described in relation to the first aspect when executing computer program.
Fourth aspect, the embodiment of the present disclosure also provide a kind of computer storage medium, are stored thereon with computer program, institute
State the file memory method realized when computer program is executed by processor as described in relation to the first aspect.
Based on any of the above-described aspect, the beneficial effect of the disclosure is:
The embodiment of the present disclosure is by the corresponding DN mark of the file identification and each DN that obtain file to be stored, to file identification
Hash hash is carried out, corresponding cryptographic Hash is obtained, according to cryptographic Hash, determines target DN mark from the corresponding DN mark of each DN,
Allow to the file identification according to file to be stored, the corresponding target DN mark of file to be stored is obtained, further, it is possible to will
File to be stored is sent to the corresponding target DN of target DN mark and is stored, so that storing to file to be stored
When, file to be stored is distributed to rapidly unique DN corresponding to it by the rapidity that can be hashed based on Hash, realization, meanwhile,
It is also based on the randomness of Hash hash, file to be stored is more equally distributed in each DN, and then is reduced each
The problem of file is unevenly distributed weighing apparatus in a DN, to balance the load of each DN.
Detailed description of the invention
It, below will be to needed in the embodiment attached in order to illustrate more clearly of the technical solution of the embodiment of the present disclosure
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the disclosure, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the flow diagram of the file memory method of embodiment of the present disclosure offer;
Fig. 2 shows another flow diagrams for the file memory method that the embodiment of the present disclosure provides;
Fig. 3 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer;
Fig. 4 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer;
Fig. 5 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer;
Fig. 6 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer;
Fig. 7 shows the structural schematic diagram of the videotex system of embodiment of the present disclosure offer;
Fig. 8 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer;
Fig. 9 shows the structural schematic diagram of the file storage device of embodiment of the present disclosure offer;
Figure 10 shows another structural schematic diagram of the file storage device of embodiment of the present disclosure offer;
Figure 11 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer;
Figure 12 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer;
Figure 13 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer;
Figure 14 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer;
Figure 15 shows the structural schematic diagram of the storage management apparatus of embodiment of the present disclosure offer.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present disclosure clearer, below in conjunction with the embodiment of the present disclosure
In attached drawing, the technical solution in the embodiment of the present disclosure is clearly and completely described, it is clear that described embodiment is
Disclosure a part of the embodiment, instead of all the embodiments.The disclosure being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the disclosure provided in the accompanying drawings is not intended to limit below claimed
The scope of the present disclosure, but be merely representative of the selected embodiment of the disclosure.Based on the embodiment in the disclosure, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model of disclosure protection
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
The embodiment of the present disclosure provides a kind of file memory method, and this method can be applied in distributed memory system
It entreats storage management apparatus (Central Management, CM).Distributed memory system includes: CM and multiple back end
(Data Node, DN), for example, CM can be the equipment that management server or computer etc. have data-handling capacity, and DN can
To be storage server, disk or other storage mediums etc. for storing data, the disclosure to this with no restriction.
In distributed memory system, CM can be connect with external device, receive the file to be stored that external device is sent,
And file to be stored is distributed to each DN and is stored.Wherein, external device includes: computer, server, microphone array
One of column and other data acquisition equipments such as video camera or camera are a variety of;For example, in field of video monitoring, outside
Boundary's equipment may include: computer and camera, and camera can collect the video image of monitoring area and be sent to calculating
Machine, computer can be handled the video image received, obtained video file and are sent to CM, and CM can will be received
Video file be distributed to different DN and stored, to realize the distributed storage to video file.
Fig. 1 shows the flow diagram of the file memory method of embodiment of the present disclosure offer.As shown in Figure 1, this document
Storage method may include:
S101, the file identification for obtaining file to be stored and the corresponding DN mark of each DN.
Specifically, file to be stored can be video file, voice document, text document or picture etc., each wait deposit
Storage file all has corresponding file identification, for example, file identification can be the specific security level identification etc. of filename, file, text
Part identifies the unique identities attribute that may indicate that file to be stored.
Also there is each DN corresponding DN to identify, and DN mark can be the DN title similar to file identification, such as: DN title
It can be DN1、DN2、DN3…....DNnDeng the number to DN, to distinguish different DN;In addition, DN mark is also possible to often
A distinctive device number of DN equipment, for example, DN identifies the equipment that can be the storage server if DN is storage server
Number.Likewise, the corresponding DN mark of DN may also indicate that the unique identities attribute of DN for each DN.
S102, Hash hash is carried out to file identification, obtains corresponding cryptographic Hash.
Specifically, Hash hash can input random length the output that regular length is transformed by hashing algorithm, institute
The hashed value of output is cryptographic Hash.Hash hash is carried out by the file identification to file to be stored, can be transformed it into
The cryptographic Hash of regular length, for example, Hash hash can be carried out to the filename of file to be stored, so as to be converted into
Fixed integer, such as: 1,2,3.
S103, according to cryptographic Hash, determine target DN mark from the corresponding DN mark of each DN.
It specifically, can be according to the cryptographic Hash, never after the corresponding cryptographic Hash of file identification for obtaining file to be stored
The corresponding unique DN mark of the cryptographic Hash is obtained with calculating in the corresponding multiple DN marks of DN, is identified as target DN.For example, if
It is respectively DN there are the corresponding DN mark of three DN1、DN2And DN3, Hash is carried out for the filename of some file to be stored P
Obtained cryptographic Hash is 3 after hash, then can determine DN3For target DN mark.
It should be noted that this determines the explanation that the mode that target DN is identified is merely exemplary according to cryptographic Hash, at this
In the other embodiments of open embodiment, it is also possible to realize the determination for identifying target DN according to other preset algorithms.Example
Such as, DN mark is followed successively by DN if it exists1To DNnN DN, then preset algorithm can be is with the cryptographic Hash that Hash hashes
A value x is randomly generated into n from 1 for benchmark, then DN corresponding to generated value xxAs target DN mark.In addition, this is pre-
Imputation method can also refer to carry out other operations according to rule to cryptographic Hash, to obtain unique DN mark, for preset algorithm
Concrete type, the disclosure is not construed as limiting.
S104, it file to be stored is sent to target DN identifies corresponding target DN and store.
Specifically, for file to be stored, corresponding to file identification (such as: filename) be fixed, then
It is also fixed DN mark according to the obtained target DN mark of above-mentioned steps S102 and step S103, that is, the disclosure is implemented
In example, target DN mark is one-to-one relationship with file to be stored (or file identification of file to be stored).And institute as above
It states, for each DN, the corresponding DN mark of DN may also indicate that the unique identities attribute of DN, therefore, target DN mark pair
It is also one-to-one relationship between the target DN answered and file to be stored.
It is stored it is alternatively possible to which file to be stored is sent to above-mentioned target DN.
From the above mentioned, the embodiment of the present disclosure is identified by the corresponding DN of file identification and each DN for obtaining file to be stored,
Hash hash is carried out to file identification, obtains corresponding cryptographic Hash, according to cryptographic Hash, determines mesh from the corresponding DN mark of each DN
DN mark is marked, the file identification according to file to be stored is allowed to, the corresponding target DN mark of file to be stored is obtained, into one
File to be stored can be sent to the corresponding target DN of target DN mark and stored, so that treating storage text by step
When part is stored, file to be stored be distributed to rapidly corresponding to it only by the rapidity that can be hashed based on Hash, realization
One DN is more equally distributed in file to be stored in each DN at the same time it can also the randomness hashed based on Hash,
And then the problem of file is unevenly distributed weighing apparatus in each DN is reduced, to balance the load of each DN.
Fig. 2 shows another flow diagrams for the file memory method that the embodiment of the present disclosure provides.
Optionally, as shown in Fig. 2, the corresponding DN mark of each DN of above-mentioned acquisition, comprising:
Minimum capacity in the capacity of S201, the capacity for obtaining each DN and each DN.
Specifically, for DN, in different distributed memory systems, the capacity of DN can be identical, can also not
Together, for example, in some distributed memory systems, the capacity of DN only several hundred G, and in some biggish distributed memory systems,
The capacity of DN can have thousands of G or G up to ten thousand;In the same distributed memory system, the capacity of different DN may be identical, can also
Can be different, for example, the capacity of some DN may be 100G, and the capacity of some DN is only in the same distributed memory system
Only 75G or 50G.
It is alternatively possible to obtain the capacity of each DN.It, can be according to bubble sort, selection after the capacity for getting each DN
The sort algorithms such as sequence, are ranked up the capacity of acquired each DN, to promptly determine minimum capacity therein.
S202, for any one DN, according to the capacity and minimum capacity of DN, create n DN for DN and identify, wherein n is
Integer greater than 0.
It specifically,, can be by the capacity of the DN and above-mentioned minimum for each DN after determination obtains above-mentioned minimum capacity
Capacity is compared, and judges the capacity of the DN and the relative size of minimum capacity, can if the capacity of the DN is bigger than minimum capacity
To create n mark for the DN according to the relative size of the capacity of the DN and minimum capacity.When the capacity of DN holds relative to minimum
When measuring bigger, the value of n is bigger.For any one DN, for minimum capacity, minimum 1 times, therefore, n's
Minimum value is 1, that is, n is the integer greater than 0.
For example, two DN are respectively DN if it existsaAnd DNb, wherein DNaCapacity be 150G, DNbCapacity be 50G, then
In DNaAnd DNbIn obtained minimum capacity be 50G.At this point, for DNaFor, capacity is 3 times relative to minimum capacity,
It then accordingly can be DNaCreate 3 marks;For DNbFor, capacity is 1 times relative to minimum capacity, then accordingly may be used
Think DNbCreate 1 mark.
From the above mentioned, the embodiment of the present disclosure is right by obtaining the minimum capacity in the capacity of each DN and the capacity of each DN
In any one DN, according to the capacity and minimum capacity of DN, n DN mark is created for DN, is allowed to for each DN capacity
Inconsistent situation creates corresponding n DN according to the amount of capacity of each DN for it and identifies, so that above-mentioned steps S103
It is middle according to cryptographic Hash, when determining that target DN is identified from the corresponding DN mark of each DN, the biggish DN of capacity can have more DN
Mark participates in this process, so that file, in distribution procedure, the probability that the biggish DN of capacity is distributed to is higher, further
Balance of the file between each DN is improved, the load of each DN can be more effectively balanced.
Fig. 3 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer.
Optionally, as shown in figure 3, above-mentioned capacity and minimum capacity according to DN, creates n DN mark for DN, comprising:
The quotient that S301, the capacity for calculating DN are removed by minimum capacity, obtains calculated result.
S302, calculated result is rounded, obtains n.
S303, n DN mark is created for DN.
Specifically, can carry out division arithmetic by capacity to DN and minimum capacity, and to resulting calculated result into
After row is rounded, using the result after rounding as the value of n, to create n DN mark for DN.
With DNaAnd DNbFor, following three kinds are co-existed in for scheme one described in above-mentioned steps S301, S302 and S303
Situation:
1, assume DNaCapacity be 100G, DNbCapacity be 50G;
In the 1st kind of situation, minimum capacity 50G, by DNaCapacity 100G and minimum capacity 50G carry out division arithmetic
Afterwards, can just divide exactly, calculated result is just integer 2, therefore, after being rounded to 2, integer is remained as, so, Ke Yiwei
DNaCreate 2 DN marks.
2, assume DNaCapacity be 120G, DNbCapacity be 50G;
In the 2nd kind of situation, minimum capacity 50G, by DNaCapacity 120G and minimum capacity 50G carry out division arithmetic
Afterwards, obtaining result is 2.4, calculated result and non-integer.Calculated result can be rounded according to the following two kinds mode at this time:
1) decimal place due to 2.4 is 0.4, and can be rounded in the way of rounding up is 2, so, it can
Think DNaCreate 2 DN marks;
It 2) can be by DNaCapacity 120G point be 50G, 50G and 20G three parts, DN create to every part and is identified, thus
It can be DNaCreate 3 DN marks.That is, no matter decimal place thereafter is how many, can be rounded for 2.4
For 1 to be DNaIncrease by 1 DN mark.
3, assume DNaCapacity be 130G, DNbCapacity be 50G;
In the 3rd kind of situation, minimum capacity 50G, by DNaCapacity 130G and minimum capacity 50G carry out division arithmetic
Afterwards, obtaining result is 2.6, cannot equally be divided exactly.It is similar with above-mentioned 2nd kind of situation, for decimal place 0.6, can also take
Two ways, that is, be rounded in the way of rounding up as 1, no matter can also directly be given up with its size,
The integer-bit of calculated result is only taken, specific rounding process repeats no more.
Fig. 4 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer.
Optionally, as shown in figure 4, the corresponding DN mark of each DN of above-mentioned acquisition, comprising:
S401, the capacity and preset capacity for obtaining each DN.
Wherein, preset capacity can be preset value.It is alternatively possible to according to different distributed memory systems,
The size of preset capacity is configured.For example, preset capacity can be 20G in some lesser distributed memory systems
Or 50G, in some biggish distributed memory systems, preset capacity is also possible to 100G, 200G or other bigger values,
The disclosure to this with no restriction.
S402, for any one DN, judge whether the capacity of DN is greater than preset capacity.
S403, if more than preset capacity, then according to the capacity of DN and preset capacity, create n DN for DN and identify, wherein n
For the integer greater than 0;Otherwise, 1 DN mark is created for DN.
Optionally, for any one DN, the capacity of the DN can be compared with the size of preset capacity, if
The capacity that judgement obtains DN is greater than preset capacity, then can be according to the capacity of DN and the relative size of preset capacity, for DN wound
Build n DN mark.Specifically, for creating the specific of DN mark for DN according to the capacity of DN and the relative size of preset capacity
Process is referred to the comparison procedure of DN capacity and minimum capacity described in previous embodiment, and details are not described herein for the disclosure.
Optionally, if the capacity of DN is less than or equal to preset capacity, 1 DN mark can be created for the DN.For example, if
Preset capacity is 50G, and the capacity of DN is 50G or smaller 30G, 20G etc., then only can create 1 DN mark to the DN.
It should be noted that in the other embodiments of the embodiment of the present disclosure, can not also by the capacity of DN and it is above-mentioned most
Low capacity or preset capacity are compared, but carry out the obtained capability value of operation according to the capacity to each DN, to each DN
Create corresponding DN mark.For example, the operation that can be averaged to the capacity of each DN got, then with average appearance
Amount is foundation, creates corresponding DN to each DN and identifies;The capacity of each DN can also be ranked up according to amount of capacity, then
The capacity for choosing wherein some sequence location is compared as foundation with the capacity of each DN, e.g., if pressing to the capacity of each DN
After being ranked up from small to large according to capacity, the DN capacity of 20 percent or 30 percent corresponding position in queue can be chosen
As foundation etc., equally that is not required for the disclosure.
Fig. 5 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer.
Optionally, as shown in figure 5, it is above-mentioned according to cryptographic Hash, target DN mark, packet are determined from the corresponding DN mark of each DN
It includes:
S501, the corresponding DN mark of each DN is ranked up, obtains identifying queue by the DN that m DN mark forms, wherein
Each DN mark in DN mark queue all has corresponding sequence number and sequence number is less than or equal to m.
Specifically, it can be ranked up according to certain ordering rule DN mark corresponding to each DN.For example, disclosure portion
Divide in embodiment, the corresponding DN mark of each DN can be upset, and all DN are identified using random algorithm and are carried out
Sequence;It is also possible to be ranked up it according to the creation time of the corresponding DN mark of each DN.
DN mark corresponding to each DN is ranked up as procedure described above, and the available DN being made of m DN mark is marked
Know queue, m be each DN corresponding DN mark quantity and.For the DN identifies queue, wherein each DN mark has
There is corresponding sequence number and sequence number is less than or equal to m.Each DN mark institute in the DN mark queue of m DN mark composition is right
The sequence number answered can be with are as follows: (1,2 ... m-1, m) or (0,1,2 ... m-2, m-1).For example, if some DN identifies queue
Are as follows: (DN1、DN2、DN3、DN4、DN5), then the DN identify each DN in queue identify corresponding sequence number can be with are as follows: (1,2,3,4,
Or (0,1,2,3,4) 5).
S502, according to cryptographic Hash and m, calculate target sequence number.
It specifically, can be according to the quantity and m of the corresponding DN mark of above-mentioned each DN, and by being breathed out to file identification
The uncommon obtained cryptographic Hash of hash, calculates target sequence number.For example, it may be carrying out asking poor, summation, quadrature to cryptographic Hash and m
Equal operations, obtain corresponding calculated result, and determine target sequence number according to acquired calculated result.
S503, it is identified in queue from DN, chooses the corresponding DN mark of target sequence number and identified as target DN.
As described above, DN can then be identified to target sequence number corresponding position in queue after obtaining target sequence number
DN mark is identified as target DN, is sent file to be stored in the corresponding DN of target DN mark and is stored.
For example, identifying queue (DN with above-mentioned DN1、DN2、DN3、DN4、DN5) for, if each DN mark in DN mark queue
Knowing corresponding sequence number is (0,1,2,3,4), and obtained calculated result is 3 in above-mentioned steps S502, then target sequence number is
3,3 corresponding DN can be identified into DN4It is identified as target DN.
Optionally, above-mentioned according to cryptographic Hash and m, calculate target sequence number, comprising:
According to cryptographic Hash to m remainder, target sequence number is obtained.
Optionally, the file identification of file to be stored is carried out Hash to hash obtained cryptographic Hash being one whole
Number can carry out complementation to above-mentioned m according to the integer, and using remainder as target sequence number.
For example, if the i.e. value of m is 7, then can be carried out according to 3 Dui 7 when cryptographic Hash is 3, and one to co-exist in 7 DN mark
Remainder, obtaining remainder is 1, to be 1 according to the target sequence number that cryptographic Hash 3 and m are calculated, at this point it is possible to choose DN mark
Know the corresponding DN mark in 1 position in queue to identify as target DN.
Fig. 6 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer.
Optionally, as shown in fig. 6, it is above-mentioned file to be stored be sent to target DN identify corresponding target DN store
Before, this method further include:
S601, judge that target DN identifies the residual capacity of corresponding target DN and whether is greater than default residual capacity threshold value.
If the residual capacity of S602, target DN are greater than default residual capacity threshold value, file to be stored is sent to target
DN is stored.
Wherein, the value that residual capacity threshold value may be default settings is preset.For example, default residual capacity threshold value can be
1G, 2G or 5G etc., when the residual capacity of target DN is unsatisfactory for being greater than the condition of the default residual capacity threshold value, it may be considered that
The capacity of target DN will be occupied full or residual capacity may be insufficient.So can be with S601 through the above steps to target DN
Judged, presets residual capacity threshold value when the residual capacity of target DN is greater than, is i.e. when the residual capacity of target DN is enough, just will
File to be stored is sent to target DN and is stored.
As described above, if the residual capacity of target DN, which is less than or equal to, presets residual capacity threshold value, in delete target DN
Meet the storage file of preset requirement.
Specifically, when the residual capacity of target DN is less than or equal to default residual capacity threshold value, i.e. the remaining of target DN is held
It, can be to meet the storage file of preset requirement in delete target DN, to increase the residual capacity of target DN, for wait deposit when amount is insufficient
It stores up file and enough memory spaces is provided.Wherein, the storage file for meeting preset requirement can refer to: the file that has damaged,
Or the file of no longer valid (such as: not using).
Optionally, the above-mentioned storage file for meeting preset requirement can also refer to storage file within a preset period of time.
So can be according to the corresponding storage time of storage file in target DN, by the storage of storage time within a preset period of time
File is deleted.
Wherein, preset time period can refer to several days or a period of time earliest in the corresponding storage time of storage file,
It such as can be 3 days, 7 days, be also possible to think some special time period of setting, such as can be a few days or certain is several small
When etc..
For example, it is usually present the demand of the preceding document of new video monitoring file covering in video monitoring system, because
This, preset time period can be set to earliest 1 day, can be with full in delete target DN when the residual capacity deficiency of target DN
Earliest 1 day video monitoring file of foot is provided enough with increasing the residual capacity of target DN for video monitoring file to be stored
Memory space.Optionally, if the residual capacity of target DN still talks deficiency, then may be used after the video monitoring file of earliest 1 day of deletion
Earliest 1 day storage file in remaining storage file to continue delete target DN, until the residual capacity of target DN is greater than upper
Until stating default residual capacity threshold value.
As a result, in video monitoring system, the above method provided by the embodiment of the present disclosure can make whenever DN connects
When closely completely, by deleting the file of earliest time in DN, the capacity equilibrium of lasting guarantee DN and the availability of service.
It should also be noted that, under normal conditions, the quantity of back end DN is fixed in distributed memory system, but
Needs can also be encountered once in a while to add DN into system or delete DN situation.For example, needing should when some DN is damaged in system
DN is deleted;Alternatively, may then need to add new DN into system in system when lack of memory capacity.When need will be in system
When some DN is deleted, directly the DN can be deleted, and can be by the above method provided by the embodiment of the present disclosure, based on residue
The maximum DN of capacity creates the corresponding DN mark of DN that a new DN mark replaces the deletion, can be from surplus that is, being equivalent to
The maximum DN of covolume amount fictionalizes a DN and fills up at the DN of the deletion, to guarantee the clock availability and capacity of service
It is harmonious.Correspondingly, after completion of the above process, the variation time that DN mark can be updated, for example, can choose deletion DN
DN mark creation time and adjacent DN mark creation time between some time be updated as the time is changed, with
The variation time for guaranteeing each DN mark is state incremented by successively.In addition, can then add when needing to add DN into system for this
The DN added creates new DN mark, and DN mark is placed in the end of above-mentioned DN mark queue, then updates DN mark
The variation time is current time.
Based on described in previous embodiment, the embodiment of the present disclosure also provides a kind of videotex system and is applied to the view
The file memory method of frequency file system.
Fig. 7 shows the structural schematic diagram of the videotex system of embodiment of the present disclosure offer.As shown in fig. 7, the video
File system includes: multiple video cameras 710, computer 720, CM 730 and multiple DN 740;Video camera 710 can collect view
Frequency evidence is sent to computer 720;Computer 720 can handle video data to obtain video file, and will handle
To video file be sent to CM 730;The video file received can be distributed to each DN 740 and deposited by CM 730
Storage.
Fig. 8 shows the another flow diagram of the file memory method of embodiment of the present disclosure offer.
As shown in figure 8, the file memory method applied to the videotex system that the embodiment of the present disclosure provides, it can be with
Include:
Minimum capacity in the capacity of S801, the capacity for obtaining each DN and each DN.
S802, for any one DN, calculate the quotient that the capacity of DN is removed by minimum capacity, obtain calculated result.
S803, calculated result is rounded, obtains n, n is the integer greater than 0.
S804, n DN mark is created for DN.
S805, the corresponding DN mark of each DN is ranked up, obtains identifying queue by the DN that m DN mark forms, wherein
Each DN mark in DN mark queue all has corresponding sequence number and sequence number is less than or equal to m.
S806, the file identification for obtaining file to be stored, and Hash hash is carried out, obtain corresponding cryptographic Hash.
S807, according to cryptographic Hash to m remainder, obtain target sequence number.
S808, it is identified in queue from DN, chooses the corresponding DN mark of target sequence number and identified as target DN.
S809, judge that target DN identifies the residual capacity of corresponding target DN and whether is greater than default residual capacity threshold value.
If the residual capacity of S810, target DN are greater than default residual capacity threshold value, file to be stored is sent to target
DN is stored.
If the residual capacity of S811, target DN are less than or equal to default residual capacity threshold value, according to depositing in target DN
The corresponding storage time of file is stored up, the storage file of storage time within a preset period of time is deleted.
The embodiment of the present disclosure also provides a kind of file storage device, which can be applied to institute in preceding method embodiment
The CM in distributed memory system stated.
Fig. 9 shows the structural schematic diagram of the file storage device of embodiment of the present disclosure offer.
As shown in figure 9, this document storage device includes: to obtain module 10, for obtaining the file identification of file to be stored
DN mark corresponding with each DN;Hash module 20 obtains corresponding cryptographic Hash for carrying out Hash hash to file identification;Really
Cover half block 30, for determining target DN mark from the corresponding DN mark of each DN according to cryptographic Hash;Sending module 40, being used for will
File to be stored is sent to the corresponding target DN of target DN mark and is stored.
Figure 10 shows another structural schematic diagram of the file storage device of embodiment of the present disclosure offer.
Optionally, as shown in Figure 10, obtain module 10 include: the first acquisition submodule 11, for obtain each DN capacity,
And the minimum capacity in the capacity of each DN;First creation submodule 12, for for any one DN: according to the capacity of DN and
Minimum capacity creates n DN mark for DN, wherein n is the integer greater than 0.
Optionally, the first creation submodule 12 is specifically used for, and calculates the quotient that the capacity of DN is removed by minimum capacity, is counted
Calculate result;Calculated result is rounded, n is obtained;N DN mark is created for DN.
Figure 11 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer.
Optionally, as shown in figure 11, obtaining module 10 includes: the second acquisition submodule 13, for obtaining the capacity of each DN
And preset capacity;Second creation submodule 14, for for any one DN: judging whether the capacity of DN is greater than preset capacity;
If more than preset capacity, then according to the capacity of DN and preset capacity, n DN mark is created for DN, wherein n is whole greater than 0
Number;Otherwise, 1 DN mark is created for DN.
Figure 12 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer.
Optionally, as shown in figure 12, determining module 30, comprising: sorting sub-module 31, for the corresponding DN of each DN to be identified
It is ranked up, obtains identifying queue by the DN that m DN mark forms, wherein each DN mark in DN mark queue all has
Corresponding sequence number and sequence number are less than or equal to m;Computational submodule 32, for calculating target sequence according to cryptographic Hash and m
Number;Submodule 33 is chosen, is identified for from DN mark queue, choosing the corresponding DN mark of target sequence number as target DN.
Optionally, computational submodule 32 are specifically used for obtaining target sequence number to m remainder according to cryptographic Hash.
Figure 13 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer.
Optionally, as shown in figure 13, this document storage device further include: judgment module 50, for judging that target DN is identified
Whether the residual capacity of corresponding target DN is greater than default residual capacity threshold value;Sending module 40 is used to hold in the residue of target DN
When amount is greater than default residual capacity threshold value, file to be stored is sent to target DN and is stored.
Figure 14 shows the another structural schematic diagram of the file storage device of embodiment of the present disclosure offer.
Optionally, as shown in figure 14, this document storage device further include: removing module 60, for the residue in target DN
Capacity is less than or equal to default residual capacity threshold value, and the storage file of preset requirement is met in delete target DN.
Optionally, removing module 60, specifically for will store according to the corresponding storage time of storage file in target DN
The storage file of time within a preset period of time is deleted.
Due to the above-mentioned file storage device that the embodiment of the present disclosure provides, for executing in disclosure preceding method embodiment
The file memory method, so, there are preceding method whole beneficial effects as described in the examples, the disclosure is herein no longer
It repeats.
It should be noted that above-mentioned file storage device described in the embodiment of the present disclosure is only schematical,
The division of module is also possible to other modes, for example, it may be multiple modules are integrated together or some above-mentioned module
Multiple modules can also be divided into realize corresponding function, in the specific implementation process, can also be selected according to actual needs
Module some or all of is selected in this document storage device to realize that the scheme of the embodiment of the present disclosure, the disclosure are not made to have herein
Body limitation.
Optionally, the embodiment of the present disclosure also provides a kind of storage management apparatus, the storage management apparatus and multiple data sections
Point DN forms distributed memory system.
Figure 15 shows the structural schematic diagram of the storage management apparatus of embodiment of the present disclosure offer.
As shown in figure 15, which includes: processor 1001 and memory 1002, is stored in memory 1002
There is the computer program that can be run in processor 1001, processor 1001 is realized when executing computer program such as previous embodiment institute
The file memory method stated.Specific implementation is similar with technical effect, and which is not described herein again.
Optionally, the embodiment of the present disclosure also provides a kind of computer storage medium, is stored thereon with computer program, described
File memory method as in the foregoing embodiment is realized when computer program is executed by processor.
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair
Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.
Claims (20)
1. a kind of file memory method, which is characterized in that the method is applied to the centralized storage pipe in distributed memory system
Equipment CM is managed, the distributed memory system includes: CM and multiple back end DN;The described method includes:
Obtain the file identification and the corresponding DN mark of each DN of file to be stored;
Hash hash is carried out to the file identification, obtains corresponding cryptographic Hash;
According to the cryptographic Hash, target DN mark is determined from the corresponding DN mark of each DN;
The file to be stored is sent to the corresponding target DN of the target DN mark to store.
2. the method according to claim 1, wherein described obtain the corresponding DN mark of each DN, comprising:
Obtain the minimum capacity in the capacity of each DN and the capacity of each DN;
For any one of DN:
According to the capacity of the DN and the minimum capacity, n DN mark is created for the DN, wherein n is the integer greater than 0.
3. according to the method described in claim 2, it is characterized in that, the capacity and the minimum capacity according to the DN,
N DN mark is created for the DN, comprising:
The quotient that the capacity of the DN is removed by the minimum capacity is calculated, calculated result is obtained;
The calculated result is rounded, n is obtained;
N DN mark is created for the DN.
4. the method according to claim 1, wherein described obtain the corresponding DN mark of each DN, comprising:
Obtain the capacity and preset capacity of each DN;
For any one of DN:
Judge whether the capacity of the DN is greater than the preset capacity;
If more than the preset capacity, then according to the capacity of the DN and the preset capacity, n DN mark is created for the DN
Know, wherein n is the integer greater than 0;
Otherwise, 1 DN mark is created for the DN.
5. method according to claim 1-4, which is characterized in that it is described according to the cryptographic Hash, from each described
Target DN mark is determined in the corresponding DN mark of DN, comprising:
The corresponding DN mark of each DN is ranked up, obtains the DN mark queue being made of m DN mark, wherein described
Each DN mark in DN mark queue all has corresponding sequence number and the sequence number is less than or equal to the m;
According to the cryptographic Hash and the m, target sequence number is calculated;
From DN mark queue, chooses the corresponding DN mark of the target sequence number and identified as the target DN.
6. according to the method described in claim 5, it is characterized in that, described according to the cryptographic Hash and the m, calculating target sequence
Columns, comprising:
According to the cryptographic Hash to the m remainder, the target sequence number is obtained.
7. the method according to claim 1, wherein described be sent to the target DN for the file to be stored
It identifies before corresponding target DN stored, the method also includes:
Judge that the target DN identifies the residual capacity of corresponding target DN and whether is greater than default residual capacity threshold value;
If the residual capacity of the target DN is greater than default residual capacity threshold value, the file to be stored is sent to the mesh
Mark DN is stored.
8. the method according to the description of claim 7 is characterized in that being preset if the residual capacity of the target DN is less than or equal to
Residual capacity threshold value then deletes the storage file for meeting preset requirement in the target DN.
9. according to the method described in claim 8, it is characterized in that, described delete in the target DN meets depositing for preset requirement
Store up file, comprising:
According to the corresponding storage time of storage file in the target DN, by the storage text of storage time within a preset period of time
Part is deleted.
10. a kind of file storage device, which is characterized in that described device is applied to the centralized storage pipe in distributed memory system
Equipment CM is managed, the distributed memory system includes: CM and multiple back end DN;Described device includes:
Module is obtained, the corresponding DN mark of the file identification and each DN for obtaining file to be stored;
Hash module obtains corresponding cryptographic Hash for carrying out Hash hash to the file identification;
Determining module determines target DN mark from the corresponding DN mark of each DN for according to the cryptographic Hash;
Sending module is stored for the file to be stored to be sent to the corresponding target DN of the target DN mark.
11. device according to claim 10, which is characterized in that the acquisition module includes:
First acquisition submodule, for obtaining the minimum capacity in the capacity of each DN and the capacity of each DN;
First creation submodule, for for any one of DN: according to the capacity of the DN and the minimum capacity, for institute
It states DN and creates n DN mark, wherein n is the integer greater than 0.
12. device according to claim 11, which is characterized in that the first creation submodule is specifically used for, and calculates institute
The quotient that the capacity of DN is removed by the minimum capacity is stated, calculated result is obtained;The calculated result is rounded, n is obtained;It is described
DN creates n DN mark.
13. device according to claim 10, which is characterized in that the acquisition module includes:
Second acquisition submodule, for obtaining the capacity and preset capacity of each DN;
Second creation submodule, for for any one of DN: judging whether the capacity of the DN is greater than the default appearance
Amount;If more than the preset capacity, then according to the capacity of the DN and the preset capacity, n DN mark is created for the DN,
Wherein, n is the integer greater than 0;Otherwise, 1 DN mark is created for the DN.
14. the described in any item devices of 0-13 according to claim 1, which is characterized in that the determining module, comprising:
Sorting sub-module obtains being identified by the DN that m DN mark forms for the corresponding DN mark of each DN to be ranked up
Queue, wherein each DN mark in the DN mark queue all has corresponding sequence number and the sequence number is less than or waits
In the m;
Computational submodule, for calculating target sequence number according to the cryptographic Hash and the m;
Submodule is chosen, for from DN mark queue, choosing described in the corresponding DN mark conduct of the target sequence number
Target DN mark.
15. device according to claim 14, which is characterized in that the computational submodule is specifically used for according to the Kazakhstan
Uncommon value obtains the target sequence number to the m remainder.
16. device according to claim 10, which is characterized in that described device further include:
Whether judgment module is greater than default residual capacity for judging that the target DN identifies the residual capacity of corresponding target DN
Threshold value;
The sending module is used for when the residual capacity of the target DN is greater than default residual capacity threshold value, by described wait store
File is sent to the target DN and is stored.
17. device according to claim 16, which is characterized in that described device further include:
Removing module is less than or equal to default residual capacity threshold value for the residual capacity in the target DN, deletes the mesh
Meet the storage file of preset requirement in mark DN.
18. device according to claim 17, which is characterized in that the removing module is specifically used for according to the target
The corresponding storage time of storage file in DN, the storage file of storage time within a preset period of time is deleted.
19. a kind of storage management apparatus, which is characterized in that the storage management apparatus and multiple back end DN composition are distributed
Storage system;The storage management apparatus includes: processor and memory, and the meter that can be run in processor is stored in memory
Calculation machine program, processor realize such as the described in any item file memory methods of claim 1-9 when executing computer program.
20. a kind of computer storage medium, is stored thereon with computer program, which is characterized in that the computer program is located
It manages when device executes and realizes such as the described in any item file memory methods of claim 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910582756.4A CN110275873A (en) | 2019-06-28 | 2019-06-28 | File memory method, device, storage management apparatus and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910582756.4A CN110275873A (en) | 2019-06-28 | 2019-06-28 | File memory method, device, storage management apparatus and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110275873A true CN110275873A (en) | 2019-09-24 |
Family
ID=67963804
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910582756.4A Pending CN110275873A (en) | 2019-06-28 | 2019-06-28 | File memory method, device, storage management apparatus and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110275873A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110572478A (en) * | 2019-09-30 | 2019-12-13 | 重庆紫光华山智安科技有限公司 | Data transmission method and system based on distributed architecture service and FTP service |
CN110765094A (en) * | 2019-10-24 | 2020-02-07 | 重庆紫光华山智安科技有限公司 | File creation method, device, system and storage medium |
CN111147540A (en) * | 2019-11-18 | 2020-05-12 | 深圳市元征科技股份有限公司 | File transmission method, device, equipment and storage medium |
CN113793087A (en) * | 2021-02-26 | 2021-12-14 | 北京京东振世信息技术有限公司 | Method and device for sorting articles |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101294819A (en) * | 2008-06-05 | 2008-10-29 | 凯立德欣技术(深圳)有限公司 | Navigation system client terminal, service terminal, and map data providing and responding method |
CN104636286A (en) * | 2015-02-06 | 2015-05-20 | 华为技术有限公司 | Data access method and equipment |
CN105511801A (en) * | 2015-11-12 | 2016-04-20 | 长春理工大学 | Data storage method and apparatus |
CN105956068A (en) * | 2016-04-27 | 2016-09-21 | 湖南蚁坊软件有限公司 | Webpage URL repetition elimination method based on distributed database |
CN107133228A (en) * | 2016-02-26 | 2017-09-05 | 华为技术有限公司 | A kind of method and device of fast resampling |
CN107450855A (en) * | 2017-08-08 | 2017-12-08 | 山东浪潮云服务信息科技有限公司 | A kind of model for distributed storage variable data distribution method and system |
CN109241161A (en) * | 2018-08-09 | 2019-01-18 | 深圳市雅码科技有限公司 | A kind of meteorological data management method |
CN109254729A (en) * | 2018-08-24 | 2019-01-22 | 杭州宏杉科技股份有限公司 | A kind of method and apparatus of object storage |
CN109542330A (en) * | 2017-09-21 | 2019-03-29 | 杭州海康威视***技术有限公司 | Date storage method, data query method and device |
-
2019
- 2019-06-28 CN CN201910582756.4A patent/CN110275873A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101294819A (en) * | 2008-06-05 | 2008-10-29 | 凯立德欣技术(深圳)有限公司 | Navigation system client terminal, service terminal, and map data providing and responding method |
CN104636286A (en) * | 2015-02-06 | 2015-05-20 | 华为技术有限公司 | Data access method and equipment |
CN105511801A (en) * | 2015-11-12 | 2016-04-20 | 长春理工大学 | Data storage method and apparatus |
CN107133228A (en) * | 2016-02-26 | 2017-09-05 | 华为技术有限公司 | A kind of method and device of fast resampling |
CN105956068A (en) * | 2016-04-27 | 2016-09-21 | 湖南蚁坊软件有限公司 | Webpage URL repetition elimination method based on distributed database |
CN107450855A (en) * | 2017-08-08 | 2017-12-08 | 山东浪潮云服务信息科技有限公司 | A kind of model for distributed storage variable data distribution method and system |
CN109542330A (en) * | 2017-09-21 | 2019-03-29 | 杭州海康威视***技术有限公司 | Date storage method, data query method and device |
CN109241161A (en) * | 2018-08-09 | 2019-01-18 | 深圳市雅码科技有限公司 | A kind of meteorological data management method |
CN109254729A (en) * | 2018-08-24 | 2019-01-22 | 杭州宏杉科技股份有限公司 | A kind of method and apparatus of object storage |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110572478A (en) * | 2019-09-30 | 2019-12-13 | 重庆紫光华山智安科技有限公司 | Data transmission method and system based on distributed architecture service and FTP service |
CN110765094A (en) * | 2019-10-24 | 2020-02-07 | 重庆紫光华山智安科技有限公司 | File creation method, device, system and storage medium |
CN111147540A (en) * | 2019-11-18 | 2020-05-12 | 深圳市元征科技股份有限公司 | File transmission method, device, equipment and storage medium |
CN113793087A (en) * | 2021-02-26 | 2021-12-14 | 北京京东振世信息技术有限公司 | Method and device for sorting articles |
CN113793087B (en) * | 2021-02-26 | 2024-04-16 | 北京京东振世信息技术有限公司 | Method and device for sorting objects |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110275873A (en) | File memory method, device, storage management apparatus and storage medium | |
CN108427956B (en) | A kind of clustering objects method and apparatus | |
CN102655503B (en) | Use the Resourse Distribute in shared resource pond | |
CN104731647A (en) | Task processing method and system | |
CN114090244B (en) | Service arrangement method, device, system and storage medium | |
CN107797865A (en) | User task processing method and application server | |
CN107404541A (en) | A kind of method and system of peer-to-peer network transmission neighbor node selection | |
Jenkins et al. | A gossip protocol for subgroup multicast | |
CN108121511A (en) | Data processing method, device and equipment in a kind of distributed edge storage system | |
CN107203532A (en) | Construction method, the implementation method of search and the device of directory system | |
FR3025384A1 (en) | METHOD FOR MONITORING AND ROUTING CONFIGURATION ALERT IN A CLUSTER COMPRISING STATIC COMMUNICATION LINKS AND COMPUTER PROGRAM USING SAID METHOD | |
CN110601994A (en) | Load balancing method for micro-service chain perception in cloud environment | |
CN108234242A (en) | A kind of method for testing pressure and device based on stream | |
CN105183585A (en) | Data backup method and device | |
CN107453948A (en) | The storage method and system of a kind of network measurement data | |
KR101780534B1 (en) | Method and system for extracting image feature based on map-reduce for searching image | |
CN106878356B (en) | Scheduling method and computing node | |
CN106506647A (en) | A kind of client has the intelligence community cloud storage system of data backup device | |
Hanczewski et al. | Performance modelling of video-on-demand systems | |
CN111294553B (en) | Method, device, equipment and storage medium for processing video monitoring service signaling | |
CN110162666A (en) | A kind of the execution method and executive device of retrieval tasks | |
CN114936097A (en) | Processing node determination method, processing node determination device, computer equipment and storage medium | |
EP2439907A1 (en) | Method of data storing in a distributed data storage system and corresponding device | |
CN106874218B (en) | A kind of distribution method and its device of mapped address space | |
Zhang et al. | Scalable fast scheduling for optical flow switching using sampled entropy and mutual information broadcast |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190924 |
|
RJ01 | Rejection of invention patent application after publication |