CN111291009B - File block storage method and device - Google Patents
File block storage method and device Download PDFInfo
- Publication number
- CN111291009B CN111291009B CN202010214923.2A CN202010214923A CN111291009B CN 111291009 B CN111291009 B CN 111291009B CN 202010214923 A CN202010214923 A CN 202010214923A CN 111291009 B CN111291009 B CN 111291009B
- Authority
- CN
- China
- Prior art keywords
- storage
- cluster
- access
- node
- grouping
- 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.)
- Active
Links
Images
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
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 embodiment of the application provides a file block storage method and device, which are used for determining node grouping results of cluster storage nodes by predicting storage access rates of all cluster storage nodes in a cloud storage cluster, and associating access heat of all blocks in a file to be stored with the node grouping results of the cluster storage nodes, so that better distribution of all blocks of the file to be stored is determined, and further concurrent reading quantity of the file is effectively balanced.
Description
Technical Field
The application relates to the technical field of operating system storage, in particular to a file block storage method and device.
Background
In the cloud storage cluster, file data is usually stored in a plurality of blocks so as to effectively improve the reading performance during subsequent parallel reading, but excessive concurrent reading amount can generate a packet loss phenomenon, network delay and the like. Therefore, how to further determine a better distribution of blocks of the file to be stored to effectively balance the concurrent read volume is a great challenge in the art.
Disclosure of Invention
In view of the foregoing, an object of the present application is to provide a method and apparatus for storing file blocks, which can determine a better distribution of each block of a file to be stored, so as to effectively balance concurrent reading amounts of the file.
According to a first aspect of the present application, there is provided a file block storage method applied to a server communicatively connected to a cloud storage cluster, the method including:
acquiring a file storage access record in the cloud storage cluster, and establishing a load distribution model of the cloud storage cluster according to the file storage access record;
predicting storage access rates of all cluster storage nodes in the cloud storage clusters according to the load distribution model, and grouping all cluster storage nodes according to a prediction result to obtain a node grouping result;
and determining target cluster storage nodes corresponding to the blocks according to the access heat of the blocks in the file to be stored and the node grouping result, and storing the blocks into the target cluster storage nodes corresponding to the blocks.
In a possible implementation manner of the first aspect, the step of obtaining a file storage access record in the cloud storage cluster includes:
obtaining a target record field related to a request state in each storage access request sent to the cloud storage cluster, and generating a file storage access record of each cluster storage node in the cloud storage cluster according to the target record field;
And summarizing the file storage access records of each cluster storage node to obtain the file storage access records of the cloud storage clusters.
In a possible implementation manner of the first aspect, the step of establishing a load distribution model of the cloud storage cluster according to the file storage access record includes:
extracting load characteristics, performance index characteristics and array type vector characteristics of each storage cluster node in the cloud storage cluster from the file storage access record, wherein the load characteristics comprise access data quantity and access arrival time, the performance index characteristics comprise response delay characteristics, and the array type vector characteristics comprise cache utilization rate and cache hit ratio of the storage cluster nodes;
and establishing a load distribution model of the cloud storage cluster by taking the load characteristic, the performance index characteristic and the array type vector characteristic of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when each storage access request is received as result variables.
In a possible implementation manner of the first aspect, the step of establishing a load distribution model of the cloud storage cluster with the load feature, the performance index feature, and the array type vector feature of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when receiving each storage access request as result variables includes:
Fusing the feature vectors corresponding to the load feature, the performance index feature and the array vector feature of each storage cluster node in a preset feature traversal range to obtain a fused feature vector sequence in the preset feature traversal range;
calculating a fusion weight coefficient corresponding to each fusion feature vector in the fusion feature vector sequence, and taking the fusion feature vector corresponding to the smallest fusion weight coefficient in the fusion weight coefficients corresponding to all the fusion feature vectors obtained through calculation as the target feature vector of each storage cluster node;
sequentially performing association calculation on the target feature vector serving as an independent variable, the request time and the request response time according to the feature value of the preset feature traversal range to obtain a corresponding load distribution relation matrix;
extracting components of the target feature vector by using the load distribution relation matrix to form a plurality of feature components, and establishing a load distribution mapping relation according to the corresponding relation between the associated objects in the feature components and the load distribution relation in the feature characterization information of the feature components in the process of forming the plurality of feature components, wherein the established load distribution mapping relation comprises load distribution relations corresponding to all the associated objects in the feature components;
And fusing the established load distribution mapping relations to generate a load distribution model of the cloud storage cluster.
In a possible implementation manner of the first aspect, the step of predicting a storage access rate of each cluster storage node in the cloud storage cluster according to the load distribution model includes:
determining storage process parameters of each storage process of each cluster storage node in the cloud storage cluster and duration occupied by the storage process according to the load distribution model;
determining access prediction parameters of storage access processes required by distribution of the storage processes in each cluster storage node according to storage process parameters of the storage processes in each cluster storage node and duration occupied by the storage processes;
according to the access prediction parameters of the storage access process required by each storage process, simulating each storage access process into a storage access call object, wherein the call parameters corresponding to the storage access call object are call parameters except the call parameters of the current stored file fragments contained in the storage process;
According to the call parameters corresponding to the storage access call objects, establishing a load distribution relation of the storage access call objects, and determining a load distribution association position of the load distribution relation to obtain load characteristics of a first storage access call object in the load distribution association position;
when load feature screening is carried out on each storage access call object after a first storage access call object according to the sequence number of the storage access call object, screening is carried out on the load features of the storage access call object and each storage access call object after the storage access call object, according to the screened load features, the load distribution relation of the storage access call object is reestablished, the load distribution association position of the reestablished load distribution relation is determined, and the screening load features of the storage access call object in the load distribution association position of the reestablished load distribution relation are obtained;
and after the screening load characteristics of all the storage access calling objects are obtained, taking the average value of the storage access rates in the characteristic sequence formed by the screening load characteristics of all the storage access calling objects as the storage access rate of each corresponding cluster storage node.
In a possible implementation manner of the first aspect, the step of grouping the cluster storage nodes according to the prediction result to obtain a node grouping result includes:
determining a storage allocation area participated in storage allocation by each cluster storage node according to the storage access rate of each cluster storage node;
taking the storage allocation areas participated in storage allocation by each cluster storage node as input areas, and extracting grouping feature sequences of the storage allocation areas participated in storage allocation by each cluster storage node according to set grouping parameters;
constructing a grouping decision tree of the grouping feature sequence, wherein the grouping decision tree comprises decision points, state nodes connected with the decision points and decision result nodes, the decision points are used for obtaining decision parameters of the grouping feature sequence, the state nodes are used for obtaining decision states among the decision parameters corresponding to the connected decision points, and the decision result nodes are used for obtaining decision results of the connected state nodes;
and processing the grouping feature sequence according to the grouping decision tree to obtain node grouping results of all the cluster storage nodes, wherein each node grouping in the node grouping results corresponds to one storage access type.
In a possible implementation manner of the first aspect, according to the access heat of each partition in the file to be stored and the node grouping result, determining a target cluster storage node corresponding to each partition, and storing each partition in the corresponding target cluster storage node, where the method includes:
determining the storage allocation proportion and the storage access type of each block according to the access heat of each block in the file to be stored, wherein different storage access types respectively correspond to different access heat ranges;
and determining node groups matched with the storage access types of the blocks from the node grouping result, determining the target cluster storage nodes corresponding to the blocks in each matched node group according to the storage allocation proportion of the blocks, and storing the blocks in the corresponding target cluster storage nodes.
According to a second aspect of the present application, there is provided a file block storage device applied to a server communicatively connected to a cloud storage cluster, the device comprising:
the acquisition module is used for acquiring file storage access records in the cloud storage cluster and establishing a load distribution model of the cloud storage cluster according to the file storage access records;
The prediction grouping module is used for predicting the storage access rate of each cluster storage node in the cloud storage cluster according to the load distribution model, and grouping the cluster storage nodes according to a prediction result to obtain a node grouping result;
the determining module is used for determining the target cluster storage nodes corresponding to the blocks according to the access heat of the blocks in the file to be stored and the node grouping result, and storing the blocks into the target cluster storage nodes corresponding to the blocks.
According to a third aspect of the present application, there is provided a server comprising a machine-readable storage medium storing machine-executable instructions and a processor which, when executing the machine-executable instructions, implements the aforementioned file chunk store method.
According to a fourth aspect of the present application, there is provided a computer-readable storage medium having stored therein computer-executable instructions that, when executed, implement the foregoing file chunk storing method.
Based on any one of the above aspects, the method and the device for determining the access heat of the cloud storage cluster determine node grouping results of the cluster storage nodes by predicting storage access rates of all cluster storage nodes in the cloud storage cluster, and correlate access heat of all blocks in the file to be stored with the node grouping results of the cluster storage nodes, so that better distribution of all the blocks of the file to be stored is determined, and concurrent reading amounts of the file are effectively balanced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 shows an application scenario schematic diagram of a file block storage system provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart of a file block storage method according to an embodiment of the present disclosure;
FIG. 3 shows one of the sub-step flow diagrams of step S110 shown in FIG. 2;
FIG. 4 shows a second sub-step flow diagram of step S110 shown in FIG. 2;
fig. 5 shows one of the sub-step flow diagrams of step S120 shown in fig. 2;
FIG. 6 shows a second sub-step flow diagram of step S120 shown in FIG. 2;
fig. 7 shows a schematic flow chart of the substeps of step S130 shown in fig. 2;
FIG. 8 is a schematic functional block diagram of a file chunk store device according to an embodiment of the present disclosure;
Fig. 9 is a schematic component structure of a server for implementing the file chunk storing method according to the embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the accompanying drawings in the present application are only for the purpose of illustration and description, and are not intended to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this application, illustrates operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Moreover, one or more other operations may be added to the flow diagrams and one or more operations may be removed from the flow diagrams as directed by those skilled in the art.
Fig. 1 shows an application scenario of a file chunk storage system 10 according to an embodiment of the present application. In this embodiment, the file block storage system 10 may include a server 100 and a cloud storage cluster 200 communicatively connected to the server 100. The cloud storage cluster 200 may include a plurality of cluster storage nodes, each for distributing storage of a corresponding file fragment.
In other possible embodiments, the file-slicing storage system 10 may include only a portion of the components shown in FIG. 1 or may include other components as well.
In some embodiments, the server 100 may be a single server or a group of servers. The server farm may be centralized or distributed (e.g., server 100 may be a distributed system). In some embodiments, server 100 may be local or remote to cloud storage cluster 200. For example, server 100 may access information stored in cloud storage cluster 200 and a database, or any combination thereof, via a network. As another example, the server 100 may be directly connected to at least one of the cloud storage cluster 200 and the database to access information and/or data stored therein. In some embodiments, server 100 may be implemented on a cloud platform; for example only, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud (community cloud), distributed cloud, inter-cloud (inter-cloud), multi-cloud (multi-cloud), and the like, or any combination thereof.
In some embodiments, the server 100 may include a processor. The processor may process information and/or data related to the service request to perform one or more functions described herein. The processor may include one or more processing cores (e.g., a single core processor (S) or a multi-core processor (S)).
The aforementioned database may store data and/or instructions. In some embodiments, the database may store data assigned to cloud storage cluster 200. In some embodiments, the database may store data and/or instructions of the exemplary methods described in the present application. In some embodiments, the database may include mass storage, removable storage, volatile read-write memory, or read-only memory, or the like, or any combination thereof.
In some embodiments, the database may be connected to a network to communicate with one or more components in the file-sharding storage system 10 (e.g., server 100, cloud storage cluster 200, etc.). One or more components in file-slicing storage system 10 may access data or instructions stored in a database via a network. In some embodiments, the database may be directly connected to one or more components in the file-sharded storage system 10 (e.g., server 100, cloud storage cluster 200, etc., or in some embodiments, the database may be part of server 100 as well).
Fig. 2 shows a flow chart of a file-slicing storage method provided in an embodiment of the present application, where in this embodiment, the file-slicing storage method may be executed by the server shown in fig. 1. It should be understood that, in other embodiments, the order of some steps in the file fragment storing method of this embodiment may be interchanged according to actual needs, or some steps may be omitted or deleted. The detailed steps of the file fragment storage method are described below.
Step S110, obtaining a file storage access record in the cloud storage cluster 200, and building a load distribution model of the cloud storage cluster 200 according to the file storage access record.
Step S120, predicting storage access rates of all cluster storage nodes in the cloud storage cluster 200 according to the load distribution model, and grouping all cluster storage nodes according to the prediction result to obtain a node grouping result.
Step S130, determining target cluster storage nodes corresponding to the blocks according to the access heat of the blocks in the file to be stored and the node grouping result, and storing the blocks in the target cluster storage nodes corresponding to the blocks.
In this embodiment, the storage access rate of each cluster storage node in the cloud storage cluster 200 is predicted to determine a node grouping result of the cluster storage node, and the access heat of each partition in the file to be stored is associated with the node grouping result of the cluster storage node, so that the better distribution of each partition of the file to be stored is determined, and the concurrent reading quantity of the file is effectively balanced.
In one possible implementation, with respect to step S110, considering that each time a storage access request is sent to the cloud storage cluster 200, the relevant access record is typically recorded by a record field therein, referring to fig. 3 in combination, step S110 may be further implemented by the following sub-steps:
sub-step S111, obtaining a target record field related to the request status in each storage access request sent to the cloud storage cluster 200, and generating a file storage access record of each cluster storage node in the cloud storage cluster 200 according to the target record field.
And a substep S112, summarizing the file storage access records of each cluster storage node to obtain the file storage access records of the cloud storage cluster 200.
For example, it is possible to collect file storage access records on each cluster storage node for each storage access request, based on target record fields containing { request-size, offset, latency, start-time, finish-time } fields, and integrate these local file storage access records into a global file storage access record.
In one possible implementation manner, for step S110, for a plurality of cluster storage nodes capable of allocating resources, how much parallel reading efficiency can be improved and the amount of the parallel reading efficiency needs to be quantitatively measured, in order to accurately build a load distribution model of the cloud storage cluster 200 so as to facilitate the subsequent completion of the allocation of file block storage, referring to fig. 4, step S110 may be further implemented by the following substeps:
Sub-step S113 extracts the load characteristics, performance index characteristics, and array type vector characteristics of each storage cluster node in the cloud storage cluster 200 from the file storage access record.
In this embodiment, the load feature may include an access data amount and an access arrival time, the performance index feature may include a response delay feature, and the array type vector feature may include a cache utilization rate and a cache hit ratio of the storage cluster node.
In the substep S114, the load distribution model of the cloud storage cluster 200 is built by taking the load feature, the performance index feature and the array type vector feature of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when each storage access request is received as result variables.
For example, as a possible example, the present embodiment may fuse the feature vectors corresponding to the load feature, the performance index feature, and the array-type vector feature of each storage cluster node in a preset feature traversal range (for example, a range from feature 1 to feature 10), to obtain a fused feature vector sequence in the preset feature traversal range. For example, a fused feature vector sequence composed of a fused feature vector 1, a fused feature vector 2, a fused feature vector 3, a fused feature vector 4, a fused feature vector 5, a fused feature vector 6, a fused feature vector 7, a fused feature vector 8, a fused feature vector 9, and a fused feature vector 10 can be obtained.
Based on the above, the fusion weight coefficient corresponding to each fusion feature vector in the fusion feature vector sequence can be further calculated, and the fusion feature vector corresponding to the smallest fusion weight coefficient in all fusion feature vectors obtained through calculation is used as the target feature vector of each storage cluster node. And then, sequentially carrying out association calculation on the target feature vector serving as an independent variable, the request time and the request response time according to the feature value of the preset feature traversing range so as to obtain a corresponding load distribution relation matrix.
Therefore, the load distribution relation matrix can be utilized to extract the components of the target feature vector to form a plurality of feature components, and in the process of forming the plurality of feature components, the load distribution mapping relation is established according to the corresponding relation between the association objects in the feature components contained in the feature characterization information of the feature components and the load distribution relation.
The load distribution mapping relationship established above may include load distribution relationships corresponding to all the associated objects in the feature components, so that each load distribution mapping relationship established may be fused to generate a load distribution model of the cloud storage cluster 200.
On the basis of the above-mentioned load distribution model of the cloud storage cluster 200, referring further to fig. 5, step S120 may further include the following sub-steps:
sub-step S121, determining, according to the load distribution model, a storage process parameter of each storage process of each cluster storage node in the cloud storage cluster 200 and a duration occupied by the storage process.
And a sub-step S122, determining access prediction parameters of storage access processes required by the distribution of the storage processes in each cluster storage node according to the storage process parameters of the storage processes in each cluster storage node and the duration occupied by the storage processes.
In the substep S123, according to the access prediction parameters of the storage access process required by each storage process, each storage access process is simulated as a storage access call object, where the call parameters corresponding to the storage access call object are call parameters other than the call parameters of the current stored file fragments contained in the storage process.
And sub-step S124, establishing a load distribution relation of the storage access call object according to the call parameters corresponding to the storage access call object, and determining a load distribution association position of the load distribution relation to obtain the load characteristic of the first storage access call object in the load distribution association position.
And sub-step S125, when the load characteristic screening is carried out on each storage access call object after the first storage access call object according to the sequence number of the storage access call object, the load characteristics of the storage access call object and each storage access call object after the storage access call object are screened, the load distribution relation of the storage access call object is reestablished according to the screened load characteristics, the load distribution association position of the reestablished load distribution relation is determined, and the screened load characteristics of the storage access call object in the load distribution association position of the reestablished load distribution relation are obtained.
And step S126, after the screening load characteristics of all the storage access calling objects are obtained, taking the average value of the storage access rates in the characteristic sequence formed by the screening load characteristics of all the storage access calling objects as the storage access rate of each corresponding cluster storage node.
Based on the above steps, the embodiment effectively predicts the storage access rate of each cluster storage node, so that each cluster storage node is conveniently grouped according to the storage access rate of each cluster storage node, and the storage access efficiency and the heat degree of file access are considered to be strongly correlated, so that the better concurrency can be effectively determined in the process of carrying out file block storage subsequently, and the storage access efficiency is improved.
Based on the above description, further to step S120, in a possible implementation, please refer to fig. 6 in combination, the following sub-steps may be further included:
in a substep S127, a storage allocation area in which each cluster storage node participates in storage allocation is determined according to the storage access rate of each cluster storage node.
In the substep S128, the storage allocation area in which each cluster storage node participates in storage allocation is taken as an input area, and the group feature sequence of the storage allocation area in which each cluster storage node participates in storage allocation is extracted according to the set group parameters.
Sub-step S129, constructing a grouping decision tree of the grouping feature sequence, wherein the grouping decision tree comprises decision points, state nodes connected with the decision points and decision result nodes, the decision points are used for obtaining decision parameters of the grouping feature sequence, the state nodes are used for obtaining decision states among the decision parameters corresponding to the connected decision points, and the decision result nodes are used for obtaining decision results of the connected state nodes.
And sub-step S1295, processing the grouping feature sequence according to the grouping decision tree to obtain node grouping results of all the cluster storage nodes, wherein each node grouping in the node grouping results corresponds to one storage access type.
Based on the above substeps, in this embodiment, node grouping is performed on each cluster storage node through the decision tree, and by referring to the storage access rate of each cluster storage node, the node grouping result can be more associated with the storage access efficiency thereof, and further can be associated with the subsequent file access heat.
In one possible implementation, referring further to fig. 7, step S130 may be further implemented by the following sub-steps:
and sub-step S131, determining the storage allocation proportion and the storage access type of each block according to the access heat of each block in the file to be stored.
And sub-step S132, determining node groups matched with the storage access types of the blocks from the node grouping result, determining the respective corresponding target cluster storage nodes of the blocks in each matched node group according to the storage allocation proportion of the blocks, and storing the blocks in the respective corresponding target cluster storage nodes.
In this embodiment, different storage access types respectively correspond to different access heat ranges. For example, the storage access type of the file can be determined according to different size distributions of the access heat range, that is, the storage access type is strongly related to the access heat of each partition, so that the node grouping matched with the storage access type of each file partition can be determined from the node grouping result obtained in the above, then the respective corresponding target cluster storage node of each partition is determined in each matched node grouping according to the storage allocation proportion of each partition, each partition is stored in the respective corresponding target cluster storage node, the better distribution of each partition of the file to be stored can be determined, and the concurrent reading quantity of the file can be effectively balanced.
Based on the same inventive concept, please refer to fig. 8, which is a schematic diagram illustrating functional modules of the file-chunk storage device 110 according to an embodiment of the present application, where the embodiment may divide the functional modules of the file-chunk storage device 110 according to the above-mentioned method embodiment. For example, each functional module may be divided corresponding to each function, or two or more functions may be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation. For example, in the case of dividing each function module by the corresponding function, the file-fragment storage device 110 shown in fig. 8 is only one device diagram. The file-fragmentation storage 110 may include an acquisition module 111, a prediction grouping module 112, and a determination module 113, and the functions of the respective functional modules of the file-fragmentation storage 110 are described in detail below.
The obtaining module 111 is configured to obtain a file storage access record in the cloud storage cluster 200, and establish a load distribution model of the cloud storage cluster 200 according to the file storage access record. It is understood that the acquisition module 111 may be used to perform the step S110 described above, and reference may be made to the details of the implementation of the acquisition module 111 regarding the step S110 described above.
The prediction grouping module 112 is configured to predict storage access rates of each cluster storage node in the cloud storage cluster 200 according to the load distribution model, and group each cluster storage node according to the prediction result, so as to obtain a node grouping result. It will be appreciated that the predictive grouping module 112 may be used to perform step S120 described above, and reference may be made to the details of the implementation of the predictive grouping module 112 as described above with respect to step S120.
The determining module 113 is configured to determine, according to the access heat of each partition in the file to be stored and the node grouping result, a target cluster storage node corresponding to each partition, and store each partition in the corresponding target cluster storage node. It is understood that the determining module 113 may be used to perform the above step S130, and reference may be made to the above description of the step S130 for a detailed implementation of the determining module 113.
In one possible implementation, the obtaining module 111 may obtain the file storage access record in the cloud storage cluster 200 by:
obtaining a target record field related to a request state in each storage access request sent to the cloud storage cluster 200, and generating a file storage access record of each cluster storage node in the cloud storage cluster 200 according to the target record field;
And summarizing the file storage access records of each cluster storage node to obtain the file storage access records of the cloud storage cluster 200.
In one possible implementation, the acquisition module 111 may build a load distribution model of the cloud storage cluster 200 by:
extracting load characteristics, performance index characteristics and array type vector characteristics of each storage cluster node in the cloud storage cluster 200 from the file storage access records, wherein the load characteristics comprise access data quantity and access arrival time, the performance index characteristics comprise response delay characteristics, and the array type vector characteristics comprise cache utilization rate and cache hit ratio of the storage cluster nodes;
the load distribution model of the cloud storage cluster 200 is established with the load characteristic, the performance index characteristic and the array type vector characteristic of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when each storage access request is received as result variables.
In one possible implementation, the acquisition module 111 may build a load distribution model of the cloud storage cluster 200 by:
in a preset feature traversal range, fusing the feature vectors corresponding to the load feature, the performance index feature and the array type vector feature of each storage cluster node to obtain a fused feature vector sequence in the preset feature traversal range;
Calculating a fusion weight coefficient corresponding to each fusion feature vector in the fusion feature vector sequence, and taking the fusion feature vector corresponding to the smallest fusion weight coefficient in the fusion weight coefficients corresponding to all the fusion feature vectors obtained through calculation as a target feature vector of each storage cluster node;
sequentially performing association calculation on the target feature vector serving as an independent variable, the request time and the request response time according to the feature value of the preset feature traversal range to obtain a corresponding load distribution relation matrix;
extracting components of the target feature vector by using a load distribution relation matrix to form a plurality of feature components, and establishing a load distribution mapping relation according to the corresponding relation between the associated objects in the feature components and the load distribution relation in the feature characteristic information of the feature components in the process of forming the plurality of feature components, wherein the established load distribution mapping relation comprises load distribution relations corresponding to all the associated objects in the feature components;
and fusing the established load distribution mapping relations to generate a load distribution model of the cloud storage cluster 200.
In one possible implementation, the prediction grouping module 112 may predict the storage access rates of the individual cluster storage nodes in the cloud storage cluster 200 by:
Determining storage process parameters of each storage process of each cluster storage node in the cloud storage cluster 200 and duration occupied by the storage process according to the load distribution model;
determining access prediction parameters of storage access processes required by the distribution of the storage processes in each cluster storage node according to the storage process parameters of the storage processes in each cluster storage node and the duration occupied by the storage processes;
according to the access prediction parameters of the storage access process required by each storage process, simulating each storage access process into a storage access call object, wherein the call parameters corresponding to the storage access call object are call parameters except the call parameters of the current stored file fragments contained in the storage process;
according to the call parameters corresponding to the storage access call objects, establishing a load distribution relation of the storage access call objects, and determining a load distribution association position of the load distribution relation to obtain load characteristics of a first storage access call object in the load distribution association position;
when load feature screening is carried out on each storage access call object after a first storage access call object according to the sequence number of the storage access call object, screening is carried out on the load features of the storage access call object and each storage access call object after the storage access call object, according to the screened load features, the load distribution relation of the storage access call object is reestablished, the load distribution association position of the reestablished load distribution relation is determined, and the screening load features of the storage access call object in the load distribution association position of the reestablished load distribution relation are obtained;
And after the screening load characteristics of all the storage access calling objects are obtained, taking the average value of the storage access rates in the characteristic sequence formed by the screening load characteristics of all the storage access calling objects as the storage access rate of each corresponding cluster storage node.
In one possible implementation, the predictive grouping module 112 may group the cluster storage nodes in the following manner to obtain a node grouping result:
determining a storage allocation area participated in storage allocation by each cluster storage node according to the storage access rate of each cluster storage node;
taking a storage allocation area participated in storage allocation by each cluster storage node as an input area, and extracting a grouping feature sequence of the storage allocation area participated in storage allocation by each cluster storage node according to each set grouping parameter;
constructing a grouping decision tree of the grouping feature sequence, wherein the grouping decision tree comprises decision points, state nodes connected with the decision points and decision result nodes, the decision points are used for obtaining decision parameters of the grouping feature sequence, the state nodes are used for obtaining decision states among the decision parameters corresponding to the connected decision points, and the decision result nodes are used for obtaining decision results of the connected state nodes;
And processing the grouping feature sequence according to the grouping decision tree to obtain node grouping results of all the cluster storage nodes, wherein each node grouping in the node grouping results corresponds to one storage access type.
In one possible implementation manner, the determining module 113 may determine the target cluster storage node corresponding to each of the blocks, and store each of the blocks into the corresponding target cluster storage node, which includes:
determining the storage allocation proportion and the storage access type of each block according to the access heat of each block in the file to be stored, wherein different storage access types respectively correspond to different access heat ranges;
and determining node groups matched with the storage access types of the blocks from the node grouping result, determining the respective corresponding target cluster storage nodes of the blocks in each matched node group according to the storage allocation proportion of the blocks, and storing the blocks in the respective corresponding target cluster storage nodes.
Referring to fig. 9, a schematic block diagram of a server 100 for performing the above-mentioned file fragment storage method according to an embodiment of the present application is shown, where the server 100 may include a file fragment storage device 110, a machine-readable storage medium 120, and a processor 130.
In this embodiment, the machine-readable storage medium 120 and the processor 130 are both located in the server 100 and are separately provided. However, it should be understood that the machine-readable storage medium 120 may also be separate from the server 100 and accessible by the processor 130 through a bus interface. In the alternative, machine-readable storage medium 120 may be integrated into processor 130, and may be, for example, a cache and/or general purpose registers.
The processor 130 is a control center of the server 100 and connects various portions of the entire server 100 using various interfaces and lines to perform various functions and processes of the server 100 by running or executing software programs and/or modules stored in the machine-readable storage medium 120 and invoking data stored in the machine-readable storage medium 120, thereby performing overall monitoring of the server 100. Optionally, the processor 130 may include one or more processing cores; for example, processor 130 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor.
The processor 130 may be a general-purpose central processing unit (Central Processing Unit, CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling program execution of the file-slicing storage method provided in the above method embodiment.
The machine-readable storage medium 120 may be, but is not limited to, ROM or other type of static storage device, RAM or other type of dynamic storage device, which may store static information and instructions, or Electrically Erasable Programmabler-Only MEMory (EEPROM), compact Read-Only MEMory (CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The machine-readable storage medium 120 may reside separately and be coupled to the processor 130 by a communication bus. The machine-readable storage medium 120 may also be integral to the processor. Wherein the machine-readable storage medium 120 is used to store machine-executable instructions for performing aspects of the present application. The processor 130 is configured to execute machine-executable instructions stored in the machine-readable storage medium 120 to implement the file-fragmentation storage method provided by the foregoing method embodiments.
The file-tile storage 110 may include software functional modules (e.g., the acquisition module 111, the predictive grouping module 112, and the determination module 113 shown in fig. 8) stored on the machine-readable storage medium 120, which when executed by the processor 130, implement the file-tile storage method provided by the foregoing method embodiments.
Since the server 100 provided in the embodiment of the present application is another implementation form of the method embodiment executed by the server 100, and the server 100 may be used to execute the file fragment storage method provided in the method embodiment, the technical effects that can be obtained by the method embodiment may refer to the method embodiment and will not be described herein.
Further, the embodiment of the application further provides a readable storage medium containing computer executable instructions, which when executed can be used to implement the file fragment storage method provided in the above method embodiment.
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present application is not limited to the above method operations, and may also perform the related operations in the file fragment storage method provided in any embodiment of the present application.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the present application has been described herein in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the figures, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
The foregoing is merely various embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. The file block storage method is characterized by being applied to a server in communication connection with a cloud storage cluster, and comprises the following steps:
acquiring a file storage access record in the cloud storage cluster, and establishing a load distribution model of the cloud storage cluster according to the file storage access record;
predicting storage access rates of all cluster storage nodes in the cloud storage clusters according to the load distribution model, and grouping all cluster storage nodes according to a prediction result to obtain a node grouping result;
determining target cluster storage nodes corresponding to the blocks according to the access heat of the blocks in the file to be stored and the node grouping result, and storing the blocks into the target cluster storage nodes corresponding to the blocks; wherein:
The step of establishing a load distribution model of the cloud storage cluster according to the file storage access record comprises the following steps:
extracting load characteristics, performance index characteristics and array type vector characteristics of each storage cluster node in the cloud storage cluster from the file storage access record, wherein the load characteristics comprise access data quantity and access arrival time, the performance index characteristics comprise response delay characteristics, and the array type vector characteristics comprise cache utilization rate and cache hit ratio of the storage cluster nodes;
establishing a load distribution model of the cloud storage cluster by taking the load characteristic, the performance index characteristic and the array type vector characteristic of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when each storage access request is received as result variables;
predicting storage access rates of each cluster storage node in the cloud storage cluster according to the load distribution model, including:
determining storage process parameters of each storage process of each cluster storage node in the cloud storage cluster and duration occupied by the storage process according to the load distribution model;
Determining access prediction parameters of storage access processes required by distribution of the storage processes in each cluster storage node according to storage process parameters of the storage processes in each cluster storage node and duration occupied by the storage processes;
according to the access prediction parameters of the storage access process required by each storage process, simulating each storage access process into a storage access call object, wherein the call parameters corresponding to the storage access call object are call parameters except the call parameters of the current stored file fragments contained in the storage process;
according to the call parameters corresponding to the storage access call objects, establishing a load distribution relation of the storage access call objects, and determining a load distribution association position of the load distribution relation to obtain load characteristics of a first storage access call object in the load distribution association position;
when load feature screening is carried out on each storage access call object after a first storage access call object according to the sequence number of the storage access call object, screening is carried out on the load features of the storage access call object and each storage access call object after the storage access call object, according to the screened load features, the load distribution relation of the storage access call object is reestablished, the load distribution association position of the reestablished load distribution relation is determined, and the screening load features of the storage access call object in the load distribution association position of the reestablished load distribution relation are obtained;
And after the screening load characteristics of all the storage access calling objects are obtained, taking the average value of the storage access rates in the characteristic sequence formed by the screening load characteristics of all the storage access calling objects as the storage access rate of each corresponding cluster storage node.
2. The method for storing file blocks according to claim 1, wherein the step of obtaining a file storage access record in the cloud storage cluster includes:
obtaining a target record field related to a request state in each storage access request sent to the cloud storage cluster, and generating a file storage access record of each cluster storage node in the cloud storage cluster according to the target record field;
and summarizing the file storage access records of each cluster storage node to obtain the file storage access records of the cloud storage clusters.
3. The method for storing file blocks according to claim 1, wherein the step of establishing the load distribution model of the cloud storage cluster by using the load characteristic, the performance index characteristic and the array type vector characteristic of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when receiving each storage access request as result variables comprises:
Fusing the feature vectors corresponding to the load feature, the performance index feature and the array vector feature of each storage cluster node in a preset feature traversal range to obtain a fused feature vector sequence in the preset feature traversal range;
calculating a fusion weight coefficient corresponding to each fusion feature vector in the fusion feature vector sequence, and taking the fusion feature vector corresponding to the smallest fusion weight coefficient in the fusion weight coefficients corresponding to all the fusion feature vectors obtained through calculation as the target feature vector of each storage cluster node;
sequentially performing association calculation on the target feature vector serving as an independent variable, the request time and the request response time according to the feature value of the preset feature traversal range to obtain a corresponding load distribution relation matrix;
extracting components of the target feature vector by using the load distribution relation matrix to form a plurality of feature components, and establishing a load distribution mapping relation according to the corresponding relation between the associated objects in the feature components and the load distribution relation in the feature characterization information of the feature components in the process of forming the plurality of feature components, wherein the established load distribution mapping relation comprises load distribution relations corresponding to all the associated objects in the feature components;
And fusing the established load distribution mapping relations to generate a load distribution model of the cloud storage cluster.
4. The method for storing file blocks according to claim 1, wherein the step of grouping the cluster storage nodes according to the prediction result to obtain a node grouping result comprises:
determining a storage allocation area participated in storage allocation by each cluster storage node according to the storage access rate of each cluster storage node;
taking the storage allocation areas participated in storage allocation by each cluster storage node as input areas, and extracting grouping feature sequences of the storage allocation areas participated in storage allocation by each cluster storage node according to set grouping parameters;
constructing a grouping decision tree of the grouping feature sequence, wherein the grouping decision tree comprises decision points, state nodes connected with the decision points and decision result nodes, the decision points are used for obtaining decision parameters of the grouping feature sequence, the state nodes are used for obtaining decision states among the decision parameters corresponding to the connected decision points, and the decision result nodes are used for obtaining decision results of the connected state nodes;
And processing the grouping feature sequence according to the grouping decision tree to obtain node grouping results of all the cluster storage nodes, wherein each node grouping in the node grouping results corresponds to one storage access type.
5. The method for storing file blocks according to claim 1, wherein the step of determining the respective corresponding target cluster storage nodes of each block according to the access heat of each block in the file to be stored and the node grouping result, and storing each block in the respective corresponding target cluster storage node comprises the steps of:
determining the storage allocation proportion and the storage access type of each block according to the access heat of each block in the file to be stored, wherein different storage access types respectively correspond to different access heat ranges;
and determining node groups matched with the storage access types of the blocks from the node grouping result, determining the target cluster storage nodes corresponding to the blocks in each matched node group according to the storage allocation proportion of the blocks, and storing the blocks in the corresponding target cluster storage nodes.
6. A file block storage device, characterized by being applied to a server communicatively connected to a cloud storage cluster, the device comprising:
the acquisition module is used for acquiring file storage access records in the cloud storage cluster and establishing a load distribution model of the cloud storage cluster according to the file storage access records;
the prediction grouping module is used for predicting the storage access rate of each cluster storage node in the cloud storage cluster according to the load distribution model, and grouping the cluster storage nodes according to a prediction result to obtain a node grouping result;
the determining module is used for determining target cluster storage nodes corresponding to the blocks according to the access heat of the blocks in the file to be stored and the node grouping result, and storing the blocks into the target cluster storage nodes corresponding to the blocks; wherein:
the acquisition module is used for establishing a load distribution model of the cloud storage cluster according to the file storage access records by the following modes:
extracting load characteristics, performance index characteristics and array type vector characteristics of each storage cluster node in the cloud storage cluster from the file storage access record, wherein the load characteristics comprise access data quantity and access arrival time, the performance index characteristics comprise response delay characteristics, and the array type vector characteristics comprise cache utilization rate and cache hit ratio of the storage cluster nodes;
Establishing a load distribution model of the cloud storage cluster by taking the load characteristic, the performance index characteristic and the array type vector characteristic of each storage cluster node as dependent variables and the request time and the request response time of each storage cluster node when each storage access request is received as result variables;
the prediction grouping module is used for predicting storage access rates of each cluster storage node in the cloud storage cluster by the following steps:
determining storage process parameters of each storage process of each cluster storage node in the cloud storage cluster and duration occupied by the storage process according to the load distribution model;
determining access prediction parameters of storage access processes required by distribution of the storage processes in each cluster storage node according to storage process parameters of the storage processes in each cluster storage node and duration occupied by the storage processes;
according to the access prediction parameters of the storage access process required by each storage process, simulating each storage access process into a storage access call object, wherein the call parameters corresponding to the storage access call object are call parameters except the call parameters of the current stored file fragments contained in the storage process;
According to the call parameters corresponding to the storage access call objects, establishing a load distribution relation of the storage access call objects, and determining a load distribution association position of the load distribution relation to obtain load characteristics of a first storage access call object in the load distribution association position;
when load feature screening is carried out on each storage access call object after a first storage access call object according to the sequence number of the storage access call object, screening is carried out on the load features of the storage access call object and each storage access call object after the storage access call object, according to the screened load features, the load distribution relation of the storage access call object is reestablished, the load distribution association position of the reestablished load distribution relation is determined, and the screening load features of the storage access call object in the load distribution association position of the reestablished load distribution relation are obtained;
and after the screening load characteristics of all the storage access calling objects are obtained, taking the average value of the storage access rates in the characteristic sequence formed by the screening load characteristics of all the storage access calling objects as the storage access rate of each corresponding cluster storage node.
7. The file chunk store of claim 6, wherein the predictive grouping module is configured to group the individual cluster storage nodes to obtain a node grouping result by:
determining a storage allocation area participated in storage allocation by each cluster storage node according to the storage access rate of each cluster storage node;
taking the storage allocation areas participated in storage allocation by each cluster storage node as input areas, and extracting grouping feature sequences of the storage allocation areas participated in storage allocation by each cluster storage node according to set grouping parameters;
constructing a grouping decision tree of the grouping feature sequence, wherein the grouping decision tree comprises decision points, state nodes connected with the decision points and decision result nodes, the decision points are used for obtaining decision parameters of the grouping feature sequence, the state nodes are used for obtaining decision states among the decision parameters corresponding to the connected decision points, and the decision result nodes are used for obtaining decision results of the connected state nodes;
and processing the grouping feature sequence according to the grouping decision tree to obtain node grouping results of all the cluster storage nodes, wherein each node grouping in the node grouping results corresponds to a storage access type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010214923.2A CN111291009B (en) | 2020-03-25 | 2020-03-25 | File block storage method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010214923.2A CN111291009B (en) | 2020-03-25 | 2020-03-25 | File block storage method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291009A CN111291009A (en) | 2020-06-16 |
| CN111291009B true CN111291009B (en) | 2023-05-09 |
Family
ID=71019558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010214923.2A Active CN111291009B (en) | 2020-03-25 | 2020-03-25 | File block storage method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291009B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116776341B (en) * | 2023-04-23 | 2023-11-24 | 安徽安天利信工程管理股份有限公司 | Provider database file management system |
| CN116541365B (en) * | 2023-07-06 | 2023-09-15 | 成都泛联智存科技有限公司 | File storage method, device, storage medium and client |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103220367A (en) * | 2013-05-13 | 2013-07-24 | 深圳市中博科创信息技术有限公司 | Data replicating method and data storing system |
| CN110703980A (en) * | 2018-07-09 | 2020-01-17 | 网宿科技股份有限公司 | File transmission method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9727578B2 (en) * | 2012-09-28 | 2017-08-08 | International Business Machines Corporation | Coordinated access to a file system's shared storage using dynamic creation of file access layout |
| CA2867589A1 (en) * | 2013-10-15 | 2015-04-15 | Coho Data Inc. | Systems, methods and devices for implementing data management in a distributed data storage system |
-
2020
- 2020-03-25 CN CN202010214923.2A patent/CN111291009B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103220367A (en) * | 2013-05-13 | 2013-07-24 | 深圳市中博科创信息技术有限公司 | Data replicating method and data storing system |
| CN110703980A (en) * | 2018-07-09 | 2020-01-17 | 网宿科技股份有限公司 | File transmission method and device |
Non-Patent Citations (2)
| Title |
|---|
| 侯婕 ; .云计算下海量激光雷达数据动态存储系统设计.科技通报.2018,(09),全文. * |
| 冯向科 ; 邓莹 ; .双控云存储集群平台的形式化建模.电脑知识与技术.2018,(28),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291009A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109194584A (en) | A kind of flux monitoring method, device, computer equipment and storage medium | |
| CN111291009B (en) | File block storage method and device | |
| CN109309596B (en) | Pressure testing method and device and server | |
| US10061678B2 (en) | Automated validation of database index creation | |
| CN111767211A (en) | Test method and device of alliance chain, storage medium and electronic device | |
| CN110602227B (en) | Intelligent contract management method and related device | |
| CN110046093A (en) | Interface test method, device, computer equipment and storage medium | |
| CN111090401B (en) | Storage device performance prediction method and device | |
| CN114090204A (en) | Resource prediction method and device | |
| CN113342526A (en) | Dynamic management and control method, system, terminal and medium for cloud computing mobile network resources | |
| CN111427696B (en) | Service resource scheduling method and device | |
| EP4152715A1 (en) | Method and apparatus for determining resource configuration of cloud service system | |
| CN107844496B (en) | Statistical information output method and device | |
| CN116955148A (en) | Service system testing method, device, equipment, storage medium and product | |
| CN116962419A (en) | Method and device for generating server allocation policy, electronic equipment and storage medium | |
| CN107104829B (en) | Physical equipment matching distribution method and device based on network topology data | |
| Hanczewski et al. | A Multiparameter Analytical Model of the Physical Infrastructure of a Cloud-Based System | |
| Singh et al. | Estimating quantiles from the union of historical and streaming data | |
| CN114466019B (en) | Distributed computing system, load balancing method, device and storage medium | |
| CN117453493B (en) | GPU computing power cluster monitoring method and system for large-scale multi-data center | |
| EP3216167B1 (en) | Orchestrator and method for virtual network embedding using offline feedback | |
| CN116886777B (en) | Service flow distribution method and device for container arrangement platform | |
| CN117176728B (en) | Industrial Internet of things dispatching method and dispatching system based on cloud edge cooperative technology | |
| CN108319704A (en) | A kind of method, apparatus, equipment and the storage medium of analysis data | |
| WO2024125028A1 (en) | Pressure testing method and apparatus, and related device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |