CN109241178A - The method and apparatus for managing memory space - Google Patents
The method and apparatus for managing memory space Download PDFInfo
- Publication number
- CN109241178A CN109241178A CN201810804528.2A CN201810804528A CN109241178A CN 109241178 A CN109241178 A CN 109241178A CN 201810804528 A CN201810804528 A CN 201810804528A CN 109241178 A CN109241178 A CN 109241178A
- Authority
- CN
- China
- Prior art keywords
- time
- memory space
- objects
- metadata
- statistical information
- 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
Abstract
Provide a kind of method and apparatus for managing memory space, it is indexed at the first time by introducing, it include all object metadatas of index at the first time using first time search index, and calculate the capacity increment statistical information of each object in one or more objects, the capacity increment statistical information of obtained one or more objects is subjected to polymerization processing using same static fields, obtain polymerization result, it obtains indexing the polymerization result in the time slicing of instruction for same static fields at the first time, finally memory space is managed using polymerization result, help to improve the management performance of memory space.
Description
Technical field
This application involves field of storage, and more particularly, to a kind of method and apparatus for managing memory space.
Background technique
Object storage service (Object Storage Service) is that one kind can store document, picture, audio-visual video etc.
The cloud storage service of unstructured data can provide magnanimity, safe, highly reliable, inexpensive data storage capacities.Simply deposit
Storage service (simple storage service, S3) provides object by simple network service (Web Services) interface
Storage service.S3 provides the access of declarative state transfer (representational state transfer, REST) form
Interface allows users to easily by accessing object storage service in Web application.
Bucket (bucket), also referred to as memory paragraph, memory space, container as S3 system.User can create multiple buckets,
There is no limit for quantity, format (can be file, picture, video etc.) and the size summation for the object stored in each bucket.Currently,
S3 system charging mode is divided into detailed charging information and statistics charge information.For example, when user uploads a 5GB file, upper
Charging is carried out according to uninterrupted when passing request；If file is not deleted always, the memory space of S3 system is occupied, then is also wanted
According to the occupied time statistical information charging of memory space.
In the prior art, statistical information charging is to be written or delete data in user by the synchronous charging in foreground
While, S3 system needs the synchronous statistics charge information in foreground.But in big concurrent scene, (for example same user is in same a period of time
Between point write-in or delete a large amount of objects) or bottom there are scenes, the foreground synchronized update statistics affairs such as IO is abnormal and just will appear
The problems such as statistical information charging is not allowed.Therefore, it needs to propose that a kind of method for managing memory space promotes managerial energy.
Summary of the invention
In view of this, this application provides a kind of method and apparatus for managing memory space to have by introducing time index
Help improve the management performance of memory space.
It include multiple clothes in distributed objects storage system in a first aspect, providing a kind of method for managing memory space
Business node, the service node are used for storage object, which comprises inquiry includes all object metas indexed at the first time
Data, the first time index is used to indicate the period where the time for executing management operation to the object, described right
Object metadata is the corresponding object metadata of one or more objects；Calculate the appearance of each object in one or more of objects
Accrual accounting information is measured, the capacity increment statistical information includes the size of object, wherein the capacity increment statistical information is
By the corresponding object metadata record of object；The capacity increment statistical information of obtained one or more objects is used same
Static fields carry out polymerization processing, obtain polymerization result, and the polymerization result includes: when first time index indicates
Between the variable quantity of memory space that is occupied in section, according to one or more objects of static fields statistics.
In the embodiment of the present application, statistics node includes the institute indexed the first time using first time search index
There is object metadata, the capacity increment statistical information of each object in one or more of objects is then calculated, by what is obtained
The capacity increment statistical information of one or more objects carries out polymerization processing using same static fields, obtains polymerization result, institute
State polymerization result include: the first time index instruction period in, according to the static fields statistics one or
The variable quantity for the memory space that multiple objects occupy finally is carried out the management of memory space using obtained polymerization result, helped
In the management performance for improving memory space.Further, compared to the mode of foreground synchronized update charging, counting node can make
Asynchronous statistics charging is carried out with above-mentioned polymerization result, reduces the processing affairs of foreground process, helps to improve foreground performance.
In one possible implementation, before the inquiry includes all object metadatas indexed at the first time,
The method also includes:
Object Management group request from the user is obtained, the Object Management group request executes management to the first object for requesting
Operation, first object is an object in one or more of objects, and the management operation includes in following operation
Any one: new Object, upload object, delete object；
The first time index is distributed according to the period where the time when getting Object Management group request；
The metadata of the first object of generation is requested based on the Object Management group, wherein in the metadata of first object
It is indexed including the first time；
Store the first time index.
Therefore, after statistics node receives the Object Management group request of user on foreground, by obtaining current time index (ratio
As first time indexes), and first time index is stored into disk, in order to subsequent use.
In one possible implementation, the capacity increment statistical information of obtained one or more objects is used same
One static fields carry out polymerization processing, including,
For meeting the object of the static fields within the period of first time index instruction:
The memory space that the object that cumulative new Object operation creates occupies；
Cumulative upload object operates the memory space that uploaded object occupies；
Subtract the memory space of deleted object release.
Therefore, whether new Object or upload object, or deletion object, after the embodiment of the present application is based on the period
Platform statistical is applicable in.
In one possible implementation, the method also includes:
In the case where obtaining all one or more object metadatas including first time index, alternatively,
In the case where the corresponding memory headroom of the accrual accounting information reaches memory threshold, the one or more of object metas of lower wall
Data.
Therefore, statistics node is by setting preset condition, so that object metadata lower wall when meeting preset condition, avoids
It is to the holding time of memory headroom too long.
In one possible implementation, the method also includes: using the polymerization result manage memory space.
Optionally, memory space is managed using the polymerization result, comprising:
Charging is carried out based on variable quantity of the polymerization result to memory space.
Therefore, service node can be used above-mentioned polymerization result and carry out asynchronous statistics charging, reduce the place of foreground process
Director's business, helps to improve foreground performance.
Second aspect provides a kind of device for managing memory space, which includes for executing above-mentioned first aspect
Or the method for the management memory space in first aspect in any implementation method.
The third aspect provides a kind of device for managing memory space, which includes: processor and memory；This is deposited
For storing instruction, when the apparatus is operative, which executes the instruction of memory storage to reservoir, so that the device is held
Management memory space method in any implementation method of the above-mentioned first aspect of row or first aspect.It should be noted that this is deposited
Reservoir can integrate in processor, be also possible to independently of except processor.
Fourth aspect provides a kind of computer readable storage medium, which has program,
It is above-mentioned in a first aspect, and its any one of possible implementation management that the program executes the device for managing memory space
The method of memory space.
5th aspect, provides a kind of chip system, including processor, which is connected with memory, the processing
Device from memory for calling and running computer program, so that the computer equipment for being equipped with the chip system executes
Either state in either side and its possible embodiment method.The memory can be located inside the chip system, can also
To be located at outside the chip system.
6th aspect, provide a kind of program, the program when being executed by processor, for execute in a first aspect, and its
The method of any one of possible implementation management memory space.
7th aspect, provides a kind of program product, described program product includes: program code, works as said program code
It is managed scan module, computing module, processing module, management module or the place of the device (for example, service node) of memory space
Manage device, input/output interface operation when so that described device execute it is above-mentioned in a first aspect, and its in possible implementation
The method of any management memory space.
Detailed description of the invention
Fig. 1 is the schematic diagram of synchronized update statistics charge information in the prior art.
Fig. 2 is the schematic diagram indexed according to the service node acquisition time of the embodiment of the present application.
Fig. 3 is the schematic diagram using the period of the embodiment of the present application.
Fig. 4 is the schematic flow chart according to the method for the management memory space of the embodiment of the present application.
Fig. 5 is the schematic diagram according to an example of the background update charging metadata of the embodiment of the present application.
Fig. 6 is the schematic block diagram according to the device of the management memory space of the embodiment of the present application.
Fig. 7 is the schematic block diagram according to the statistics node of the embodiment of the present application.
Specific embodiment
Below in conjunction with attached drawing, the technical solution in the application is described.
The technical solution of the embodiment of the present application can be applied to the storage system for having regulatory requirement to memory space, distribution
Object storage system or cloud storage system.Optionally, the technical solution of the embodiment of the present application can be applied to simple storage service
In (simple storage service, S3).S3 provides object storage service by simple Web Services interface
(Object Storage Service).For example, the technical solution of the embodiment of the present application can be applied to the member in storage system
The statistics charge system of data.
Currently, storage system is to update statistics in such a way that foreground is synchronous when updating charge information in the prior art
Charge information, for example, user, while being written or deleting data, system can synchronized update statistics charge information.User is logical
Cross client to S3 interface send operation requests, which may include one or more in following: upload object, on
Biography section, deletion object, deletion section, covering upload object, covering upload section, bucket deletion etc..These operations will lead to customer charge
Increase, therefore be related to carrying out charging depending on the user's operation, that is to say, that S3 system is synchronous more for aforesaid operations request
Change billing increment information.By taking user requests upload object as an example, it is described here in conjunction with the schematic diagram in Fig. 1.Fig. 1 is existing
The schematic diagram of synchronized update statistics charge information in technology.As shown in Figure 1, S3 system, which receives user, passes through client to S3 interface
The upload operation of transmission is requested, and then generates corresponding metadata according to the data information of user.Then, S3 system reception comes from
The flow data of customer side, and by flow data write-in distributed memory system hard disk.S3 system deposits metadata write-in distribution
The hard disk of storage system.Meanwhile S3 system foreground meeting synchronous recording charging metadata, specifically i.e.: generating charging in upload object
Billing increment information is placed in waiting list (queue) by increment information, then uses function (for example, poll () function)
Current file pointer is suspended to waiting list, the charging metadata of each user of synchronized update, wherein different numbers in Fig. 1
The charging metadata of (including 1,2 and 3) is the charging metadata of different user, has N number of charging in the single bucket under each user
Metadata, recording in charging metadata has: the information such as object number, object size for including in corresponding bucket.S3 system is based on this
Secondary upload operation requests corresponding increment information, requests corresponding increment information to be added to charging metadata this upload operation
In.Finally, lower wall charging metadata (lower wall, which refers to, to be stored charging metadata into non-volatile memory medium from memory,
Such as storage is into hard disk), the operation of this upload request is completed.
In big concurrent scene, the mode of above-mentioned synchronized update statistics charge information is simultaneously not suitable for.For example, if same user
At same time point, a large amount of objects are written in request, then synchronous statistics bulk information are needed, if synchronized update failure due to time-out
Or the failure due to version conflict, it will statistical information is caused to update failure.Therefore, the application is quasi- introduces the general of period
It reads, the time index asynchronous management memory space (for example, statistics that backstage carries out charge information) based on the period, to improve system
Count the performance of charging.
The method of the management memory space of the embodiment of the present application can be applied in distributed objects storage system, distributed
It include multiple service nodes in object storage system, the service node is used for storage object；It can be corresponding to storage object
Object metadata (metadata can be referred to as)；Optionally, metadata can also be taken by individual one or more metadata
Business device storage.Method in the embodiment of the present application can (management node can be point by the management node in distributed memory system
Host node in cloth storage system, for managing multiple service nodes) or service node (Service Node) execution, also
It can be executed by third party's node in distributed memory system, for the convenience of description, execution the embodiment of the present application method
Node is referred to as statistics node.Statistics node is synchronous for use by foreground process in the Object Management group request for receiving user
The object write time index of family request operation, in order to which the asynchronous scanning in backstage uses.It should be understood that management node can be with
It is one in service node, the function of storage object is provided while possessing management function；It is also possible to dedicated management
Node does not provide the store function of object.
The acquisition process that will be detailed below time index in the embodiment of the present application, specifically includes:
Object Management group request from the user is obtained, the Object Management group request executes management to the first object for requesting
Operation, the management operation include any one of following operation: new Object, deletes object at upload object；
The first time index is distributed according to the period where the time when getting Object Management group request；
The metadata of the first object of generation is requested based on the Object Management group, wherein in the metadata of first object
It is indexed including the first time；
Store the first time index.
Specifically, statistics node is after the Object Management group request for receiving user, acquisition is currently received Object Management group request
Time where period corresponding time index (such as index at the first time), and object is written into obtained time index
Metadata in.Node is counted in the metadata of the first object of lower wall, needs to store first time index into disk, with
It is used convenient for the asynchronous scanning in backstage.
Here the format of the first object is not construed as limiting, for example, the first object can be the files such as video, photo, music,
A part of file or other data except file.It should be understood that retouched by taking the first object as an example here
State, actually user request management the corresponding metadata of object can in the way of above-mentioned first object write time rope
Draw, this is not construed as limiting.
Time index is for identifying the different periods in the embodiment of the present application, and each period, there are corresponding time ropes
Draw.Time index may also be referred to as the description that time tag, time slicing value etc. have index function.Wherein, the period refers to
One section of duration, may also be referred to as time slicing, for example, 1 point 05 assigns at 1 point can be for 30 seconds 06 minutes if dividing according to the time
One period, 1 point can be period ... etc. in 08 minutes at 31 seconds 06 minutes to 1 point.Period corresponding time index
Can be incremented by successively sequentially in time since a value, for example, if the period when it is 150 seconds a length of, time index from
0 starts, and increased every 150 seconds and adds 1, specifically i.e.: the corresponding time index of first 150s is 0, when second 150s is corresponding
Between index be 1 ... the corresponding time index of n-th 150s is N-1.Optionally, in specific implementation, time index can pass through length
Integer long [int] definition, for example, time index can indicate that int value is only increased since 0, and with fixation with int value
Time increase, every preset time (such as 150 seconds) plus one.Certainly, time index is intended merely to distinguish the different periods,
Therefore there can also be other implementing methods, for example, by using descending integer as time index, 2 system numbers are as time rope
Draw, or uses English alphabet, Chinese character as index.Optionally, the naming rule indexed by setting time, Ke Yicong
The worth precedence relationship for knowing the period of time index.
By taking service node is executing subject as an example, service node can be obtained at the first time by login mechanism from host node
Index, alternatively, the first time index can be generated in service node.Optionally, it if host node breaks down, services
Node can also be indexed by the slave node acquisition time of host node, be not construed as limiting to this.For example, as shown in Fig. 2, distributed right
As storage system may include multiple service nodes, host node and slave node.When multiple service nodes can be obtained by host node
Between index.Also, the content stored in host node can also be backed up in the slave node of host node.In this way, even if main section
Failure has occurred in point, and time index can be obtained by nor affecting on service node.
In addition, the difference with service node is that management node receives user if the above method is executed by management node
Object Management group request after, can be corresponding from the local period that directly acquire where being currently received the time that Object Management group is requested
Time index (for example indexing at the first time), and will be in the metadata of obtained time index write-in object.
It should be noted that statistics node and uses first time rope in the operation for the Object Management group request for executing user
Draw query object metadata be it is asynchronous, can by using different processes realize asynchronous operation.For example, statistics node is being held
The Object Management group request of row user operates with foreground process, after use when first time search index object metadata
Platform process.Wherein, foreground process is usually what user used, needs higher response speed；Background process substantially not with
Family interaction, the demand to response speed be not high.Since foreground object management operation and background scanning are asynchronous, in this way, even if
It is big concurrent (for example, same user is written or deletes a large amount of objects at same time point) scene, foreground performance will not be influenced.
In order to make it easy to understand, the process of write time index is described by taking the process of upload object as an example below:
Statistics node is after the upload object request for receiving user, available logical timer.Optionally, logical timer is
Refer to the current newest time index (or time tag value) obtained from host node.For example, if the period divided with 150s, the 1st
A period corresponds to time index 0, and the 2nd period corresponds to time index 1 ..., etc. then the logical timer obtained can be
Time index 1.Before statistics node acquisition time index, there may be other statistics nodes to obtain time index
Value, therefore the time index obtained at this time is newest time index this moment.Alternatively, logical timer be also possible to it is current newest
Logical timer, statistics node are based on the current newest available time index of logical timer.For example, if the period with 150s draw
Point, the 1st period is 1s- 150s, and the 2nd period is 151s- 300s ..., etc. if the logical timer obtained
It is 90s, then statistics node can learn that the value of time index is 0.Node is counted after obtaining time index, when by this
Between index write-in object metadata in.Compared to the process of existing upload object, the time has been increased newly in object metadata here
Index increases time index Create Time:X newly for example, the time index can be indicated using X in object metadata.
Similarly, by taking the process for deleting object as an example: statistics node is after receiving the deletion object requests of user, it is also desirable to
Newest time index is obtained, and in the corresponding object metadata of object that time index write-in is needed to delete.
In the embodiment of the present application, by time index by the corresponding object of object in distributed memory system (object)
Manage request operation (Object Management group request operation may include any one of new Object, upload object, deletion object)
Time divides according to time shaft.For example, as shown in figure 3, the corresponding Object Management group request of object in distributed memory system is grasped
The time of work can be divided according to the time shaft of N number of period, be specifically included:
Object in period 0 includes video 1 and music 1.Namely: video 1 and music 1 be performed management operation when
Between point belong within the scope of the period 0.The time for executing management operation specifically can be the time for starting to execute, at other
It can be the time for executing and completing in embodiment, in a further embodiment, be also possible to some equipment (such as S3 management section
The service node of point or S3) receive the time for executing the request of management.Wherein, it can be stamped respectively in video 1 and music 1
The label of period 0, for example, the request of the corresponding Object Management group of video 1 is delete operation, then the corresponding time tag of video 1 is
Erasing time (delete time) 0, for another example, the request of the corresponding Object Management group of music 1 are newly-built operations, then music 1 is corresponding
Time tag is creation time (create time) 0；
Object in period 1 includes photo 2, video 2 and music 1, wherein can be divided in photo 2, video 1 and music 1
The label of period 1 is not stamped, for example, the request of the corresponding Object Management group of photo 2 is delete operation, then corresponding time of photo 2
Label is erasing time (delete time) 1, and for another example, the request of the corresponding Object Management group of video 2 is newly-built operation, then video 2
Corresponding time tag is creation time (create time) 1, and for another example, the request of the corresponding Object Management group of music 1 is newly-built behaviour
Make, then the corresponding time tag of music 1 is creation time (create time) 1；
Object in period 2 includes backup 1, for example, the corresponding Object Management group request of backup 1 is upload operation, then it is standby
1 corresponding time tag of part is uplink time (upload time) 2；…；
Object in period N includes backup 2 and backup 3, for example, the corresponding Object Management group request of backup 2 is to upload behaviour
Make, then backing up 2 corresponding time tags is uplink time (upload time) N, and for another example, 3 corresponding Object Management groups of backup are asked
The newly-built operation of Seeking Truth, then backing up 3 corresponding time tags is creation time (create time) N.
Described above is how the process of write time index, how be described below using time index.
Fig. 4 shows the schematic flow chart of the method 200 of the management memory space according to the embodiment of the present application.The side
Method 200 can be executed by the device (virtual bench that physical entity device or software program module form) of management memory space, than
Such as, it can be executed by service node or management node.As shown in figure 4, the method 200 includes:
S210, inquiry include all object metadatas of index at the first time, wherein include one in the object metadata
The corresponding metadata of a or multiple objects, the first time index were used to indicate where the time for executing management operation to object
Period.
If method 200 is executed by service node, it includes the first time that service node can be inquired to management node
All object metadatas of index, alternatively, if method 200 is executed by management node, management node can include in local search
All object metadatas of the first time index.
By taking first time indexes as an example, statistics node carries out the overall situation to distributed objects storage system by background process and sweeps
Retouch, enumerate (list) go out it is all include index at the first time objects, with obtain include one indexed at the first time or
Multiple object metadatas.In other words, for the object metadata in each period, time index can be based on by counting node
It is scanned.
Optionally, one or more object metadatas including first time index can be user and request to delete
Object metadata, be also possible to the metadata that user requests the object uploaded, be also possible to the newly-built object of user's request
Metadata, this is not construed as limiting.
S220 calculates the capacity increment statistical information of each object in one or more of objects, the capacity increment
Statistical information includes the size of object.
Wherein, the capacity increment statistical information is used for the capacity or memory space that objects of statistics occupies.If object pair
The Object Management group request operation answered is to delete object, then capacity increment statistical information statistics is negative increment, that is, needs to delete
Memory space；If the corresponding Object Management group request operation of object is upload or new Object, capacity increment statistical information system
Meter is positive increment, i.e., object needs the amount of capacity that occupies.The purpose of above-mentioned capacity increment statistical information is objects of statistics
The memory space for occupying or deleting.
It optionally, can also include the number of object in the capacity increment statistical information.It should be understood that the number of object is simultaneously
It is not necessarily meant to, can be used for the memory space of ancillary statistics object occupancy.
Optionally, statistics node can calculate the appearance of each object after obtaining said one or multiple object metadatas
Measure accrual accounting information.For example, if user requests to upload an object to be that 5GB (Gigabyte) (5GB is the object uploaded
The amount of capacity for needing to occupy) operation, then capacity increment statistical information can be { 5GB ,+1 }.For another example, if user
The operation that an object is 2GB is deleted in request, then capacity increment statistical information can be { 2GB, -1 }.
The capacity increment statistical information of obtained one or more objects is polymerize by S230 using same static fields
Processing, obtains polymerization result, and the polymerization result includes: within the period of first time index instruction, according to
The variable quantity for the memory space that one or more objects of static fields statistics occupy.
Above-mentioned polymerization processing is specific i.e.: statistics node is right after the capacity increment statistical information for obtaining each object
The memory space occupied for the capacity increment statistical information of same static fields is counted, to obtain for same statistics
The polymerization result of field.
Wherein, it can be a kind of object meta with specific feature for the capacity increment statistical information of same static fields
The capacity increment statistical information of data, for example, belong to it is same user's or same bucket in or same file folder appearance
Accrual accounting information is measured, this is not construed as limiting.
Optionally, static fields may include any one of following field: the words such as user, file, priority, bucket
Section.In other words, it can be stored according to user, file, priority or bucket as the range counted according to the period
The statistics of the occupied dosage in space.
Optionally, statistics node after the capacity increment statistical information for obtaining each object, can will it is described each
The capacity increment statistical information of object is added in caching.Specifically, caching can be divided into multiple memory headrooms, for same
The capacity increment statistical information of one static fields, can be stored in identical memory headroom.
Optionally, the capacity increment statistical information of the one or more objects that will be obtained using same static fields into
Row polymerization processing, including,
For meeting the object of the static fields within the period of first time index instruction:
The memory space that the object that cumulative new Object operation creates occupies；
Cumulative upload object operates the memory space that uploaded object occupies；
Subtract the memory space of deleted object release.
Specifically, counting node for meeting same statistics word within the period of first time index instruction
The object of section can subtract the memory space of object release, if right if the corresponding management operation request of object is removal request
As corresponding management operation request is upload or request to create, the then memory space that the object that can add up occupies.
With static fields be user for example, same user can upload multiple data in section at the same time, for example,
Party A-subscriber uploads video 5GB, music 1GB, picture 10GB, deletes picture 2GB, completes upload operation in period N,
So statistics node statistics go out multiple object accrual accounting information, and polymerization result after caching is added are as follows: and {+5GB ,+1 }++
1GB ,+1 }+{+10GB ,+1 }+{ -2GB, -1 }={ 14GB, 2 }.
Optionally, statistics node manages memory space using the polymerization result.
Specifically, statistics node can be used above-mentioned polymerization result and be managed to memory space, including statistics charging,
The operation such as dilatation is carried out based on number of threads.
Optionally, statistics node carries out charging based on variable quantity of the polymerization result to memory space.For example, statistics section
Above-mentioned polymerization result can be used in point, and the size of the memory space based on occupancy occupies duration or carries out charging using flow.
By taking above-mentioned polymerization result { 14GB, 2 } as an example, if according to capacity charging, it is assumed that the expense unit price of every GB memory space is x,
Corresponding charging result is 14GB*x, alternatively, if according to capacity and number charging, it is assumed that the expense unit price of every GB memory space
It is a, the expense unit price of number is y, then corresponding charging result is: 14GB*a+2*b.
It in the embodiment of the present application, include the one or more object metadatas indexed at the first time by inquiring, then
The capacity increment statistical information for calculating each object in one or more objects, the capacity of obtained one or more objects is increased
It measures statistical information and using same static fields carries out polymerization processing, obtain within the period that the first time indexes instruction,
According to the polymerization result that same static fields count, the management of memory space is finally carried out using polymerization result, is helped to improve
The management performance of memory space.Further, in statistics charge system, compared to the mode of foreground synchronized update charging, originally
Application embodiment can be used above-mentioned polymerization result and carry out asynchronous statistics charging, reduces the processing affairs of foreground process, helps
In raising foreground performance.
Optionally, the method 200 further include: obtaining all one or more including first time index
In the case where object metadata, alternatively, reaching the feelings of memory threshold in the corresponding memory headroom of the capacity increment statistical information
Under condition, the one or more of object metadatas of lower wall.
Optionally, the memory threshold can be pre-set.
Specifically, in the case that the caching of memory headroom reaches memory threshold, or about the first time rope
After the metadata drawn all has been enumerated, global team is added in the charging metadata indexed about the first time by statistics node
Column, asynchronous lower wall, and update the corresponding statistics charging metadata of user.
In order to facilitate the understanding of those skilled in the art, being carried out below with reference to process of the Fig. 5 to background update charging metadata
Description.As shown in figure 5, statistics node carries out backstage whole scan to distributed objects storage system, and enumerates and all include
All metadata (can be multiple users in the metadata of the period) of time index N, for example, the object being listed is
Create Time=N or Delete Time=N etc..Then, storage system according to enumerate come object metadata, meter
The capacity increment statistical information of this time operation is calculated, the memory space that objects of statistics occupies obtains capacity increment statistical information, then
Capacity increment statistical information is added in caching, wherein the information of the same user is stored in identical memory headroom (ratio
Such as, in Fig. 5, number 1 indicates the memory headroom of user 1, and number 2 indicates the memory headroom of user 2, and number 3 indicates user's 3
Memory headroom).Polymerization processing is carried out to all requests of each user in Fig. 5, obtains the corresponding polymerization result of each user.It can
Selection of land, whether the memory headroom that can also calculate capacity increment statistical information occupancy reaches memory threshold, if capacity increment is united
The memory headroom that meter information occupies reaches memory threshold, alternatively, all scanning through all objects including time index N
After metadata, then capacity increment statistical information can be added in asynchronous lower wall queue.Here it is possible to will be held using poll function
The file pointer of amount accrual accounting information is added in asynchronous lower wall queue, and line asynchronous of going forward side by side updates, and finally uses each user
Polymerization result carry out metadata charging.
The method that the management memory space according to the embodiment of the present application is described in detail above in association with Fig. 1 to Fig. 5.Below will
In conjunction with Fig. 6 and Fig. 7 description according to device/equipment of the management memory space of the embodiment of the present application.It should be understood that embodiment of the method institute
The technical characteristic of description is equally applicable to following Installation practice.
Fig. 6 shows the schematic block diagram of the device 600 of the management memory space according to the embodiment of the present application, device 600
It can execute and count step performed by node in the above method, therefore be referred to foregoing teachings, be not detailed herein.Distribution
It include multiple service nodes in formula object storage system, the service node is used for storage object；The corresponding object meta number of object
According to can be stored by service node or metadata node.Described device 600 can be realized in a manner of software and/or hardware, right
This is not construed as limiting.As shown in fig. 6, described device 600 includes:
Enquiry module 610 includes all object metadatas indexed at the first time for inquiring, the first time index
The period being used to indicate where the time for executing management operation to the object；
Computing module 620, for calculating the capacity increment statistical information of each object in one or more of objects, institute
State the size that capacity increment statistical information includes object, wherein the capacity increment statistical information is by the corresponding object of object
Metadata record；
Processing module 630, for the capacity increment statistical information of obtained one or more objects to be used same statistics
Field carries out polymerization processing, obtains polymerization result, and the polymerization result includes: the period in first time index instruction
The variable quantity of the memory space of one or more objects occupancy interior, according to static fields statistics.
In an optional implementation manner, described device 600 further include:
Module is obtained, for obtaining before enquiry module inquiry includes all object metadatas indexed at the first time
Object Management group from the user is taken to request, the Object Management group request executes management operation to the first object for requesting, described
First object is an object in one or more of objects, and the management operation includes any one of following operation:
New Object, deletes object at upload object；
Distribution module, for according to described in the period distribution where the time when getting Object Management group request
It indexes at the first time；
Generation module, for requesting the metadata of the first object of generation based on the Object Management group, wherein described first pair
It include indexing the first time in the metadata of elephant；
Memory module, for storing the first time index.
In an optional implementation manner, the capacity for one or more objects that the processing module 630 is used to arrive
Accrual accounting information carries out polymerization processing using same static fields, specifically includes,
For meeting the object of the static fields within the period of first time index instruction:
The memory space that the object that cumulative new Object operation creates occupies；
Cumulative upload object operates the memory space that uploaded object occupies；
Subtract the memory space of deleted object release.
In an optional implementation manner, described device 600 further include:
Accounting module, for carrying out charging based on variable quantity of the polymerization result to memory space.
It should be understood that can correspond to preceding method embodiment according to the device 600 of the management memory space of the embodiment of the present application
(including the method in Fig. 4), and above and other management operation and/or function of the modules in device 600 is respectively
The corresponding steps of the aforementioned each method of realization, therefore the beneficial effect in preceding method embodiment also may be implemented, for letter
It is clean, it does not repeat here.
Above-mentioned enquiry module 610, computing module 620 and processing module 630 can be realized by the processor 701 in Fig. 7.
Optionally, obtaining module can be realized by the input/output interface 703 in Fig. 7, distribution module, accounting module and generation mould
Block can also realize that memory module can be realized by the memory 702 in Fig. 7 by above-mentioned processor 701.
Fig. 7 shows the schematic block diagram of the statistics node 700 according to the embodiment of the present application.By executing program generation
Code, statistics node 700, which can execute, counts step performed by node in the above method, therefore the present embodiment is not detailed.Such as
Shown in Fig. 7, the statistics node 700 includes:
Processor 701, memory 702 and input/output interface 703.
It is communicated with each other, is passed by internal connecting path between processor 701, memory 702 and input/output interface 703
Pass control and/or data-signal.In a possible design, processor 701, memory 702 and input/output interface 703
It can be realized by chip.The memory 702 can store program code, the program that processor 701 calls memory 702 to store
Code, to realize the corresponding function of the statistics node.
The processor 701 is used for: by background process using at the first time index to distributed objects storage system into
Row whole scan, to inquire all object metadatas for including index at the first time, first time index is used to indicate pair
Object executes the period where the time of management operation, and the object metadata is the corresponding object meta of one or more objects
Data；Calculate the capacity increment statistical information of each object in one or more of objects, the capacity increment statistical information
Size including object, wherein the capacity increment statistical information is recorded by the corresponding object metadata of object；It will obtain
The capacity increment statistical informations of one or more objects carry out polymerization processing using same static fields, obtain polymerization result,
The polymerization result includes: within the period of first time index instruction, according to one of static fields statistics
Or the variable quantity of the memory space of multiple objects occupancy.Optionally, the processor 701 using the polymerization result for being managed
Memory space.
The processor 701 is for executing relative program, to realize the revealed method of the embodiment of the present application.It was realizing
Cheng Zhong, each step of above method embodiment can pass through the integrated logic circuit of the hardware in processor or software form
Instruction is completed.Above-mentioned processor 701 can be general processor, digital signal processor (digital signal
Processor, DSP), it is specific integrated circuit (application specific integrated circuit, ASIC), existing
At programmable gate array (field programmable gate array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components, can also be System on Chip/SoC (system on chip, SoC), can be with
It is central processing unit (central processor unit, CPU), can also be network processing unit (network
Processor, NP), it can also be digital signal processing circuit (digital signal processor, DSP), can also be
Microcontroller (micro controller unit, MCU), can also be programmable controller (programmable logic
Device, PLD) or other integrated chips.May be implemented or execute disclosed each method in the embodiment of the present application, step and
Logic diagram.General processor can be microprocessor or the processor is also possible to any conventional processor etc..In conjunction with
The step of method disclosed in the embodiment of the present application, can be embodied directly in hardware decoding processor and execute completion, or with decoding
Hardware and software module combination in processor execute completion.Software module can be located at random access memory, flash memory, read-only storage
In the storage medium of this fields such as device, programmable read only memory or electrically erasable programmable memory, register maturation.It should
Storage medium can be located at memory 702, and processor 701 reads the information in memory 702, complete the above method in conjunction with its hardware
The step of.
The memory 702 is used to store: the program code run for processor 701.Memory 702 can be interior
It deposits or solid-state hard disk SSD.It is appreciated that the memory 702 in the embodiment of the present application can be volatile memory or non-easy
The property lost memory, or may include both volatile and non-volatile memories.Wherein, nonvolatile memory can be read-only deposit
Reservoir (read-only memory, ROM), erasable is compiled programmable read only memory (programmable ROM, PROM)
Journey read-only memory (erasable PROM, EPROM), electrically erasable programmable read-only memory (electrically
EPROM, EEPROM) or flash memory.Volatile memory can be random access memory (random access memory,
RAM), it is used as External Cache.By exemplary but be not restricted explanation, the RAM of many forms is available, such as static
Random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic
Random access memory (synchronous DRAM, SDRAM), double data speed synchronous dynamic RAM
(double data rate SDRAM, DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (enhanced
SDRAM, ESDRAM), synchronized links dynamic random access memory (synchlink DRAM, SLDRAM) and direct rambus
Random access memory (direct rambus RAM, DR RAM).It should be noted that the memory of system and method described herein
It is intended to include but is not limited to the memory of these and any other suitable type.
In some cases, together with processor 701 can integrate with memory 702.
As another form of the present embodiment, a kind of computer readable storage medium is provided, is stored thereon with instruction, it should
Instruction is performed the method for executing and managing memory space in above method embodiment.Computer readable storage medium is for example interior
It deposits, hard disk, readable optical disk, flash disk etc..
As another form of the present embodiment, a kind of computer program product comprising instruction is provided, which is held
The method that memory space is managed in above method embodiment is executed when row.
The method that above-mentioned the embodiment of the present application discloses can be applied in processor, or be realized by processor.Processor
It may be a kind of IC chip, the processing capacity with signal.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
It should be understood that magnitude of the sequence numbers of the above procedures are not meant to execute suitable in the various embodiments of the application
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the implementation without coping with the embodiment of the present invention
Process constitutes any restriction.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read only memory ROM, random access memory ram, magnetic disk or light
The various media that can store program code such as disk.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application should be based on the protection scope of the described claims.
Claims (10)
1. a kind of method for managing memory space, which is characterized in that it include multiple service nodes in distributed objects storage system,
The service node is used for storage object, which comprises
Inquiry includes all object metadatas of index at the first time, and the first time index, which is used to indicate, holds the object
Period where the time of row management operation, the object metadata is the corresponding object metadata of one or more objects；
Calculate the capacity increment statistical information of each object in one or more of objects, the capacity increment statistical information packet
Include the size of object, wherein the capacity increment statistical information is recorded by the corresponding object metadata of object；
The capacity increment statistical information of obtained one or more objects is subjected to polymerization processing using same static fields, is obtained
Polymerization result, the polymerization result include: to unite within the period of first time index instruction, according to the static fields
The variable quantity for the memory space that one or more objects of meter occupy.
2. the method according to claim 1, wherein including all objects indexed at the first time in the inquiry
Before metadata, the method also includes:
Object Management group request from the user is obtained, the Object Management group request executes management behaviour to the first object for requesting
Make, first object is an object in one or more of objects, and the management operation includes in following operation
Any one: new Object, deletes object at upload object；
The first time index is distributed according to the period where the time when getting Object Management group request；
The metadata of the first object of generation is requested based on the Object Management group, wherein include in the metadata of first object
The first time index；
Store the first time index.
3. method according to claim 1 or 2, which is characterized in that the capacity of the one or more objects that will be obtained
Accrual accounting information carries out polymerization processing using same static fields, including,
For meeting the object of the static fields within the period of first time index instruction:
The memory space that the object that cumulative new Object operation creates occupies；
Cumulative upload object operates the memory space that uploaded object occupies；
Subtract the memory space of deleted object release.
4. according to the method in any one of claims 1 to 3, which is characterized in that the method also includes:
Charging is carried out based on variable quantity of the polymerization result to memory space.
5. a kind of statistics node, for the space hold of object in statistical cloth object storage system, the statistics node packet
Processor, storage medium and interface are included, computer program is stored in the storage medium, the interface connects for correspondence with foreign country
It connects, the processor executes following methods by running the computer program:
Inquiry includes all object metadatas of index at the first time, and the first time index, which is used to indicate, holds the object
Period where the time of row management operation, the object metadata is the corresponding object metadata of one or more objects；
Calculate the capacity increment statistical information of each object in one or more of objects, the capacity increment statistical information packet
Include the amount of capacity of object, wherein the capacity increment statistical information is recorded by the corresponding object metadata of object；
The capacity increment statistical information of obtained one or more objects is subjected to polymerization processing using same static fields, is obtained
Polymerization result, the polymerization result include: to unite within the period of first time index instruction, according to the static fields
The variable quantity for the memory space that one or more objects of meter occupy.
6. a kind of device for managing memory space, which is characterized in that it include multiple service nodes in distributed objects storage system,
The service node is used for storage object, and described device includes:
Enquiry module includes all object metadatas indexed at the first time for inquiring, and the first time index is for referring to
Show the period where the time for executing management operation to the object；
Computing module, for calculating the capacity increment statistical information of each object in one or more of objects, the capacity
Accrual accounting information includes the size of object, wherein the capacity increment statistical information is by the corresponding object metadata of object
Record；
Processing module, for carrying out the capacity increment statistical information of obtained one or more objects using same static fields
Polymerization processing, obtains polymerization result, and the polymerization result includes: within the period of first time index instruction, basis
The variable quantity for the memory space that one or more objects of the static fields statistics occupy.
7. device according to claim 6, which is characterized in that described device further include:
Module is obtained, for obtaining and before enquiry module inquiry includes all object metadatas indexed at the first time
It is requested from the Object Management group of user, the Object Management group request executes management operation to the first object for requesting, and described first
Object is an object in one or more of objects, and the management operation includes any one of following operation: newly-built
Object, deletes object at upload object；
Distribution module, for according to the period distribution described first where the time when getting Object Management group request
Time index；
Generation module, for requesting the metadata of the first object of generation based on the Object Management group, wherein first object
It include indexing the first time in metadata；
Memory module, for storing the first time index.
8. device according to claim 6 or 7, which is characterized in that the processing module is used for the one or more that will be arrived
The capacity increment statistical information of object carries out polymerization processing using same static fields, specifically includes,
For meeting the object of the static fields within the period of first time index instruction:
The memory space that the object that cumulative new Object operation creates occupies；
Cumulative upload object operates the memory space that uploaded object occupies；
Subtract the memory space of deleted object release.
9. the device according to any one of claim 6 to 8, which is characterized in that described device further include:
Accounting module, for carrying out charging based on variable quantity of the polymerization result to memory space.
10. a kind of computer readable storage medium, which is characterized in that it is stored with program in the computer readable storage medium,
The method that described program makes the device for managing memory space execute any one of the claims 1 to 4 management memory space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810804528.2A CN109241178A (en) | 2018-07-20 | 2018-07-20 | The method and apparatus for managing memory space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810804528.2A CN109241178A (en) | 2018-07-20 | 2018-07-20 | The method and apparatus for managing memory space |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109241178A true CN109241178A (en) | 2019-01-18 |
Family
ID=65072798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810804528.2A Pending CN109241178A (en) | 2018-07-20 | 2018-07-20 | The method and apparatus for managing memory space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241178A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110888872A (en) * | 2019-10-16 | 2020-03-17 | 浙江大搜车软件技术有限公司 | Data storage method and device, computer equipment and storage medium |
| CN111221824A (en) * | 2020-01-02 | 2020-06-02 | 广州虎牙科技有限公司 | Storage optimization method, device, equipment and medium of storage space |
| CN111241097A (en) * | 2020-01-08 | 2020-06-05 | 北京松果电子有限公司 | Method of processing object, apparatus for processing object, and storage medium |
| CN111723202A (en) * | 2020-05-19 | 2020-09-29 | 支付宝(杭州)信息技术有限公司 | Public opinion data processing device, method and system |
| CN111797174A (en) * | 2019-04-08 | 2020-10-20 | 华为技术有限公司 | Method and apparatus for managing spatiotemporal data |
| CN111881133A (en) * | 2020-07-24 | 2020-11-03 | 苏州浪潮智能科技有限公司 | Storage bucket management method and device, computer equipment and readable storage medium |
| CN113064859A (en) * | 2021-03-26 | 2021-07-02 | 山东英信计算机技术有限公司 | Metadata processing method and device, electronic equipment and storage medium |
| CN113111194A (en) * | 2021-04-07 | 2021-07-13 | 山东英信计算机技术有限公司 | Object metadata aggregation method, reading method, device, equipment and storage medium |
| CN113177068A (en) * | 2021-03-15 | 2021-07-27 | 新华三信息安全技术有限公司 | Aggregated data query method, equipment and medium |
| CN116521094A (en) * | 2023-07-03 | 2023-08-01 | 之江实验室 | Metadata storage method and device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN85100285A (en) * | 1985-04-01 | 1985-09-10 | 北京大学 | High resolution chinese character pattern gerenator |
| CN85103698A (en) * | 1984-06-22 | 1986-11-12 | 北方电信有限公司 | Send digital signal and additional signal |
| CN103218175B (en) * | 2013-04-01 | 2015-10-28 | 无锡成电科大科技发展有限公司 | The cloud storage platform access control system of many tenants |
| CN107633045A (en) * | 2017-09-15 | 2018-01-26 | 龙存(苏州)科技有限公司 | The statistical method and its system of tenant data capacity in a kind of cloud storage service |
-
2018
- 2018-07-20 CN CN201810804528.2A patent/CN109241178A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN85103698A (en) * | 1984-06-22 | 1986-11-12 | 北方电信有限公司 | Send digital signal and additional signal |
| CN85100285A (en) * | 1985-04-01 | 1985-09-10 | 北京大学 | High resolution chinese character pattern gerenator |
| CN103218175B (en) * | 2013-04-01 | 2015-10-28 | 无锡成电科大科技发展有限公司 | The cloud storage platform access control system of many tenants |
| CN107633045A (en) * | 2017-09-15 | 2018-01-26 | 龙存(苏州)科技有限公司 | The statistical method and its system of tenant data capacity in a kind of cloud storage service |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111797174A (en) * | 2019-04-08 | 2020-10-20 | 华为技术有限公司 | Method and apparatus for managing spatiotemporal data |
| CN110888872A (en) * | 2019-10-16 | 2020-03-17 | 浙江大搜车软件技术有限公司 | Data storage method and device, computer equipment and storage medium |
| CN111221824A (en) * | 2020-01-02 | 2020-06-02 | 广州虎牙科技有限公司 | Storage optimization method, device, equipment and medium of storage space |
| CN111241097A (en) * | 2020-01-08 | 2020-06-05 | 北京松果电子有限公司 | Method of processing object, apparatus for processing object, and storage medium |
| CN111241097B (en) * | 2020-01-08 | 2024-03-12 | 北京小米松果电子有限公司 | Method for processing object, device for processing object and storage medium |
| CN111723202A (en) * | 2020-05-19 | 2020-09-29 | 支付宝(杭州)信息技术有限公司 | Public opinion data processing device, method and system |
| CN111881133B (en) * | 2020-07-24 | 2022-12-06 | 苏州浪潮智能科技有限公司 | Storage bucket management method and device, computer equipment and readable storage medium |
| CN111881133A (en) * | 2020-07-24 | 2020-11-03 | 苏州浪潮智能科技有限公司 | Storage bucket management method and device, computer equipment and readable storage medium |
| CN113177068A (en) * | 2021-03-15 | 2021-07-27 | 新华三信息安全技术有限公司 | Aggregated data query method, equipment and medium |
| CN113064859A (en) * | 2021-03-26 | 2021-07-02 | 山东英信计算机技术有限公司 | Metadata processing method and device, electronic equipment and storage medium |
| CN113111194A (en) * | 2021-04-07 | 2021-07-13 | 山东英信计算机技术有限公司 | Object metadata aggregation method, reading method, device, equipment and storage medium |
| CN116521094A (en) * | 2023-07-03 | 2023-08-01 | 之江实验室 | Metadata storage method and device, computer equipment and storage medium |
| CN116521094B (en) * | 2023-07-03 | 2023-11-14 | 之江实验室 | Metadata storage method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241178A (en) | The method and apparatus for managing memory space | |
| US11146502B2 (en) | Method and apparatus for allocating resource | |
| US9372880B2 (en) | Reclamation of empty pages in database tables | |
| CN104067216B (en) | System and method for implementing expansible data storage service | |
| CN106294352B (en) | A kind of document handling method, device and file system | |
| US9965207B2 (en) | Maintenance of cloned computer data | |
| US9348855B2 (en) | Supporting big data in enterprise content management systems | |
| US20190026317A1 (en) | Memory use in a distributed index and query system | |
| EP3958122A1 (en) | Memory management method, apparatus, and system | |
| CN104021451A (en) | Mixed enterprise content management method and system based on cloud storage and local storage | |
| CN110287201A (en) | Data access method, device, equipment and storage medium | |
| EP3103039B1 (en) | System and method for an efficient database storage model based on sparse files | |
| CN110968589A (en) | Self-adding ID management method and device in distributed system | |
| CN105354090B (en) | The management method and device of virtual unit | |
| US9380126B2 (en) | Data collection and distribution management | |
| CN113448946B (en) | Data migration method and device and electronic equipment | |
| CN110457307B (en) | Metadata management system, user cluster creation method, device, equipment and medium | |
| CN108574718A (en) | A kind of cloud host creation method and device | |
| CN109144689B (en) | Task scheduling method, device and computer program product | |
| CN109725844B (en) | Disk allocation method, device and storage system | |
| US20230063541A1 (en) | Determining computer resource usage at multiple levels of a container orchestration system hierarchy | |
| CN108604231A (en) | Mirror processing method and computing device | |
| CN111061888B (en) | Image acquisition method and system | |
| CN110554915A (en) | Information processing method and device, computer storage medium and terminal | |
| CN113890872B (en) | Data set uploading method and device, electronic equipment and storage medium |
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 |