WO2021128892A1 - 一种批量创建文件的方法、装置、设备及存储介质 - Google Patents
一种批量创建文件的方法、装置、设备及存储介质 Download PDFInfo
- Publication number
- WO2021128892A1 WO2021128892A1 PCT/CN2020/110731 CN2020110731W WO2021128892A1 WO 2021128892 A1 WO2021128892 A1 WO 2021128892A1 CN 2020110731 W CN2020110731 W CN 2020110731W WO 2021128892 A1 WO2021128892 A1 WO 2021128892A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- client
- creation
- file
- files
- destination client
- Prior art date
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
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
-
- 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
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
- G06F16/164—File meta data generation
-
- 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
Definitions
- the present invention relates to the technical field of distributed file systems, and more specifically, to a method, device, equipment, and storage medium for creating files in batches.
- Distributed cluster storage is widely used in various scenarios of current big data (such as high performance, video surveillance, radio and television media assets, etc.).
- big data such as high performance, video surveillance, radio and television media assets, etc.
- the premise of big data computing is to organize and store massive amounts.
- the inventor found that one of the indicators that affect the performance of the distributed file system is the file creation performance. Therefore, how to improve the file creation performance has become an important goal.
- the purpose of the present invention is to provide a method, device, equipment and storage medium for creating files in batches, which can realize the improvement of file creation performance and further realize the improvement of distributed file system performance.
- a method of creating files in batches including:
- Receive multiple creation requests sent by the destination client realize the simultaneous creation of multiple files based on the received creation request, store the metadata of each file created, and complete the destination client corresponding to all files Release the specified directory after the batch is created.
- the method before receiving the authorization request sent by the target client, the method further includes:
- Each created file is assigned a file number belonging to the preset range; wherein the metadata of the file includes the file number of the file.
- the method further includes:
- a corresponding file name is set for each file created, and the file name of each file created is associated with the file number; wherein the metadata of the file includes the file name and the file with the association number.
- it also includes:
- the destination client When the batch creation of all files corresponding to the destination client is not completed, and an authorization request sent by a client other than the destination client is received, the destination client is instructed to forcibly refresh the destination client cache To obtain all the creation requests refreshed by the target client, and execute the step of simultaneously creating corresponding multiple files based on the received creation request.
- it also includes:
- each creation request recorded by the destination client re-sent by the destination client is received; wherein, the client The client records the creation request corresponding to each file to be created.
- the method further includes:
- the method further includes:
- a device for creating files in batches including:
- the determining module is configured to: receive an authorization request sent by a target client, and determine that the directory corresponding to the authorization request is a designated directory; wherein, the target client is any client that needs to create a batch of files;
- the judgment module is used to judge whether the designated directory has been authorized to other clients except the destination client, and if so, wait until all files corresponding to the client with authority to the designated directory are completed After the batch is created, the designated directory is released, and the designated directory is authorized to the destination client, if not, the designated directory is authorized to the destination client; wherein, the designated directory only allows Access to a client with authority to the specified directory;
- the creation module is used to: receive multiple creation requests sent by the destination client, realize the simultaneous creation of multiple files based on the received creation request, store the metadata of each file created, and complete the purpose
- the client releases the designated directory after the batch creation of all files corresponding to it.
- a device for creating files in batches including:
- Memory used to store computer programs
- the processor is used to implement the steps of the method for creating files in batches as described in any one of the preceding items when the computer program is executed.
- a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and when the computer program is executed by a processor, implements the steps of the method for creating files in batches as described in any one of the above items.
- the present invention provides a method, device, equipment, and storage medium for creating files in batches.
- the method includes: receiving an authorization request sent by a destination client, and determining that a directory corresponding to the authorization request is a designated directory; wherein, the The destination client is any client that needs to create a batch of files; it is judged whether the specified directory has been authorized to other clients except the destination client, and if so, it waits until completion and the specified directory After the authorized client corresponds to the batch creation of all files, release the designated directory and authorize the designated directory to the destination client, if not, authorize the designated directory to the destination client; Wherein, the designated directory only allows clients with permission to access the designated directory; receives multiple creation requests sent by the destination client, and realizes the simultaneous creation of multiple files based on the received creation request, and stores Create the obtained metadata of each file, and release the designated directory after completing the batch creation of all files corresponding to the destination client.
- this application when a client needs to create files in batches, it can apply for the authority to obtain the specified directory. If the specified directory is not currently authorized to other clients, it can obtain the authority of the specified directory and then in the specified directory Realize batch creation of files under the following, otherwise, you need to remove the access permission of other clients to the specified directory and then obtain the permission of the specified directory, and then realize the batch creation of files under the specified directory. It can be seen that this application can not only create files that need to be created in batches under the instructions of the client, improve file creation performance, and thereby improve the performance of the distributed file system; moreover, it can avoid multiple files by setting exclusive permissions for specified directories.
- the client realizes the same name of the created file when creating a file in the specified directory, which will lead to the failure of file creation, ensuring the effective realization of file batch creation, and avoiding the realization of the file in the specified directory on a client
- other clients cannot access valid files and other information when accessing the specified directory, which ensures the validity of the information obtained by the client.
- FIG. 1 is a flowchart of a method for creating files in batches according to an embodiment of the present invention
- FIG. 2 is a schematic structural diagram of an apparatus for creating files in batches according to an embodiment of the present invention.
- FIG. 1 shows a flowchart of a method for creating files in batches according to an embodiment of the present invention, which may include:
- S11 Receive the authorization request sent by the target client, and determine that the directory corresponding to the authorization request is a designated directory; where the target client is any client that needs to create a batch of files.
- the execution subject of the method for creating files in batches provided by the embodiment of the present invention can be a corresponding device, and the device can be set in the client. Therefore, the execution subject of the method can be a server, and the execution subject of the method is the server below. Give specific instructions.
- any client that needs to create files in batches can be called a destination client, so as to realize batch creation of files on any client.
- the destination client needs to create files in batches, it can send an authorization request to the server.
- the server can determine the directory corresponding to the authorization request, that is, the directory identifier carried in the authorization request, which is The directory where the destination client needs to create files in batches can be called a designated directory.
- the batch creation of files in this embodiment also realizes the creation of multiple files at the same time, and the server can provide MDS (Meta Data Server Metadata Service), and the method for batch creation of files implemented in the embodiment of this application is implemented based on this MDS. of.
- MDS Metal Data Server Metadata Service
- S12 Determine whether the specified directory has been authorized to other clients except the destination client. If so, wait until the batch creation of all files corresponding to the client with permission to the specified directory is completed, then release the specified directory, and Authorize the designated directory to the target client, if not, authorize the designated directory to the target client; where the designated directory only allows access to the client with permission to the designated directory.
- an exclusive directory Cap (Capability, metadata operation permission) is introduced.
- a client holds the Cap of a directory, other clients cannot operate the directory for reading, writing, or reading.
- File creation and other operations specifically, when a directory is a designated directory, the designated directory can only be authorized to one client at the same time, and the client to which the designated directory is authorized is the client that has access rights to the designated directory , That is, it is a client that can perform operations such as reading and writing of information and file creation in the specified directory.
- Other clients that are not authorized cannot access the specified directory; because if multiple clients create files in the specified directory at the same time, It may happen that the names of files created by different clients are the same, but in fact it is not allowed to have the same file names.
- the name of the created file may be the same when the file is created, which will cause the file creation to fail; and if a client creates a file or reads and writes in a directory, other clients cannot access the directory at this time.
- the latest data information that is, the effective data information cannot be accessed. Therefore, by setting the permissions of the directory above, it can also avoid that when a client realizes file creation in a certain directory, other clients cannot access the directory when accessing the directory. In the case of data information such as valid documents.
- the server determines the designated directory, it can determine whether the designated directory is currently authorized to other clients other than the target client, that is, whether there are other clients other than the target client. It has permission to the specified directory. If it is, the specified directory cannot be authorized to the target client. Therefore, you need to wait for the batch creation of all files that the client that currently has permission to the specified directory needs to achieve, and then release the specified directory, that is, release After the client that has the authority to the specified directory has the authority to the specified directory, the specified directory does not have the authority to the client, then the specified directory can be authorized to the target client; if not, the specified directory can be directly authorized to Destination client.
- the destination client can wait until the specified directory is released and have the permissions of the specified directory, or it can implement the sequential creation of files in a conventional way. Specifically, it can be set according to actual needs, and all are within the protection scope of the present invention.
- S13 Receive multiple creation requests sent by the destination client, realize the simultaneous creation of multiple files based on the received creation request, store the metadata of each file created, and complete the batch of all files on the destination client Release the specified directory after creation.
- the destination client After the destination client applies for the permission of the specified directory, it can package the creation request within a certain period of time (or a certain entry) at the same time, and send the packaged result to the server, so that the server can parse the packaged result to the contained Create request, and then realize the batch creation of corresponding files, that is, create at the same time, and store the metadata of each file created, and then release the specified directory after the creation of all the files that the target client needs to create, for other customers End acquisition.
- a certain time may be the total time required to instruct the server to realize batch file creation
- a certain entry may be the total number of files that need to be created when instructing the server to realize file batch creation, so as to meet the needs of the target client. Batch creation of files.
- this application when a client needs to create files in batches, it can apply for the authority to obtain the specified directory. If the specified directory is not currently authorized to other clients, it can obtain the authority of the specified directory and then in the specified directory Realize batch creation of files under the following, otherwise, you need to remove the access permission of other clients to the specified directory and then obtain the permission of the specified directory, and then realize the batch creation of files under the specified directory. It can be seen that this application can not only create files that need to be created in batches under the instructions of the client, improve file creation performance, and thereby improve the performance of the distributed file system; moreover, it can avoid multiple files by setting exclusive permissions for specified directories.
- the client realizes the same name of the created file when creating a file in the specified directory, which will lead to the failure of file creation, ensuring the effective realization of file batch creation, and avoiding the realization of the file in the specified directory on a client
- other clients cannot access information such as valid files when accessing the specified directory, which ensures the validity of the information obtained by the client.
- Each created file is assigned a file number belonging to a preset range; the metadata of the file includes the file number of the file.
- the file number of each file can be quickly obtained, thereby increasing the file creation rate. Therefore, in this embodiment, when receiving the destination client's sending After the connection request, you can establish a connection with the target client, and apply for a certain range (the preset range can be set according to actual needs) for the target client from the metadata pool.
- the file number Inode, the serial number of the file, includes In CInode
- the file number distribution can be directly realized when creating files, and there is no need to obtain them from the metadata pool, which greatly improves the file creation rate.
- the server after the server pre-applies for a certain range of file numbers for the target client, it can notify the target client of all the file numbers allocated to the target client, so that the target client can determine the file number created based on this File number.
- the destination client needs to create files in batches, the file numbers allocated to the destination client have been used up, then a certain range of file numbers can be allocated to the destination client in the metadata pool, and so on to ensure the purpose The client has sufficient file numbers for file creation.
- a corresponding file name is set for each created file, and the file name of each created file is associated with the file number; wherein the metadata of the file includes the associated file name and file number.
- the creation request sent by the destination client can carry the file name set by the client for the corresponding file (that is, the name of the file), so that the name of the created file is set to the file name carried in the corresponding creation request, and each The file name of each file is associated with the file number, and is stored as metadata, so that it is convenient to find the file.
- the associated information can specifically be CInode (metadata Inode information, mainly including file attributes) and CDentry (metadata directory items, mainly including file names), and CInode contains the file number, and CDentry contains the file name, so the association
- CInode and CDentry contains the associated file name and file number, and then the associated CInode and CDentry are included in the metadata for storage, such as stored in the metadata pool.
- the destination client When the batch creation of all files corresponding to the destination client is not completed, and an authorization request sent by other clients except the destination client is received, the destination client is instructed to forcibly refresh all the creation requests cached by the destination client to obtain the destination For all creation requests refreshed by the client, the steps of simultaneously creating corresponding multiple files based on the received creation request are executed.
- the client for the purpose of this embodiment can package and send all the files it needs to create to the server corresponding to the creation request, or it can divide all the files it needs to create into multiple batches, and then package the creation requests contained in each batch in turn. Send to the server, which can be determined according to the actual situation.
- the target client's application for having permission to the specified directory may include the time period required to have the permission to the specified directory and the total number of all files that need to be created in the specified directory, and The batch creation of all files corresponding to the destination client is not completed. Specifically, it can be the time period during which the destination client has permission to the specified directory and/or the number of files created in the specified directory.
- the destination client can cache the creation requests that need to be sent and have not yet been sent locally; if the destination client has not completed the batch creation of all files corresponding to the destination client and receives authorization requests sent by other clients, the destination client can be judged Whether there is a creation request that has not been sent to the server? If so, you can notify the destination client to forcefully refresh its cache creation request to the server, so that the server can realize the corresponding file batch creation and file metadata storage, etc.
- the server can complete the file batch creation and file metadata storage corresponding to the creation request that the target client has sent to the server, and then release the specified directory after the batch creation of all files that the target client needs to create and the corresponding metadata storage Permission, which can facilitate other clients to use the specified directory.
- each creation request of the destination client record sent by the destination client is received; the client records each file that needs to be created The corresponding creation request.
- the client can also record the creation request that needs to be sent locally before sending the creation request to the server, and if the server fails during the processing of batch creation requests, the server needs to repair the failure, and the server is repaired and can work normally Later, the client needs to resend the record creation request to the server, and the server re-implements the batch file creation after receiving the creation request resent by the client, thereby ensuring the effective realization of the client batch creation of files.
- the server After the server completes the batch creation of all files corresponding to the destination client, it can return confirmation information to the destination client, so that the destination client knows that all the files it needs to create have been created, and then delete the record creation request, thereby avoiding Waste of storage space in the destination client.
- the target client By sending a marking instruction to the target client, the target client can be instructed to record the successful mark of the batch file creation in the log after receiving the marking instruction for later query.
- a method for creating files in batches may include:
- the server When the server establishes a connection with the client, the server applies for a certain range of Inodes from the metadata pool and notifies the client;
- the server When the client creates a file in a certain directory, it applies to the server for the exclusive Cap of the directory. If no other client uses the directory, the server agrees to authorize the exclusive Cap of the directory to the client; if other clients are using the directory , The server refuses to authorize the exclusive Cap, and then agrees to authorize the exclusive Cap of the directory to the client after all the file creation of other clients is completed.
- the client After the client has applied for the exclusive Cap of the directory, it will package the creation request for a certain period of time (or a certain request item) at the same time and send it to the server. The client will also record the sent request (for troubleshooting); if it has not reached a certain time or During the entry period, if other clients apply to the server for the exclusive Cap of the directory, the server will notify the client to force the creation request in the cache to be refreshed, and then release the exclusive Cap;
- the server After the server receives the client's batch creation request, it parses the batch creation request, creates the corresponding file, associates the CInode and CDentry of the file, drops all created metadata into the metadata pool, and then responds to the client (can include confirmation information) And mark instruction) request completion;
- the client After the client receives the response from the server, it cleans up the sent requests recorded in the client, marking the completion of this batch creation business;
- the client needs to resend the batch creation request to the server for processing again.
- the method for creating files in batches in a distributed file system proposed in the present application can greatly improve file creation performance and metadata creation performance, especially the creation performance of small file scenarios, thereby improving the creation performance of the distributed file system.
- the embodiment of the present invention also provides an apparatus for creating files in batches, as shown in FIG. 2, which may specifically include:
- the determining module 11 is configured to: receive an authorization request sent by a target client, and determine that the directory corresponding to the authorization request is a designated directory; where the target client is any client that needs to create a batch of files;
- the judging module 12 is used for judging whether the specified directory has been authorized to other clients except the destination client, and if so, it waits until the batch creation of all files corresponding to the client with authority to the specified directory is completed, Release the designated directory, and authorize the designated directory to the target client, if not, authorize the designated directory to the target client; among them, the designated directory only allows clients with permission to the designated directory to access;
- the creation module 13 is used to: receive multiple creation requests sent by the destination client, realize the simultaneous creation of multiple files based on the received creation request, store the metadata of each file created, and respond to the destination client after completing the creation request Release the specified directory after batch creation of all files.
- the connection module is used for: before receiving the authorization request sent by the target client, receiving the connection request sent by the target client, responding to the connection request to establish a connection with the target client, and pre-applying for a preset range of file numbers for the target client;
- the allocation module is used for: after realizing the simultaneous creation of corresponding multiple files based on the received creation request, respectively assigning a file number belonging to a preset range to each created file; wherein the metadata of the file includes the file number of the file.
- the setting module is used to: after realizing the simultaneous creation of multiple files based on the received creation request, set the corresponding file name for each file created, and associate the file name of each file created with the file number ; Among them, the metadata of the file includes the associated file name and file number.
- the instruction module is used to: when the batch creation of all files corresponding to the destination client is not completed, and the authorization request sent by other clients except the destination client is received, then the destination client is instructed to forcibly refresh all the caches of the destination client.
- the creation request is to obtain all creation requests refreshed by the target client, and execute the step of simultaneously creating corresponding multiple files based on the received creation request.
- the reconstruction module is used to: if a failure occurs during the batch creation of all files corresponding to the destination client, then after the failure is repaired, each creation request recorded by the destination client re-sent by the destination client is received; among them, the client records Each file to be created corresponds to a creation request.
- the return module is used to: after achieving the batch creation of all files corresponding to the destination client, return to the destination client a confirmation message corresponding to the success of the batch creation of all files, so as to instruct the destination client to delete the creation request of the record.
- the sending module is used to send a marking instruction to the target client after the batch creation of all files corresponding to the target client is realized, so as to instruct the target client to record the successful mark of the batch file creation in the file creation log.
- the embodiment of the present invention also provides a device for creating files in batches, which may include:
- Memory used to store computer programs
- the processor is used to implement the steps of any one of the methods for creating files in batches when the computer program is executed.
- the embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored.
- a computer program is stored on which a computer program is stored.
- the steps of any one of the methods for creating files in batches can be realized.
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)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
- Storage Device Security (AREA)
Abstract
一种批量创建文件的方法、装置、设备及存储介质，该方法包括：接收目的客户端发送的授权请求，并确定与授权请求对应的目录为指定目录（S11）；判断指定目录是否已被授权给除目的客户端之外的其他客户端，如果是，则等待直至完成与对指定目录具有权限的客户端对应全部文件的批量创建后，释放指定目录，将指定目录授权给目的客户端，如果否，则将指定目录授权给目的客户端（S12）；接收目的客户端发送的多个创建请求，基于接收的创建请求实现相应的多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成目的客户端对应全部文件的批量创建后释放指定目录（S13）。所述方法能够提高文件创建性能，提高分布式文件系统的性能。
Description
本申请要求于2019年12月18日提交中国专利局、申请号为201911385174.3、发明名称为“一种批量创建文件的方法、装置、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本发明涉及分布式文件系统技术领域，更具体地说，涉及一种批量创建文件的方法、装置、设备及存储介质。
分布式集群存储在当前大数据的多种场景下(如高性能、视频监控、广电媒资等)广泛应用，分布式文件系统中存在海量数据，而大数据计算的前提则是组织和存储海量数据，发明人研究发现，影响分布式文件系统性能的指标之一则为文件创建性能，因此如何实现文件创建性能的提高则成为一项重要目标。
发明内容
本发明的目的是提供一种批量创建文件的方法、装置、设备及存储介质，能够实现文件创建性能的提高，进而实现分布式文件系统性能的提高。
为了实现上述目的，本发明提供如下技术方案：
一种批量创建文件的方法，包括：
接收目的客户端发送的授权请求，并确定与所述授权请求对应的目录为指定目录；其中，所述目的客户端为需要进行批量文件创建的任意客户端；
判断所述指定目录是否已被授权给除所述目的客户端之外的其他客户端，如果是，则等待直至完成与对所述指定目录具有权限的客户端对应全部文件的批量创建后，释放所述指定目录，并将所述指定目录授权给所述目的客户端，如果否，则将所述指定目录授权给所述目的客户端；其中，所述指定目录仅允许对所述指定目录具有权限的客户端进行访问；
接收所述目的客户端发送的多个创建请求，基于接收的创建请求实现相应的多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成所述目的客户端对应全部文件的批量创建后释放所述指定目录。
优选的，接收目的客户端发送的授权请求之前，还包括：
接收所述目的客户端发送的连接请求，响应所述连接请求以建立与所述目的客户端的连接，并为所述目的客户端预申请预设范围的文件号；
基于接收的创建请求实现相应多个文件的同时创建之后，还包括：
为创建得到的每个文件分别分配属于所述预设范围的文件号；其中，所述文件的元数据包括所述文件的文件号。
优选的，基于接收的创建请求实现相应多个文件的同时创建之后，还包括：
为创建得到的每个文件分别设置相应的文件名，将创建得到的每个文件的文件名与文件号建立关联；其中，所述文件的元数据包括具有关联的所述文件名及所述文件号。
优选的，还包括：
当未完成所述目的客户端对应全部文件的批量创建时，接收到除所述目的客户端之外的其他客户端发送的授权请求，则指示所述目的客户端强制刷新所述目的客户端缓存的全部创建请求，以获取所述目的客户端刷新的全部创建请求，执行基于接收的创建请求实现相应的多个文件的同时创建的步骤。
优选的，还包括：
如果实现所述目的客户端对应全部文件的批量创建的过程中出现故障，则在故障修复后接收所述目的客户端重新发送的所述目的客户端记录的每个创建请求；其中，所述客户端记录需创建的每个文件对应的创建请求。
优选的，实现所述目的客户端对应全部文件的批量创建之后，还包括：
返回给所述目的客户端对应全部文件的批量创建成功的确认信息，以指示所述目的客户端删除记录的创建请求。
优选的，实现所述目的客户端对应全部文件的批量创建之后，还包括：
发送标记指令至所述目的客户端，以指示所述目的客户端在文件创建的日志中记录此次批量文件创建成功的标记。
一种批量创建文件的装置，包括：
确定模块，用于：接收目的客户端发送的授权请求，并确定与所述授权请求对应的目录为指定目录；其中，所述目的客户端为需要进行批量文件创建的任意客户端；
判断模块，用于：判断所述指定目录是否已被授权给除所述目的客户端之外的其他客户端，如果是，则等待直至完成与对所述指定目录具有权限的客户端对应全部文件的批量创建后，释放所述指定目录，并将所述指定目录授权给所述目的客户端，如果否，则将所述指定目录授权给所述目的客户端；其中，所述指定目录仅允许对所述指定目录具有权限的客户端进行访问；
创建模块，用于：接收所述目的客户端发送的多个创建请求，基于接收的创建请求实现相应多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成所述目的客户端对应全部文件的批量创建后释放所述指定目录。
一种批量创建文件的设备，包括：
存储器，用于存储计算机程序；
处理器，用于执行所述计算机程序时实现如上任一项所述批量创建文件的方法的步骤。
一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如上任一项所述批量创建文件的方法的步骤。
本发明提供了一种批量创建文件的方法、装置、设备及存储介质，该方法包括：接收目的客户端发送的授权请求，并确定与所述授权请求对应的目录为指定目录；其中，所述目的客户端为需要进行批量文件创建的任意客户端；判断所述指定目录是否已被授权给除所述目的客户端之外的其他客户端，如果是，则等待直至完成与对所述指定目录具有权限的客户端对应全部文件的批量创建后，释放所述指定目录，并将所述指定目录授权 给所述目的客户端，如果否，则将所述指定目录授权给所述目的客户端；其中，所述指定目录仅允许对所述指定目录具有权限的客户端进行访问；接收所述目的客户端发送的多个创建请求，基于接收的创建请求实现相应的多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成所述目的客户端对应全部文件的批量创建后释放所述指定目录。本申请公开的技术方案中，在客户端需要批量创建文件时，可以申请获取指定目录的权限，如果指定目录当前未被授权给其他客户端，则可以获取到指定目录的权限，进而在指定目录下实现文件的批量创建，否则，则需要解除其他客户端对指定目录的访问权限后获取指定目录的权限，进而在指定目录下实现文件的批量创建。可见，本申请不仅能够在客户端的指示下批量创建其所需创建的文件，提高文件创建性能，进而提高分布式文件系统的性能；并且，通过为指定目录设置独占权限的方式，能够避免多个客户端同时在指定目录下实现文件创建时可能出现的创建的文件的名称相同，进而导致文件创建失败的情况，保证了文件批量创建的有效实现，并且能够避免在一个客户端在指定目录下实现文件创建时，其他客户端访问指定目录无法访问到有效的文件等信息的情况，保证了客户端获取信息的有效性。
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。
图1为本发明实施例提供的一种批量创建文件的方法的流程图；
图2为本发明实施例提供的一种批量创建文件的装置的结构示意图。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没 有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
请参阅图1，其示出了本发明实施例提供的一种批量创建文件的方法的流程图，可以包括：
S11：接收目的客户端发送的授权请求，并确定与授权请求对应的目录为指定目录；其中，目的客户端为需要进行批量文件创建的任意客户端。
本发明实施例提供的一种批量创建文件的方法的执行主体可以为对应的装置，而该装置可以设置于客户端，因此该方法的执行主体可以为服务器，以下以该方法的执行主体为服务器进行具体说明。
当任意客户端需要批量创建文件时，可以称该需要批量创建文件的任意客户端为目的客户端，从而实现任意客户端的文件批量创建。目的客户端在需要批量创建文件时，可以向服务器发送授权请求，服务器接收到目的客户端发送的授权请求后，可以确定授权请求对应的、也即授权请求中携带的目录标识对应的目录，为目的客户端需要批量创建文件的目录，可以称为指定目录。另外，本实施例中批量创建文件也即同时实现多个文件的创建，而服务器能够提供MDS(Meta Data Server元数据服务)，本申请实施例实现的批量创建文件的方法则是基于该MDS实现的。
S12：判断指定目录是否已被授权给除目的客户端之外的其他客户端，如果是，则等待直至完成与对指定目录具有权限的客户端对应全部文件的批量创建后，释放指定目录，并将指定目录授权给目的客户端，如果否，则将指定目录授权给目的客户端；其中，指定目录仅允许对指定目录具有权限的客户端进行访问。
需要说明的是，本实施例中引入一种独占目录的Cap(Capability，元数据操作权限)，当某个客户端持有某目录的Cap时，其他客户端则无法操作该目录进行读写、文件创建等操作；具体来说，当某目录为指定目录时，指定目录在同一时刻只能被授权给一个客户端，指定目录被授权给的客户端则为对指定目录具有访问权限的客户端，也即为能够在指定目录下实现信息读写、文件创建等操作的客户端，其他未被授权给的客户端则无法访问指定目录；由于如果多个客户端同时在指定目录下创建文件，则可 能出现不同客户端创建的文件的名称相同的情况，但是实际上是不允许文件名称相同的情况的，因此通过上述对目录的权限的设置，能够避免多个客户端同时在同一目录下实现文件创建时可能出现的创建的文件的名称相同，进而导致文件创建失败的情况；并且，如果某个客户端在目录下创建文件或者读写时，其他客户端此时访问该目录则无法访问到最新的数据信息，也即无法访问到有效的数据信息，因此通过上述对目录的权限的设置，还能够避免在一个客户端在某目录下实现文件创建时，其他客户端访问该目录下无法访问到有效的文件等数据信息的情况。因此，本实施例中服务器在确定出指定目录后，可以判断指定目录当前是否已经被授权给除了目的客户端之外的其他客户端，也即当前是否具有除了目的客户端之外的其他客户端对指定目录具有权限，如果是，则无法将指定目录授权给目的客户端，因此需要等待完成当前对指定目录具有权限的客户端需要实现的全部文件的批量创建后，释放指定目录，也即解除对指定目录具有权限的客户端对指定目录的权限后，指定目录不具有对其有权限的客户端，此时可以将指定目录授权给目的客户端；如果否，则可以直接将指定目录授权给目的客户端。
另外，如果指定目录已被授权给除目的客户端之外的其他客户端，则目的客户端可以等待至指定目录被释放后拥有指定目录的权限，也可以是按照常规方式实现文件的依次创建，具体可以根据实际需要进行设定，均在本发明的保护范围之内。
S13：接收目的客户端发送的多个创建请求，基于接收的创建请求实现相应的多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成目的客户端对应全部文件的批量创建后释放指定目录。
目的客户端申请得到指定目录的权限后，可以将一定时间内(或一定条目)的创建请求同时打包，将打包得到的结果发送给服务器，从而使得服务器由打包得到的结果中解析到其包含的创建请求，进而实现对应的文件的批量创建，也即同时创建，并存储得到创建得到的每个文件的元数据，进而实现目的客户端需创建的全部文件的创建后释放指定目录，供其他客户端获取。另外，本实施例中一定时间可以是指示服务器实现文件批量创 建时需用的总时间，一定条目则可以是指示服务器实现文件批量创建时需创建的文件的总数量，从而按照目的客户端的需求实现文件的批量创建。
本申请公开的技术方案中，在客户端需要批量创建文件时，可以申请获取指定目录的权限，如果指定目录当前未被授权给其他客户端，则可以获取到指定目录的权限，进而在指定目录下实现文件的批量创建，否则，则需要解除其他客户端对指定目录的访问权限后获取指定目录的权限，进而在指定目录下实现文件的批量创建。可见，本申请不仅能够在客户端的指示下批量创建其所需创建的文件，提高文件创建性能，进而提高分布式文件系统的性能；并且，通过为指定目录设置独占权限的方式，能够避免多个客户端同时在指定目录下实现文件创建时可能出现的创建的文件的名称相同，进而导致文件创建失败的情况，保证了文件批量创建的有效实现，并且能够避免在一个客户端在指定目录下实现文件创建时，其他客户端访问指定目录无法访问到有效的文件等信息的情况，保证了客户端获取信息的有效性。
本发明实施例提供的一种批量创建文件的方法，接收目的客户端发送的授权请求之前，还可以包括：
接收目的客户端发送的连接请求，响应连接请求以建立与目的客户端的连接，并为目的客户端预申请预设范围的文件号；
基于接收的创建请求实现相应多个文件的同时创建之后，还包括：
为创建得到的每个文件分别分配属于预设范围的文件号；其中，文件的元数据包括文件的文件号。
需要说明的是，本实施例中为了实现相应多个文件的同时创建时可以快速获取到每个文件的文件号，进而提高了文件创建的速率，因此本实施例中在接收到目的客户端发送的连接请求后，可以建立与目的客户端的连接，并从元数据池中为目的客户端申请一定范围(预设范围，可以根据实际需要进行设定)的文件号(Inode，文件的序号，包含于CInode中)，进而在创建文件时可以直接实现文件号的分配，无需再由元数据池中获取，大大提高了文件创建速率。其中，服务器在为目的客户端预申请到一定范围的文件号后，可以将为目的客户端分配的文件号均通知给目的客户端， 进而使得目的客户端能够获知后基于此确定创建的文件的文件号。另外，如果目的客户端需要批量创建文件时，为目的客户端分配的文件号已经用完，则可以再由元数据池中为目的客户端分配一定范围的文件号，以此类推，以保证目的客户端具有充足的文件号进行文件创建。
本发明实施例提供的一种批量创建文件的方法，基于接收的创建请求实现相应多个文件的同时创建之后，还可以包括：
为创建得到的每个文件分别设置相应的文件名，将创建得到的每个文件的文件名与文件号建立关联；其中，文件的元数据包括具有关联的文件名及文件号。
目的客户端发送的创建请求中可以携带有客户端为对应文件设置的文件名(即文件的名称)，从而将创建得到的文件的名称设置为对应的创建请求中携带的文件名，并且将每个文件的文件名和文件号相关联，作为元数据实现存储，从而方便对于文件的查找等。另外，具有关联的信息具体可以为CInode(元数据Inode信息，主要包括文件属性)及CDentry(元数据目录项，主要包括文件名)，而CInode中包含文件号，CDentry中包含文件名，因此关联的CInode及CDentry，则包含关联的文件名及文件号，进而将关联的CInode及CDentry包含于元数据中进行存储，如存储至元数据池中。
本发明实施例提供的一种批量创建文件的方法，还可以包括：
当未完成目的客户端对应全部文件的批量创建时，接收到除目的客户端之外的其他客户端发送的授权请求，则指示目的客户端强制刷新目的客户端缓存的全部创建请求，以获取目的客户端刷新的全部创建请求，执行基于接收的创建请求实现相应的多个文件的同时创建的步骤。
需要说明的是，本实施例目的客户端可以将其需要创建的全部文件对应创建请求打包发送给服务器，也可以将其需要创建的全部文件分成多批后，依次将每批包含的创建请求打包发送给服务器，具体可以根据实际情况确定；对应的，目的客户端申请具有对指定目录具有权限可以包括需要对指定目录具有权限的时间段及需要在指定目录下创建的全部文件的总数量，而未完成目的客户端对应全部文件的批量创建，具体可以是对指定目 录具有权限的时长未达到目的客户端申请具有对指定目录具有权限的时间段，和/或在指定目录下创建的文件的数量未达到目的客户端需创建的全部文件的总数量。另外，目的客户端可以将需要发送的且还未发送的创建请求缓存在本地；如果未完成目的客户端对应全部文件的批量创建时接收到其他客户端发送的授权请求，则可以判断目的客户端是否还具有未发送到服务器的创建请求，如果是，则可以通知目的客户端强制刷新其缓存的创建请求至服务器，以由服务器实现相应的文件批量创建及文件元数据存储等，如果否，则可以由服务器完成目的客户端已经发送给服务器的创建请求对应的文件批量创建及文件元数据存储等，进而在实现目的客户端需创建的全部文件的批量创建及对应元数据存储后释放指定目录的权限，从而能够便于其他客户端对于指定目录的使用。
本发明实施例提供的一种批量创建文件的方法，还可以包括：
如果实现目的客户端对应全部文件的批量创建的过程中出现故障，则在故障修复后接收目的客户端重新发送的目的客户端记录的每个创建请求；其中，客户端记录需创建的每个文件对应的创建请求。
客户端在发送创建请求至服务器前还可以在本地记录需要发送的创建请求，进而如果服务器在处理批量的创建请求期间出现故障，则服务器需要对该故障进行修复，并且服务器修复完成且可以正常工作后，客户端需要将记录的创建请求重新发送给服务器，服务器在接收到客户端重新发送的创建请求后重新实现批量文件创建，从而保证了客户端批量创建文件的有效实现。
本发明实施例提供的一种批量创建文件的方法，实现目的客户端对应全部文件的批量创建之后，还可以包括：
返回给目的客户端对应全部文件的批量创建成功的确认信息，以指示目的客户端删除记录的创建请求。
在服务器完成目的客户端对应全部文件的批量创建后，可以向目的客户端返回确认信息，从而使得目的客户端获知其需创建的全部文件已经创建完成的信息，进而删除记录的创建请求，从而避免对目的客户端中存储空间的浪费。
并且，实现目的客户端对应全部文件的批量创建之后，还可以包括：
发送标记指令至目的客户端，以指示目的客户端在文件创建的日志中记录此次批量文件创建成功的标记。
通过向目的客户端发送标记指令，能够指示目的客户端在接收到标记指令后在日志中记录此次批量文件创建成功的标记，以供后期进行查询。
在一种具体实现场景中，本申请实施例提供的一种批量创建文件的方法可以包括：
(1)Inode预分配：
服务器与客户端建立连接时，服务器从元数据池中申请一定范围的Inode，并通知客户端；
(2)Cap申请：
当客户端在某个目录下创建文件时，向服务器申请目录独占Cap，若无其他客户端使用该目录，则服务器同意授权给客户端该目录的独占Cap；若有其他客户端正在使用该目录，则服务器拒绝授权独占Cap，至完成其他客户端的全部文件创建后再同意授权给客户端该目录的独占Cap。
(3)批量发送：
客户端申请到目录的独占Cap后，将一定时间内(或一定请求条目)的创建请求同时打包，发送给服务器，客户端同时记录已经发送的请求(为了故障处理)；若尚未达到一定时间或条目期间，有其他客户端向服务器申请该目录独占Cap，服务器会通知该客户端强制刷新缓存内创建请求，再释放独占Cap；
(4)服务器处理批量请求：
服务器收到客户端批量创建请求后，解析批量创建请求，创建相应的文件，并关联文件的CInode与CDentry，将所有创建的元数据落入元数据池，再向客户端应答(可以包括确认信息及标记指令)请求完成；
(5)完成阶段：
客户端收到服务器应答后，清理客户端中记录的已发送请求，标识本次批量创建业务完成；
(6)故障修复：
若服务器在处理批量创建请求期间故障，在服务器恢复阶段，客户端需要将批量创建请求重新发送给服务器，以供再次处理。
本申请提出的分布式文件系统中批量创建文件的方法，可以极大提升文件创建性能及元数据创建性能，特别是小文件场景的创建性能，进而提高分布式文件系统的创建性能。
本发明实施例还提供了一种批量创建文件的装置，如图2所示，具体可以包括：
确定模块11，用于：接收目的客户端发送的授权请求，并确定与授权请求对应的目录为指定目录；其中，目的客户端为需要进行批量文件创建的任意客户端；
判断模块12，用于：判断指定目录是否已被授权给除目的客户端之外的其他客户端，如果是，则等待直至完成与对指定目录具有权限的客户端对应全部文件的批量创建后，释放指定目录，并将指定目录授权给目的客户端，如果否，则将指定目录授权给目的客户端；其中，指定目录仅允许对指定目录具有权限的客户端进行访问；
创建模块13，用于：接收目的客户端发送的多个创建请求，基于接收的创建请求实现相应多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成目的客户端对应全部文件的批量创建后释放指定目录。
本发明实施例提供的一种批量创建文件的装置，还可以包括：
连接模块，用于：接收目的客户端发送的授权请求之前，接收目的客户端发送的连接请求，响应连接请求以建立与目的客户端的连接，并为目的客户端预申请预设范围的文件号；
分配模块，用于：基于接收的创建请求实现相应多个文件的同时创建之后，为创建得到的每个文件分别分配属于预设范围的文件号；其中，文件的元数据包括文件的文件号。
本发明实施例提供的一种批量创建文件的装置，还可以包括：
设置模块，用于：基于接收的创建请求实现相应多个文件的同时创建之后，为创建得到的每个文件分别设置相应的文件名，将创建得到的每个文件的文件名与文件号建立关联；其中，文件的元数据包括具有关联的文 件名及文件号。
本发明实施例提供的一种批量创建文件的装置，还可以包括：
指示模块，用于：当未完成目的客户端对应全部文件的批量创建时，接收到除目的客户端之外的其他客户端发送的授权请求，则指示目的客户端强制刷新目的客户端缓存的全部创建请求，以获取目的客户端刷新的全部创建请求，执行基于接收的创建请求实现相应的多个文件的同时创建的步骤。
本发明实施例提供的一种批量创建文件的装置，还可以包括：
重建模块，用于：如果实现目的客户端对应全部文件的批量创建的过程中出现故障，则在故障修复后接收目的客户端重新发送的目的客户端记录的每个创建请求；其中，客户端记录需创建的每个文件对应的创建请求。
本发明实施例提供的一种批量创建文件的装置，还可以包括：
返回模块，用于：实现目的客户端对应全部文件的批量创建之后，返回给目的客户端对应全部文件的批量创建成功的确认信息，以指示目的客户端删除记录的创建请求。
本发明实施例提供的一种批量创建文件的装置，还可以包括：
发送模块，用于：实现目的客户端对应全部文件的批量创建之后，发送标记指令至目的客户端，以指示目的客户端在文件创建的日志中记录此次批量文件创建成功的标记。
本发明实施例还提供了一种批量创建文件的设备，可以包括：
存储器，用于存储计算机程序；
处理器，用于执行计算机程序时实现如上任一项批量创建文件的方法的步骤。
本发明实施例还提供了一种计算机可读存储介质，计算机可读存储介质上存储有计算机程序，计算机程序被处理器执行时可以实现如上任一项批量创建文件的方法的步骤。
需要说明的是，本发明实施例提供的一种批量创建文件的装置、设备及存储介质中相关部分的说明请参见本发明实施例提供的一种批量创建文件的方法中对应部分的详细说明，在此不再赘述。另外，本发明实施例提 供的上述技术方案中与现有技术中对应技术方案实现原理一致的部分并未详细说明，以免过多赘述。
对所公开的实施例的上述说明，使本领域技术人员能够实现或使用本发明。对这些实施例的多种修改对本领域技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本发明的精神或范围的情况下，在其它实施例中实现。因此，本发明将不会被限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。
Claims (10)
- 一种批量创建文件的方法，其特征在于，包括：接收目的客户端发送的授权请求，并确定与所述授权请求对应的目录为指定目录；其中，所述目的客户端为需要进行批量文件创建的任意客户端；判断所述指定目录是否已被授权给除所述目的客户端之外的其他客户端，如果是，则等待直至完成与对所述指定目录具有权限的客户端对应全部文件的批量创建后，释放所述指定目录，并将所述指定目录授权给所述目的客户端，如果否，则将所述指定目录授权给所述目的客户端；其中，所述指定目录仅允许对所述指定目录具有权限的客户端进行访问；接收所述目的客户端发送的多个创建请求，基于接收的创建请求实现相应的多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成所述目的客户端对应全部文件的批量创建后释放所述指定目录。
- 根据权利要求1所述的方法，其特征在于，接收目的客户端发送的授权请求之前，还包括：接收所述目的客户端发送的连接请求，响应所述连接请求以建立与所述目的客户端的连接，并为所述目的客户端预申请预设范围的文件号；基于接收的创建请求实现相应多个文件的同时创建之后，还包括：为创建得到的每个文件分别分配属于所述预设范围的文件号；其中，所述文件的元数据包括所述文件的文件号。
- 根据权利要求2所述的方法，其特征在于，基于接收的创建请求实现相应多个文件的同时创建之后，还包括：为创建得到的每个文件分别设置相应的文件名，将创建得到的每个文件的文件名与文件号建立关联；其中，所述文件的元数据包括具有关联的所述文件名及所述文件号。
- 根据权利要求1所述的方法，其特征在于，还包括：当未完成所述目的客户端对应全部文件的批量创建时，接收到除所述目的客户端之外的其他客户端发送的授权请求，则指示所述目的客户端强制刷新所述目的客户端缓存的全部创建请求，以获取所述目的客户端刷新 的全部创建请求，执行基于接收的创建请求实现相应的多个文件的同时创建的步骤。
- 根据权利要求1所述的方法，其特征在于，还包括：如果实现所述目的客户端对应全部文件的批量创建的过程中出现故障，则在故障修复后接收所述目的客户端重新发送的所述目的客户端记录的每个创建请求；其中，所述客户端记录需创建的每个文件对应的创建请求。
- 根据权利要求5所述的方法，其特征在于，实现所述目的客户端对应全部文件的批量创建之后，还包括：返回给所述目的客户端对应全部文件的批量创建成功的确认信息，以指示所述目的客户端删除记录的创建请求。
- 根据权利要求6所述的方法，其特征在于，实现所述目的客户端对应全部文件的批量创建之后，还包括：发送标记指令至所述目的客户端，以指示所述目的客户端在文件创建的日志中记录此次批量文件创建成功的标记。
- 一种批量创建文件的装置，其特征在于，包括：确定模块，用于：接收目的客户端发送的授权请求，并确定与所述授权请求对应的目录为指定目录；其中，所述目的客户端为需要进行批量文件创建的任意客户端；判断模块，用于：判断所述指定目录是否已被授权给除所述目的客户端之外的其他客户端，如果是，则等待直至完成与对所述指定目录具有权限的客户端对应全部文件的批量创建后，释放所述指定目录，并将所述指定目录授权给所述目的客户端，如果否，则将所述指定目录授权给所述目的客户端；其中，所述指定目录仅允许对所述指定目录具有权限的客户端进行访问；创建模块，用于：接收所述目的客户端发送的多个创建请求，基于接收的创建请求实现相应多个文件的同时创建，存储创建得到的每个文件的元数据，并在完成所述目的客户端对应全部文件的批量创建后释放所述指定目录。
- 一种批量创建文件的设备，其特征在于，包括：存储器，用于存储计算机程序；处理器，用于执行所述计算机程序时实现如权利要求1至7任一项所述批量创建文件的方法的步骤。
- 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1至7任一项所述批量创建文件的方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911385174.3 | 2019-12-28 | ||
| CN201911385174.3A CN111046001B (zh) | 2019-12-28 | 2019-12-28 | 一种批量创建文件的方法、装置、设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021128892A1 true WO2021128892A1 (zh) | 2021-07-01 |
Family
ID=70241006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/110731 WO2021128892A1 (zh) | 2019-12-28 | 2020-08-24 | 一种批量创建文件的方法、装置、设备及存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111046001B (zh) |
| WO (1) | WO2021128892A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113760853A (zh) * | 2021-08-16 | 2021-12-07 | 联想凌拓科技有限公司 | 一种目录处理方法、服务器以及存储介质 |
| CN116611988A (zh) * | 2023-05-23 | 2023-08-18 | 北京优贝卡科技有限公司 | 图像处理方法、电子设备和存储介质 |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111046001B (zh) * | 2019-12-28 | 2023-03-14 | 浪潮电子信息产业股份有限公司 | 一种批量创建文件的方法、装置、设备及存储介质 |
| CN112597120B (zh) * | 2020-11-30 | 2022-05-27 | 新华三大数据技术有限公司 | 一种目录管理方法及装置 |
| CN115580610B (zh) * | 2022-09-22 | 2024-03-19 | 广州文远知行科技有限公司 | 一种批量文件上传的方法、装置、设备及可读存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024016A (zh) * | 2010-11-04 | 2011-04-20 | 天津曙光计算机产业有限公司 | 一种分布式文件系统快速数据恢复的方法 |
| CN103179185A (zh) * | 2012-12-25 | 2013-06-26 | 中国科学院计算技术研究所 | 一种分布式文件系统客户端缓存中文件创建方法及其系统 |
| US20170031781A1 (en) * | 2015-07-28 | 2017-02-02 | International Business Machines Corporation | Real time and scalable space-time data recovery from existing backup systems |
| CN111046001A (zh) * | 2019-12-28 | 2020-04-21 | 浪潮电子信息产业股份有限公司 | 一种批量创建文件的方法、装置、设备及存储介质 |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9361229B2 (en) * | 2008-08-25 | 2016-06-07 | International Business Machines Corporation | Distributed shared caching for clustered file systems |
| US9307025B1 (en) * | 2011-03-29 | 2016-04-05 | Riverbed Technology, Inc. | Optimized file creation in WAN-optimized storage |
| EP2541473A1 (en) * | 2011-06-27 | 2013-01-02 | Amadeus S.A.S. | Method and system for a pre-shopping reservation system with increased search efficiency |
| US20130218934A1 (en) * | 2012-02-17 | 2013-08-22 | Hitachi, Ltd. | Method for directory entries split and merge in distributed file system |
| US10264071B2 (en) * | 2014-03-31 | 2019-04-16 | Amazon Technologies, Inc. | Session management in distributed storage systems |
| CN104021137B (zh) * | 2014-04-21 | 2017-06-09 | 中国科学院计算技术研究所 | 一种基于目录授权的客户端本地开闭文件的方法及系统 |
| CN104113587B (zh) * | 2014-06-23 | 2017-08-01 | 华中科技大学 | 一种分布式文件系统客户端元数据缓存优化方法 |
| CN105630810B (zh) * | 2014-10-30 | 2019-05-21 | 曙光信息产业股份有限公司 | 一种对于海量小文件在分布式存储系统中上载的方法 |
| CN105512279B (zh) * | 2015-12-04 | 2019-05-03 | 华为技术有限公司 | 一种元数据访问方法、相关设备及系统 |
| CN106485156B (zh) * | 2016-09-22 | 2019-05-17 | 中广核工程有限公司 | 一种用于文件批量授权的装置和方法 |
| CN109408474B (zh) * | 2018-11-09 | 2021-11-19 | 郑州云海信息技术有限公司 | 一种文件创建方法及客户端 |
| CN110138881A (zh) * | 2019-06-05 | 2019-08-16 | 安徽三实信息技术服务有限公司 | 一种分布式存储系统及其存储方法 |
| CN110597773B (zh) * | 2019-08-28 | 2022-07-29 | 北京梦想绽放科技有限公司 | 在计算机设备和虚拟现实设备之间共享文件的方法和装置 |
-
2019
- 2019-12-28 CN CN201911385174.3A patent/CN111046001B/zh active Active
-
2020
- 2020-08-24 WO PCT/CN2020/110731 patent/WO2021128892A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024016A (zh) * | 2010-11-04 | 2011-04-20 | 天津曙光计算机产业有限公司 | 一种分布式文件系统快速数据恢复的方法 |
| CN103179185A (zh) * | 2012-12-25 | 2013-06-26 | 中国科学院计算技术研究所 | 一种分布式文件系统客户端缓存中文件创建方法及其系统 |
| US20170031781A1 (en) * | 2015-07-28 | 2017-02-02 | International Business Machines Corporation | Real time and scalable space-time data recovery from existing backup systems |
| CN111046001A (zh) * | 2019-12-28 | 2020-04-21 | 浪潮电子信息产业股份有限公司 | 一种批量创建文件的方法、装置、设备及存储介质 |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113760853A (zh) * | 2021-08-16 | 2021-12-07 | 联想凌拓科技有限公司 | 一种目录处理方法、服务器以及存储介质 |
| CN113760853B (zh) * | 2021-08-16 | 2024-02-20 | 联想凌拓科技有限公司 | 一种目录处理方法、服务器以及存储介质 |
| CN116611988A (zh) * | 2023-05-23 | 2023-08-18 | 北京优贝卡科技有限公司 | 图像处理方法、电子设备和存储介质 |
| CN116611988B (zh) * | 2023-05-23 | 2024-04-26 | 释空(上海)展示制作有限公司 | 图像处理方法、电子设备和存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111046001B (zh) | 2023-03-14 |
| CN111046001A (zh) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021128892A1 (zh) | 一种批量创建文件的方法、装置、设备及存储介质 | |
| CN110489382B (zh) | 一种云手机游戏进度数据的处理方法、系统和存储介质 | |
| US7783737B2 (en) | System and method for managing supply of digital content | |
| JP2008518284A (ja) | 固定内容分散データ記憶のためのメタデータ管理 | |
| CN108885671B (zh) | 一种目录删除方法、装置和存储服务器 | |
| WO2002095588B1 (en) | Decentralized virus scanning for stored data | |
| US9445162B2 (en) | Interactive personal/internet protocol television reservation system, reservation plan management method and device | |
| CN110008041B (zh) | 一种消息处理方法及装置 | |
| WO2021098260A1 (zh) | 一种数据删除方法、系统、设备及计算机可读存储介质 | |
| KR20100067976A (ko) | 분산 저장된 컨텐츠 파일의 동기화 방법 | |
| US8447825B2 (en) | File sharing system and file sharing method | |
| WO2021003798A1 (zh) | 一种实现域名访问加速的方法和系统 | |
| WO2021169163A1 (zh) | 一种文件数据存取方法、装置和计算机可读存储介质 | |
| CN114443166B (zh) | 一种共享文件处理方法、装置及介质 | |
| US8725887B2 (en) | License management system and function providing device | |
| US7840671B2 (en) | Managing the size and accessibility of a name service | |
| WO2024169280A1 (zh) | 元数据管理方法、装置、设备、服务器及可读存储介质 | |
| US11853229B2 (en) | Method and apparatus for updating cached information, device, and medium | |
| CN107357808B (zh) | 数据管理方法、装置及设备 | |
| CN111309799A (zh) | 数据合并的实现方法、装置、系统及存储介质 | |
| CN110737635B (zh) | 一种数据分块方法 | |
| CN111176559B (zh) | 数据写入方法及装置、双活系统 | |
| CN113094754B (zh) | 大数据平台数据修改系统及修改、响应、缓存、校验方法 | |
| WO2020073517A1 (zh) | 基于分布式存储系统的数据归档方法、装置、计算机设备 | |
| CN106557530A (zh) | 业务系统、数据修复方法及装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20907209 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20907209 Country of ref document: EP Kind code of ref document: A1 |