CN112035064A - Distributed migration method for object storage - Google Patents
Distributed migration method for object storage Download PDFInfo
- Publication number
- CN112035064A CN112035064A CN202010882876.9A CN202010882876A CN112035064A CN 112035064 A CN112035064 A CN 112035064A CN 202010882876 A CN202010882876 A CN 202010882876A CN 112035064 A CN112035064 A CN 112035064A
- Authority
- CN
- China
- Prior art keywords
- node
- migration
- task
- file
- distributed
- 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
- 238000013508 migration Methods 0.000 title claims abstract description 127
- 230000005012 migration Effects 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012216 screening Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
- G06F3/0607—Improving or facilitating administration, e.g. storage management by facilitating the process of upgrading existing storage systems, e.g. for improving compatibility between host and storage device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0638—Organizing or formatting or addressing of data
- G06F3/0643—Management of files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
- G06F3/0647—Migration mechanisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention particularly relates to a distributed migration method for object storage. The distributed migration method for object storage deploys a distributed cluster which comprises a main node and a plurality of auxiliary nodes, and filters each node through object name, storage type, storage authority, object size or creation time period, and migrates only the nodes meeting the requirements; when a bad node appears in the migration object in the migration process, the task of the bad node is distributed to the rest of the surviving nodes in the migration object. The distributed migration method for the object storage deploys a migration cluster capable of being automatically established and automatically maintained based on the characteristics of the object storage S3 protocol, efficiently and safely migrates the object from one object storage system to another object storage system, and reduces manual operation and maintenance work to the maximum extent.
Description
Technical Field
The invention relates to the technical field of cloud computing and object storage migration, in particular to a distributed migration method for object storage.
Background
The object storage is a distributed storage product which can natively support an HTTP/HTTPS protocol, and the service of the object storage can be directly used as long as the Internet is connected. With the development and maturity of object storage, more and more internet websites and APPs begin to store some static resources in the object storage service, which not only reduces the pressure of the server, but also can reduce the cost.
There are many different object storage service providers, and when a user wants to replace an object storage service provider or to make security redundancy at multiple object storage service providers, a need for object storage migration arises. However, the existing migration tool is low in efficiency and often is deployed as a single machine, and the purpose of increasing the speed cannot be achieved by establishing a cluster.
In order to efficiently and safely migrate objects from one object storage system to another object storage system, the invention provides a distributed migration method for object storage.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a simple and efficient distributed migration method for object storage.
The invention is realized by the following technical scheme:
a distributed migration method for object storage, characterized by: deploying a distributed cluster which comprises a main node and a plurality of auxiliary nodes, screening each node through an object name, a storage type, a storage authority, an object size or a creation time period, and only migrating the nodes meeting the requirements;
when a bad node appears in the migration object in the migration process, the task of the bad node is distributed to the rest of the surviving nodes in the migration object.
The method comprises the following steps:
s1, preparation of original object storage service
Creating a special file folder for migration in a bucket to be migrated of an original object storage service, and creating a migration information file below the special file folder for storing target object storage bucket information and a migration object screening rule;
after the migration starts and before the migration ends, the objects in the original object bucket can be added but cannot be deleted, and the added objects cannot be migrated.
S2, preparation and starting of migration nodes
The migration node sets a starting parameter before starting;
after all nodes of the distributed cluster are connected with the original object storage bucket, whether a file named a master exists or not is inquired in a migration folder so as to determine a main node and an auxiliary node; the secondary node reads the content of the master file and sends a registration request to the primary node according to host and ip information recorded in the master file; after the initialization is finished, the main node also sends a registration request to the main node, and starts a migration task of the main node;
after receiving the registration request, the main node creates a task file with the host of the registration node as the name and a log file with the host.log of the node as the name in the migration folder; the task file is responsible for storing the distributed tasks and the ip of the secondary node, and the log file is responsible for storing the executed progress of the node when the node rises;
s3, adding new nodes and executing migration tasks
The migration task is stored in a file named by the node host in the barrel in the form of Etag prefix; when a new node is registered and added into the distributed cluster, the main node takes out a proper Etag prefix from an existing node, puts the Etag prefix into a task file of the new node, identifies which node a task comes from in the file, and then deletes the taken-out Etag prefix from the task file of the existing node;
when the master node creates a log file of a new node, adding the latest log of each Etag prefix taken from the old node into the log file of the new node, and continuing the task by the new node according to the Etag prefix in the log file;
starting from the task with the least total number of the taken objects by the new node, if the object list taken out by the task at a certain time contains the end marks of other tasks, starting other tasks corresponding to the end marks, migrating the tasks in parallel with the task, and so on until all tasks distributed by the new node are performed together;
when a node executes a migration task, a batch of object lists are taken from an original object storage bucket every time, then the task list of the node is checked to obtain the latest task prefix of the node, and then the selected migration object is transmitted to a new object storage bucket according to a migration object screening rule and an Etag prefix; after the batch of objects is transmitted, the end mark of the taken object list, the total number of the taken objects and the Etag prefix screened this time are recorded;
s4, node self-management
The main node and the auxiliary node are provided with health check interfaces;
the method comprises the steps that a main node regularly checks the health condition of a secondary node, and when finding that the secondary node is hung, the main node immediately distributes tasks of the hung secondary node to other surviving secondary nodes in an average mode;
the secondary node also checks the health condition of the primary node at regular time, when the primary node is found to be hung, the oldest secondary node except the primary node is automatically changed into the primary node, the ip and host in the master file are rewritten into the master file, and then the task of maintaining the cluster by the primary node is executed;
s5, ending the migration task
When the end mark of the task log is null, the task is shown to have traversed all the existing objects, the migration object of the task is migrated to the maximum, the task is terminated, and the task is not distributed to a new node when the new node is added;
and when all migration tasks of the distributed cluster are completed, the main node prints an end log to prompt that the migration tasks are completed.
In step S1, the storage target object bucket information includes the access-key, the secret-key, and the end and bucket name information of the target object bucket; the node joins the new object bucket by reading the migration information file and places the object into the new object bucket.
In step S2, the start parameters include the folder name of the migration dedicated folder, the file name of the migration information file, the node name of the migration node (which must be unique in the whole migration cluster), and the access-key, the secret-key, the end and the bucket name information stored in the object to be migrated.
In step S2, if the file named master is not found in the migration folder after the distributed cluster node is connected to the original object bucket, a master file is created, and the content of the master file is modified to its own host name and ip, indicating that the node is the master node;
if the file named master exists in the migration folder, the migration folder represents that a main node exists in the distributed cluster and the main node is a secondary node.
In step S1, the migration information file may further set an upper limit of the cluster size, where the index is an n-th power of 16;
in step S3, tasks are assigned according to the top m characters of Etag of the migration target, and the tasks are divided into 16mM is a natural number obtained according to the cluster scale n in the migration information file;
when the main node receives the registration request for the first time, the main node writes all the prefixes into the task file of the registration node.
If m is 1, namely the first character of the Etag is allocated, dividing the task into 16 parts; if m is 2, i.e. assigned with the first two characters of Etag, the task is divided into 256, and so on.
In step S3, the master node periodically checks whether each node has a duplicate task, and if a duplicate task is found, deletes the duplicate task of the node with a large number of tasks.
In step S4, when the oldest secondary node and primary node in the distributed cluster are hung up simultaneously, the ip and host in the master file remain unchanged as the original primary node, and the secondary node is changed into the primary node until the health check of the secondary node on the primary node is continuously invalid; if the health check of the secondary node on the primary node is still continuously invalid, the old secondary node becomes the primary node again, and so on.
In step S5, after the secondary node completes all its tasks, it automatically resets and adds the cluster as a new node to seek a new task.
The invention has the beneficial effects that: the distributed migration method for the object storage deploys a migration cluster capable of being automatically established and automatically maintained based on the characteristics of the object storage S3 protocol, efficiently and safely migrates the object from one object storage system to another object storage system, and reduces manual operation and maintenance work to the maximum extent.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating a relationship between each node and each file of the distributed migration system for object storage according to the present invention.
Fig. 2 is a schematic flow chart of a new node adding system of the present invention.
FIG. 3 is a schematic diagram of a distributed migration process for object storage according to the present invention.
Fig. 4 is a schematic diagram of a method for managing a secondary node by a primary node according to the present invention.
Fig. 5 is a schematic diagram of the method for checking the primary node by the secondary node according to the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the embodiment of the present invention. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The distributed migration method for object storage deploys a distributed cluster which comprises a main node and a plurality of auxiliary nodes, and filters each node through object name, storage type, storage authority, object size or creation time period, and migrates only the nodes meeting the requirements;
when a bad node appears in the migration object in the migration process, the task of the bad node is distributed to the rest of the surviving nodes in the migration object.
The method comprises the following steps:
s1, preparation of original object storage service
Creating a special file folder for migration in a bucket to be migrated of an original object storage service, and creating a migration information file below the special file folder for storing target object storage bucket information and a migration object screening rule;
after the migration starts and before the migration ends, objects in the original object storage bucket can be added but cannot be deleted, and the added objects cannot be migrated;
a bucket is the name of the storage space in the object store, and is migrated in units of buckets when migrated.
An object is the smallest unit of storage within an object store, and there can be as many as millions of objects within a bucket.
S2, preparation and starting of migration nodes
The migration node sets a starting parameter before starting;
after all nodes of the distributed cluster are connected with the original object storage bucket, whether a file named a master exists or not is inquired in a migration folder so as to determine a main node and an auxiliary node; the secondary node reads the content of the master file and sends a registration request to the primary node according to host and ip information recorded in the master file; after the initialization is finished, the main node also sends a registration request to the main node, and starts a migration task of the main node;
after receiving the registration request, the main node creates a task file with the host of the registration node as the name and a log file with the host.log of the node as the name in the migration folder; the task file is responsible for storing the distributed tasks and the ip of the secondary node, and the log file is responsible for storing the executed progress of the node when the node rises;
s3, adding new nodes and executing migration tasks
Etag is a 16-ary string, which is calculated from the file content and time, and thus can function as a hash, with a separate Etag for each object.
The migration task is stored in a file named by the node host in the barrel in the form of Etag prefix; when a new node is registered and added into the distributed cluster, the main node takes out a proper Etag prefix from an existing node, puts the Etag prefix into a task file of the new node, identifies which node a task comes from in the file, and then deletes the taken-out Etag prefix from the task file of the existing node;
when the master node creates a log file of a new node, adding the latest log of each Etag prefix taken from the old node into the log file of the new node, and continuing the task by the new node according to the Etag prefix in the log file;
starting from the task with the least total number of the taken objects by the new node, if the object list taken out by the task at a certain time contains the end marks of other tasks, starting other tasks corresponding to the end marks, migrating the tasks in parallel with the task, and so on until all tasks distributed by the new node are performed together;
for example, a new node takes four tasks a, b, c, and d out of other nodes, and arranges the tasks in order of the number of objects that have been delivered from small to large. Firstly, a task a is carried out, when an object list taken out by the task a at a certain time contains an end mark of the task b, the task b also starts to be transmitted in parallel with the task a, then if the end mark of the task c is met, the task c is started, and the like, until the four tasks a, b, c and d distributed by a new node are carried out together.
When a node executes a migration task, a batch of object lists (such as 1000 objects) are taken from an original object storage bucket every time, then the task list of the node is checked to obtain the latest task prefix of the node, and then the selected migration object is transmitted to a new object storage bucket according to a migration object screening rule and an Etag prefix; after the batch of objects is transmitted, recording the end mark of the taken object list (a batch of objects can be taken down next by the mark), the total number of the taken objects and the Etag prefix screened this time;
s4, node self-management
The main node and the auxiliary node are provided with health check interfaces;
the primary node regularly checks the health condition of the secondary node, and when finding that the secondary node hangs down, the primary node immediately distributes the tasks of the hung-down secondary node to other surviving secondary nodes in an average way, and the distribution process is as shown in the attached figure 2.
The secondary node also checks the health condition of the primary node at regular time, when the primary node is found to be hung, the oldest secondary node except the primary node is automatically changed into the primary node, the ip and host in the master file are rewritten into the master file, and then the task of maintaining the cluster by the primary node is executed;
s5, ending the migration task
When the object list in the bucket is acquired, if the acquisition does not acquire the last object of the list, the last object name acquired in the acquisition is used as an end mark, and when the acquisition is performed again next time, the mark is taken as a parameter, and then the rest of objects are continuously acquired. If the acquisition has acquired the last of the list, the end marker will be null.
When the end mark of the task log is null, the task is shown to have traversed all the existing objects, the migration object of the task is migrated to the maximum, the task is terminated, and the task is not distributed to a new node when the new node is added;
and when all migration tasks of the distributed cluster are completed, the main node prints an end log to prompt that the migration tasks are completed.
In step S1, the storage target object bucket information includes the access-key, the secret-key, and the end and bucket name information of the target object bucket; the node joins the new object bucket by reading the migration information file and places the object into the new object bucket.
In step S2, the start parameters include the folder name of the migration dedicated folder, the file name of the migration information file, the node name of the migration node (which must be unique in the whole migration cluster), and the access-key, the secret-key, the end and the bucket name information stored in the object to be migrated.
The access-key, the secret-key and the endpoint are keys and addresses, and the three information can be connected with the object storage service to perform operations such as uploading, downloading, management and the like.
In step S2, if the file named master is not found in the migration folder after the distributed cluster node is connected to the original object bucket, a master file is created, and the content of the master file is modified to its own host name and ip, indicating that the node is the master node;
if the file named master exists in the migration folder, the migration folder represents that a main node exists in the distributed cluster and the main node is a secondary node.
In step S1, the migration information file may further set an upper limit of the cluster size, where the index is an n-th power of 16;
in step S3, tasks are assigned according to the top m characters of Etag of the migration target, and the tasks are divided into 16mM is a natural number obtained according to the cluster scale n in the migration information file;
when the main node receives the registration request for the first time, the main node writes all the prefixes into the task file of the registration node.
If m is 1, namely the first character of the Etag is allocated, dividing the task into 16 parts; if m is 2, i.e. assigned with the first two characters of Etag, the task is divided into 256, and so on.
In step S3, the master node periodically checks whether each node has a duplicate task, and if a duplicate task is found, deletes the duplicate task of the node with a large number of tasks.
In step S4, when the oldest secondary node and primary node in the distributed cluster are hung up simultaneously, the ip and host in the master file remain unchanged as the original primary node, and the secondary node is changed into the primary node until the health check of the secondary node on the primary node is continuously invalid; if the health check of the secondary node on the primary node is still continuously invalid, the old secondary node becomes the primary node again, and so on.
In step S5, after the secondary node completes all its tasks, it automatically resets and adds the cluster as a new node to seek a new task.
The above-described embodiment is only one specific embodiment of the present invention, and general changes and substitutions by those skilled in the art within the technical scope of the present invention are included in the protection scope of the present invention.
Claims (9)
1. A distributed migration method for object storage, characterized by: deploying a distributed cluster which comprises a main node and a plurality of auxiliary nodes, screening each node through an object name, a storage type, a storage authority, an object size or a creation time period, and only migrating the nodes meeting the requirements;
when a bad node appears in the migration object in the migration process, the task of the bad node is distributed to the rest of the surviving nodes in the migration object.
2. The distributed migration method for object storage according to claim 1, comprising the steps of:
s1, preparation of original object storage service
Creating a special file folder for migration in a bucket to be migrated of an original object storage service, and creating a migration information file below the special file folder for storing target object storage bucket information and a migration object screening rule;
after the migration starts and before the migration ends, objects in the original object storage bucket can be added but cannot be deleted, and the added objects cannot be migrated;
s2, preparation and starting of migration nodes
The migration node sets a starting parameter before starting;
after all nodes of the distributed cluster are connected with the original object storage bucket, whether a file named a master exists or not is inquired in a migration folder so as to determine a main node and an auxiliary node; the secondary node reads the content of the master file and sends a registration request to the primary node according to host and ip information recorded in the master file; after the initialization is finished, the main node also sends a registration request to the main node, and starts a migration task of the main node;
after receiving the registration request, the main node creates a task file with the host of the registration node as the name and a log file with the host.log of the node as the name in the migration folder; the task file is responsible for storing the distributed tasks and the ip of the secondary node, and the log file is responsible for storing the executed progress of the node;
s3, adding new nodes and executing migration tasks
The migration task is stored in a file named by the node host in the barrel in the form of Etag prefix; when a new node is registered and added into the distributed cluster, the main node takes out a proper Etag prefix from an existing node, puts the Etag prefix into a task file of the new node, identifies which node a task comes from in the file, and then deletes the taken-out Etag prefix from the task file of the existing node;
when the master node creates a log file of a new node, adding the latest log of each Etag prefix taken from the old node into the log file of the new node, and continuing the task by the new node according to the Etag prefix in the log file;
starting from the task with the least total number of the taken objects by the new node, if the object list taken out by the task at a certain time contains the end marks of other tasks, starting other tasks corresponding to the end marks, migrating the tasks in parallel with the task, and so on until all tasks distributed by the new node are performed together;
when a node executes a migration task, a batch of object lists are taken from an original object storage bucket every time, then the task list of the node is checked to obtain the latest task prefix of the node, and then the selected migration object is transmitted to a new object storage bucket according to a migration object screening rule and an Etag prefix; after the batch of objects is transmitted, the end mark of the taken object list, the total number of the taken objects and the Etag prefix screened this time are recorded;
s4, node self-management
The main node and the auxiliary node are provided with health check interfaces;
the method comprises the steps that a main node regularly checks the health condition of a secondary node, and when finding that the secondary node is hung, the main node immediately distributes tasks of the hung secondary node to other surviving secondary nodes in an average mode;
the secondary node also checks the health condition of the primary node at regular time, when the primary node is found to be hung, the oldest secondary node except the primary node is automatically changed into the primary node, the ip and host in the master file are rewritten into the master file, and then the task of maintaining the cluster by the primary node is executed;
s5, ending the migration task
When the end mark of the task log is null, the task is shown to have traversed all the existing objects, the migration object of the task is migrated to the maximum, the task is terminated, and the task is not distributed to a new node when the new node is added;
and when all migration tasks of the distributed cluster are completed, the main node prints an end log to prompt that the migration tasks are completed.
3. The distributed migration method for object storage according to claim 2, wherein: in step S1, the storage target object bucket information includes the access-key, the secret-key, and the end and bucket name information of the target object bucket; the node joins the new object bucket by reading the migration information file and places the object into the new object bucket.
4. The distributed migration method for object storage according to claim 2, wherein: in step S2, the start parameters include the folder name of the migration specific folder, the file name of the migration information file, the node name of the migration node, and the access-key, the secret-key, the end point, and the bucket name information stored in the object to be migrated.
5. The distributed migration method for object storage according to claim 2, wherein: in step S2, if the file named master is not found in the migration folder after the distributed cluster node is connected to the original object bucket, a master file is created, and the content of the master file is modified to its own host name and ip, indicating that the node is the master node;
if the file named master exists in the migration folder, the migration folder represents that a main node exists in the distributed cluster and the main node is a secondary node.
6. The distributed migration method for object storage according to claim 5, wherein: in step S1, the migration information file may further set an upper limit of the cluster size, where the index is an n-th power of 16;
in step S3, tasks are assigned according to the top m characters of Etag of the migration target, and the tasks are divided into 16mPreparing;
when the main node receives the registration request for the first time, the main node writes all the prefixes into the task file of the registration node.
7. The distributed migration method for object storage according to claim 2, wherein: in step S3, the master node periodically checks whether each node has a duplicate task, and if a duplicate task is found, deletes the duplicate task of the node with a large number of tasks.
8. The distributed migration method for object storage according to claim 2, wherein: in step S4, when the oldest secondary node and primary node in the distributed cluster are hung up simultaneously, the ip and host in the master file remain unchanged as the original primary node, and the secondary node is changed into the primary node until the health check of the secondary node on the primary node is continuously invalid; if the health check of the secondary node on the primary node is still continuously invalid, the old secondary node becomes the primary node again, and so on.
9. The distributed migration method for object storage according to claim 2, wherein: in step S5, after the secondary node completes all its tasks, it automatically resets and adds the cluster as a new node to seek a new task.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010882876.9A CN112035064A (en) | 2020-08-28 | 2020-08-28 | Distributed migration method for object storage |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010882876.9A CN112035064A (en) | 2020-08-28 | 2020-08-28 | Distributed migration method for object storage |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112035064A true CN112035064A (en) | 2020-12-04 |
Family
ID=73585991
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010882876.9A Pending CN112035064A (en) | 2020-08-28 | 2020-08-28 | Distributed migration method for object storage |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112035064A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114138209A (en) * | 2022-02-07 | 2022-03-04 | 苏州浪潮智能科技有限公司 | OSD (on screen display) deploying method and device and computer readable storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150277955A1 (en) * | 2014-03-31 | 2015-10-01 | Fujitsu Limited | System and method for controlling virtual-machine migrations based on processor usage rates and traffic amounts |
CN106777164A (en) * | 2016-12-20 | 2017-05-31 | 东软集团股份有限公司 | A kind of Data Migration cluster and data migration method |
CN106844510A (en) * | 2016-12-28 | 2017-06-13 | 北京五八信息技术有限公司 | The data migration method and device of a kind of distributed experiment & measurement system |
CN107153512A (en) * | 2017-04-01 | 2017-09-12 | 华为技术有限公司 | A kind of data migration method and device |
CN107391629A (en) * | 2017-06-30 | 2017-11-24 | 北京奇虎科技有限公司 | Data migration method, system, server and computer-readable storage medium between cluster |
CN108021336A (en) * | 2016-10-31 | 2018-05-11 | 甲骨文国际公司 | Data layout scheme for seamless Data Migration |
CN109271098A (en) * | 2018-07-18 | 2019-01-25 | 成都华为技术有限公司 | A kind of data migration method and device |
CN110267060A (en) * | 2019-07-24 | 2019-09-20 | 北京视界云天科技有限公司 | Video file stores method for implanting, device, computer equipment and storage medium |
CN110333986A (en) * | 2019-06-19 | 2019-10-15 | 上海二三四五网络科技有限公司 | A method of ensureing redis cluster availability |
CN111309259A (en) * | 2020-02-14 | 2020-06-19 | 苏州浪潮智能科技有限公司 | Data migration method, system, storage medium and data migration terminal |
-
2020
- 2020-08-28 CN CN202010882876.9A patent/CN112035064A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150277955A1 (en) * | 2014-03-31 | 2015-10-01 | Fujitsu Limited | System and method for controlling virtual-machine migrations based on processor usage rates and traffic amounts |
CN108021336A (en) * | 2016-10-31 | 2018-05-11 | 甲骨文国际公司 | Data layout scheme for seamless Data Migration |
CN106777164A (en) * | 2016-12-20 | 2017-05-31 | 东软集团股份有限公司 | A kind of Data Migration cluster and data migration method |
CN106844510A (en) * | 2016-12-28 | 2017-06-13 | 北京五八信息技术有限公司 | The data migration method and device of a kind of distributed experiment & measurement system |
CN107153512A (en) * | 2017-04-01 | 2017-09-12 | 华为技术有限公司 | A kind of data migration method and device |
CN107391629A (en) * | 2017-06-30 | 2017-11-24 | 北京奇虎科技有限公司 | Data migration method, system, server and computer-readable storage medium between cluster |
CN109271098A (en) * | 2018-07-18 | 2019-01-25 | 成都华为技术有限公司 | A kind of data migration method and device |
CN110333986A (en) * | 2019-06-19 | 2019-10-15 | 上海二三四五网络科技有限公司 | A method of ensureing redis cluster availability |
CN110267060A (en) * | 2019-07-24 | 2019-09-20 | 北京视界云天科技有限公司 | Video file stores method for implanting, device, computer equipment and storage medium |
CN111309259A (en) * | 2020-02-14 | 2020-06-19 | 苏州浪潮智能科技有限公司 | Data migration method, system, storage medium and data migration terminal |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114138209A (en) * | 2022-02-07 | 2022-03-04 | 苏州浪潮智能科技有限公司 | OSD (on screen display) deploying method and device and computer readable storage medium |
CN114138209B (en) * | 2022-02-07 | 2022-04-22 | 苏州浪潮智能科技有限公司 | OSD (on screen display) deploying method and device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9898521B2 (en) | Massively scalable object storage system | |
EP2501108B1 (en) | Massively scalable object storage system | |
CN107450961B (en) | Distributed deep learning system based on Docker container and construction method and working method thereof | |
US8140625B2 (en) | Method for operating a fixed prefix peer to peer network | |
CN107959579B (en) | Multi-system deployment method and deployment system | |
WO2017092470A1 (en) | Data storage method and device | |
EP3200431A2 (en) | Massively scalable object storage system | |
CN107203617B (en) | The online migratory system of mysql and method based on MHA | |
US10908834B2 (en) | Load balancing for scalable storage system | |
US9270613B2 (en) | Cluster-free techniques for enabling a directory protocol-based domain name system (DNS) service for high availability | |
EP3442201B1 (en) | Cloud platform construction method and cloud platform | |
CN106790131B (en) | Parameter modification method and device and distributed platform | |
CN111444157A (en) | Distributed file system and data access method | |
JP5907419B2 (en) | Distributed processing system, distributed processing method, and distributed processing program | |
CN112035064A (en) | Distributed migration method for object storage | |
WO2016073019A1 (en) | Generating a unique identifier for an object in a distributed file system | |
CN107180034A (en) | The group system of MySQL database | |
CN110298031B (en) | Dictionary service system and model version consistency distribution method | |
CN110958293A (en) | File transmission method, system, server and storage medium based on cloud server | |
CN109800388A (en) | A kind of edit methods of JSON data, apparatus and system | |
CN115495432A (en) | Method, device and equipment for supporting multiple instances | |
CN112631727B (en) | Monitoring method and device for pod group pod | |
CN114640678A (en) | Pod management method, device and medium based on SR-IOV | |
CN109947451B (en) | Cluster application file updating method, system, medium and equipment | |
GB2542585A (en) | Task scheduler and task scheduling process |
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 |