CN109101195A - A kind of method, apparatus and readable storage medium storing program for executing of the read-write of memcached company-data - Google Patents
A kind of method, apparatus and readable storage medium storing program for executing of the read-write of memcached company-data Download PDFInfo
- Publication number
- CN109101195A CN109101195A CN201810887848.9A CN201810887848A CN109101195A CN 109101195 A CN109101195 A CN 109101195A CN 201810887848 A CN201810887848 A CN 201810887848A CN 109101195 A CN109101195 A CN 109101195A
- Authority
- CN
- China
- Prior art keywords
- data
- cluster
- node
- memory node
- preset strategy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1458—Management of the backup or restore process
- G06F11/1464—Management of the backup or restore process for networked environments
-
- 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
- G06F3/0614—Improving the reliability of storage systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses the method, apparatus and readable storage medium storing program for executing of a kind of read-write of memcached company-data.The described method includes: the cluster is written in the data based on preset strategy when data are written to the cluster;When reading data to the cluster, the data are read from the cluster based on preset strategy.Using the embodiment of the present invention, by being write data into based on preset strategy or read data from the cluster, there is no the mechanism of any communication, problems difficult in maintenance for the node that can overcome in memcached cluster.
Description
Technical field
The present invention relates to the communication technology, the espespecially a kind of method, apparatus and readable storage of the read-write of memcached company-data
Medium.
Background technique
With the fast development of memory hardware, DRAM price is lower and lower, and more and more applications can put dsc data
Into memory, to improve access speed, the overall performance of system is provided.Memcached is in a key/value distribution
Storage system is deposited, by very extensive application with memory buffers data.Memcached formula memory storage system is mainly deposited using upper
In following problems:
There is no the mechanism of any communication for node in first, memcached cluster, and all about distributed strategy is all
It is to be safeguarded by client, is not substantially real distributed system, client is to access the application journey of memcached
Sequence needs to handle complicated distributed service logic, becomes Fat Client, is not easy to maintenance applications, and cannot be multiplexed,
Result in application development cost;
After second, memcached cluster internal partial node delay machine, not any High Availabitity measure directly affects application
The access of program or client needs handle more complicated task;
Third, the node after delay machine is restored, without any data, are visited because memcached is internal storage data system
When asking the node, empty information will be returned to client.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of method, apparatus of memcached company-data read-write
And readable storage medium storing program for executing, there is no the mechanism of any communication for the node that can overcome in memcached cluster, and difficult in maintenance asks
Topic.
In order to reach the object of the invention, the present invention provides a kind of method of memcached company-data read-write, features
It is, which comprises
When data are written to the cluster, the data are written by the cluster based on preset strategy;
When reading data to the cluster, the data are read from the cluster based on preset strategy.
Further, the preset strategy includes: according to memory node in the key value of the data and the cluster
The number of number acquisition memory node.
Further, the method also includes,
When judging that the corresponding memory node of the number works normally,
It is described that the data are written by the cluster based on preset strategy, comprising: the number is written into the data
Corresponding memory node and backup node;
It is described that the data are read from the cluster based on preset strategy, comprising: from the corresponding storage section of the number
The reading data in point.
Further, the method also includes,
When judging the corresponding memory node delay machine of the number,
It is described that the data are written by the cluster based on preset strategy, comprising: backup node is written into the data;
After the memory node restores, the data backed up in the backup node to the memory node are synchronized to described deposit
Store up node;
It is described that the data are read from the cluster based on preset strategy, comprising: described in backup node reading
Data.
Further, the number according to memory node in the key value of the data and the cluster obtains storage section
The number of point, comprising:
For the key value of the data divided by the number of memory node in the cluster, the remainder of acquisition is the volume of memory node
Number.
In order to reach the object of the invention, the present invention also provides a kind of devices of memcached company-data read-write, special
Sign is that described device includes writing module and read module:
The write module, for the data being written based on preset strategy when data are written to the cluster
The cluster;
The read module, for being read from the cluster based on preset strategy when reading data to the cluster
Take the data.
Further, which is characterized in that
The preset strategy includes: to be obtained according to the number of memory node in the key value of the data and the cluster
The number of memory node.
Further, described device further includes judgment module,
When the judgment module judges that the corresponding memory node of the number works normally,
The write module is based on preset strategy and the cluster is written in the data, comprising: the data are written
It is described to number corresponding memory node and backup node;
The read module is based on preset strategy and reads the data from the cluster, comprising: corresponds to from the number
Memory node in the reading data.
Further, described device further includes,
When the judgment module judges the corresponding memory node delay machine of the number,
The write module is based on preset strategy and the cluster is written in the data, comprising: the data are written
Backup node;It is after the memory node restores, the data backed up in the backup node to the memory node are same
It walks to the memory node;
The read module is based on preset strategy and reads the data from the cluster, comprising: from the backup node
Read the data.
In order to reach the object of the invention, the present invention also provides a kind of computer readable storage mediums, are stored thereon with meter
Calculation machine program, which is characterized in that the step of above method is realized when the program is executed by processor.
Compared with prior art, the present invention includes when data are written to the cluster, and being based on preset strategy will be described
The cluster is written in data;When reading data to the cluster, the number is read from the cluster based on preset strategy
According to.By writing data into based on preset strategy or reading data from the cluster, memcached cluster can be overcome
There is no the mechanism of any communication, problems difficult in maintenance for interior node.
Further, described based on preset tactful by institute when judging the corresponding memory node delay machine of the number
It states data and the cluster is written, comprising: backup node is written into the data, and is marked;When the memory node restores
Afterwards, the data being marked described in the backup node are synchronized to the memory node;It is described based on it is preset strategy from
The cluster reads the data, comprising: and the data are read from the backup node, make memcached delay machine part of nodes,
Nor affect on the use on upper layer.
Further, described based on preset tactful by institute when judging the corresponding memory node delay machine of the number
It states data and the cluster is written, comprising: backup node is written into the data, and is marked;When the memory node restores
Afterwards, the data being marked described in the backup node are synchronized to the memory node, after overcoming the recovery of delay machine node,
When accessing the delay machine node, the problem of empty information will being returned to client.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
Attached drawing is used to provide to further understand technical solution of the present invention, and constitutes part of specification, with this
The embodiment of application technical solution for explaining the present invention together, does not constitute the limitation to technical solution of the present invention.
Fig. 1 is the flow chart for the method that the memcached company-data of the embodiment of the present invention one is read and write;
Fig. 2 is another flow chart for the method that the memcached company-data of the embodiment of the present invention two is read and write;
Fig. 3 is the structural schematic diagram for the device that the memcached company-data of the embodiment of the present invention three is read and write.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention
Embodiment be described in detail.It should be noted that in the absence of conflict, in the embodiment and embodiment in the application
Feature can mutual any combination.
Step shown in the flowchart of the accompanying drawings can be in a computer system such as a set of computer executable instructions
It executes.Also, although logical order is shown in flow charts, and it in some cases, can be to be different from herein suitable
Sequence executes shown or described step.
Embodiment one
A kind of method for present embodiments providing memcached company-data read-write, as shown in Figure 1, this method includes
S11-S12:
S11, when to cluster be written data when, cluster is write data into based on preset strategy;
S12, when to cluster read data when, data are read from cluster based on preset strategy.
In the embodiment of the present invention, by being write data into based on preset strategy or reading data from the cluster,
The node in memcached cluster can be overcome there is no the mechanism of any communication, problem difficult in maintenance can effectively drop
The complexity of low client logic.
In one alternate embodiment, preset strategy includes: of memory node in key value and cluster according to data
Number obtains the number of memory node.
Optionally, the above method further includes, when judging that numbering corresponding memory node works normally, being based on preset
Strategy writes data into cluster, comprising: writes data into the corresponding memory node of number and backup node;Based on preset strategy
Data are read from cluster, comprising: from the reading data numbered in corresponding memory node.
Optionally, the above method further includes, when judging to number corresponding memory node delay machine, being based on preset strategy
Write data into cluster, comprising: write data into backup node;After memory node restores, it will be deposited in backup node to described
The data that storage node is backed up are synchronized to memory node;Data are read from cluster based on preset strategy, comprising: are saved from backup
Point reads data.
Data are written in the form of key/value, and key is an id, and value is specific effective information, for example, one
A authentication information, key are the id of token, and value is then the specifying information of connection.
The number that the memory node is restored in backup database can be navigated to by carrying out hash algorithm according to key
According to.
If one of memcached node delay machine, mproxy goes memcached backup node access evidence.When delaying
After machine node restores, the data that mproxy can back up memcached the node are restored on the memcached node.In order to
It allows mproxy to avoid the problem that single-point, disposes multiple mproxy, then front end is protected using the method for keepalived+haproxy
The High Availabitity for hindering mproxy, to reach the High Availabitity of whole system.
In one alternate embodiment, memory node is obtained according to the number of memory node in the key value and cluster of data
Number, comprising:
For the key value of data divided by the number of memory node in cluster, the remainder of acquisition is the number of memory node.
Application program, that is, client sends key/value data to mproxy, rather than directly transmits memcached section
Point, mproxy calculate hash value divided by taking the remainder after memcached number according to key, and remainder is exactly to need in memcached cluster
Store the serial number of the memcached node of data.Mproxy the data forwarding to corresponding memcached node, meanwhile,
The data forwarding to memcached backup node.
When the corresponding data of client access key, corresponding memcached is positioned by same calculation method and is saved
The data retrieval is returned to client by point, then, mproxy.
In the embodiment of the present invention, when data are written to the cluster, the data are written by institute based on preset strategy
State cluster;When reading data to the cluster, the data are read from the cluster based on preset strategy.Compared to routine
Client be to access the application program of memcached to need to handle complicated distributed service logic, can overcome
There is no the mechanism of any communication, problems difficult in maintenance for node in memcached cluster.
In the embodiment of the present invention, a kind of method of memcached cluster High Availabitity is proposed, client can be effectively reduced
While holding the complexity of logic, memcached cluster is made to have the function of High Availabitity, it is fully transparent to client.Client
Only needing to configure the address ip can be carried out the read-write of caching, even if memcached delay machine part of nodes, nor affects on
The use of layer.
Embodiment two
Above-described embodiment method is specifically described in the present embodiment.
Memcached is a kind of high performance distributed memory target cache system, and there are multiple in memcached system
Memory node;The application increases multiple agent node mproxy between front end and memcached system;Agent node mproxy
It can be managed collectively rear end memcached node, the autosynchronous function of data after backup functionality and the recovery of delay machine node is provided
Energy;Keepalived+haproxy High Availabitity framework is used in the node of front end.
In this example, before memcached cluster high availability method, following dispose need to be carried out:
(1) Partition of role and number;
Partition of role is carried out to the cache node in memcached system, is divided into memory node and backup node;Role draws
/ after, the node in memcached system is numbered;
In this example, as shown in Fig. 2, including three cache nodes in memcached system, enable two of them for storage section
Point, a backup node as memory node;The number of two memory nodes is respectively memcached0 and memcached1,
The number of backup node is memcached_backup;
According to of the factor designs memcached system interior joint such as specific business access amount, performance requirement and budget
It counts, the cache node in memcached system can be three or more, and the number of backup node is at least one;
(2) caching agent node is disposed;
Caching agent node mproxy can be communicated with all memory nodes and backup node, and have memory node
With the ip information of backup node;
In this example, two caching agent nodes, respectively mproxy1 and mproxy2 are disposed, two caching agent nodes
In configuration file, preserve memory node memcached0's and memcached1 and backup node memcached_backup
Ip information;
(3) front end is disposed;
In this example, front end includes three nodes, disposes keepalived and haproxy respectively, and keepalived is that height can
Use software;Haproxy is load balancing software, and the load balancing of interior configuration is leastconn;
After the completion of the deployment of front end, vip is generated on a node wherein, two caching agents are configured to front end
In haproxy, request is preferentially assigned in the lesser caching agent node of load, after the deployment of above-mentioned (1)~(3), basis
Environment configurations are completed.
After the completion of basic environment configuration, data are written to high-availability cluster to distributed memory storage system, comprising:
(1) direct access cache agent node;
Data are sent the caching agent node where vip;
Caching agent node where vip can be realized by keepalived.
(2) memory node that the data should be stored is calculated by caching agent node;
Caching agent node calculates the number for the memory node that the data should be stored according to the key of data, and data are sent out
It is sent to and the corresponding memory node of number is calculated and transmits data to backup node, wherein memory node calculation method are as follows:
Hash (key) %n, n are the number of the memory node configured in caching agent node.
(3) whether the memory node that judgement should store is normal;
In memcached node write-in data procedures into distributed memory storage system, calculated number is corresponded to
Memory node normal operating conditions when, the memory node and backup node is written into the data;
When the memory node delay machine of data to be written, the memory node of the delay machine is labeled as offline, directly standby
Data are written in part node, and the data are marked;After the memory node of delay machine restores, need this in backup node
It should be synchronized on the memory node by the data that the delay machine node saves;
In this example, when starting caching agent node, mark one of them for main caching agent node, master cache agency
Node acts to synchronize.Although the memory node not synchronized may be coupled to, but in unusable state;Together
After the completion of step, another caching agent node, synchronization action is notified to terminate, the node after recovery can be accessed normally.
Include: when reading data from memcached system
Caching agent node calculates the number of the memory node where data, and calculation method should be stored with the data are calculated
Memory node it is identical;Data are read according to the memory node where calculated result from data;
When the memory node delay machine where data, caching agent node is directly read from backup node, is then returned to
Load balancing software haproxy, haproxy are returned again to the application program of front end;
The invention proposes a kind of methods of memcached cluster High Availabitity, when memcached cluster delay machine part of nodes
Afterwards, the normal read and write access of client is not influenced, and node can be with automatically synchronizing data after restoring, all are transparent to client, letter
Change client logic, it is only necessary to configure a vip, while but also with the function of load balancing and High Availabitity.
Embodiment three
A kind of device of memcached company-data read-write is present embodiments provided, is described in above method embodiment
It is applicable in this present embodiment, shown in Fig. 3, which includes writing module 31 and read module 32:
Mould 31 is written, for writing data into cluster based on preset strategy when data are written to cluster;
Read module 32, for reading data from cluster based on preset strategy when reading data to cluster.
In one alternate embodiment, preset strategy includes: of memory node in key value and cluster according to data
Number obtains the number of memory node.
Optionally, above-mentioned apparatus further includes judgment module 33,
When judgment module 33 judges that numbering corresponding memory node works normally,
Writing module 31 is based on preset strategy and writes data into cluster, comprising: writes data into the corresponding storage of number
Node and backup node;
Read module 32 is based on preset strategy and reads data from cluster, comprising: from the corresponding memory node of number
Read data.
Optionally, above-mentioned apparatus further includes,
When judgment module 33 is judged to number corresponding memory node delay machine,
Writing module 31 is based on preset strategy and writes data into cluster, comprising: writes data into backup node;Work as storage
After node restores, the data backed up in backup node to the memory node are synchronized to memory node;
Read module 32 is based on preset strategy and reads data from cluster, comprising: reads data from backup node.
The embodiment of the present invention also provides a kind of computer storage medium, and the computer storage medium is stored with computer journey
Sequence;After the computer program is performed, the side of the memcached company-data read-write of previous embodiment offer can be realized
Method, for example, executing method as shown in Figure 1.
Although disclosed herein embodiment it is as above, the content only for ease of understanding the present invention and use
Embodiment is not intended to limit the invention.Technical staff in any fields of the present invention is taken off not departing from the present invention
Under the premise of the spirit and scope of dew, any modification and variation, but the present invention can be carried out in the form and details of implementation
Scope of patent protection, still should be subject to the scope of the claims as defined in the appended claims.
Claims (10)
1. a kind of method of memcached company-data read-write, which is characterized in that the described method includes:
When data are written to the cluster, the data are written by the cluster based on preset strategy;
When reading data to the cluster, the data are read from the cluster based on preset strategy.
2. the method according to claim 1, wherein
The preset strategy includes: to be obtained according to the number of memory node in the key/value value of the data and the cluster
Take the number of memory node.
3. according to the method described in claim 2, it is characterized in that, the method also includes,
When judging that the corresponding memory node of the number works normally,
It is described that the data are written by the cluster based on preset strategy, comprising: the number is written into the data and is corresponded to
Memory node and backup node;
It is described that the data are read from the cluster based on preset strategy, comprising: from the corresponding memory node of the number
The reading data.
4. according to the method described in claim 2, it is characterized in that, the method also includes,
When judging the corresponding memory node delay machine of the number,
It is described that the data are written by the cluster based on preset strategy, comprising: backup node is written into the data;Work as institute
After stating memory node recovery, the data backed up in the backup node to the memory node are synchronized to the storage and are saved
Point;
It is described that the data are read from the cluster based on preset strategy, comprising: to read the data from the backup node.
5. according to the method described in claim 2, it is characterized in that, the key/value value according to the data and described
The number of memory node obtains the number of memory node in cluster, comprising:
For the key value of the data divided by the number of memory node in the cluster, the remainder of acquisition is the number of memory node.
6. a kind of device of memcached company-data read-write, which is characterized in that described device includes writing module and reading mould
Block:
The write module, for when to the cluster be written data when, based on it is preset strategy will the data write-in described in
Cluster;
The read module, for reading institute from the cluster based on preset strategy when reading data to the cluster
State data.
7. device according to claim 6, which is characterized in that
The preset strategy includes: to obtain storage according to the number of memory node in the key value of the data and the cluster
The number of node.
8. device according to claim 7, which is characterized in that described device further includes judgment module,
When the judgment module judges that the corresponding memory node of the number works normally,
The write module is based on preset strategy and the cluster is written in the data, comprising: will be described in data write-in
Number corresponding memory node and backup node;
The read module is based on preset strategy and reads the data from the cluster, comprising: deposits from the number is corresponding
Store up the reading data in node.
9. device according to claim 7, which is characterized in that described device further includes judgment module,
When the judgment module judges the corresponding memory node delay machine of the number,
The write module is based on preset strategy and the cluster is written in the data, comprising: the data are written and back up
Node;After the memory node restores, the data backed up in the backup node to the memory node are synchronized to
The memory node;
The read module is based on preset strategy and reads the data from the cluster, comprising: reads from the backup node
The data.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of any one of claim 1-5 the method is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810887848.9A CN109101195A (en) | 2018-08-07 | 2018-08-07 | A kind of method, apparatus and readable storage medium storing program for executing of the read-write of memcached company-data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810887848.9A CN109101195A (en) | 2018-08-07 | 2018-08-07 | A kind of method, apparatus and readable storage medium storing program for executing of the read-write of memcached company-data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109101195A true CN109101195A (en) | 2018-12-28 |
Family
ID=64848990
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810887848.9A Pending CN109101195A (en) | 2018-08-07 | 2018-08-07 | A kind of method, apparatus and readable storage medium storing program for executing of the read-write of memcached company-data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109101195A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109769028A (en) * | 2019-01-25 | 2019-05-17 | 深圳前海微众银行股份有限公司 | Redis cluster management method, device, equipment and readable storage medium storing program for executing |
CN111241437A (en) * | 2020-01-06 | 2020-06-05 | 广州虎牙科技有限公司 | Data processing method, device, server and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102968310A (en) * | 2012-12-05 | 2013-03-13 | 武汉烽火普天信息技术有限公司 | Integrated high-performance application software architecture and construction method thereof |
CN107346307A (en) * | 2016-05-04 | 2017-11-14 | 北京京东尚科信息技术有限公司 | Distributed cache system and method |
CN107749887A (en) * | 2017-10-25 | 2018-03-02 | 暴风集团股份有限公司 | A kind of CDN resource allocations, localization method and device and CDN system |
-
2018
- 2018-08-07 CN CN201810887848.9A patent/CN109101195A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102968310A (en) * | 2012-12-05 | 2013-03-13 | 武汉烽火普天信息技术有限公司 | Integrated high-performance application software architecture and construction method thereof |
CN107346307A (en) * | 2016-05-04 | 2017-11-14 | 北京京东尚科信息技术有限公司 | Distributed cache system and method |
CN107749887A (en) * | 2017-10-25 | 2018-03-02 | 暴风集团股份有限公司 | A kind of CDN resource allocations, localization method and device and CDN system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109769028A (en) * | 2019-01-25 | 2019-05-17 | 深圳前海微众银行股份有限公司 | Redis cluster management method, device, equipment and readable storage medium storing program for executing |
CN111241437A (en) * | 2020-01-06 | 2020-06-05 | 广州虎牙科技有限公司 | Data processing method, device, server and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7480654B2 (en) | Achieving cache consistency while allowing concurrent changes to metadata | |
US10747745B2 (en) | Transaction execution commitment without updating of data row transaction status | |
CN105190622B (en) | Quick collapse for distributed data base system restores | |
CN100583050C (en) | Method for protecting and recovering continuous data based on time stamp diary memory | |
CN102831156B (en) | Distributed transaction processing method on cloud computing platform | |
KR100978156B1 (en) | Method, apparatus, system and computer readable recording medium for line swapping scheme to reduce back invalidations in a snoop filter | |
CN106055431A (en) | Data backup and recovery method and data backup and recovery device based on snapshot online rollback | |
CN108076090A (en) | Data processing method and storage management system | |
CN104281506A (en) | Data maintenance method and system for file system | |
CN102955845A (en) | Data access method and device as well as distributed database system | |
CN105701219B (en) | A kind of implementation method of distributed caching | |
CN104965850A (en) | Database high-available implementation method based on open source technology | |
CN105843702A (en) | Method and device for data backup | |
CN103986779B (en) | A kind of application data transmission method, device and terminal device | |
CN103138912A (en) | Data synchronizing method and data synchronizing system | |
EP3178022A1 (en) | Data storage upon database failure | |
CN107368583A (en) | A kind of method and system of more cluster information inquiries | |
CN106933494A (en) | Mix the operating method and device of storage device | |
CN109101195A (en) | A kind of method, apparatus and readable storage medium storing program for executing of the read-write of memcached company-data | |
US11687533B2 (en) | Centralized storage for search servers | |
CN101126998A (en) | Assembling type computer system high speed cache data backup processing method and system | |
CN108762982A (en) | A kind of database restoring method, apparatus and system | |
CN101458655A (en) | Internal memory management method, system and internal memory control device | |
CN104484136B (en) | A kind of method of sustainable high concurrent internal storage data | |
CN102004773A (en) | Data read-write processing method and web application server |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181228 |