CN103036717A - Consistency maintenance system and methods for distributed-type data - Google Patents
Consistency maintenance system and methods for distributed-type data Download PDFInfo
- Publication number
- CN103036717A CN103036717A CN2012105353763A CN201210535376A CN103036717A CN 103036717 A CN103036717 A CN 103036717A CN 2012105353763 A CN2012105353763 A CN 2012105353763A CN 201210535376 A CN201210535376 A CN 201210535376A CN 103036717 A CN103036717 A CN 103036717A
- Authority
- CN
- China
- Prior art keywords
- data
- maintenance
- node
- message
- lock
- 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.)
- Granted
Links
Images
Abstract
Provided is a consistency maintenance system and methods for distributed-type data in a distributed-type cluster system. The consistency maintenance system and methods for distributed-type data is composed of a cluster management node, a global lock management node and a plurality of data maintenance nodes which are scattered in the system, wherein the data maintenance nodes are the isomorphic nodes suitable for storing one or more data replicas. The data maintenance nodes are provided with three modules of monitoring events, maintaining data consistency and sending events. The global lock management node is responsible for storing and managing update locks of all the data in a system, and storing all information of the data maintenance nodes. The global lock management node is provided with three modules of receiving and sending massage, the update locks requesting queue, and the information management for data maintenance nodes. The cluster management node is responsible for managing the latest information of all the nodes in the system, and testing the state of each node in the system periodically. The consistency maintenance system and methods for distributed-type data have the advantages of being reliable and flexible in work methods. Besides, a client can develop a data update towards a plurality of targets at the same time. The consistency maintenance system and methods for distributed-type data have a simple operation, a less communication overhead, a short updating time delay, and a promising application prospects.
Description
Technical field
The present invention relates to a kind of consistency maintenance system and method for distributed data, belong to the technical field of computer.
Background technology
Distributed system is in the system that is carried out the distributed treatment task by the multiprocessor architecture of interconnection of telecommunication network.Because the every piece of data in the distributed cluster system all is stored in a plurality of nodes in the distributed type assemblies, when the data on certain clustered node wherein are updated, how to realize with guarantee this group system in all the other nodes on data trnascription also can carry out identical renewal operation be a focus paying close attention to of scientific and technical personnel in the industry so that all copies of each data in the whole group system all guarantee consistent problem.
The prior art that solves the distributed data coherence method mainly contains following five kinds, but there are respectively different shortcomings in it.The below introduces respectively it:
Main update method: when having many piece of data copy of data in the system, setting one of them data is master data.During each the renewal, first master data is upgraded; After master data was updated successfully, updating message sent to other data trnascription from master data, so that data trnascription also carries out same renewal operation.Its shortcoming is: updating message must send to all back end within the short as far as possible time, if can not be sent completely at short notice, system will produce out-of-date data; And in case the node at master data place breaks down, the data trnascription node can not obtain updating message.
The mirror image update method: the method is not considered the data trnascription of each data, only considers each master data and the mirror image that is defined on the master data, when upgrading master data, refreshes simultaneously the mirror image that is defined on the master data.Its shortcoming is: mirror image data is read-only and can not write, and has certain restriction.
Lazy update method: the method is that the renewal operation of data is not to carry out at once, but only has when data are accessed, just carries out and upgrades operation.Its defective is the time delay that has increased the client-access data, and especially when a plurality of Concurrency Access carried out simultaneously, time delay was more obvious, and, be easy to cause deadlock.
The message queue method: the method is that all renewal operation informations all leave in the message queue, and by nodes sharing all in the system, the message in this message queue is processed according to the principle of first in first out.Because the message in the message queue is processed according to first in first out, and the limited length system of message queue, when packet many when concurrent updating message and message is larger, easily cause overflowing of message queue, cause losing of updating message.
Affairs control method: affairs refer to a series of atomic operation, and data communication device is crossed this a series of atomic operation of execution, transfers to another coherency state from a coherency state.The shortcoming of this method is: when affairs occuring upgrading unsuccessfully, can cause that affairs restart the increasing of frequency, and, when local matter and global transaction are carried out simultaneously, be easy to cause Data Update inconsistent.
In a word, in data updating process, the node failure that the above-mentioned data consistency update method of prior art may occur and network service fault aspect all exist imperfection local.Therefore, in the industry scientific and technical personnel also in the solution of seeking diligently to be correlated with.
Summary of the invention
In view of this, the consistency maintenance system and method that the purpose of this invention is to provide a kind of distributed data, the present invention is used under the distributed network environment, realize the consistency maintenance of distributed data, and can effectively reduce cost on network communication, improve reliability, high efficiency and availability that distributed data is upgraded.
In order to achieve the above object, the invention provides the consistency maintenance system of distributed data in a kind of distributed cluster system, it is characterized in that, this system is comprised of cluster management node, global lock management node and a plurality of data maintenance node, wherein:
A plurality of data maintenance nodes, be arranged in dispersedly distributed cluster system, each data maintenance node is can receive the Data Update request of client and have the same treatment function and uniquely identified isomorphism node separately, each data maintenance node stores the copy of one or more data, each data is with mutually different unique identification and different editions number, but the unique identification of all copies of same data is all identical, and after each Data Update success, version number is corresponding change also; Be provided with action listener, data consistency maintenance and event and send totally three modules;
The global lock management node is responsible for the renewal of all data in the store and management system and is locked, and all data maintenance nodal informations in the storage system, is used for the broadcast data updating message; The node that also will contain the identical data copy belongs to same group, and each data maintenance node can belong to a plurality of groups; Global lock management node receive data upgrades the lock request message, and after the renewal of data lock is applied for successfully, transfer of data in the distributed cluster system between each data maintenance node and without the global lock management node, in order to reduce its communications burden and Reduction of failure probability of occurrence, improve system reliability; When the data maintenance node needs more new data, first to the renewal lock of this target data of global lock management node application; If the renewal of this target data lock is temporarily unavailable, then corresponding renewal lock request queue is put in the renewal lock request of this target data, until this updating target data lock is available; Be provided with the message sink that is linked in sequence and sending module, renewal lock request queue, data maintenance nodal information administration module totally three parts;
The cluster management node is in charge of the information that all nodes in the system comprise the data of its IP address, listening port number, running status and storage, and the up-to-date information of each node is provided for the data maintenance nodal information administration module in the global lock management node; Be responsible for the running status of each data maintenance node in the cycle detecting system, and the storage data maintenance nodal information that is in normal operating condition and can reaches, and deletion is in abnormal operating condition, inaccessible data maintenance nodal information, guarantee only to store the data maintenance nodal information that can reach in the cluster management node, unreachable node does not participate in the maintenance update of data consistency.
The renewal lock of described data is used for limiting the access to data: if the data maintenance node will upgrade certain data, at first must obtain to the application of global lock management node the renewal lock of this target data, after successfully obtaining the updating target data lock, this target data just no longer receives the read-write requests of client, until the renewal of this target data lock is released; If the renewal of this target data lock temporarily can not be used, then the update request of this target data is placed in the corresponding renewal lock request queue, until this updating target data lock can use.
In order to achieve the above object, the present invention also provides the method for work of the consistency maintenance system of distributed data in a kind of distributed cluster system, it is characterized in that: described method comprises following operating procedure:
(1) the interim host node of initiate the data maintenance node of Data Update request, namely only managing the Data Update request of self initiating sends first the Data Update lock request message of the uniqueness sign that comprises the target data that its node uniqueness sign and expectation upgrade to the global lock management node; At this moment, interim host node does not upgrade target data, and the state to be updated such as is in;
(2) message sink in the global lock management node and sending module receive this Data Update lock request message, judge the update request that whether comprises a plurality of target datas in this message; If then this message is divided into separately independently a plurality of Data Update request messages, and puts into respectively the renewal lock request queue of corresponding data; If not, then this message is directly sent in the renewal lock request queue of target data; The message of upgrading in the lock request queue is to send to data maintenance nodal information administration module according to the first-in first-out mode;
(3) after data maintenance nodal information administration module receives this message, search out first the data maintenance node group that contains target data, and to the group in this Data Update request message of data maintenance node broadcasts; Simultaneously, the time window initial value of receipt message is set also, prepares in the time window of this setting, receive the affirmation message whether data that the Maintenance Point that contains target data sends are updated successfully;
(4) after other data maintenance nodes that contain target data receive this Data Update request message, resolve and carry out the updating target data operation in this message: if deletion action, then directly delete the corresponding data in the target data, and increase the version number of these data; If rolling back action, the then directly the last renewal of carrying out of rollback target data, and the version number of minimizing data; If increase or retouching operation, then the data maintenance node first from interim host node obtain new suffix according to content after, just upgrade target data, increase simultaneously the version number of data;
(5) contain the updating target data success of other data maintenance nodes of target data after, send the acknowledge message that is updated successfully of the version number that comprises after this updating target data success to the global lock management node;
(6) the data maintenance nodal information administration module in the global lock management node resends the Data Update request to upgrading failed data maintenance node, until just receive when being updated successfully acknowledge message with interior in the maximum of sending times, judge whether again to receive and remove beyond the interim host node, all contain the affirmation message of the Data Update success that other data maintenance nodes of target data send, in order to take corresponding different post-treatment operations;
(7) in distributed cluster system, after data maintenance nodal information administration module is finished all operations were of a Data Update, the time window value of its receipt message is adjusted, to adapt to the variation of network environment.
The consistency maintenance system and method for distributed data of the present invention have a following multiple advantages:
Data maintenance node in the distributed node group system of the present invention all is isomorphism and equity, does not have permanent host node.When the data maintenance node of initiating the renewal operation breaks down, can select in this cluster other data maintenance nodes that comprise identical data again to initiate the Data Update operation requests, functional reliability and the flexibility of system have so just been improved, in addition, data consistency provided by the invention is strong consistency.And client can be initiated the Data Update operation simultaneously to a plurality of target datas.In data updating process, introduce the version number of data, the unnecessary operation overhead that brings to reduce network failure.
In addition, the data maintenance node of initiating the Data Update operation among the present invention is in the end just executing data renewal operation of stage, this strategy can be in the situation that the failure of data maintenance node generation Data Update, reduce the data maintenance node of this initiation Data Update operation and carry out the rolling back action expense, also shortened the time of implementation of data consistency renewal process.
In a word, the present invention had both combined the reliability that distributed computing technology embodies, and (data that are embodied in the data cluster are distributed in a plurality of data maintenance nodes, and the data maintenance node all is isomorphisms), combine again the high efficiency of centralized management and availability (being embodied in the renewal lock of all data in the global lock management node management cluster).Therefore, application prospect of the present invention is good.
Description of drawings
Fig. 1 is that the general structure of distributed data consistency maintenance of the present invention system forms schematic diagram.
Fig. 2 is that the data maintenance intra-node structure in the system of the present invention forms schematic diagram.
Fig. 3 is the global lock management node internal structure schematic diagram in the system of the present invention.
Fig. 4 is the consistency maintenance system works method distributed data consistency maintenance sequential schematic diagram under normal circumstances of distributed data of the present invention.
Fig. 5 is the distributed data consistency maintenance sequential schematic diagram of consistency maintenance system works method when the failure of data maintenance node updates of distributed data of the present invention.
Fig. 6 is distributed data consistency maintenance sequential schematic diagram in the inventive method HP M situation.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, the present invention is described in further detail below in conjunction with accompanying drawing.
The application scenarios of the consistency maintenance system and method for distributed data of the present invention is:
When client is initiated to comprise the Data Update request of increase, deletion or modification to certain the data maintenance node in the system of the present invention, this data maintenance node at first sends to the global lock management node with this Data Update request, and the global lock management node is transmitted to this Data Update request again removes the node of initiating update request every other data maintenance node in addition, that comprise this target data; After the data on other data maintenance nodes all are updated successfully, initiate the data maintenance node of update request and just this target data is carried out the renewal operation; Then, return the affirmation message that updating target data is finished for again the client of initiating the Data Update request.If the updating target data failure, then all data maintenance nodes are all abandoned this Data Update, and all data in the assurance system under any circumstance all are consistent.
Referring to Fig. 1, the structure of introducing distributed data consistency maintenance of the present invention system forms: formed by cluster management node, global lock management node and a plurality of data maintenance node, wherein:
A plurality of data maintenance nodes: be arranged in dispersedly distributed cluster system, each data maintenance node is can receive the Data Update request of client and have the same treatment function and uniquely identified isomorphism node separately, each data maintenance node stores the copy of one or more data, each data is with mutually different unique identification and different editions number, but the unique identification of all copies of same data is all identical, after each Data Update success, version number is corresponding change also; Be provided with action listener, data consistency maintenance and event and send totally three modules (referring to Fig. 2).The function of these modules is:
Action listener module: be used for to monitor client and send to Data Update request message on this data maintenance node or other node of system and send to Data Update request message and/or data rewind operation information on this data maintenance node, and a transfer of messages that receives is processed to the data consistency maintenance module.Data rewind is to cancel the last Data Update operation of carrying out.
Data consistency maintenance module: be used for to be kept at first in the client data update inquiry information formation of this data consistency maintenance module from the Data Update request message that client sends, in order to process message in this formation according to first in first out, send Data Update lock request message to the event sending module simultaneously; And for the Data Update request message from other nodes that receives, then directly upgrade the target data in this message; The Data Update operation comprises: the increase of data content, deletion, modification or data rewind; After each Data Update success or after the rolling back action success, the version number that should change simultaneously these data, and being updated successfully or failed affirmation message, rolling back action is successful or failed affirmation message sends to the event sending module.
The event sending module: successful or failed affirmation message, rolling back action success or failed affirmation message or the Data Update lock request message of Data Update that is used for receiving sends to the global lock management node.
The global lock management node: be responsible for the renewal lock of all data in the store and management system, and all data maintenance nodal informations in the storage system, be used for the broadcast data updating message; The node that also will contain the identical data copy belongs to same group, and each data maintenance node can belong to a plurality of groups; Global lock management node receive data upgrades the lock request message, and after the renewal of data lock is applied for successfully, transfer of data in the distributed cluster system between each data maintenance node and without the global lock management node, in order to reduce its communications burden and Reduction of failure probability of occurrence, improve system reliability.When the data maintenance node carries out Data Update, lock to the renewal of this target data of global lock management node application first; If the renewal of this target data lock is temporarily unavailable, then corresponding renewal lock request queue is put in the renewal lock request of this target data, until this updating target data lock is available.Be provided with the message sink that is linked in sequence and sending module, renewal lock request queue, data maintenance nodal information administration module totally three parts (referring to Fig. 3), the function of these three modules is respectively:.
Message sink and sending module: the Data Update request message of being responsible for the one or more data of renewal of receive data Maintenance Point transmission, when if update inquiry information comprises the update request of a plurality of data, after then message sink and sending module will be divided into Data Update request independent of each other to the update request of a plurality of target datas that comprise in this message, send to respectively in the renewal lock request queue of corresponding data, so that the update request of each target data is processed respectively separately concurrently, upgrade simultaneously to support a plurality of target datas.This module also receives upgrades the affirmation message whether Data Update that lock request queue sends is finished, and this acknowledge message is transmitted to the data maintenance node of initiating the Data Update request, this data maintenance node feeds back to client to this acknowledge message again, so that client judges according to its affirmation message that receives whether Data Update is successful.
Upgrade lock request queue: be in charge of the renewal lock request message of all data in this system, and according to the message in the principle sequential processes formation of first in first out; Be provided with a plurality of respectively Data Update lock request queues corresponding with the different pieces of information in the system, in order to can send to the message in this formation data maintenance nodal information administration module, and releasing request message is locked in the renewal that receive data Maintenance Point information management module returns, can process the next lock request message that upgrades so that upgrade lock request queue, and after finishing processing, send the affirmation message whether Data Update is finished to the message delivery and reception module.
Data maintenance nodal information administration module: be responsible for a plurality of data maintenance nodes that disperse are divided into different node groups, each node group contains a identical data at least, and is in charge of and comprises: the IP address of each node, listening port number and whether be in each node group information of normal operating condition.Be provided with the time window of receipt message, and adjust in real time this time window size according to the variation of network environment.Be responsible for the Data Update information broadcast to all data maintenance nodes that contain this data trnascription in the system, and the Data Update of receive data Maintenance Point feedback or rolling back action successful affirmation message whether; If this acknowledge message does not arrive, then abandon waiting for this acknowledge message in time window is set duration.Also obtain the latest state information of the data trnascription of the running status of port numbers that all data maintenance nodes this system comprise IP address, the monitoring of node, node and storage thereof according to setting-up time from the cluster management node; And according to the synchronous relevant information of himself storing of all data maintenance node up-to-date informations of storing on the cluster management node, so that distributed system is when carrying out the consistent data maintenance update, minimizing unsuccessfully causes the rolling back action expense of the data maintenance node that is updated successfully because of inaccessible data maintenance node updates, thereby improves reliability and high efficiency that data consistency is safeguarded.Data maintenance nodal information administration module also arranges the maximum of Data Update request repeat number of times and the maximum of data rewind operation requests sending times.
Cluster management node: be in charge of the information that all nodes in the system comprise the data of its IP address, listening port number, running status and storage, and the up-to-date information of each node is provided for the data maintenance nodal information administration module in the global lock management node.Be responsible for the running status of each data maintenance node in the cycle detecting system, and the storage data maintenance nodal information that is in normal operating condition and can reaches, and deletion is in abnormal operating condition, inaccessible data maintenance nodal information, guarantee only to store the data maintenance nodal information that can reach in the cluster management node, unreachable node does not participate in the maintenance update of data consistency.
Referring to Fig. 4 ~ Fig. 6, introduce the method for work of the consistency maintenance system of distributed data in the distributed cluster system of the present invention, for convenience of description, the data maintenance node of initiating the Data Update request is called interim host node, interim host node is only managed the Data Update request of self initiating.The method comprises following operating procedure:
Step 1, the data maintenance node (interim host node) of initiating the Data Update request sends the uniquely identified Data Update lock request message of the target data that comprises its node self unique identification and expect to upgrade to the global lock management node; At this moment, interim host node does not upgrade target data, and the state to be updated such as is in.
Step 2, the message sink in the global lock management node and sending module receive this Data Update lock request message, judge the update request that whether comprises a plurality of target datas in this message; If then this message is divided into separately independently a plurality of Data Update request messages, and puts into respectively the renewal lock request queue of corresponding data; If not, then this message is directly sent in the renewal lock request queue of target data.The message of upgrading in the lock request queue is to send to data maintenance nodal information administration module according to the first-in first-out mode.
Step 3 after data maintenance nodal information administration module receives this message, searches out first the data maintenance node group that contains target data, and to the group in this Data Update request message of data maintenance node broadcasts; Simultaneously, the time window initial value of receipt message is set also, prepares in the time window of this setting, receive the affirmation message whether data that the Maintenance Point that contains target data sends are updated successfully.
Step 4, after other data maintenance nodes that contain target data receive this Data Update request message, resolve and carry out the updating target data operation in this message: if deletion action is then directly deleted the corresponding data in the target data, and increase the version number of these data; If rolling back action, the then directly the last renewal of carrying out of rollback target data, and the version number of minimizing data; If increase or retouching operation, then the data maintenance node first from interim host node obtain new suffix according to content after, just upgrade target data, increase simultaneously the version number of data.
Step 5, contain the updating target data success of other data maintenance nodes of target data after, send the acknowledge message that is updated successfully of the version number that comprises after this updating target data success to the global lock management node.
Step 6, data maintenance nodal information administration module in the global lock management node judges whether to receive to be removed beyond the interim host node, all contain the affirmation message of the Data Update success that other data maintenance nodes of target data send, in order to take corresponding different following post-treatment operations:
Referring to Fig. 4, introduce the sequential of Method of data consistency maintenance operating process under normal circumstances first.So-called normal condition is that the network service between each data maintenance node is not broken down in the distributed system, and each data maintenance node self is also working properly, any fault do not occur.Its operating procedure is:
(61) data maintenance nodal information administration module sends the affirmation message of updating target data success to interim host node, after interim host node receives this acknowledge message, take out the team's message in the formation of client data update inquiry information, according to this team message the target data on himself node is upgraded accordingly operation and increased its version number, simultaneously respectively to the affirmation message of data maintenance nodal information administration module and its updating target data success of client feedback.
(62) after data maintenance nodal information administration module receives the affirmation message that is updated successfully of interim host node transmission, to the renewal lock request queue transmission updating target data lock releasing request message of target data; So that upgrade the renewal lock that lock request queue discharges target data, for the renewal lock request use of next data.
If in the step (6), when data maintenance nodal information administration module does not receive the affirmation message of the Data Update success that all other data maintenance nodes that contain target data send, (concrete condition is: the network connection between the failure of data maintenance node updates, the data maintenance node breaks down following three kinds of abnormal conditions namely to occur, and the network connection fault exists simultaneously between the failure of data maintenance node updates and the data maintenance node) time, the treatment step of execution is as described below:
(6A) data maintenance nodal information administration module reset receive that the data maintenance node contain target data sends be updated successfully acknowledge message time window size and the maximum times that again sends the Data Update request to upgrading failed data maintenance node; Then, to there not being to send the update inquiry information that the data maintenance node that is updated successfully acknowledge message sends target data again.
After (6B) the data maintenance node receives this update inquiry information again, first relatively the version number of its target data whether with this message in versions of data number identical, if both are identical, then directly send the affirmation message that is updated successfully to data maintenance nodal information administration module; Otherwise, again upgrade target data and be updated successfully acknowledge message to the transmission of data maintenance nodal information administration module.
(6C) data maintenance nodal information administration module to upgrade failed data maintenance node in the sending times maximum of its setting with the interior Data Update request that resends, and all in the time window of setting, just receive all and once upgraded the acknowledge message that is updated successfully that failed data maintenance node returns, then carry out respective handling according to step (61) and (62) and operate; Otherwise, data maintenance nodal information administration module sends target data rolling back action message to having sent the data maintenance node that is updated successfully acknowledge message, so that this data maintenance node is after receiving this rolling back action message, cancel the last executed renewal operation of target data, and feed back the affirmation message whether rolling back action is finished; After this, data maintenance nodal information administration module is finished the data maintenance node of acknowledge message to not sending rolling back action, in the maximum number of retransmissions of setting with the interior rollback operation information that again sends; At last, data maintenance nodal information administration module sends the affirmation message of updating target data failure to interim host node.
After (6D) interim host node receives the affirmation message of renewal failure of target data, directly abandon the team's message in the formation of client data update inquiry information, the while sends respectively the affirmation message of updating target data failure to data maintenance nodal information administration module and client.
After (6E) data maintenance nodal information administration module receives the affirmation message of the updating target data failure that interim host node sends, renewal lock request queue to target data sends renewal lock releasing request message, so that upgrade the renewal lock that lock request queue discharges target data, in order to being transferred to the next lock request message that upgrades, it uses; After client arrived and upgrades failed affirmation message, other data maintenance node that contains target data was initiated update inquiry information again in the selection cluster, perhaps stops this Data Update solicit operation.
Referring to Fig. 5, when introducing the failure of data maintenance node updates, the time sequential routine that data consistency is safeguarded schemes again.The data maintenance node updates refers to that unsuccessfully factor data Maintenance Point faults itself causes the operation failure of Data Update, the data consistency renewal process of this moment and the difference of consistent update process under normal circumstances are: when data maintenance nodal information administration module do not receive all data maintenance nodes be updated successfully message the time, just to the data maintenance node of transmission Data Update failure again broadcast data update inquiry information.
Referring to Fig. 6, when introducing HP M, the time sequential routine of Method of data consistency maintenance figure:
HP M refers to the network connection interruption between the node, refers to that perhaps the message transmission time delay that network congestion causes strengthens, and causes message not arrive in setting-up time, thereby causes message to be dropped.Both differences of the data consistency maintenance process when the data consistency maintenance process during HP M and the failure of above-mentioned data maintenance node updates are: when the data maintenance node receives the Data Update request message again, not to re-execute the Data Update operation at once, but the version number that checks first target data whether with successfully upgrade after versions of data number consistent, if so, then directly send the affirmation message that is updated successfully; If not, just re-execute the renewal operation of data.
When if the failure of data maintenance node updates exists simultaneously with network failure, data consistency attended operation of the present invention is the processing mode under comprehensive above-mentioned two kinds of abnormal conditions, and this situation also is the mode that the inventive method is often used in implementation data consistency maintenance renewal process.Because it unsuccessfully is by which kind of situation to be caused that Data Update can't be judged by system itself.
Step 7 in distributed cluster system, after data maintenance nodal information administration module is finished all operations were of a Data Update, is adjusted the time window value of its receipt message, to adapt to the variation of network environment.
Claims (8)
1. the consistency maintenance system of distributed data in the distributed cluster system is characterized in that, this system is comprised of cluster management node, global lock management node and a plurality of data maintenance node, wherein:
A plurality of data maintenance nodes, be arranged in dispersedly distributed cluster system, each data maintenance node is can receive the Data Update request of client and have the same treatment function and uniquely identified isomorphism node separately, each data maintenance node stores the copy of one or more data, each data is with mutually different unique identification and different editions number, but the unique identification of all copies of same data is all identical, and after each Data Update success, version number is corresponding change also; Be provided with action listener, data consistency maintenance and event and send totally three modules;
The global lock management node is responsible for the renewal of all data in the store and management system and is locked, and all data maintenance nodal informations in the storage system, is used for the broadcast data updating message; The node that also will contain the identical data copy belongs to same group, and each data maintenance node can belong to a plurality of groups; Global lock management node receive data upgrades the lock request message, and after the renewal of data lock is applied for successfully, transfer of data in the distributed cluster system between each data maintenance node and without the global lock management node, in order to reduce its communications burden and Reduction of failure probability of occurrence, improve system reliability; When the data maintenance node needs more new data, first to the renewal lock of this target data of global lock management node application; If the renewal of this target data lock is temporarily unavailable, then corresponding renewal lock request queue is put in the renewal lock request of this target data, until this updating target data lock is available; Be provided with the message sink that is linked in sequence and sending module, renewal lock request queue, data maintenance nodal information administration module totally three parts;
The cluster management node is in charge of the information that all nodes in the system comprise the data of its IP address, listening port number, running status and storage, and the up-to-date information of each node is provided for the data maintenance nodal information administration module in the global lock management node; Be responsible for the running status of each data maintenance node in the cycle detecting system, and the storage data maintenance nodal information that is in normal operating condition and can reaches, and deletion is in abnormal operating condition, inaccessible data maintenance nodal information, guarantee only to store the data maintenance nodal information that can reach in the cluster management node, unreachable node does not participate in the maintenance update of data consistency.
2. maintenance system according to claim 1, it is characterized in that: the application scenarios of described system is: when client is initiated to comprise the Data Update request of increase, deletion or modification to certain the data maintenance node in this system, described data maintenance node at first sends to the global lock management node with this Data Update request, and the global lock management node is transmitted to this Data Update request again removes the node of initiating update request every other data maintenance node in addition, that comprise this target data; After the data on other data maintenance nodes all are updated successfully, initiate the data maintenance node of update request and just this target data is carried out the renewal operation; Then, return the affirmation message that updating target data is finished for again the client of initiating the Data Update request; If the updating target data failure, then all data maintenance nodes are all abandoned this Data Update, and all data in the assurance system under any circumstance all are consistent.
3. maintenance system according to claim 1, it is characterized in that: the renewal lock of described data is used for limiting the access to data: if the data maintenance node will upgrade certain data, at first must obtain to the application of global lock management node the renewal lock of this target data, after successfully obtaining the updating target data lock, this target data just no longer receives the read-write requests of client, until the renewal of this target data lock is released; If the renewal of this target data lock temporarily can not be used, then the update request of this target data is placed in the corresponding renewal lock request queue, until this updating target data lock can use.
4. maintenance system according to claim 1, it is characterized in that: the function of the modules in the described data maintenance node is as follows:
The action listener module be used for to be monitored client and is sent to Data Update request message on this data maintenance node or other node of system and send to Data Update request message and/or data rewind operation information on this data maintenance node; And a transfer of messages that receives is processed to the data consistency maintenance module; Described data rewind is to cancel the last Data Update operation of carrying out;
The data consistency maintenance module, be used for to be kept at first in the client data update inquiry information formation of this data consistency maintenance module from the Data Update request message that client sends, in order to process message in this formation according to first in first out, send Data Update lock request message to the event sending module simultaneously; And for the Data Update request message from other nodes that receives, then directly upgrade the target data in this message; The Data Update operation comprises: the increase of data content, deletion, modification or data rewind; After each Data Update success or after the rolling back action success, the version number that should change simultaneously these data, and being updated successfully or failed affirmation message, rolling back action is successful or failed affirmation message sends to the event sending module;
The event sending module, successful or failed affirmation message, rolling back action success or failed affirmation message or the Data Update lock request message of Data Update that is used for receiving sends to the global lock management node.
5. maintenance system according to claim 1, it is characterized in that: the function of modules is as follows in the described global lock management node:
Message sink and sending module, be responsible for the Data Update request message of the one or more data of renewal of receive data Maintenance Point transmission, when if update inquiry information comprises the update request of a plurality of data, after then message sink and sending module will be divided into Data Update request independent of each other to the update request of a plurality of target datas that comprise in this message, send to respectively in the renewal lock request queue of corresponding data, so that the update request of each target data is processed respectively concurrently separately, upgrade simultaneously to support a plurality of target datas; This module also receives upgrades the affirmation message whether Data Update that lock request queue sends is finished, and this acknowledge message is transmitted to the data maintenance node of initiating the Data Update request, this data maintenance node feeds back to client to this acknowledge message again, so that client judges according to its affirmation message that receives whether Data Update is successful;
Upgrade lock request queue, be in charge of the renewal lock request message of all data in this system, and according to the message in the principle sequential processes formation of first in first out; Be provided with a plurality of respectively Data Update lock request queues corresponding with the different pieces of information in the system, in order to can send to the message in this formation data maintenance nodal information administration module, and releasing request message is locked in the renewal that receive data Maintenance Point information management module returns, can process the next lock request message that upgrades so that upgrade lock request queue, and after finishing processing, send the affirmation message whether Data Update is finished to the message delivery and reception module;
Data maintenance nodal information administration module, be responsible for a plurality of data maintenance nodes that scatter are divided into different node groups, each node group contains at least a identical data and is in charge of and comprises: the IP address of each node, listening port number and whether be in the information of normal operating condition; Be provided with the time window of receipt message, and adjust in real time this time window size according to the variation of network environment; Be responsible for the Data Update information broadcast to all data maintenance nodes that contain this data trnascription in the system, and receive whether successful affirmation message of the Data Update of feedback or rolling back action, if acknowledge message does not arrive, then abandon receiving this message in time window is set duration; Also obtain the up-to-date information of the data trnascription of the running status of port numbers that all data maintenance nodes this system comprise IP address, the monitoring of node, node and storage thereof according to setting-up time from the cluster management node; So that according to the synchronous relevant information of himself storing of all data maintenance node up-to-date informations of storing on the cluster management node, so that distributed system is when carrying out the consistent data maintenance update, minimizing unsuccessfully causes the rolling back action expense of the data maintenance node that is updated successfully because of inaccessible data maintenance node updates, thereby improves reliability and high efficiency that data consistency is safeguarded; Data maintenance nodal information administration module also arranges the maximum of Data Update request repeat number of times and the maximum of data rewind operation requests sending times.
6. the method for work of the consistency maintenance system of distributed data in the distributed cluster system, it is characterized in that: described method comprises following operating procedure:
(1) the interim host node of initiate the data maintenance node of Data Update request, namely only managing the Data Update request of self initiating sends first the Data Update lock request message of the uniqueness sign that comprises the target data that its node uniqueness sign and expectation upgrade to the global lock management node; At this moment, interim host node does not upgrade target data, and the state to be updated such as is in;
(2) message sink in the global lock management node and sending module receive this Data Update lock request message, judge the update request that whether comprises a plurality of target datas in this message; If then this message is divided into separately independently a plurality of Data Update request messages, and puts into respectively the renewal lock request queue of corresponding data; If not, then this message is directly sent in the renewal lock request queue of target data; The message of upgrading in the lock request queue is to send to data maintenance nodal information administration module according to the first-in first-out mode;
(3) after data maintenance nodal information administration module receives this message, search out first the data maintenance node group that contains target data, and to the group in this Data Update request message of data maintenance node broadcasts; Simultaneously, the time window initial value of receipt message is set also, prepares in the time window of this setting, receive the affirmation message whether data that the Maintenance Point that contains target data sends are updated successfully;
(4) after other data maintenance nodes that contain target data receive this Data Update request message, resolve and carry out the updating target data operation in this message: if deletion action, then directly delete the corresponding data in the target data, and increase the version number of these data; If rolling back action, the then directly the last renewal of carrying out of rollback target data, and the version number of minimizing data; If increase or retouching operation, then the data maintenance node first from interim host node obtain new suffix according to content after, just upgrade target data, increase simultaneously the version number of data;
(5) contain the updating target data success of other data maintenance nodes of target data after, send the acknowledge message that is updated successfully of the version number that comprises after this updating target data success to the global lock management node;
(6) the data maintenance nodal information administration module in the global lock management node judges whether to receive and removes beyond the interim host node, all contain the affirmation message of the Data Update success that other data maintenance nodes of target data send, in order to take corresponding different post-treatment operations;
(7) in distributed cluster system, after data maintenance nodal information administration module is finished all operations were of a Data Update, the time window value of its receipt message is adjusted, to adapt to the variation of network environment.
7. method of work according to claim 6, it is characterized in that: in the described step (6), when data maintenance nodal information administration module received the affirmation message of the Data Update success that the every other data maintenance node that contains target data sends, the subsequent processing steps of execution was as follows:
(61) data maintenance nodal information administration module sends the affirmation message of updating target data success to interim host node, after interim host node receives this acknowledge message, take out the team's message in the formation of client data update inquiry information, and the target data of himself node is upgraded accordingly and increased its version number according to this team message, simultaneously respectively to the affirmation message of data maintenance nodal information administration module and its updating target data success of client feedback;
(62) after data maintenance nodal information administration module receives the affirmation message that is updated successfully of interim host node transmission, to the renewal lock request queue transmission updating target data lock releasing request message of target data; So that upgrade the renewal lock that lock request queue discharges target data, for the renewal lock request use of next data.
8. according to claim 6 or 7 described method of works, it is characterized in that: in the described step (6), when data maintenance nodal information administration module did not receive the affirmation message of the Data Update success that all other data maintenance nodes that contain target data send, the subsequent processing steps of execution was as follows:
(6A) data maintenance nodal information administration module reset receive that the data maintenance node contain target data sends be updated successfully acknowledge message time window size, and arrange and upgrade the maximum times that failed data maintenance node sends the Data Update request again; Then, to there not being to send the update inquiry information that the data maintenance node that is updated successfully acknowledge message sends target data again;
After (6B) the data maintenance node receives this update inquiry information again, first relatively the version number of its target data whether with this message in versions of data number identical, if both are identical, then directly send the affirmation message that is updated successfully to data maintenance nodal information administration module; Otherwise, again upgrade target data, and be updated successfully acknowledge message to the transmission of data maintenance nodal information administration module;
(6C) data maintenance nodal information administration module to upgrade failed data maintenance node in the sending times maximum of its setting with the interior Data Update request that resends, and in the time window of setting, just receive all and once upgraded the acknowledge message that is updated successfully that failed data maintenance node returns, then carry out respective handling according to step (61) and (62) and operate; Otherwise, just send target data rolling back action message to having sent the data maintenance node that is updated successfully acknowledge message, so that this data maintenance node is after receiving this rolling back action message, cancel the last executed renewal operation of target data, and feed back the affirmation message whether rolling back action is finished; After this, data maintenance nodal information administration module is finished the data maintenance node of acknowledge message to not sending rolling back action, in the maximum number of retransmissions of setting with the interior rollback operation information that again sends; At last, send the affirmation message of updating target data failure to interim host node;
After (6D) interim host node receives the affirmation message of renewal failure of target data, directly abandon the team's message in the formation of client data update inquiry information, the while sends respectively the affirmation message of updating target data failure to data maintenance nodal information administration module and client;
After (6E) data maintenance nodal information administration module receives the affirmation message of the updating target data failure that interim host node sends, renewal lock request queue to target data sends renewal lock releasing request message, so that upgrade the renewal lock that lock request queue discharges target data, in order to being transferred to the next lock request message that upgrades, it uses; After client arrived and upgrades failed affirmation message, other data maintenance node that contains target data was initiated update inquiry information again in the selection cluster, perhaps stops this Data Update solicit operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210535376.3A CN103036717B (en) | 2012-12-12 | 2012-12-12 | The consistency maintenance system and method for distributed data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210535376.3A CN103036717B (en) | 2012-12-12 | 2012-12-12 | The consistency maintenance system and method for distributed data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103036717A true CN103036717A (en) | 2013-04-10 |
| CN103036717B CN103036717B (en) | 2015-11-04 |
Family
ID=48023230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210535376.3A Expired - Fee Related CN103036717B (en) | 2012-12-12 | 2012-12-12 | The consistency maintenance system and method for distributed data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103036717B (en) |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559319A (en) * | 2013-11-21 | 2014-02-05 | 华为技术有限公司 | Cache synchronization method and equipment for distributed cluster file system |
| CN103731485A (en) * | 2013-12-26 | 2014-04-16 | 华为技术有限公司 | Network equipment, cluster storage system and distributed lock management method |
| CN103744719A (en) * | 2013-12-30 | 2014-04-23 | 华为技术有限公司 | Lock management method, lock management system, lock management system configuration method and lock management system configuration device |
| CN104133831A (en) * | 2014-02-25 | 2014-11-05 | 清华大学 | Cross-domain data connecting system, cross-domain data connecting method and node |
| CN104135505A (en) * | 2014-03-06 | 2014-11-05 | 清华大学 | Data connection method and system across data center |
| CN104252466A (en) * | 2013-06-26 | 2014-12-31 | 阿里巴巴集团控股有限公司 | Stream computing processing method, equipment and system |
| CN104348906A (en) * | 2014-09-16 | 2015-02-11 | 深圳市华为技术软件有限公司 | Data consultation method and device in distributed type system |
| CN104407814A (en) * | 2014-11-21 | 2015-03-11 | 华为技术有限公司 | Method and device for data double writing |
| CN104750738A (en) * | 2013-12-30 | 2015-07-01 | 中国移动通信集团公司 | Data information updating method, data node, management node and system |
| CN105068877A (en) * | 2015-07-14 | 2015-11-18 | 许继电气股份有限公司 | Method for transmitting data consistency among a plurality of priority tasks |
| CN105227683A (en) * | 2015-11-11 | 2016-01-06 | 中国建设银行股份有限公司 | A kind of LDAP company-data synchronous method and system |
| CN105528464A (en) * | 2016-01-28 | 2016-04-27 | 北京宇航系统工程研究所 | Version management system capable of automatically judging technical condition consistency of associated data |
| CN105550319A (en) * | 2015-12-12 | 2016-05-04 | 天津南大通用数据技术股份有限公司 | Optimization method for high-concurrency persistence of cluster consistency service |
| CN105721617A (en) * | 2016-04-28 | 2016-06-29 | 安徽四创电子股份有限公司 | Rolling update method for cloud service system |
| CN105765948A (en) * | 2014-10-29 | 2016-07-13 | 华为技术有限公司 | Information updating method, apparatus, and device |
| CN105786955A (en) * | 2015-01-08 | 2016-07-20 | 国际商业机器公司 | Data replication in a database management system |
| CN105868002A (en) * | 2015-01-22 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Method for processing retransmission request in distributed calculation and device thereof |
| CN105897366A (en) * | 2016-04-01 | 2016-08-24 | 浪潮电子信息产业股份有限公司 | Method and system for ensuring time consistency of computer cluster nodes |
| CN106209926A (en) * | 2015-04-30 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of data-updating method and equipment |
| CN106302625A (en) * | 2015-06-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Data-updating method, device and related system |
| WO2017063520A1 (en) * | 2015-10-15 | 2017-04-20 | 中兴通讯股份有限公司 | Method and apparatus for operating database |
| CN106802939A (en) * | 2016-12-30 | 2017-06-06 | 华为技术有限公司 | A kind of method and system of resolving data conflicts |
| CN106888245A (en) * | 2016-06-07 | 2017-06-23 | 阿里巴巴集团控股有限公司 | A kind of data processing method, apparatus and system |
| CN107391620A (en) * | 2017-07-06 | 2017-11-24 | 天脉聚源(北京)传媒科技有限公司 | A kind of method and device for handling collaboration update abnormal |
| CN107450991A (en) * | 2017-07-24 | 2017-12-08 | 无锡江南计算技术研究所 | A kind of efficiently distributed global lock coordination approach |
| CN107491335A (en) * | 2017-08-31 | 2017-12-19 | 郑州云海信息技术有限公司 | The upgrade method and upgrade-system of a kind of cluster controller |
| CN107689889A (en) * | 2017-08-28 | 2018-02-13 | 长沙曙通信息科技有限公司 | A kind of cluster multinode state information maintenance implementation method |
| CN107783860A (en) * | 2016-08-31 | 2018-03-09 | 阿里巴巴集团控股有限公司 | The recovery point objectives monitoring method and equipment of a kind of data transfer |
| CN107977376A (en) * | 2016-10-24 | 2018-05-01 | 腾讯科技（深圳）有限公司 | Distributed data base system and transaction methods |
| CN108023908A (en) * | 2016-10-31 | 2018-05-11 | 腾讯科技（深圳）有限公司 | Data-updating method, apparatus and system |
| CN108234641A (en) * | 2017-12-29 | 2018-06-29 | 北京奇虎科技有限公司 | Data read-write method and device based on distributed consensus protocol realization |
| CN108614873A (en) * | 2018-04-20 | 2018-10-02 | 新华三技术有限公司 | A kind of data processing method and device |
| CN108924206A (en) * | 2018-06-26 | 2018-11-30 | 郑州云海信息技术有限公司 | A kind of cluster event synchronizing method, device and the equipment of distributed system |
| CN109408203A (en) * | 2018-11-01 | 2019-03-01 | 无锡华云数据技术服务有限公司 | A kind of implementation method, device, the computing system of queue message consistency |
| CN109739935A (en) * | 2019-01-09 | 2019-05-10 | 腾讯科技（深圳）有限公司 | Method for reading data, device, electronic equipment and storage medium |
| CN109862102A (en) * | 2019-02-25 | 2019-06-07 | 交通银行股份有限公司 | A kind of more copy concurrent control systems of distributed data, server and method |
| CN109901947A (en) * | 2017-12-07 | 2019-06-18 | 罗德施瓦兹两合股份有限公司 | Fault tolerant data memory access units, method fault tolerant data storage access system and access data storage |
| CN110096517A (en) * | 2014-11-04 | 2019-08-06 | 阿里巴巴集团控股有限公司 | Data cached monitoring method, device and system based on distributed system |
| CN110381124A (en) * | 2019-06-28 | 2019-10-25 | 苏州浪潮智能科技有限公司 | A kind of application method and device for locking resource |
| CN111695018A (en) * | 2019-03-13 | 2020-09-22 | 阿里巴巴集团控股有限公司 | Data processing method and device, distributed network system and computer equipment |
| CN112035721A (en) * | 2020-07-22 | 2020-12-04 | 大箴(杭州)科技有限公司 | Crawler cluster monitoring method and device, storage medium and computer equipment |
| CN112136118A (en) * | 2018-05-03 | 2020-12-25 | Arm有限公司 | Transport protocol in a data processing network |
| CN112506859A (en) * | 2020-08-21 | 2021-03-16 | 海信视像科技股份有限公司 | Method for maintaining hard disk data and display device |
| CN113037552A (en) * | 2016-12-21 | 2021-06-25 | 瞻博网络公司 | Network method, network device, and computer-readable storage medium |
| CN113239013A (en) * | 2021-05-17 | 2021-08-10 | 北京青云科技股份有限公司 | Distributed system and storage medium |
| CN114490691A (en) * | 2022-02-15 | 2022-05-13 | 北京中电兴发科技有限公司 | Distributed system data consistency method |
| CN114945026A (en) * | 2022-04-24 | 2022-08-26 | 网易（杭州）网络有限公司 | Data processing method, device and system |
| WO2023185934A1 (en) * | 2022-03-31 | 2023-10-05 | 阿里云计算有限公司 | Data processing method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1719831A (en) * | 2005-07-15 | 2006-01-11 | 清华大学 | High-available distributed boundary gateway protocol system based on cluster router structure |
| US20070226269A1 (en) * | 2006-03-24 | 2007-09-27 | International Business Machines Corporation | Method and system for an update synchronization of a domain information file |
| CN102117287A (en) * | 2009-12-30 | 2011-07-06 | 成都市华为赛门铁克科技有限公司 | Distributed file system access method, a metadata server and client side |
-
2012
- 2012-12-12 CN CN201210535376.3A patent/CN103036717B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1719831A (en) * | 2005-07-15 | 2006-01-11 | 清华大学 | High-available distributed boundary gateway protocol system based on cluster router structure |
| US20070226269A1 (en) * | 2006-03-24 | 2007-09-27 | International Business Machines Corporation | Method and system for an update synchronization of a domain information file |
| CN102117287A (en) * | 2009-12-30 | 2011-07-06 | 成都市华为赛门铁克科技有限公司 | Distributed file system access method, a metadata server and client side |
Cited By (80)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104252466A (en) * | 2013-06-26 | 2014-12-31 | 阿里巴巴集团控股有限公司 | Stream computing processing method, equipment and system |
| CN103559319B (en) * | 2013-11-21 | 2017-07-07 | 华为技术有限公司 | The cache synchronization method and equipment of distributed cluster file system |
| CN103559319A (en) * | 2013-11-21 | 2014-02-05 | 华为技术有限公司 | Cache synchronization method and equipment for distributed cluster file system |
| CN103731485A (en) * | 2013-12-26 | 2014-04-16 | 华为技术有限公司 | Network equipment, cluster storage system and distributed lock management method |
| WO2015100973A1 (en) * | 2013-12-30 | 2015-07-09 | 华为技术有限公司 | Lock management method and system, and lock management system configuration method and device |
| CN103744719A (en) * | 2013-12-30 | 2014-04-23 | 华为技术有限公司 | Lock management method, lock management system, lock management system configuration method and lock management system configuration device |
| US10042678B2 (en) | 2013-12-30 | 2018-08-07 | Huawei Technologies Co., Ltd. | Lock management method and system, method and apparatus for configuring lock management system |
| CN104750738B (en) * | 2013-12-30 | 2018-06-26 | 中国移动通信集团公司 | A kind of method for updating the data information, back end, management node and system |
| CN104750738A (en) * | 2013-12-30 | 2015-07-01 | 中国移动通信集团公司 | Data information updating method, data node, management node and system |
| CN104133831B (en) * | 2014-02-25 | 2017-07-07 | 清华大学 | Cross-domain data system of connections, cross-domain data coupling method and node |
| CN104133831A (en) * | 2014-02-25 | 2014-11-05 | 清华大学 | Cross-domain data connecting system, cross-domain data connecting method and node |
| CN104135505A (en) * | 2014-03-06 | 2014-11-05 | 清华大学 | Data connection method and system across data center |
| CN104135505B (en) * | 2014-03-06 | 2017-05-24 | 清华大学 | Data connection method and system across data center |
| CN104348906A (en) * | 2014-09-16 | 2015-02-11 | 深圳市华为技术软件有限公司 | Data consultation method and device in distributed type system |
| CN104348906B (en) * | 2014-09-16 | 2018-05-04 | 华为技术有限公司 | Data agreement method and device in a kind of distributed system |
| CN105765948A (en) * | 2014-10-29 | 2016-07-13 | 华为技术有限公司 | Information updating method, apparatus, and device |
| CN110096517A (en) * | 2014-11-04 | 2019-08-06 | 阿里巴巴集团控股有限公司 | Data cached monitoring method, device and system based on distributed system |
| CN104407814A (en) * | 2014-11-21 | 2015-03-11 | 华为技术有限公司 | Method and device for data double writing |
| CN104407814B (en) * | 2014-11-21 | 2017-10-17 | 华为技术有限公司 | Double method and apparatus for writing data |
| CN105786955A (en) * | 2015-01-08 | 2016-07-20 | 国际商业机器公司 | Data replication in a database management system |
| CN105868002B (en) * | 2015-01-22 | 2020-02-21 | 阿里巴巴集团控股有限公司 | Method and device for processing retransmission request in distributed computing |
| CN105868002A (en) * | 2015-01-22 | 2016-08-17 | 阿里巴巴集团控股有限公司 | Method for processing retransmission request in distributed calculation and device thereof |
| US10536514B2 (en) | 2015-01-22 | 2020-01-14 | Alibaba Group Holding Limited | Method and apparatus of processing retransmission request in distributed computing |
| CN106209926A (en) * | 2015-04-30 | 2016-12-07 | 阿里巴巴集团控股有限公司 | A kind of data-updating method and equipment |
| CN106209926B (en) * | 2015-04-30 | 2019-06-21 | 阿里巴巴集团控股有限公司 | A kind of data-updating method and equipment |
| TWI693547B (en) * | 2015-04-30 | 2020-05-11 | 香港商阿里巴巴集團服務有限公司 | Information updating method and equipment |
| US10761724B2 (en) | 2015-04-30 | 2020-09-01 | Alibaba Group Holding Limited | System, method, and apparatus for updating data in a distributed storage system |
| CN106302625A (en) * | 2015-06-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | Data-updating method, device and related system |
| CN106302625B (en) * | 2015-06-26 | 2019-10-25 | 阿里巴巴集团控股有限公司 | Data-updating method, device and related system |
| CN105068877B (en) * | 2015-07-14 | 2018-07-17 | 许继电气股份有限公司 | Data consistency transmission method between a kind of multipriority task |
| CN105068877A (en) * | 2015-07-14 | 2015-11-18 | 许继电气股份有限公司 | Method for transmitting data consistency among a plurality of priority tasks |
| WO2017063520A1 (en) * | 2015-10-15 | 2017-04-20 | 中兴通讯股份有限公司 | Method and apparatus for operating database |
| CN105227683A (en) * | 2015-11-11 | 2016-01-06 | 中国建设银行股份有限公司 | A kind of LDAP company-data synchronous method and system |
| CN105550319A (en) * | 2015-12-12 | 2016-05-04 | 天津南大通用数据技术股份有限公司 | Optimization method for high-concurrency persistence of cluster consistency service |
| CN105550319B (en) * | 2015-12-12 | 2019-06-25 | 天津南大通用数据技术股份有限公司 | The optimization method of persistence under a kind of cluster Consistency service high concurrent |
| CN105528464A (en) * | 2016-01-28 | 2016-04-27 | 北京宇航系统工程研究所 | Version management system capable of automatically judging technical condition consistency of associated data |
| CN105528464B (en) * | 2016-01-28 | 2019-03-26 | 北京宇航系统工程研究所 | A kind of edition management system judging automatically associated data state of the art consistency |
| CN105897366B (en) * | 2016-04-01 | 2018-09-04 | 浪潮电子信息产业股份有限公司 | A kind of method and system ensureing computer cluster node time consistency |
| CN105897366A (en) * | 2016-04-01 | 2016-08-24 | 浪潮电子信息产业股份有限公司 | Method and system for ensuring time consistency of computer cluster nodes |
| CN105721617A (en) * | 2016-04-28 | 2016-06-29 | 安徽四创电子股份有限公司 | Rolling update method for cloud service system |
| CN105721617B (en) * | 2016-04-28 | 2019-05-14 | 安徽四创电子股份有限公司 | A kind of rolling update method of cloud service system |
| CN106888245A (en) * | 2016-06-07 | 2017-06-23 | 阿里巴巴集团控股有限公司 | A kind of data processing method, apparatus and system |
| CN107783860A (en) * | 2016-08-31 | 2018-03-09 | 阿里巴巴集团控股有限公司 | The recovery point objectives monitoring method and equipment of a kind of data transfer |
| US11243920B2 (en) | 2016-10-24 | 2022-02-08 | Tencent Technology (Shenzhen) Company Limited | Distributed database system, transaction processing method, lock server and storage medium |
| CN107977376B (en) * | 2016-10-24 | 2020-07-07 | 腾讯科技（深圳）有限公司 | Distributed database system and transaction processing method |
| CN107977376A (en) * | 2016-10-24 | 2018-05-01 | 腾讯科技（深圳）有限公司 | Distributed data base system and transaction methods |
| CN108023908B (en) * | 2016-10-31 | 2020-04-24 | 腾讯科技（深圳）有限公司 | Data updating method, device and system |
| CN108023908A (en) * | 2016-10-31 | 2018-05-11 | 腾讯科技（深圳）有限公司 | Data-updating method, apparatus and system |
| CN113037552A (en) * | 2016-12-21 | 2021-06-25 | 瞻博网络公司 | Network method, network device, and computer-readable storage medium |
| WO2018120810A1 (en) * | 2016-12-30 | 2018-07-05 | 华为技术有限公司 | Method and system for solving data collision |
| CN106802939A (en) * | 2016-12-30 | 2017-06-06 | 华为技术有限公司 | A kind of method and system of resolving data conflicts |
| CN106802939B (en) * | 2016-12-30 | 2020-04-03 | 华为技术有限公司 | Method and system for solving data conflict |
| CN107391620A (en) * | 2017-07-06 | 2017-11-24 | 天脉聚源(北京)传媒科技有限公司 | A kind of method and device for handling collaboration update abnormal |
| CN107450991A (en) * | 2017-07-24 | 2017-12-08 | 无锡江南计算技术研究所 | A kind of efficiently distributed global lock coordination approach |
| CN107689889A (en) * | 2017-08-28 | 2018-02-13 | 长沙曙通信息科技有限公司 | A kind of cluster multinode state information maintenance implementation method |
| CN107491335A (en) * | 2017-08-31 | 2017-12-19 | 郑州云海信息技术有限公司 | The upgrade method and upgrade-system of a kind of cluster controller |
| CN109901947B (en) * | 2017-12-07 | 2022-01-04 | 罗德施瓦兹两合股份有限公司 | Fault tolerant data storage access unit, fault tolerant data storage access system and method of accessing data storage |
| CN109901947A (en) * | 2017-12-07 | 2019-06-18 | 罗德施瓦兹两合股份有限公司 | Fault tolerant data memory access units, method fault tolerant data storage access system and access data storage |
| CN108234641A (en) * | 2017-12-29 | 2018-06-29 | 北京奇虎科技有限公司 | Data read-write method and device based on distributed consensus protocol realization |
| CN108234641B (en) * | 2017-12-29 | 2021-01-29 | 北京奇元科技有限公司 | Data reading and writing method and device based on distributed consistency protocol |
| CN108614873A (en) * | 2018-04-20 | 2018-10-02 | 新华三技术有限公司 | A kind of data processing method and device |
| CN108614873B (en) * | 2018-04-20 | 2020-11-06 | 新华三技术有限公司 | Data processing method and device |
| CN112136118A (en) * | 2018-05-03 | 2020-12-25 | Arm有限公司 | Transport protocol in a data processing network |
| CN108924206A (en) * | 2018-06-26 | 2018-11-30 | 郑州云海信息技术有限公司 | A kind of cluster event synchronizing method, device and the equipment of distributed system |
| CN109408203A (en) * | 2018-11-01 | 2019-03-01 | 无锡华云数据技术服务有限公司 | A kind of implementation method, device, the computing system of queue message consistency |
| CN109739935B (en) * | 2019-01-09 | 2022-12-30 | 腾讯科技（深圳）有限公司 | Data reading method and device, electronic equipment and storage medium |
| CN109739935A (en) * | 2019-01-09 | 2019-05-10 | 腾讯科技（深圳）有限公司 | Method for reading data, device, electronic equipment and storage medium |
| CN109862102B (en) * | 2019-02-25 | 2022-01-28 | 交通银行股份有限公司 | Distributed data multi-copy concurrency control system, server and method |
| CN109862102A (en) * | 2019-02-25 | 2019-06-07 | 交通银行股份有限公司 | A kind of more copy concurrent control systems of distributed data, server and method |
| CN111695018A (en) * | 2019-03-13 | 2020-09-22 | 阿里巴巴集团控股有限公司 | Data processing method and device, distributed network system and computer equipment |
| CN111695018B (en) * | 2019-03-13 | 2023-05-30 | 阿里云计算有限公司 | Data processing method and device, distributed network system and computer equipment |
| CN110381124A (en) * | 2019-06-28 | 2019-10-25 | 苏州浪潮智能科技有限公司 | A kind of application method and device for locking resource |
| CN112035721A (en) * | 2020-07-22 | 2020-12-04 | 大箴(杭州)科技有限公司 | Crawler cluster monitoring method and device, storage medium and computer equipment |
| CN112506859A (en) * | 2020-08-21 | 2021-03-16 | 海信视像科技股份有限公司 | Method for maintaining hard disk data and display device |
| CN113239013A (en) * | 2021-05-17 | 2021-08-10 | 北京青云科技股份有限公司 | Distributed system and storage medium |
| CN113239013B (en) * | 2021-05-17 | 2024-04-09 | 北京青云科技股份有限公司 | Distributed system and storage medium |
| CN114490691A (en) * | 2022-02-15 | 2022-05-13 | 北京中电兴发科技有限公司 | Distributed system data consistency method |
| CN114490691B (en) * | 2022-02-15 | 2022-08-16 | 北京中电兴发科技有限公司 | Distributed system data consistency method |
| WO2023185934A1 (en) * | 2022-03-31 | 2023-10-05 | 阿里云计算有限公司 | Data processing method and device |
| CN114945026A (en) * | 2022-04-24 | 2022-08-26 | 网易（杭州）网络有限公司 | Data processing method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103036717B (en) | 2015-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103036717B (en) | The consistency maintenance system and method for distributed data | |
| US9715522B2 (en) | Information processing apparatus and control method | |
| CN107771321B (en) | Recovery in a data center | |
| Lin et al. | Towards a non-2pc transaction management in distributed database systems | |
| WO2018103318A1 (en) | Distributed transaction handling method and system | |
| US7801997B2 (en) | Asynchronous interconnect protocol for a clustered DBMS | |
| US8639890B2 (en) | Data segment version numbers in distributed shared memory | |
| US7765186B1 (en) | Update-anywhere replication of distributed systems | |
| US9116862B1 (en) | System and method for data replication using a single master failover protocol | |
| US8719225B1 (en) | System and method for log conflict detection and resolution in a data store | |
| US9063787B2 (en) | System and method for using cluster level quorum to prevent split brain scenario in a data grid cluster | |
| US9489434B1 (en) | System and method for replication log branching avoidance using post-failover rejoin | |
| Kemme et al. | Database replication: a tale of research across communities | |
| US7330860B2 (en) | Fault tolerant mechanism to handle initial load of replicated object in live system | |
| CN103297268A (en) | P2P (peer to peer) technology based distributed data consistency maintaining system and method | |
| CN108710638B (en) | Distributed concurrency control method and system based on mixed RDMA operation | |
| US20060253856A1 (en) | Fault tolerant distributed lock management | |
| US7734582B2 (en) | Apparatus, system, and method for cache synchronization | |
| CN110535680B (en) | Byzantine fault-tolerant method | |
| US9411869B2 (en) | Replication between sites using keys associated with modified data | |
| CN102831156A (en) | Distributed transaction processing method on cloud computing platform | |
| KR101296778B1 (en) | Method of eventual transaction processing on nosql database | |
| JP2004152247A (en) | Transaction cache consistency maintenance system in mobile computer environment, and its method | |
| KR20040015223A (en) | Resource action in clustered computer system incorporating prepare operation | |
| CN1677887A (en) | N+1 duplicates data real-time synchronising method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhao Yao Inventor after: Song Yingying Inventor after: Yang Fangchun Inventor after: Zou Hua Inventor after: Niu Kun Inventor after: Zhang Wentao Inventor after: Wan Neng Inventor after: Peng Shukai Inventor after: Zou Zhiyong Inventor before: Zhao Yao Inventor before: Zou Zhiyong Inventor before: Song Yingying Inventor before: Peng Shukai Inventor before: Yang Fangchun Inventor before: Zou Hua |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20151104 Termination date: 20211212 |