WO2017015961A1 - 一种用于双活数据中心的仲裁方法、装置及系统 - Google Patents
一种用于双活数据中心的仲裁方法、装置及系统 Download PDFInfo
- Publication number
- WO2017015961A1 WO2017015961A1 PCT/CN2015/085591 CN2015085591W WO2017015961A1 WO 2017015961 A1 WO2017015961 A1 WO 2017015961A1 CN 2015085591 W CN2015085591 W CN 2015085591W WO 2017015961 A1 WO2017015961 A1 WO 2017015961A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data center
- arbitration
- data
- arbitration device
- communication
- 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.)
- Ceased
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1044—Group management mechanisms
- H04L67/1051—Group master selection mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
- H04L41/0668—Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0695—Management of faults, events, alarms or notifications the faulty arrangement being the maintenance, administration or management system
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0811—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking connectivity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
- H04L67/101—Server selection for load balancing based on network conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/61—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources taking into account QoS or priority requirements
Definitions
- the present invention relates to the field of computer technologies, and in particular, to an arbitration method, apparatus, and system for a dual-active data center.
- a dual-active data center means that two data centers simultaneously undertake business and back up each other to improve the overall service capacity and system resource utilization of the two data centers.
- the two data centers in the active data center send a heartbeat packet to each other at a set time. If the heartbeat packet of the other party is not received within the set time, the backup is interrupted. At this point, if both data centers continue to undertake business, there will be data inconsistency.
- the arbitration mechanism is one of the means to avoid the data inconsistency problem.
- the implementation method is as follows: two data centers respectively send arbitration requests to arbitration devices set up independently of the two data centers, and the arbitration device determines the winning data center according to the arbitration request. The winning data center continues to provide services (ie, undertake business), and the unsuccessful data center stops providing services.
- the embodiment of the present invention provides an arbitration method, device and system for a dual-active data center.
- the technical solution is as follows:
- an embodiment of the present invention provides an arbitration method for a dual-active data center, where the arbitration method includes:
- the arbitration device When the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot enter During the arbitration, the first data center views a predetermined arbitration policy
- the first data center determines that the first data center is a priority data center according to the arbitration policy, the first data center continues to provide a service
- the first data center determines, according to the arbitration policy, that the first data center is not a priority data center, the first data center stops providing services;
- the first data center and the second data center are dual active data centers.
- the arbitration method further includes:
- the first data center When the first data center is in a set abnormal state, and the communication between the first data center and the second data center is not disconnected, the first data center is to the second data center Sending a notification message, the notification message is used to indicate that the second data center provides a service in place of the first data center.
- the arbitrating device is configured to use a disaster recovery device, where the disaster recovery device is configured to back up data of the first data center and the second data center.
- the arbitration method further includes:
- the first data center determines that the communication with the second data center is disconnected, and the arbitration device can perform arbitration
- the first data center sends a arbitration to the arbitration device by using a data backup link.
- the data backup link is configured to transmit backup data sent by the first data center to the arbitration device.
- the first data center When the first data center needs to send the arbitration request and the data of the first data center to the arbitration device, the first data center preferentially sends the arbitration request to the arbitration device; or
- the arbitration method further includes:
- the first data center monitors in real time whether the communication between the first data center and the arbitration device, and between the second data center and the arbitration device is disconnected;
- the first data center sets an arbitration device flag according to the monitoring result, including:
- the first data center determines that communication with the arbitration device is not disconnected, or when the first data center determines that communication between the second data center and the arbitration device is not disconnected And the first data center sets the arbitration device flag bit to be arbitrated by the arbitration device;
- the first data center sets the arbitration device flag when the first data center determines that communication with the arbitration device is disconnected and determines that communication with the second data center is broken Set to the arbitration device capable of arbitration;
- the first data center determines that communication with the arbitration device is disconnected, and determines that communication between the second data center and the arbitration device is disconnected, the first data center will The arbitration device flag is set such that the arbitration device cannot arbitrate.
- the arbitration method further includes:
- the arbitration device When the first data center determines that the communication with the second data center is disconnected, and the arbitration device can perform arbitration, the first data center views the arbitration policy
- the first data center determines that the first data center is the priority data center according to the arbitration policy, the first data center immediately sends an arbitration request to the arbitration device;
- the first data center determines that the first data center is not the priority data center according to the arbitration policy, the first data center delays the set time and sends an arbitration request to the arbitration device.
- the arbitration device adopts a cloud server.
- the first data center and the second data center are dual active data centers.
- the arbitration apparatus further includes:
- a state determining module configured to determine whether the first data center is in a set abnormal state
- a message sending module configured to: when the first data center is in a set abnormal state, and the communication between the first data center and the second data center is not disconnected, to the second data center Sending a notification message, the notification message is used to indicate that the second data center provides a service in place of the first data center.
- the arbitrating device is configured to use a disaster recovery device, where the disaster recovery device is configured to back up data of the first data center and the second data center.
- the arbitration device further includes:
- a request sending module configured to send an arbitration request to the arbitration device by using a data backup link when communication between the first data center and the second data center is disconnected, and the arbitration device can perform arbitration
- the data backup link is configured to transmit backup data sent by the first data center to the arbitration device.
- the request sending module is configured to:
- the arbitration request is sent to the arbitration device preferentially;
- the arbitration apparatus further includes:
- a monitoring module configured to monitor, in real time, whether communication between the first data center and the arbitration device, and between the second data center and the arbitration device is disconnected;
- a setting module configured to set an arbitration device flag according to the monitoring result, where the arbitration device flag is used to indicate whether the arbitration device can perform arbitration
- an arbitration device determining module configured to determine, by the first data center, whether the arbitration device can perform arbitration according to the arbitration device flag bit.
- the setting module is configured to:
- the arbitration device is when the communication between the first data center and the arbitration device is not disconnected, or when it is determined that the communication between the second data center and the arbitration device is not disconnected
- the flag bit is set to enable arbitration by the arbitration device
- the arbitration device flag is set to be arbitrated by the arbitration device
- the arbitration device flag is set to The arbitration equipment cannot be arbitrated.
- the arbitration apparatus further includes:
- a second viewing module configured to: when the communication between the first data center and the second data center is disconnected, and the arbitration device can perform arbitration, view the arbitration policy;
- a second service module when determining that the first data center is the priority data center according to the arbitration policy, immediately sending an arbitration request to the arbitration device; and determining, according to the arbitration policy, that the first data center is not In the priority data center, the arbitration request is sent to the arbitration device after the set time is delayed.
- the arbitration device adopts a cloud server.
- an embodiment of the present invention provides an arbitration system for a dual-active data center, where the arbitration system includes:
- a first data center configured to: when determining that the communication with the second data center is disconnected, and the arbitration device is unable to perform arbitration, reviewing a predetermined arbitration policy; determining the first data center according to the arbitration policy When the data center is prioritized, the service is continued; when it is determined according to the arbitration policy that the first data center is not the priority data center, the service is stopped;
- the second data center is configured to: when determining that the communication with the first data center is disconnected, and the arbitration device is unable to perform arbitration, view a preset arbitration policy; when determining according to the arbitration policy When the second data center is the priority data center, the service is continued; when it is determined that the second data center is not the priority data center according to the arbitration policy, the service is stopped;
- the first data center and the second data center are dual active data centers.
- the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration
- the first data center checks the preset arbitration policy, and determines that the first data center is based on the arbitration policy.
- the service is continued.
- the priority data center determines that the communication with the second data center is disconnected, and the arbitration device cannot arbitrate.
- only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration equipment, and guarantees the user For uninterrupted service.
- FIG. 1 is an application scenario diagram of an arbitration method for a dual-active data center according to Embodiment 1 of the present invention
- FIG. 3 is an information interaction diagram of an arbitration method for a dual-active data center according to Embodiment 2 of the present invention.
- FIG. 5 is a flowchart of an abnormal state processing procedure according to Embodiment 2 of the present invention.
- FIG. 7 is an application scenario diagram of an arbitration method for a dual-active data center according to Embodiment 4 of the present invention.
- FIG. 8 is a schematic structural diagram of an arbitration apparatus for a dual-active data center according to Embodiment 5 of the present invention.
- FIG. 9 is a schematic structural diagram of an arbitration apparatus for a dual-active data center according to Embodiment 6 of the present invention.
- FIG. 10 is a schematic diagram of hardware of an arbitration apparatus for a dual-active data center according to Embodiment 7 of the present invention.
- FIG. 11 is a schematic structural diagram of an arbitration system for a dual-active data center according to Embodiment 8 of the present invention.
- the application scenario shown in FIG. 1 is provided with a first data center 1 and a second data center 2, and the first data center 1 and the second data center 2 are active data centers, that is, the first data center 1 and the second data center. 2 Provide services at the same time and back up each other.
- the first data center 1 is connected to the second data center 2.
- the first data center 1 and the second data center 2 may be connected by an optical fiber or a network cable.
- the first data center 1 and the second data center 2 back up data through the optical fiber or the network cable, and send heartbeat packets to each other through the optical fiber or the network cable every set time (for example, 1 s) to determine the first data center and the second data center. Is the connection between disconnected?
- the data backup between the first data center 1 and the second data center 2 may be synchronous replication.
- the backup data can be transmitted by using a fast transmission link such as optical fiber, and on the other hand, the distance between the first data center 1 and the second data center 2 can be limited to a set distance (for example, 100 km).
- the first data center 1 and the second data center 2 are located in the same city.
- the first data center 1 and the second data center 2 may each include a storage layer, an application layer, a network layer, and the same layer of the first data center 1 and the second data center 2 (storage layer, application layer, or network layer)
- the arbitrating method provided by the embodiment of the present invention may be specifically applied to the same of the first data center 1 and the second data center 2, where the node is provided with one or more clusters (such as the Oracle real application cluster on the application layer).
- the arbitration of the layer may also be specifically applied to the arbitration of the same cluster on the first data center 1 and the second data center 2.
- the application scenario shown in FIG. 1 may further be provided with an arbitration device 3, the arbitration device 3 is set independently of the first data center 1 and the second data center 2, and the arbitration device 3 and the first data center 1, respectively Two data center 2 connections.
- the arbitration device 3 may be a device that is specifically configured to implement the arbitration mechanism described in the Background section.
- FIG. 1 is merely an example, and the present invention is not limited thereto.
- An embodiment of the present invention provides an arbitration method for a dual-active data center.
- the arbitration method includes:
- Step 101 When the first data center determines that the communication with the second data center is disconnected, and the arbitration When the device cannot arbitrate, the first data center checks the pre-defined arbitration policy.
- the first data center and the second data center are dual active data centers.
- whether the communication between the first data center and the second data center is disconnected may be determined according to a heartbeat packet sent between the first data center and the second data center at a set time (eg, 1 s). . If the first data center receives the heartbeat packet sent by the second data center within the set threshold time (eg, 1 s, 5 s), the first data center determines that the communication between the first data center and the second data center is not broken. If the first data center does not receive the heartbeat packet sent by the second data center within the set threshold time, the first data center determines that the communication between the first data center and the second data center is disconnected.
- a set time eg, 1 s
- the second data center determines that the communication between the first data center and the second data center is not disconnected; The second data center does not receive the heartbeat packet sent by the first data center within the set threshold time, and the second data center determines that the communication between the first data center and the second data center is disconnected.
- the method may further include:
- the first data center monitors whether communication between the first data center and the second data center is disconnected.
- Step 102 When the first data center determines that the first data center is the priority data center according to the arbitration policy, the first data center continues to provide the service.
- Step 103 When the first data center determines, according to the arbitration policy, that the first data center is not the priority data center, the first data center stops providing the service.
- the embodiment is described by taking the execution entity as the first data center as an example.
- the second data center like the first data center, performs the following steps: when the second data center determines When the communication between the first data centers is disconnected, and the arbitration device cannot perform arbitration, the second data center checks the preset arbitration policy; when the second data center determines that the second data center is the priority data center according to the arbitration policy, The second data center continues to provide the service; when the second data center determines that the second data center is not the priority data center according to the arbitration policy, the second data center stops providing the service.
- the user selects a data center as the priority data center in the active data center, and sets a flag indicating whether it is a priority data center in each data center according to the selected result, for example, 1 indicates Priority data center, 0 means not a priority data center.
- the first data center and the second data center determine whether they are priority data centers by their respective flag bits, which is prioritized.
- the data center of the data center continues to provide services, not the data center of the priority data center. The service is stopped to avoid data inconsistency due to the simultaneous provision of services by the two data centers where the backup was interrupted.
- the first data center when the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration, the first data center checks the preset arbitration policy, and determines the first according to the arbitration policy. A data center continues to provide services when the data center is prioritized, and when the first data center is determined not to be the priority data center according to the arbitration policy, the service is stopped, so that the first data center determines that the communication with the second data center is disconnected, and the arbitration is performed. When the device cannot be arbitrated, only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration device, and ensures uninterrupted service for the user.
- the embodiment of the present invention provides an arbitration method for a dual-active data center.
- a method for arbitrating a user's active data center provided in Embodiment 1 is further described in detail.
- the arbitration method includes:
- Step 201 The first data center monitors in real time whether the communication between the first data center and the arbitration device and between the second data center and the arbitration device is disconnected.
- the first data center and the second data center are dual active data centers, and the arbitration device is set independently of the first data center and the second data center.
- whether the communication between the first data center and the second data center is disconnected may be determined according to a heartbeat packet sent between the first data center and the second data center at a set time (eg, 1 s). . If the first data center receives the heartbeat packet sent by the second data center within the set threshold time (eg, 1 s, 5 s), the first data center determines that the communication between the first data center and the second data center is not broken. If the first data center does not receive the heartbeat packet sent by the second data center within the set threshold time, the first data center determines that the communication between the first data center and the second data center is disconnected.
- a set time eg, 1 s
- Step 202 The first data center sets an arbitration device flag according to the monitoring result.
- the arbitration device flag is used to indicate whether the arbitration device can arbitrate.
- the step 202 may include:
- the first data center determines that the communication with the arbitration device is not disconnected, or when the first data center determines that the communication between the second data center and the arbitration device is not disconnected, the first data center will arbitrate the device flag The bit is set to arbitration by the arbitration device;
- the first data center determines that the communication with the arbitration device is disconnected, and determines that the communication with the second data center is disconnected, the first data center sets the arbitration device flag bit to be arbitrated by the arbitration device;
- the first data center determines that the communication with the arbitration device is disconnected and determines that the communication between the second data center and the arbitration device is disconnected, the first data center sets the arbitration device flag bit to be arbitrated by the arbitration device.
- Step 203 The first data center determines whether the arbitration device can perform arbitration according to the arbitration device flag bit. When the arbitration device is capable of arbitration, steps 204a-204d are performed; when the arbitration device is unable to perform arbitration, steps 205a-205c are performed.
- an arbitration device flag of 1 indicates that the arbitration device can arbitrate
- an arbitration device flag of 0 indicates that the arbitration device cannot arbitrate.
- the step 204a may include:
- the first data center views the preset arbitration strategy
- the first data center determines that the first data center is the priority data center according to the arbitration policy, the first data center immediately sends an arbitration request to the arbitration device;
- the arbitration device may determine the arbitration result according to the order in which the arbitration request is received, that is, the arbitration device determines the sender of the first received arbitration request as the winner (the data center that continues to provide the service). Specifically, the arbitration device is provided with a flag bit, 1 indicates that the arbitration request has been received (ie, the winner has been determined), and 0 indicates that the arbitration request has not been received.
- the arbitration device checks the flag bit. If the flag bit is 0, the data center is replied to the winner, and the flag bit is changed to 0; if the flag bit is 1, Then reply to the data center that it is not the winner.
- the arbitration device can also determine the arbitration result according to the number of services undertaken by each data center, that is, the arbitration device determines the data center that bears the most business as the winner, so as to save the transition time required by the winner to undertake all the services.
- the arbitration device may also determine the arbitration result based on other criteria, which is not limited by the present invention.
- Step 204d The first data center continues or stops providing the service according to the arbitration result.
- the step 204d may include:
- the arbitration result includes that the first data center is the winner, the first data center continues to provide the service
- the first data center stops providing the service.
- Step 201 - Step 204d is an optional step. Since arbitration based on the priority data center (see steps 205a - 205c) is a pre-designation of the winner (the data center that continues to provide the service), there is a risk that the winner is the failed data center. Moreover, since the failed data center cannot send an arbitration request to the arbitration device, arbitration by the arbitration device does not present a risk that the winning party is the failed data center.
- step 201 - step 204d is performed, the arbitration device is preferentially used for arbitration. When the arbitration device cannot perform arbitration, arbitration is performed according to the priority data center.
- the risk that the winning party is the faulty data center is avoided as much as possible, and On the one hand, it also ensures that when the arbitration equipment cannot arbitrate, the winner can be determined to ensure that the service is not interrupted.
- the arbitration device that specifically implements the arbitration mechanism can be avoided, and the implementation cost is reduced.
- Step 205a When the first data center determines that the communication with the second data center is disconnected, the first data center views the preset arbitration policy. When the first data center determines that the first data center is the priority data center according to the arbitration policy, step 205b is performed; when the first data center determines that the first data center is not the priority data center according to the arbitration policy, step 205c is performed.
- Step 205b The first data center continues to provide services.
- Step 205c The first data center stops providing the service.
- the user selects a data center as the priority data center in the active data center, and sets a flag indicating whether it is a priority data center in each data center according to the result of the selection, for example, 1 indicates Priority data center, 0 means not a priority data center.
- the first data is Both the heart and the second data center determine whether they are priority data centers through their respective flag bits, and continue to provide services for the data center in the priority data center.
- the data center that is not the priority data center stops providing services to avoid interruption due to backup.
- the two data centers provide services at the same time and there is a problem of data inconsistency.
- the method may further include:
- the first data center determines whether the first data center is in a set abnormal state
- the first data center When the first data center is in the set abnormal state, and the communication between the first data center and the second data center is not disconnected, the first data center sends a notification message to the second data center, where the notification message is used to indicate Two data centers provide services in place of the first data center;
- the second data center provides services in place of the first data center according to the notification information
- the first data center stopped providing services.
- an arbitration policy is pre-configured in the first data center and the second data center, and the first data center and the second data center may periodically perform a self-test according to the arbitration policy to determine whether it is in a set abnormal state.
- the notification message is sent to the other party; when the notification message sent by the other party is received, the service is provided instead of the other party.
- the first data center stops providing the service, after receiving the message sent by the second data center instead of the handover work of the first data center providing service, or after receiving the second data center, starting to replace the first data center to provide the service.
- the data can be backed up after the first data center is completed, and the present invention is not limited after the first data center has been unable to provide the service.
- the set abnormal state may include at least one of power down, battery failure, write through operation, and dual disk failure.
- double disk failure means that the number of failed disks exceeds the number of bits that can be verified, and the data cannot be recovered and used.
- Write-through operation means that data is written to the disk in real time, and the data write rate is extremely low.
- a battery failure means that there is no backup power supply to write the data in the memory to the disk when the power is turned off. In this case, the write-through operation is generally used.
- Power loss means that there is not enough power to continue data backup.
- the operation efficiency and performance of the active data center as a whole are affected, and the first data center actively notifies the second data center to provide the service instead of providing the service.
- the data center provides the best service.
- the foregoing implementation manners and the execution of steps 201-203 are not sequential. Since the first data center is in the set abnormal state, the operating efficiency and performance of the first data center cannot meet the user's requirements, so in the case that the second data center does not fail (in the first data) The communication between the heart and the second data center is not disconnected), and the arbitration is not performed by the arbitration device or according to the priority data center, and the second data center is directly determined as the winner, saving the second data center to replace the first data center. The time required for the service to increase efficiency. When the second data center fails, the first data center may be in the set abnormal state, but may continue to provide services. In order to ensure that the service is not interrupted, the data will be survived by the arbitration device or according to the setting. The center conducts arbitration and determines the first data center as the winner.
- the first data center and the second data center will simultaneously provide services and back up each other.
- the first data center and the second data center may continue to send the heartbeat packet to the other party after determining that the communication between the first data center and the second data center is disconnected (the heartbeat packet sending interval may be the same as the first
- the heartbeat packet sending interval may be the same as the first
- the communication between the first data center and the second data center may not be disconnected, and then the heartbeat is continuously received when the set number of times is received.
- the communication recovery between the first data center and the second data center can be determined to avoid the accidental recovery of the communication between the first data center and the second data center, thereby causing a judgment error and ensuring the accuracy of the conclusion.
- the first data center and the second data center may also determine a first data center and a communication signal (such as an optical signal) reported by the communication device (such as an optical module) after the connection between the first data center and the second data center is restored. The communication between the two data centers is restored.
- the first data center when the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration, the first data center checks the preset arbitration policy, and determines the first according to the arbitration policy. A data center continues to provide services when the data center is prioritized, and when the first data center is determined not to be the priority data center according to the arbitration policy, the service is stopped, so that the first data center determines that the communication with the second data center is disconnected, and the arbitration is performed. When the device cannot be arbitrated, only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration device, and ensures uninterrupted service for the user.
- the embodiment of the present invention provides an arbitration method for a dual-active data center.
- the application scenario of the arbitration method for the active-active data center provided in this embodiment is briefly described below with reference to FIG.
- the disaster recovery device 4 is configured to back up data of the first data center 1 and the second data center 2 in the application scenario shown in FIG.
- the first data center 1 and the second data center 2 both provide services when a failure occurs.
- the disaster recovery equipment is divided into 4 points. Do not connect to the first data center 1 or the second data center 2.
- the first data center 1 and the second data center 2 are generally disposed in the same city.
- a natural disaster such as an earthquake occurs in the city where the first data center 1 and the second data center 2 are located
- the first data center 1 and the second data center 2 are likely to fail at the same time, so that the disaster recovery device 4 can provide the fault at this time.
- the service, the disaster-tolerant device 4 and the first data center 1 and the second data center 2 can be respectively disposed in two places separated by a set distance (for example, 100 km), such as in different cities (ie, two centers and three centers). It is easy to know that the data backup between the disaster recovery device 4 and the first data center 1 and the second data center 2 is asynchronously replicated because the disaster tolerance device 4 is far away from the first data center 1 and the second data center 2.
- the disaster recovery device 4 and the arbitration device 3 may be two independent devices.
- the execution steps of the first data center, the second data center, and the arbitration device are the same as those in Embodiment 2, and are not described in detail herein.
- the disaster recovery device 4 and the arbitration device 3 may also be the same device, that is, the disaster recovery device 4 implements the function of the arbitration device 3.
- an independent storage space is allocated on the disaster tolerant device 4, and is used for storing arbitration information, such as a procedure for performing arbitration, a flag indicating whether an arbitration request is received, or the like. It can be understood that the function of the arbitration device 3 is implemented by the disaster recovery device 4 compared with the special setting of the arbitration device 3, which simplifies the architecture of the active data center and greatly reduces the implementation cost.
- the execution steps of the first data center, the second data center, and the arbitration device in this embodiment are basically the same as those in Embodiment 2, except that the communication link is set. .
- the first data center sends an arbitration request to the arbitration device, which may include:
- the first data center uses the arbitration logical link to send an arbitration request to the arbitration device, and the data backup link It is divided into an arbitration logical link and a data logical link, and the data logical link is used to transmit backup data sent by the first data center to the arbitration device.
- the data backup link has a bandwidth of 50M, and 1M of the data is divided into arbitration logic links, which are used exclusively for transmitting arbitration requests.
- the bandwidth allocated to the arbitration logical link may be set by the user according to actual conditions, such as the number of data centers that perform arbitration, and will not be described in detail herein.
- the embodiment of the present invention provides an arbitration method for a dual-active data center.
- the application scenario of the arbitration method for the active-active data center provided in this embodiment is briefly described below with reference to FIG.
- the cloud server 5 may be requested to provide a virtual machine, and then the arbitration process is deployed on the applied virtual machine, and the cloud server 5 may perform arbitration.
- the cloud server 5 can use a public cloud provided by a third-party provider for free or low-cost public clouds, such as Huawei, Amazon, Facebook, and Microsoft.
- the core attribute of the public cloud is a shared resource service.
- the core attribute of the public cloud is a shared resource service.
- it also includes some settings that increase the security of data stored in the data center.
- the first data center sends an arbitration request to the arbitration device, which may include:
- the first data center uses a virtual private network (VPN) to send an arbitration request to the arbitration device.
- VPN virtual private network
- the first data center sends an arbitration request to the arbitration device, which may include:
- the first data center sends an arbitration request to the arbitration device, and the destination port of the arbitration request is a set port number.
- a firewall may be set between the first data center and the arbitration device, and the port number of the cloud server that communicates with the first data center is set through the firewall.
- the firewall directly deletes the message, that is, terminates the transmission of the message.
- the first data center sends an arbitration request to the arbitration device, which may include:
- the first data center After receiving the communication request reply sent by the arbitration device, the first data center sends an arbitration request to the arbitration device.
- a firewall may be set between the first data center and the arbitration device, and the communication between the cloud server and the first data center is set to be initiated by the first data center only through the firewall, that is, only the first data center
- the sent communication request can be transmitted to the quorum device through the firewall. If the cloud server sends a communication request to the first data center, the firewall deletes it directly, and the communication request cannot be sent to the first data center, and the communication is not established.
- the first data center when the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration, the first data center checks the preset arbitration policy, and determines the first according to the arbitration policy. A data center continues to provide services when the data center is prioritized, and when the first data center is determined not to be the priority data center according to the arbitration policy, the service is stopped, so that the first data center determines that the communication with the second data center is disconnected, and the arbitration is performed. When the device cannot be arbitrated, only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration device, and ensures uninterrupted service for the user.
- the first viewing module 501 is configured to view a preset arbitration policy when communication between the first data center and the second data center is disconnected, and the arbitration device cannot perform arbitration;
- the first service module 502 is configured to continue to provide a service when determining that the first data center is a priority data center according to the arbitration policy, and stop providing the service when determining that the first data center is not the priority data center according to the arbitration policy;
- the first data center and the second data center are dual active data centers.
- the first data center when the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration, the first data center checks the preset arbitration policy, and determines the first according to the arbitration policy. A data center continues to provide services when the data center is prioritized, and when the first data center is determined not to be the priority data center according to the arbitration policy, the service is stopped, so that the first data center determines that the communication with the second data center is disconnected, and the arbitration is performed. When the device cannot be arbitrated, only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration device, and ensures uninterrupted service for the user.
- an embodiment of the present invention provides an arbitration apparatus for a dual-active data center.
- This embodiment is a further detailed description of an arbitration apparatus for a dual-active data center provided in Embodiment 5.
- the arbitration device includes:
- the first viewing module 601 is configured to view a preset arbitration policy when communication between the first data center and the second data center is disconnected, and the arbitration device cannot perform arbitration;
- the first data center and the second data center are dual active data centers.
- the arbitration apparatus may further include:
- the arbitration logical link is used to send an arbitration request to the arbitration device.
- the data backup link is divided into an arbitration logical link and a data logical link, and the data logical link is used to transmit the backup data sent by the first data center to the arbitration device.
- the arbitration apparatus may further include:
- the monitoring module 606 is configured to monitor in real time whether the communication between the first data center and the arbitration device, and between the second data center and the arbitration device is disconnected;
- the setting module 607 is configured to set an arbitration device flag bit according to the monitoring result, where the arbitration device flag bit is used to indicate whether the arbitration device can perform arbitration;
- the arbitration device determining module 608 is configured to determine, by the first data center, whether the arbitration device can perform arbitration according to the arbitration device flag bit.
- the setting module 607 can be used,
- the arbitration device flag is set to be arbitrated by the arbitration device
- the arbitration device flag is set to the arbitration device unable to arbitrate.
- the arbitration apparatus may further include:
- a second service module 610 configured to determine, according to the arbitration policy, that the first data center is in the priority data
- the heart immediately sends an arbitration request to the arbitration device; when it is determined according to the arbitration policy that the first data center is not the priority data center, the arbitration request is sent to the arbitration device after the set time is delayed.
- the arbitration device may employ a cloud server.
- the memory 702 can be used to store software programs and application modules, and the processor 703 executes various functional applications and data processing of the system 700 by running software programs stored in the memory 702 and application modules.
- the memory 702 can mainly include a storage program area and a storage data area, wherein the storage program area can store an operating system, an application required for at least one function, and the like; the storage data area can store data (such as an advertisement) created according to the processing of the system 700. Push strategy, push record, etc.
- the memory 702 may include a high speed RAM (Random Access Memory), and may also include a non-volatile memory such as at least one magnetic disk storage device, a flash memory device, or other volatile solid state. Storage device.
- Processor 703 is the control center of system 700 that connects various portions of system 700 using various interfaces and lines.
- the processor 703 can be implemented by running or executing a software program and an application module stored in the memory 702, and calling data stored in the memory 702, between the first data center and the second data center.
- the preset arbitration policy is viewed; when the first data center is determined as the priority data center according to the arbitration policy, The service is continued; when it is determined according to the arbitration policy that the first data center is not the priority data center, the service is stopped; wherein the first data center and the second data center are dual-active data centers.
- the processor 703 may be configured to determine whether the first data center is in a set abnormal state; when the first data center is in the set abnormal state, and the first data center and the second When the communication between the data centers is not disconnected, a notification message is sent to the second data center, and the notification message is used to instruct the second data center to provide the service instead of the first data center.
- the processor 703 is configured to: when the communication between the first data center and the second data center is disconnected, and the arbitration device can perform arbitration, use the data backup link to send an arbitration request to the arbitration device, and the data backup chain The path is used to transmit backup data sent by the first data center to the arbitration device.
- the processor 703 is configured to: when the first data center needs to send the arbitration request and the data of the first data center to the arbitration device, send the arbitration request to the arbitration device preferentially; or send the arbitration logic link to the arbitration device.
- the arbitration request, the data backup link is divided into an arbitration logical link and a data logical link, and the data logical link is used to transmit backup data sent by the first data center to the arbitration device.
- the processor 703 is configured to monitor, in real time, whether communication between the first data center and the arbitration device, and between the second data center and the arbitration device is disconnected; according to the monitoring result, The arbitration device flag is set, and the arbitration device flag is used to indicate whether the arbitration device can arbitrate; the first data center determines whether the arbitration device can arbitrate according to the arbitration device flag.
- the processor 703 may implement the arbitration device when the communication between the first data center and the arbitration device is not disconnected, or when it is determined that the communication between the second data center and the arbitration device is not disconnected.
- the flag bit is set to be arbitrated by the arbitration device; when the communication between the first data center and the arbitration device is disconnected, and the communication between the first data center and the second data center is disconnected, the arbitration device flag is set to
- the arbitration device can perform arbitration; when the communication between the first data center and the arbitration device is disconnected, and the communication between the second data center and the arbitration device is determined to be disconnected, the arbitration device flag is set to the arbitration device cannot arbitrate .
- the processor 703 can implement, when the communication between the first data center and the second data center is disconnected, and the arbitration device can perform arbitration, view the arbitration policy; When the policy determines that the first data center is the priority data center, it immediately sends an arbitration request to the arbitration device; when it is determined according to the arbitration policy that the first data center is not the priority data center, the set time is delayed. The arbitration request is sent to the arbitration device.
- the arbitration device may employ a cloud server.
- the first data center when the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration, the first data center checks the preset arbitration policy, and determines the first according to the arbitration policy. A data center continues to provide services when the data center is prioritized, and when the first data center is determined not to be the priority data center according to the arbitration policy, the service is stopped, so that the first data center determines that the communication with the second data center is disconnected, and the arbitration is performed. When the device cannot be arbitrated, only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration device, and ensures uninterrupted service for the user.
- an embodiment of the present invention provides an arbitration system, where the system includes:
- the first data center 801 is configured to: when determining that the communication with the second data center 802 is disconnected, and the arbitration device is unable to perform arbitration, view the preset arbitration policy; and determine, according to the arbitration policy, that the first data center 801 is When the data center is prioritized, the service is continued; when it is determined according to the arbitration policy that the first data center 801 is not the priority data center, the service is stopped;
- the second data center 802 is configured to: when determining that the communication with the first data center 801 is disconnected, and the arbitration device is unable to perform arbitration, view the preset arbitration policy; when determining that the second data center 802 is determined according to the arbitration policy When the data center is prioritized, the service is continued; when it is determined according to the arbitration policy that the second data center 802 is not the priority data center, the service is stopped;
- the first data center 801 and the second data center 802 are dual active data centers.
- the first data center when the first data center determines that the communication with the second data center is disconnected, and the arbitration device cannot perform arbitration, the first data center checks the preset arbitration policy, and determines the first according to the arbitration policy. A data center continues to provide services when the data center is prioritized, and when the first data center is determined not to be the priority data center according to the arbitration policy, the service is stopped, so that the first data center determines that the communication with the second data center is disconnected, and the arbitration is performed. When the device cannot be arbitrated, only the priority data center continues to provide services, which solves the problem of service interruption caused by the failure of the arbitration device, and ensures uninterrupted service for the user.
- the arbitration apparatus for the active-active data center provided by the foregoing embodiment is only illustrated by the division of the above functional modules. In actual applications, The above function assignment is performed by different functional modules, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.
- the arbitration apparatus for the active-active data center provided by the foregoing embodiment is the same as the embodiment of the arbitration method for the active-active data center. The specific implementation process is described in detail in the method embodiment, and details are not described herein again.
- a person skilled in the art may understand that all or part of the steps of implementing the above embodiments may be completed by hardware, or may be instructed by a program to execute related hardware, and the program may be stored in a computer readable storage medium.
- the storage medium mentioned may be a read only memory, a magnetic disk or an optical disk or the like.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Computer And Data Communications (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Hardware Redundancy (AREA)
Abstract
本发明实施例提供了一种用于双活数据中心的仲裁方法、装置及系统,涉及计算机技术领域,所述仲裁方法包括:当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略;当根据仲裁策略确定第一数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定第一数据中心不是优先数据中心时,停止提供服务;其中,所述第一数据中心和所述第二数据中心为双活数据中心。本发明通过上述方案使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
Description
本发明涉及计算机技术领域,特别涉及一种用于双活数据中心的仲裁方法、装置及系统。
出于灾备(Disaster Recovery)的目的,一般都会建设至少两个数据中心,一个数据中心承担用户的业务,另一个数据中心备份数据、配置、业务等。双活数据中心是指两个数据中心同时承担业务且相互备份,以提高两个数据中心的整体服务能力和系统资源利用率。
双活数据中心中的两个数据中心之间每隔设定时间会向对方发送一个心跳包,若在设定时间内未接收到对方的心跳包,则备份中断。此时如果两个数据中心都继续承担业务,就会出现数据不一致的问题。仲裁机制是当前避免出现数据不一致问题的手段之一,其实现方式为:两个数据中心分别向独立于两个数据中心设置的仲裁设备发送仲裁请求,仲裁设备根据仲裁请求确定获胜的数据中心,获胜的数据中心继续提供服务(即承担业务),没有获胜的数据中心停止提供服务。
在实现本发明的过程中,发明人发现现有技术至少存在以下问题:
当仲裁设备出现故障时,仲裁机制失效。此时若两个数据中心在设定时间内未接收到对方的心跳包,则无法确定继续提供服务的数据中心。为了避免出现数据不一致的问题,两个数据中心会同时停止服务,造成服务中断。
发明内容
为了解决现有技术仲裁设备出现故障造成服务中断的问题,本发明实施例提供了一种用于双活数据中心的仲裁方法、装置及系统。所述技术方案如下:
第一方面,本发明实施例提供了一种用于双活数据中心的仲裁方法,所述仲裁方法包括:
当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进
行仲裁时,所述第一数据中心查看预先设定的仲裁策略;
当所述第一数据中心根据所述仲裁策略确定所述第一数据中心为优先数据中心时,所述第一数据中心继续提供服务;
当所述第一数据中心根据所述仲裁策略确定所述第一数据中心不是优先数据中心时,所述第一数据中心停止提供服务;
其中,所述第一数据中心和所述第二数据中心为双活数据中心。
在第一方面一种可能的实现方式中,所述仲裁方法还包括:
所述第一数据中心确定所述第一数据中心是否处于设定的异常状态;
当所述第一数据中心处于设定的异常状态,且所述第一数据中心与所述第二数据中心之间的通信没有断开时,所述第一数据中心向所述第二数据中心发送通知消息,所述通知消息用于指示所述第二数据中心代替所述第一数据中心提供服务。
在第一方面另一种可能的实现方式中,所述仲裁设备采用容灾设备,所述容灾设备用于备份所述第一数据中心和所述第二数据中心的数据。
可选地,所述仲裁方法还包括:
当所述第一数据中心确定与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,所述第一数据中心采用数据备份链路向所述仲裁设备发送仲裁请求,所述数据备份链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
优选地,所述第一数据中心采用所述数据备份链路向所述仲裁设备发送仲裁请求,包括:
当所述第一数据中心同时需要向所述仲裁设备发送所述仲裁请求和所述第一数据中心的数据时,所述第一数据中心优先向所述仲裁设备发送所述仲裁请求;或者,
所述第一数据中心采用仲裁逻辑链路向所述仲裁设备发送所述仲裁请求,所述数据备份链路划分为所述仲裁逻辑链路和数据逻辑链路,所述数据逻辑链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
在第一方面又一种可能的实现方式中,所述仲裁方法还包括:
所述第一数据中心实时监测所述第一数据中心与所述仲裁设备之间、以及所述第二数据中心与所述仲裁设备之间的通信是否断开;
所述第一数据中心根据监测结果,设置仲裁设备标志位,所述仲裁设备标
志位用于表示所述仲裁设备能否进行仲裁;
所述第一数据中心根据所述仲裁设备标志位确定所述仲裁设备能否进行仲裁。
可选地,所述第一数据中心根据监测结果,设置仲裁设备标志位,包括:
当所述第一数据中心确定与所述仲裁设备之间的通信没有断开时,或者,当所述第一数据中心确定所述第二数据中心与所述仲裁设备之间的通信没有断开时,所述第一数据中心将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;
当所述第一数据中心确定与所述仲裁设备之间的通信断开,且确定与所述第二数据中心之间的通信断开时,所述第一数据中心将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;
当所述第一数据中心确定与所述仲裁设备之间的通信断开,且确定所述第二数据中心与所述仲裁设备之间的通信断开时,所述第一数据中心将所述仲裁设备标志位设置为所述仲裁设备不能进行仲裁。
在第一方面又一种可能的实现方式中,所述仲裁方法还包括:
当所述第一数据中心确定与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,所述第一数据中心查看所述仲裁策略;
当所述第一数据中心根据所述仲裁策略确定所述第一数据中心为所述优先数据中心时,所述第一数据中心即时向所述仲裁设备发送仲裁请求;
当所述第一数据中心根据所述仲裁策略确定所述第一数据中心不是所述优先数据中心时,所述第一数据中心延迟设定时间后向所述仲裁设备发送仲裁请求。
在第一方面又一种可能的实现方式中,所述仲裁设备采用云服务器。
第二方面,本发明实施例提供了一种用于双活数据中心的仲裁装置,所述仲裁装置包括:
第一查看模块,用于当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;
第一服务模块,用于当根据所述仲裁策略确定所述第一数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定所述第一数据中心不是优先数据中心时,停止提供服务;
其中,所述第一数据中心和所述第二数据中心为双活数据中心。
在第二方面一种可能的实现方式中,所述仲裁装置还包括:
状态确定模块,用于确定所述第一数据中心是否处于设定的异常状态;
消息发送模块,用于当所述第一数据中心处于设定的异常状态,且所述第一数据中心与所述第二数据中心之间的通信没有断开时,向所述第二数据中心发送通知消息,所述通知消息用于指示所述第二数据中心代替所述第一数据中心提供服务。
在第二方面另一种可能的实现方式中,所述仲裁设备采用容灾设备,所述容灾设备用于备份所述第一数据中心和所述第二数据中心的数据。
可选地,所述仲裁装置还包括:
请求发送模块,用于当所述第一数据中心与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,采用数据备份链路向所述仲裁设备发送仲裁请求,所述数据备份链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
优选地,所述请求发送模块用于,
当所述第一数据中心同时需要向所述仲裁设备发送所述仲裁请求和所述第一数据中心的数据时,优先向所述仲裁设备发送所述仲裁请求;或者,
采用仲裁逻辑链路向所述仲裁设备发送所述仲裁请求,所述数据备份链路划分为所述仲裁逻辑链路和数据逻辑链路,所述数据逻辑链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
在第二方面又一种可能的实现方式中,所述仲裁装置还包括:
监测模块,用于实时监测所述第一数据中心与所述仲裁设备之间、以及所述第二数据中心与所述仲裁设备之间的通信是否断开;
设置模块,用于根据监测结果,设置仲裁设备标志位,所述仲裁设备标志位用于表示所述仲裁设备能否进行仲裁;
仲裁设备确定模块,用于所述第一数据中心根据所述仲裁设备标志位确定所述仲裁设备能否进行仲裁。
可选地,所述设置模块用于,
当所述第一数据中心与所述仲裁设备之间的通信没有断开时,或者,当确定所述第二数据中心与所述仲裁设备之间的通信没有断开时,将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;
当所述第一数据中心与所述仲裁设备之间的通信断开,且所述第一数据中
心与所述第二数据中心之间的通信断开时,将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;
当所述第一数据中心与所述仲裁设备之间的通信断开,且确定所述第二数据中心与所述仲裁设备之间的通信断开时,将所述仲裁设备标志位设置为所述仲裁设备不能进行仲裁。
在第二方面又一种可能的实现方式中,所述仲裁装置还包括:
第二查看模块,用于当所述第一数据中心与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,查看所述仲裁策略;
第二服务模块,当根据所述仲裁策略确定所述第一数据中心为所述优先数据中心时,即时向所述仲裁设备发送仲裁请求;当根据所述仲裁策略确定所述第一数据中心不是所述优先数据中心时,延迟设定时间后向所述仲裁设备发送仲裁请求。
在第二方面又一种可能的实现方式中,所述仲裁设备采用云服务器。
第三方面,本发明实施例提供了一种用于双活数据中心的仲裁系统,所述仲裁系统包括:
第一数据中心,用于当确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据所述仲裁策略确定所述第一数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定所述第一数据中心不是优先数据中心时,停止提供服务;
所述第二数据中心,用于当确定与所述第一数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据所述仲裁策略确定所述第二数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定所述第二数据中心不是优先数据中心时,停止提供服务;
其中,所述第一数据中心和所述第二数据中心为双活数据中心。
本发明实施例提供的技术方案的有益效果是:
通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提
供不中断的服务。
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本发明实施例1提供的一种用于双活数据中心的仲裁方法的应用场景图;
图2是本发明实施例1提供的一种用于双活数据中心的仲裁方法的流程图;
图3是本发明实施例2提供的一种用于双活数据中心的仲裁方法的信息交互图;
图4是本发明实施例2提供的确定仲裁设备是否能进行仲裁的流程图;
图5是本发明实施例2提供的异常状态处理过程的流程图;
图6是本发明实施例3提供的一种用于双活数据中心的仲裁方法的应用场景图;
图7是本发明实施例4提供的一种用于双活数据中心的仲裁方法的应用场景图;
图8是本发明实施例5提供的一种用于双活数据中心的仲裁装置的结构示意图;
图9是本发明实施例6提供的一种用于双活数据中心的仲裁装置的结构示意图;
图10是本发明实施例7提供的一种用于双活数据中心的仲裁装置的硬件示意图;
图11是本发明实施例8提供的一种用于双活数据中心的仲裁系统的结构示意图。
为使本发明的目的、技术方案和优点更加清楚,下面将结合附图对本发明实施方式作进一步地详细描述。
下面先结合图1简单介绍一下本实施例提供的用于双活数据中心的仲裁方法的应用场景:
图1所示的应用场景中设置有第一数据中心1和第二数据中心2,第一数据中心1和第二数据中心2为双活数据中心,即第一数据中心1和第二数据中心2同时提供服务且相互备份。如图1所示,第一数据中心1与第二数据中心2连接。具体地,第一数据中心1和第二数据中心2之间可以通过光纤或网线连接。第一数据中心1和第二数据中心2通过该光纤或网线备份数据,并且每隔设定时间(如1s)通过该光纤或网线相互发送心跳包,以确定第一数据中心与第二数据中心之间的连接是否断开。
在实际应用中,第一数据中心1和第二数据中心2之间的数据备份可以为同步复制。为了实现同步复制,一方面可以采用光纤等传输速度快的链路传输备份的数据,另一方面可以将第一数据中心1和第二数据中心2之间的距离限定在设定距离(如100km)内,如第一数据中心1和第二数据中心2设置在同一个城市里。
具体地,第一数据中心1和第二数据中心2可以均包括存储层、应用层、网络层,第一数据中心1和第二数据中心2的同一层(存储层、应用层、或网络层)上分别设置有一个或多个集群(如应用层上的Oracle真正应用集群)的部分节点,本发明实施例提供的仲裁方法可以具体适用于第一数据中心1和第二数据中心2的同一层的仲裁,也可以具体适用于第一数据中心1和第二数据中心2上同一个集群的仲裁。
可选地,图1所示的应用场景中还可以设置有仲裁设备3,仲裁设备3独立于第一数据中心1和第二数据中心2设置,仲裁设备3分别与第一数据中心1、第二数据中心2连接。具体地,仲裁设备3可以为用于实现背景技术部分所述的仲裁机制而专门设置的一个设备。
需要说明的是,图1所示的应用场景仅为举例,本发明并不限制于此。
实施例1
本发明实施例提供了一种用于双活数据中心的仲裁方法,参见图2,该仲裁方法包括:
步骤101:当第一数据中心确定与第二数据中心之间的通信断开,且仲裁
设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略。
在本实施例中,第一数据中心和第二数据中心为双活数据中心。
在实际应用中,第一数据中心和第二数据中心之间的通信是否断开,可以根据第一数据中心和第二数据中心之间每隔设定时间(如1s)相互发送的心跳包确定。若第一数据中心在设定的阈值时间(如1s、5s)内接收到第二数据中心发送的心跳包,则第一数据中心确定第一数据中心与第二数据中心之间的通信没有断开;若第一数据中心在设定的阈值时间内没有接收到第二数据中心发送的心跳包,则第一数据中心确定第一数据中心与第二数据中心之间的通信断开。同样地,若第二数据中心在设定的阈值时间内接收到第一数据中心发送的心跳包,则第二数据中心确定第一数据中心与第二数据中心之间的通信没有断开;若第二数据中心在设定的阈值时间内没有接收到第一数据中心发送的心跳包,则第二数据中心确定第一数据中心与第二数据中心之间的通信断开。
可选地,该方法还可以包括:
第一数据中心监测第一数据中心与第二数据中心之间的通信是否断开。
步骤102:当第一数据中心根据仲裁策略确定第一数据中心为优先数据中心时,第一数据中心继续提供服务。
步骤103:当第一数据中心根据仲裁策略确定第一数据中心不是优先数据中心时,第一数据中心停止提供服务。
需要说明的是,本实施例以执行主体为第一数据中心为例进行说明,在具体实现中,第二数据中心也会和第一数据中心一样,执行如下步骤:当第二数据中心确定与第一数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第二数据中心查看预先设定的仲裁策略;当第二数据中心根据仲裁策略确定第二数据中心为优先数据中心时,第二数据中心继续提供服务;当第二数据中心根据仲裁策略确定第二数据中心不是优先数据中心时,第二数据中心停止提供服务。
在实际应用中,用户会在双活数据中心中,选择一个数据中心作为优先数据中心,并根据选择的结果在各个数据中心中设置用于表示是否为优先数据中心的标志位,如1表示为优先数据中心,0表示不是优先数据中心。当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心和第二数据中心均通过各自的标志位确定其是否为优先数据中心,为优先数据中心的那个数据中心继续提供服务,不是优先数据中心的那个数据中心
停止提供服务,以避免由于备份中断的两个数据中心同时提供服务而出现数据不一致的问题。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例2
本发明实施例提供了一种用于双活数据中心的仲裁方法,本实施例是对实施例1提供的用户双活数据中心的仲裁方法进行进一步详细介绍,参见图3,该仲裁方法包括:
步骤201:第一数据中心实时监测第一数据中心与仲裁设备之间、以及第二数据中心与仲裁设备之间的通信是否断开。
在本实施例中,第一数据中心和第二数据中心为双活数据中心,仲裁设备独立于第一数据中心和第二数据中心设置。
在实际应用中,第一数据中心和第二数据中心之间的通信是否断开,可以根据第一数据中心和第二数据中心之间每隔设定时间(如1s)相互发送的心跳包确定。若第一数据中心在设定的阈值时间(如1s、5s)内接收到第二数据中心发送的心跳包,则第一数据中心确定第一数据中心与第二数据中心之间的通信没有断开;若第一数据中心在设定的阈值时间内没有接收到第二数据中心发送的心跳包,则第一数据中心确定第一数据中心与第二数据中心之间的通信断开。同样地,若第二数据中心在设定的阈值时间内接收到第一数据中心发送的心跳包,则第二数据中心确定第一数据中心与第二数据中心之间的通信没有断开;若第二数据中心在设定的阈值时间内没有接收到第一数据中心发送的心跳包,则第二数据中心确定第一数据中心与第二数据中心之间的通信断开。
在具体实现中,当第一数据中心确定与第二数据中心的通信没有断开时,第一数据中心可以向第二数据中心询问第二数据中心与仲裁设备之间的通信是否断开,实现确定第二数据中心与仲裁设备之间的通信是否断开。
第一数据中心和第二数据中心自身与仲裁设备之间的通信是否断开,可以根据第一数据中心和第二数据中心各自与仲裁设备之间每隔设定时间(如1s)相互发送的心跳包确定。若第一数据中心(或第二数据中心)在设定的阈值时间(如1s、5s)内接收到仲裁设备发送的心跳包,则第一数据中心(或第二数据中心)确定第一数据中心(或第二数据中心)与仲裁设备之间的通信没有断开;若第一数据中心(或第二数据中心)在设定的阈值时间内没有接收到在仲裁设备发送的心跳包,则第一数据中心(或第二数据中心)确定第一数据中心(或第二数据中心)与仲裁设备之间的通信断开。
步骤202:第一数据中心根据监测结果,设置仲裁设备标志位。
在本实施例中,仲裁设备标志位用于表示仲裁设备能否进行仲裁。
在本实施例中,参见图4,该步骤202可以包括:
当第一数据中心确定与仲裁设备之间的通信没有断开时,或者,当第一数据中心确定第二数据中心与仲裁设备之间的通信没有断开时,第一数据中心将仲裁设备标志位设置为仲裁设备能进行仲裁;
当第一数据中心确定与仲裁设备之间的通信断开,且确定与第二数据中心之间的通信断开时,第一数据中心将仲裁设备标志位设置为仲裁设备能进行仲裁;
当第一数据中心确定与仲裁设备之间的通信断开,且确定第二数据中心与仲裁设备之间的通信断开时,第一数据中心将仲裁设备标志位设置为仲裁设备不能进行仲裁。
可以理解地,当第一数据中心确定与仲裁设备之间的通信没有断开时,或者,当第一数据中心确定第二数据中心与仲裁设备之间的通信没有断开时,第一数据中心将仲裁设备标志位设置为仲裁设备能进行仲裁,即当确定有一个数据中心(第一数据中心或第二数据中心)可以使用仲裁设备时,即确定仲裁设备能进行仲裁,以充分利用仲裁设备进行仲裁,以避免存在根据优先数据中心进行仲裁(详见步骤205a-步骤205c)时优先数据中心是发生故障的一方的风险。
当第一数据中心确定与仲裁设备之间的通信断开,且确定与第二数据中心之间的通信断开时,第一数据中心将仲裁设备标志位设置为仲裁设备能进行仲裁,即当不能确定第二数据中心与仲裁设备之间的通信是否断开时,默认采用仲裁设备进行仲裁,以避免第二数据中心与仲裁设备之间的通信没有断开而继
续提供服务,同时第一数据中心刚好为优先数据中心也继续提供服务而造成数据不一致的情况发生。
步骤203:第一数据中心根据仲裁设备标志位确定仲裁设备能否进行仲裁。当仲裁设备能进行仲裁时,执行步骤204a-步骤204d;当仲裁设备不能进行仲裁时,执行步骤205a-步骤205c。
例如,仲裁设备标志位为1表示仲裁设备能进行仲裁,仲裁设备标志位为0表示仲裁设备不能进行仲裁。
步骤204a:当第一数据中心确定与第二数据中心之间的通信断开时,第一数据中心向仲裁设备发送仲裁请求。
在本实施例中,该步骤204a可以包括:
第一数据中心查看预先设定的仲裁策略;
当第一数据中心根据仲裁策略确定第一数据中心为优先数据中心时,第一数据中心即时向仲裁设备发送仲裁请求;
当第一数据中心根据仲裁策略确定第一数据中心不是优先数据中心时,第一数据中心延迟设定时间后向仲裁设备发送仲裁请求。
在实际应用中,当第一数据中心和第二数据中心之间的通信断开时,用户会希望某个数据中心能优先存活(继续提供服务的数据中心)。因此用户会在双活数据中心中,选择一个数据中心作为优先数据中心,并根据选择的结果在各个数据中心中设置用于表示是否为优先数据中心的标志位,如1表示为优先数据中心,0表示不是优先数据中心。当第一数据中心与第二数据中心之间的通信断开时,第一数据中心和第二数据中心均通过各自的标志位确定其是否为优先数据中心,为优先数据中心的那个数据中心即时向仲裁设备发送仲裁请求,不是优先数据中心的那个数据中心延迟设定时间后向仲裁设备发送仲裁请求,从而提高为优先数据中心的那个数据中心的存活概率。
步骤204b:仲裁设备根据仲裁请求,确定仲裁结果。
在具体实现中,仲裁设备可以根据接收到仲裁请求的先后顺序确定仲裁结果,即仲裁设备将最先接收到的仲裁请求的发送方确定为获胜方(继续提供服务的数据中心)。具体地,仲裁设备中设有标志位,1表示已接收过仲裁请求(即获胜方已确定),0表示未接收到仲裁请求。当某个数据中心向仲裁设备发送仲裁请求时,仲裁设备查看标志位,若标志位为0,则回复该数据中心其为获胜方,同时将该标志位改为0;若标志位为1,则回复该数据中心其不是获胜方。
仲裁设备也可以根据各数据中心承担业务的多少确定仲裁结果,即仲裁设备将承担最多业务的数据中心确定为获胜方,以节省由获胜方承担所有业务所需的过渡时间。
仲裁设备还可以根据其它基准确定仲裁结果,本发明对此不作限制。
步骤204c:仲裁设备向第一数据中心发送仲裁结果。
步骤204d:第一数据中心根据仲裁结果,继续或停止提供服务。
具体地,该步骤204d可以包括:
当仲裁结果包括第一数据中心是获胜方时,第一数据中心继续提供服务;
当仲裁结果包括第一数据中心不是获胜方时,第一数据中心停止提供服务。
需要说明的是,执行步骤204a-204d时,第一数据中心会暂停服务,以保证第一数据中心和第二数据中心的数据一致。
步骤201-步骤204d为可选步骤。由于根据优先数据中心进行仲裁(详见步骤205a-步骤205c)是预先指定获胜方(继续提供服务的数据中心),因此存在获胜方是发生故障的数据中心的风险。又由于发生故障的数据中心不可能向仲裁设备发送仲裁请求,因此由仲裁设备进行仲裁不存在获胜方是发生故障的数据中心的风险。当执行步骤201-步骤204d时,优先使用仲裁设备进行仲裁,当仲裁设备不能进行仲裁时,才根据优先数据中心进行仲裁,一方面尽可能避免产生获胜方是发生故障的数据中心的风险,另一方面也保证了在仲裁设备不能进行仲裁时,可以确定获胜方,保证服务不中断。当不执行步骤201-步骤204d时,可以避免专门设置实现仲裁机制的仲裁设备,降低了实现成本。
步骤205a:当第一数据中心确定与第二数据中心之间的通信断开时,第一数据中心查看预先设定的仲裁策略。当第一数据中心根据仲裁策略确定第一数据中心为优先数据中心时,执行步骤205b;当第一数据中心根据仲裁策略确定第一数据中心不是优先数据中心时,执行步骤205c。
步骤205b:第一数据中心继续提供服务。
步骤205c:第一数据中心停止提供服务。
如前所述,用户会在双活数据中心中,选择一个数据中心作为优先数据中心,并根据选择的结果在各个数据中心中设置用于表示是否为优先数据中心的标志位,如1表示为优先数据中心,0表示不是优先数据中心。当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中
心和第二数据中心均通过各自的标志位确定其是否为优先数据中心,为优先数据中心的那个数据中心继续提供服务,不是优先数据中心的那个数据中心停止提供服务,以避免由于备份中断的两个数据中心同时提供服务而出现数据不一致的问题。
在本实施例的一种实现方式中,参见图5,该方法还可以包括:
第一数据中心确定第一数据中心是否处于设定的异常状态;
当第一数据中心处于设定的异常状态,且第一数据中心与第二数据中心之间的通信没有断开时,第一数据中心向第二数据中心发送通知消息,通知消息用于指示第二数据中心代替第一数据中心提供服务;
第二数据中心根据通知信息代替第一数据中心提供服务;
第一数据中心停止提供服务。
在实际应用中,第一数据中心和第二数据中心中会预先配置仲裁策略,第一数据中心和第二数据中心根据仲裁策略可以定时进行自检,以确定其是否处于设定的异常状态。当确定自身处于设定的异常状态时,向对方发送通知消息;当接收到对方发送的通知消息时,替代对方提供服务。
第一数据中心停止提供服务可以在接收到第二数据中心完成代替第一数据中心提供服务的交接工作后发送的消息之后,也可以在接收到第二数据中心开始代替第一数据中心提供服务的交接工作后发送的消息之后,还可以在第一数据中心完成数据备份之后,还可以在第一数据中心已无法提供服务之后,本发明对此不作限制。
可选地,设定的异常状态可以包括掉电、电池故障、透写运行、双盘失效中的至少一种。其中,双盘失效是指失效盘数超过可校验的位数,此时数据无法恢复和使用。透写运行是指数据实时写入磁盘中,此时数据写入速率极低。电池故障是指在掉电时没有备用电源将存储器中的数据写入磁盘中,此时一般会采用透写运行。掉电是指没有足够的电能持续进行数据备份。
可以理解地,当第一数据中心处于设定的异常状态时,会影响双活数据中心整体的运行效率和性能,由第一数据中心主动通知第二数据中心代替其提供服务,可以保证双活数据中心提供最优服务。
在实际应用中,上述实现方式与步骤201-步骤203的执行没有先后顺序。由于第一数据中心处于设定的异常状态时,第一数据中心的运行效率和性能已无法满足用户需求,因此在第二数据中心没有发生故障的情况下(第一数据中
心和第二数据中心之间的通信没有断开),不再由仲裁设备或根据优先数据中心进行仲裁,直接确定第二数据中心为获胜方,节省由第二数据中心替代第一数据中心提供服务所需的时间,提高效率。当第二数据中心发生故障的情况下,第一数据中心虽然处于设定的异常状态,但是可能还能继续提供服务,为了保证服务不中断,此时会由仲裁设备或根据设定存活的数据中心进行仲裁,将第一数据中心确定为获胜方。
需要说明的是,第一数据中心和第二数据中心之间的通信在断开之后恢复连接时,第一数据中心和第二数据中心会重新同时提供服务且相互备份。具体地,第一数据中心和第二数据中心可以在确定第一数据中心和第二数据中心之间的通信断开之后,依然继续向对方发送心跳包(此时心跳包的发送间隔可以与第一数据中心和第二数据中心之间的通信没有断开时相同,也可以比第一数据中心和第二数据中心之间的通信没有断开时长),然后当连续接收到设定次数的心跳包时,即可确定第一数据中心和第二数据中心之间的通信恢复,以避免第一数据中心和第二数据中心之间的通信偶然恢复而造成判断错误,确保结论的准确性。第一数据中心和第二数据中心也可以通信设备(如光模块)在第一数据中心和第二数据中心之间的连接恢复之后上报的连通信号(如光信号)确定第一数据中心和第二数据中心之间的通信恢复。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例3
本发明实施例提供了一种用于双活数据中心的仲裁方法,下面先结合图6简单介绍一下本实施例提供的用于双活数据中心的仲裁方法的应用场景:
与图1所示的应用场景相比,图6所示的应用场景中还设置有容灾设备4,容灾设备4用于备份第一数据中心1和第二数据中心2的数据,并在第一数据中心1和第二数据中心2均发生故障时提供服务。如图6所示,容灾设备4分
别与第一数据中心1、第二数据中心2连接。
在实际应用中,如图1所示的应用场景部分所述,第一数据中心1和第二数据中心2一般设置在同一个城市里。当设置第一数据中心1和第二数据中心2的城市发生地震等自然灾害时,第一数据中心1和第二数据中心2很可能会同时发生故障,为了保证容灾设备4此时可以提供服务,容灾设备4与第一数据中心1、第二数据中心2可以分别设置在相隔距离超过设定距离(如100km)的两地,如不同的城市里(即两地三中心)。容易知道,由于容灾设备4与第一数据中心1、第二数据中心2相隔距离较远,容灾设备4与第一数据中心1、第二数据中心2之间的数据备份为异步复制。
可选地,容灾设备4和仲裁设备3可以为两个独立的设备,此时第一数据中心、第二数据中心、仲裁设备的执行步骤与实施例2相同,在此不再详述。
可选地,容灾设备4和仲裁设备3也可以为同一个设备,即由容灾设备4实现仲裁设备3的功能。在具体实现中,会在容灾设备4上划分出一块独立的存储空间,专门用于存放仲裁的信息,如进行仲裁的程序、表示是否接收到仲裁请求的标志位等。可以理解地,与专门设置仲裁设备3相比,采用容灾设备4实现仲裁设备3的功能,简化了双活数据中心的架构,大大降低了实现成本。
当容灾设备4和仲裁设备3为同一个设备时,本实施例中第一数据中心、第二数据中心、仲裁设备的执行步骤与实施例2基本相同,不同之处在于通信链路的设置。
具体地,第一数据中心向仲裁设备发送仲裁请求,可以包括:
第一数据中心采用数据备份链路向仲裁设备发送仲裁请求,数据备份链路用于传输第一数据中心发送给仲裁设备的备份数据。
可以理解地,直接采用数据备份链路传输仲裁请求,可以避免单独铺设传输仲裁请求的物理链路,进一步降低了实现成本。
在本实施例的一种实现方式中,第一数据中心采用数据备份链路向仲裁设备发送仲裁请求,可以包括:
当第一数据中心同时需要向仲裁设备发送仲裁请求和第一数据中心的数据时,第一数据中心优先向仲裁设备发送仲裁请求。
在本实施例的另一种实现方式中,第一数据中心采用数据备份链路向仲裁设备发送仲裁请求,可以包括:
第一数据中心采用仲裁逻辑链路向仲裁设备发送仲裁请求,数据备份链路
划分为仲裁逻辑链路和数据逻辑链路,数据逻辑链路用于传输第一数据中心发送给仲裁设备的备份数据。
例如,数据备份链路的带宽为50M,将其中的1M划分给仲裁逻辑链路,专门用于传输仲裁请求。
具体地,划分给仲裁逻辑链路的带宽大小可以由用户根据实际情况(如进行仲裁的数据中心的数量)进行设定,在此不再详述。
可以理解地,上述两种方式均可以实现仲裁请求的优先传输,避免由于整个数据备份链路被备份数据占用而导致无法仲裁的情况发生。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例4
本发明实施例提供了一种用于双活数据中心的仲裁方法,下面先结合图7简单介绍一下本实施例提供的用于双活数据中心的仲裁方法的应用场景:
与图1所示的应用场景相比,图7所示的应用场景中由云服务器5实现仲裁设备3的功能。如图7所示,云服务器5分别与第一数据中心1、第二数据中心2连接。
在具体实现中,可以先向云服务器5申请提供一台虚拟机,然后将进行仲裁的程序部署在申请的虚拟机上,即可由云服务器5进行仲裁。
具体地,云服务器5可以采用第三方提供商提供的免费或成本低廉的公有云,如华为、亚马逊、阿里巴巴、微软提供的公有云。
可以理解地,采用公有云实现仲裁设备3,可以大大降低仲裁设备3的实现成本。
容易知道,公有云的核心属性是共享资源服务,为了保证用户数据的安全,本实施例中除了与实施例2中第一数据中心、第二数据中心、仲裁设备的执行步骤基本相同步骤之外,还包括一些提高数据中心存储数据安全性的设置。
在本实施例的一种实现方式中,第一数据中心向仲裁设备发送仲裁请求,可以包括:
第一数据中心采用虚拟专用网络(Virtual Private Network,简称VPN)向仲裁设备发送仲裁请求。
在本实施例的另一种实现方式中,第一数据中心向仲裁设备发送仲裁请求,可以包括:
第一数据中心向仲裁设备发送仲裁请求,该仲裁请求的目的端口为设定端口号。
在实际应用中,可以在第一数据中心和仲裁设备之间设置防火墙,通过防火墙设置与第一数据中心通信的云服务器的端口号。当传输到防火墙的消息的源端口和目的端口包括除第一数据中心的端口号和设定端口号之外的端口号时,防火墙会直接将该消息删除,即终止该消息的传输。
在本实施例的又一种实现方式中,第一数据中心向仲裁设备发送仲裁请求,可以包括:
第一数据中心向仲裁设备发送通信请求;
第一数据中心在接收到仲裁设备发送的通信请求回复后,向仲裁设备发送仲裁请求。
在实际应用中,可以在第一数据中心和仲裁设备之间设置防火墙,通过防火墙将云服务器与第一数据中心之间的通信设置为只能由第一数据中心发起,即只有第一数据中心发送的通信请求才能通过防火墙传输给仲裁设备。若云服务器向第一数据中心发送通信请求,则防火墙会直接将其删除,通信请求无法发送到第一数据中心,该通信不会建立。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例5
参见图8,本发明实施例提供了一种用于双活数据中心的仲裁装置,该装置设置在第一数据中心上,该仲裁装置包括:
第一查看模块501,用于当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;
第一服务模块502,用于当根据仲裁策略确定第一数据中心为优先数据中心时,继续提供服务;当根据仲裁策略确定第一数据中心不是优先数据中心时,停止提供服务;
其中,第一数据中心和第二数据中心为双活数据中心。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例6
参见图9,本发明实施例提供了一种用于双活数据中心的仲裁装置,本实施例是对实施例5提供的用于双活数据中心的仲裁装置的进一步详细描述,该装置设置在第一数据中心上,该仲裁装置包括:
第一查看模块601,用于当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;
第一服务模块602,用于当根据仲裁策略确定第一数据中心为优先数据中心时,继续提供服务;当根据仲裁策略确定第一数据中心不是优先数据中心时,停止提供服务;
其中,第一数据中心和第二数据中心为双活数据中心。
在本实施例的一种实现方式中,该仲裁装置还可以包括:
状态确定模块603,用于确定第一数据中心是否处于设定的异常状态;
消息发送模块604,用于当第一数据中心处于设定的异常状态,且第一数据中心与第二数据中心之间的通信没有断开时,向第二数据中心发送通知消息,通知消息用于指示第二数据中心代替第一数据中心提供服务。
在本实施例的另一种实现方式中,仲裁设备可以采用容灾设备,容灾设备用于备份第一数据中心和第二数据中心的数据。
可选地,该仲裁装置还可以包括:
请求发送模块605,用于当第一数据中心与第二数据中心之间的通信断开,且仲裁设备能进行仲裁时,采用数据备份链路向仲裁设备发送仲裁请求,数据备份链路用于传输第一数据中心发送给仲裁设备的备份数据。
优选地,请求发送模块605可以用于,
当第一数据中心同时需要向仲裁设备发送仲裁请求和第一数据中心的数据时,优先向仲裁设备发送仲裁请求;或者,
采用仲裁逻辑链路向仲裁设备发送仲裁请求,数据备份链路划分为仲裁逻辑链路和数据逻辑链路,数据逻辑链路用于传输第一数据中心发送给仲裁设备的备份数据。
在本实施例的又一种实现方式中,该仲裁装置还可以包括:
监测模块606,用于实时监测第一数据中心与仲裁设备之间、以及第二数据中心与仲裁设备之间的通信是否断开;
设置模块607,用于根据监测结果,设置仲裁设备标志位,仲裁设备标志位用于表示仲裁设备能否进行仲裁;
仲裁设备确定模块608,用于第一数据中心根据仲裁设备标志位确定仲裁设备能否进行仲裁。
可选地,设置模块607可以用于,
当第一数据中心与仲裁设备之间的通信没有断开时,或者,当确定第二数据中心与仲裁设备之间的通信没有断开时,将仲裁设备标志位设置为仲裁设备能进行仲裁;
当第一数据中心与仲裁设备之间的通信断开,且第一数据中心与第二数据中心之间的通信断开时,将仲裁设备标志位设置为仲裁设备能进行仲裁;
当第一数据中心与仲裁设备之间的通信断开,且确定第二数据中心与仲裁设备之间的通信断开时,将仲裁设备标志位设置为仲裁设备不能进行仲裁。
在本实施例的又一种实现方式中,该仲裁装置还可以包括:
第二查看模块609,用于当第一数据中心与第二数据中心之间的通信断开,且仲裁设备能进行仲裁时,查看仲裁策略;
第二服务模块610,用于当根据仲裁策略确定第一数据中心为优先数据中
心时,即时向仲裁设备发送仲裁请求;当根据仲裁策略确定第一数据中心不是优先数据中心时,延迟设定时间后向仲裁设备发送仲裁请求。
在本实施例的又一种实现方式中,仲裁设备可以采用云服务器。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例7
本发明实施例提供了一种用于双活数据中心的仲裁装置,该仲裁装置可以例如是服务器、个人电脑。参见图10,该设备包括:网络接口701、存储器702以及处理器703(例如CPU),可以用于执行实施例1、实施例2、实施例3或者实施例4的方法。
下面结合图10对系统700的各个构成部件进行具体的介绍:
存储器702可用于存储软件程序以及应用模块,处理器703通过运行存储在存储器702的软件程序以及应用模块,从而执行系统700的各种功能应用以及数据处理。存储器702可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序等;存储数据区可存储根据系统700的处理所创建的数据(比如广告推送策略、推送记录)等。此外,存储器702可以包括高速RAM(Random Access Memory,随机存取存储器),还可以包括非易失性存储器(non-volatile memory),例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
处理器703是系统700的控制中心,利用各种接口和线路连接整个系统700的各个部分。
具体地,处理器703通过运行或执行存储在存储器702内的软件程序和应用模块,以及调用存储在存储器702内的数据,处理器703可以实现,当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据仲裁策略确定第一数据中心为优先数据中心时,
继续提供服务;当根据仲裁策略确定第一数据中心不是优先数据中心时,停止提供服务;其中,第一数据中心和第二数据中心为双活数据中心。
在本实施例的一种实现方式中,处理器703可实现,确定第一数据中心是否处于设定的异常状态;当第一数据中心处于设定的异常状态,且第一数据中心与第二数据中心之间的通信没有断开时,向第二数据中心发送通知消息,通知消息用于指示第二数据中心代替第一数据中心提供服务。
在本实施例的另一种实现方式中,仲裁设备可以采用容灾设备,容灾设备用于备份第一数据中心和第二数据中心的数据。
可选地,处理器703可实现,当第一数据中心与第二数据中心之间的通信断开,且仲裁设备能进行仲裁时,采用数据备份链路向仲裁设备发送仲裁请求,数据备份链路用于传输第一数据中心发送给仲裁设备的备份数据。
优选地,处理器703可实现,当第一数据中心同时需要向仲裁设备发送仲裁请求和第一数据中心的数据时,优先向仲裁设备发送仲裁请求;或者,采用仲裁逻辑链路向仲裁设备发送仲裁请求,数据备份链路划分为仲裁逻辑链路和数据逻辑链路,数据逻辑链路用于传输第一数据中心发送给仲裁设备的备份数据。
在本实施例的又一种实现方式中,处理器703可实现,实时监测第一数据中心与仲裁设备之间、以及第二数据中心与仲裁设备之间的通信是否断开;根据监测结果,设置仲裁设备标志位,仲裁设备标志位用于表示仲裁设备能否进行仲裁;第一数据中心根据仲裁设备标志位确定仲裁设备能否进行仲裁。
可选地,处理器703可实现,当第一数据中心与仲裁设备之间的通信没有断开时,或者,当确定第二数据中心与仲裁设备之间的通信没有断开时,将仲裁设备标志位设置为仲裁设备能进行仲裁;当第一数据中心与仲裁设备之间的通信断开,且第一数据中心与第二数据中心之间的通信断开时,将仲裁设备标志位设置为仲裁设备能进行仲裁;当第一数据中心与仲裁设备之间的通信断开,且确定第二数据中心与仲裁设备之间的通信断开时,将仲裁设备标志位设置为仲裁设备不能进行仲裁。
在本实施例的又一种实现方式中,处理器703可实现,当第一数据中心与第二数据中心之间的通信断开,且仲裁设备能进行仲裁时,查看仲裁策略;当根据仲裁策略确定第一数据中心为优先数据中心时,即时向仲裁设备发送仲裁请求;当根据仲裁策略确定第一数据中心不是优先数据中心时,延迟设定时间
后向仲裁设备发送仲裁请求。
在本实施例的又一种实现方式中,仲裁设备可以采用云服务器。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
实施例8
参见图11,本发明实施例提供了一种仲裁系统,该系统包括:
第一数据中心801,用于当确定与第二数据中心802之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据仲裁策略确定第一数据中心801为优先数据中心时,继续提供服务;当根据仲裁策略确定第一数据中心801不是优先数据中心时,停止提供服务;
第二数据中心802,用于当确定与第一数据中心801之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据仲裁策略确定第二数据中心802为优先数据中心时,继续提供服务;当根据仲裁策略确定第二数据中心802不是优先数据中心时,停止提供服务;
其中,第一数据中心801和第二数据中心802为双活数据中心。
本发明实施例通过当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,第一数据中心查看预先设定的仲裁策略,并当根据仲裁策略确定第一数据中心为优先数据中心时继续提供服务,当根据仲裁策略确定第一数据中心不是优先数据中心时停止提供服务,使第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,只有优先数据中心继续提供服务,解决了由于仲裁设备出现故障而造成服务中断的问题,保证了为用户提供不中断的服务。
需要说明的是:上述实施例提供的用于双活数据中心的仲裁装置在仲裁时,仅以上述各功能模块的划分进行举例说明,实际应用中,可以根据需要而
将上述功能分配由不同的功能模块完成,即将装置的内部结构划分成不同的功能模块,以完成以上描述的全部或者部分功能。另外,上述实施例提供的用于双活数据中心的仲裁装置与用于双活数据中心的仲裁方法实施例属于同一构思,其具体实现过程详见方法实施例,这里不再赘述。
上述本发明实施例序号仅仅为了描述,不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成,也可以通过程序来指令相关的硬件完成,所述的程序可以存储于一种计算机可读存储介质中,上述提到的存储介质可以是只读存储器,磁盘或光盘等。
以上所述仅为本发明的较佳实施例,并不用以限制本发明,凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。
Claims (20)
- 一种用于双活数据中心的仲裁方法,其特征在于,所述仲裁方法包括:当第一数据中心确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,所述第一数据中心查看预先设定的仲裁策略;当所述第一数据中心根据所述仲裁策略确定所述第一数据中心为优先数据中心时,所述第一数据中心继续提供服务;当所述第一数据中心根据所述仲裁策略确定所述第一数据中心不是优先数据中心时,所述第一数据中心停止提供服务;其中,所述第一数据中心和所述第二数据中心为双活数据中心。
- 根据权利要求1所述的仲裁方法,其特征在于,所述仲裁方法还包括:所述第一数据中心确定所述第一数据中心是否处于设定的异常状态;当所述第一数据中心处于设定的异常状态,且所述第一数据中心与所述第二数据中心之间的通信没有断开时,所述第一数据中心向所述第二数据中心发送通知消息,所述通知消息用于指示所述第二数据中心代替所述第一数据中心提供服务。
- 根据权利要求1或2所述的仲裁方法,其特征在于,所述仲裁设备采用容灾设备,所述容灾设备用于备份所述第一数据中心和所述第二数据中心的数据。
- 根据权利要求3所述的仲裁方法,其特征在于,所述仲裁方法还包括:当所述第一数据中心确定与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,所述第一数据中心采用数据备份链路向所述仲裁设备发送仲裁请求,所述数据备份链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
- 根据权利要求4所述的仲裁方法,其特征在于,所述第一数据中心采用所述数据备份链路向所述仲裁设备发送仲裁请求,包括:当所述第一数据中心同时需要向所述仲裁设备发送所述仲裁请求和所述第一数据中心的数据时,所述第一数据中心优先向所述仲裁设备发送所述仲裁请求;或者,所述第一数据中心采用仲裁逻辑链路向所述仲裁设备发送所述仲裁请求,所述数据备份链路划分为所述仲裁逻辑链路和数据逻辑链路,所述数据逻辑链 路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
- 根据权利要求1或2所述的仲裁方法,其特征在于,所述仲裁方法还包括:所述第一数据中心实时监测所述第一数据中心与所述仲裁设备之间、以及所述第二数据中心与所述仲裁设备之间的通信是否断开;所述第一数据中心根据监测结果,设置仲裁设备标志位,所述仲裁设备标志位用于表示所述仲裁设备能否进行仲裁;所述第一数据中心根据所述仲裁设备标志位确定所述仲裁设备能否进行仲裁。
- 根据权利要求6所述的仲裁方法,其特征在于,所述第一数据中心根据监测结果,设置仲裁设备标志位,包括:当所述第一数据中心确定与所述仲裁设备之间的通信没有断开时,或者,当所述第一数据中心确定所述第二数据中心与所述仲裁设备之间的通信没有断开时,所述第一数据中心将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;当所述第一数据中心确定与所述仲裁设备之间的通信断开,且确定与所述第二数据中心之间的通信断开时,所述第一数据中心将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;当所述第一数据中心确定与所述仲裁设备之间的通信断开,且确定所述第二数据中心与所述仲裁设备之间的通信断开时,所述第一数据中心将所述仲裁设备标志位设置为所述仲裁设备不能进行仲裁。
- 根据权利要求1或2所述的仲裁方法,其特征在于,所述仲裁方法还包括:当所述第一数据中心确定与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,所述第一数据中心查看所述仲裁策略;当所述第一数据中心根据所述仲裁策略确定所述第一数据中心为所述优先数据中心时,所述第一数据中心即时向所述仲裁设备发送仲裁请求;当所述第一数据中心根据所述仲裁策略确定所述第一数据中心不是所述优先数据中心时,所述第一数据中心延迟设定时间后向所述仲裁设备发送仲裁请求。
- 根据权利要求1或2所述的仲裁方法,其特征在于,所述仲裁设备采用 云服务器。
- 一种用于双活数据中心的仲裁装置,其特征在于,所述仲裁装置包括:第一查看模块,用于当第一数据中心与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;第一服务模块,用于当根据所述仲裁策略确定所述第一数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定所述第一数据中心不是优先数据中心时,停止提供服务;其中,所述第一数据中心和所述第二数据中心为双活数据中心。
- 根据权利要求10所述的仲裁装置,其特征在于,所述仲裁装置还包括:状态确定模块,用于确定所述第一数据中心是否处于设定的异常状态;消息发送模块,用于当所述第一数据中心处于设定的异常状态,且所述第一数据中心与所述第二数据中心之间的通信没有断开时,向所述第二数据中心发送通知消息,所述通知消息用于指示所述第二数据中心代替所述第一数据中心提供服务。
- 根据权利要求10或11所述的仲裁装置,其特征在于,所述仲裁设备采用容灾设备,所述容灾设备用于备份所述第一数据中心和所述第二数据中心的数据。
- 根据权利要求12所述的仲裁装置,其特征在于,所述仲裁装置还包括:请求发送模块,用于当所述第一数据中心与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,采用数据备份链路向所述仲裁设备发送仲裁请求,所述数据备份链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
- 根据权利要求13所述的仲裁装置,其特征在于,所述请求发送模块用于,当所述第一数据中心同时需要向所述仲裁设备发送所述仲裁请求和所述第一数据中心的数据时,优先向所述仲裁设备发送所述仲裁请求;或者,采用仲裁逻辑链路向所述仲裁设备发送所述仲裁请求,所述数据备份链路划分为所述仲裁逻辑链路和数据逻辑链路,所述数据逻辑链路用于传输所述第一数据中心发送给所述仲裁设备的备份数据。
- 根据权利要求10或11所述的仲裁装置,其特征在于,所述仲裁装置 还包括:监测模块,用于实时监测所述第一数据中心与所述仲裁设备之间、以及所述第二数据中心与所述仲裁设备之间的通信是否断开;设置模块,用于根据监测结果,设置仲裁设备标志位,所述仲裁设备标志位用于表示所述仲裁设备能否进行仲裁;仲裁设备确定模块,用于所述第一数据中心根据所述仲裁设备标志位确定所述仲裁设备能否进行仲裁。
- 根据权利要求15所述的仲裁装置,其特征在于,所述设置模块用于,当所述第一数据中心与所述仲裁设备之间的通信没有断开时,或者,当确定所述第二数据中心与所述仲裁设备之间的通信没有断开时,将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;当所述第一数据中心与所述仲裁设备之间的通信断开,且所述第一数据中心与所述第二数据中心之间的通信断开时,将所述仲裁设备标志位设置为所述仲裁设备能进行仲裁;当所述第一数据中心与所述仲裁设备之间的通信断开,且确定所述第二数据中心与所述仲裁设备之间的通信断开时,将所述仲裁设备标志位设置为所述仲裁设备不能进行仲裁。
- 根据权利要求10或11所述的仲裁装置,其特征在于,所述仲裁装置还包括:第二查看模块,用于当所述第一数据中心与所述第二数据中心之间的通信断开,且所述仲裁设备能进行仲裁时,查看所述仲裁策略;第二服务模块,当根据所述仲裁策略确定所述第一数据中心为所述优先数据中心时,即时向所述仲裁设备发送仲裁请求;当根据所述仲裁策略确定所述第一数据中心不是所述优先数据中心时,延迟设定时间后向所述仲裁设备发送仲裁请求。
- 根据权利要求10或11所述的仲裁装置,其特征在于,所述仲裁设备采用云服务器。
- 一种用于双活数据中心的仲裁装置,其特征在于,所述仲裁装置包括:网络接口、存储器和处理器;所述存储器用于存储计算机执行指令,当所述仲裁装置运行时,所述处理器执行所述存储器存储的所述计算机执行指令,以使 所述仲裁装置执行如权利要求1-9任一项所述的方法。
- 一种用于双活数据中心的仲裁系统,其特征在于,所述仲裁系统包括:第一数据中心,用于当确定与第二数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据所述仲裁策略确定所述第一数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定所述第一数据中心不是优先数据中心时,停止提供服务;所述第二数据中心,用于当确定与所述第一数据中心之间的通信断开,且仲裁设备不能进行仲裁时,查看预先设定的仲裁策略;当根据所述仲裁策略确定所述第二数据中心为优先数据中心时,继续提供服务;当根据所述仲裁策略确定所述第二数据中心不是优先数据中心时,停止提供服务;其中,所述第一数据中心和所述第二数据中心为双活数据中心。
Priority Applications (7)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP18204842.1A EP3518500B1 (en) | 2015-07-30 | 2015-07-30 | Arbitration method, apparatus, and system used in active-active data centers |
| CN201580001781.9A CN106170948B (zh) | 2015-07-30 | 2015-07-30 | 一种用于双活数据中心的仲裁方法、装置及系统 |
| EP20171475.5A EP3793172B1 (en) | 2015-07-30 | 2015-07-30 | Arbitration method, apparatus, and system used in active-active data centers |
| PCT/CN2015/085591 WO2017015961A1 (zh) | 2015-07-30 | 2015-07-30 | 一种用于双活数据中心的仲裁方法、装置及系统 |
| EP15899313.9A EP3217627B1 (en) | 2015-07-30 | 2015-07-30 | Arbitration method, apparatus and system for active-active data centers |
| US15/655,552 US10659292B2 (en) | 2015-07-30 | 2017-07-20 | Arbitration method, apparatus, and system used in active-active data centers |
| US16/870,477 US11075795B2 (en) | 2015-07-30 | 2020-05-08 | Arbitration method, apparatus, and system used in active-active data centers |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2015/085591 WO2017015961A1 (zh) | 2015-07-30 | 2015-07-30 | 一种用于双活数据中心的仲裁方法、装置及系统 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US15/655,552 Continuation US10659292B2 (en) | 2015-07-30 | 2017-07-20 | Arbitration method, apparatus, and system used in active-active data centers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2017015961A1 true WO2017015961A1 (zh) | 2017-02-02 |
Family
ID=57359013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2015/085591 Ceased WO2017015961A1 (zh) | 2015-07-30 | 2015-07-30 | 一种用于双活数据中心的仲裁方法、装置及系统 |
Country Status (4)
| Country | Link |
|---|---|
| US (2) | US10659292B2 (zh) |
| EP (3) | EP3518500B1 (zh) |
| CN (1) | CN106170948B (zh) |
| WO (1) | WO2017015961A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2021163112A (ja) * | 2020-03-31 | 2021-10-11 | 株式会社アラヤ | 情報処理装置及び情報処理方法 |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106170948B (zh) * | 2015-07-30 | 2019-11-29 | 华为技术有限公司 | 一种用于双活数据中心的仲裁方法、装置及系统 |
| CN108063787A (zh) * | 2017-06-26 | 2018-05-22 | 杭州沃趣科技股份有限公司 | 基于分布式一致性状态机实现双活架构的方法 |
| CN107911159A (zh) * | 2017-10-12 | 2018-04-13 | 北京电子工程总体研究所 | 一种基于wifi协议的星载无线容错通讯系统 |
| CN107918570B (zh) * | 2017-10-20 | 2021-07-23 | 杭州沃趣科技股份有限公司 | 一种双活系统共享仲裁逻辑盘的方法 |
| CN107995021A (zh) * | 2017-10-20 | 2018-05-04 | 杭州沃趣科技股份有限公司 | 一种基于优先级的双活系统的实现方式 |
| CN108134712B (zh) * | 2017-12-19 | 2020-12-18 | 海能达通信股份有限公司 | 一种分布式集群脑裂的处理方法、装置及设备 |
| CN110535714B (zh) | 2018-05-25 | 2023-04-18 | 华为技术有限公司 | 一种仲裁方法及相关装置 |
| US11068351B2 (en) * | 2018-11-19 | 2021-07-20 | International Business Machines Corporation | Data consistency when switching from primary to backup data storage |
| CN110442094B (zh) * | 2019-07-26 | 2021-05-07 | 新华三大数据技术有限公司 | 一种分布式系统仲裁方法及装置 |
| CN110688262B (zh) * | 2019-08-23 | 2023-01-06 | 苏州浪潮智能科技有限公司 | 一种基于主机仲裁的双活存储系统及存储方法 |
| CN112540873B (zh) * | 2020-12-03 | 2021-12-31 | 华云数据控股集团有限公司 | 容灾方法、装置、电子设备及容灾系统 |
| CN114416501A (zh) * | 2021-12-23 | 2022-04-29 | 中国农业银行股份有限公司云南省分行 | 一种存储双活及测试系统和方法 |
| CN115051911B (zh) * | 2022-06-22 | 2023-10-13 | 中国平安财产保险股份有限公司 | 一种双活容灾系统、方法、计算机设备及存储介质 |
| CN115766753B (zh) * | 2022-07-29 | 2025-09-30 | 天翼云科技有限公司 | 一种存储网关高可用方法、系统及电子设备 |
| US12373103B2 (en) * | 2022-09-19 | 2025-07-29 | Microsoft Technology Licensing, Llc | Round robin arbitration using random access memory |
| CN116347489A (zh) * | 2023-03-20 | 2023-06-27 | 南方电网数字电网集团信息通信科技有限公司 | 一种基于数据中心的业务处理方法 |
| CN117614805B (zh) * | 2023-11-21 | 2024-06-14 | 杭州沃趣科技股份有限公司 | 一种监控数据中心状态的数据处理系统 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102185717A (zh) * | 2011-05-05 | 2011-09-14 | 中国联合网络通信集团有限公司 | 业务处理设备、方法及系统 |
| CN103647849A (zh) * | 2013-12-24 | 2014-03-19 | 华为技术有限公司 | 一种业务迁移方法、装置和一种容灾系统 |
| US8745125B2 (en) * | 2011-08-25 | 2014-06-03 | Verizon Patent And Licensing Inc. | Routing traffic after power failure |
| CN104717077A (zh) * | 2013-12-11 | 2015-06-17 | 中国移动通信集团山东有限公司 | 一种管理数据中心的方法、装置及系统 |
Family Cites Families (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6529995B1 (en) * | 1999-06-18 | 2003-03-04 | Storage Technology Corporation | Method and apparatus for maintaining and restoring mapping table entries and data in a raid system |
| US7010607B1 (en) * | 1999-09-15 | 2006-03-07 | Hewlett-Packard Development Company, L.P. | Method for training a communication link between ports to correct for errors |
| US7245928B2 (en) * | 2000-10-27 | 2007-07-17 | Cellemetry, Llc | Method and system for improved short message services |
| CN101019097A (zh) * | 2004-09-13 | 2007-08-15 | 皇家飞利浦电子股份有限公司 | 分布式存储系统管理方法 |
| US7609619B2 (en) * | 2005-02-25 | 2009-10-27 | Cisco Technology, Inc. | Active-active data center using RHI, BGP, and IGP anycast for disaster recovery and load distribution |
| US7457835B2 (en) * | 2005-03-08 | 2008-11-25 | Cisco Technology, Inc. | Movement of data in a distributed database system to a storage location closest to a center of activity for the data |
| JP4577242B2 (ja) * | 2006-03-10 | 2010-11-10 | 日本電気株式会社 | データバックアップシステム、データバックアップ方法、及びその動作制御プログラム |
| US8968077B2 (en) * | 2006-04-13 | 2015-03-03 | Idt | Methods and systems for interfacing with a third-party application |
| US10026255B2 (en) * | 2006-04-13 | 2018-07-17 | Igt | Presentation of remotely-hosted and locally rendered content for gaming systems |
| US8149725B2 (en) * | 2006-07-31 | 2012-04-03 | Tekelec | Methods, systems, and computer program products for a hierarchical, redundant OAM&P architecture for use in an IP multimedia subsystem (IMS) network |
| US7925917B1 (en) * | 2008-04-03 | 2011-04-12 | United Services Automobile Association (Usaa) | Systems and methods for enabling failover support with multiple backup data storage structures |
| CN101692212B (zh) * | 2009-06-19 | 2012-11-14 | 无锡中星微电子有限公司 | 一种访问存储器的方法、系统和总线仲裁装置 |
| US8504690B2 (en) * | 2009-08-07 | 2013-08-06 | Broadcom Corporation | Method and system for managing network power policy and configuration of data center bridging |
| US8650299B1 (en) * | 2010-02-03 | 2014-02-11 | Citrix Systems, Inc. | Scalable cloud computing |
| US20120078494A1 (en) * | 2010-09-23 | 2012-03-29 | Honeywell International Inc. | Systems and methods for managing non-integrated controller pilot data link communications (cpdlc) systems on an aircraft |
| US8655516B2 (en) * | 2010-11-29 | 2014-02-18 | General Electric Company | Communication system for a rail vehicle consist and method for communicating with a rail vehicle consist |
| US8578204B1 (en) * | 2010-12-29 | 2013-11-05 | Emc Corporation | Witness facility for distributed storage system |
| JP6019653B2 (ja) * | 2012-03-24 | 2016-11-02 | 日本電気株式会社 | 情報処理システム、情報処理方法、情報処理装置およびその制御方法と制御プログラム |
| US9069799B2 (en) * | 2012-12-27 | 2015-06-30 | Commvault Systems, Inc. | Restoration of centralized data storage manager, such as data storage manager in a hierarchical data storage system |
| CN103812929A (zh) * | 2014-01-11 | 2014-05-21 | 浪潮电子信息产业股份有限公司 | 一种云数据中心管理平台双活方法 |
| GB2540329B (en) * | 2014-03-05 | 2021-01-27 | Pismo Labs Technology Ltd | Methods and systems for forwarding data |
| WO2016054770A1 (en) * | 2014-10-08 | 2016-04-14 | Intel Corporation | Techniques for checkpointing/delivery between primary and secondary virtual machines |
| CN104469699B (zh) * | 2014-11-27 | 2018-09-21 | 华为技术有限公司 | 集群仲裁方法和多集群配合系统 |
| US9953072B2 (en) * | 2014-12-31 | 2018-04-24 | Vmware, Inc. | Disaster recovery of mobile data center via location-aware cloud caching |
| US10275328B2 (en) * | 2015-04-02 | 2019-04-30 | Vmware, Inc. | Fault tolerance for hybrid cloud deployments |
| CN106170948B (zh) * | 2015-07-30 | 2019-11-29 | 华为技术有限公司 | 一种用于双活数据中心的仲裁方法、装置及系统 |
-
2015
- 2015-07-30 CN CN201580001781.9A patent/CN106170948B/zh active Active
- 2015-07-30 WO PCT/CN2015/085591 patent/WO2017015961A1/zh not_active Ceased
- 2015-07-30 EP EP18204842.1A patent/EP3518500B1/en active Active
- 2015-07-30 EP EP15899313.9A patent/EP3217627B1/en active Active
- 2015-07-30 EP EP20171475.5A patent/EP3793172B1/en active Active
-
2017
- 2017-07-20 US US15/655,552 patent/US10659292B2/en active Active
-
2020
- 2020-05-08 US US16/870,477 patent/US11075795B2/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102185717A (zh) * | 2011-05-05 | 2011-09-14 | 中国联合网络通信集团有限公司 | 业务处理设备、方法及系统 |
| US8745125B2 (en) * | 2011-08-25 | 2014-06-03 | Verizon Patent And Licensing Inc. | Routing traffic after power failure |
| CN104717077A (zh) * | 2013-12-11 | 2015-06-17 | 中国移动通信集团山东有限公司 | 一种管理数据中心的方法、装置及系统 |
| CN103647849A (zh) * | 2013-12-24 | 2014-03-19 | 华为技术有限公司 | 一种业务迁移方法、装置和一种容灾系统 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3217627A4 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2021163112A (ja) * | 2020-03-31 | 2021-10-11 | 株式会社アラヤ | 情報処理装置及び情報処理方法 |
| JP7495713B2 (ja) | 2020-03-31 | 2024-06-05 | 株式会社アラヤ | 情報処理装置及び情報処理方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20200274754A1 (en) | 2020-08-27 |
| CN106170948B (zh) | 2019-11-29 |
| EP3793172B1 (en) | 2025-07-23 |
| EP3518500A1 (en) | 2019-07-31 |
| EP3217627A1 (en) | 2017-09-13 |
| EP3793172A3 (en) | 2021-04-28 |
| EP3217627B1 (en) | 2019-02-06 |
| CN106170948A (zh) | 2016-11-30 |
| US10659292B2 (en) | 2020-05-19 |
| EP3217627A4 (en) | 2018-02-28 |
| US11075795B2 (en) | 2021-07-27 |
| US20170317875A1 (en) | 2017-11-02 |
| EP3793172A2 (en) | 2021-03-17 |
| EP3518500B1 (en) | 2022-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017015961A1 (zh) | 一种用于双活数据中心的仲裁方法、装置及系统 | |
| US20240080362A1 (en) | Storage area network attached clustered storage system | |
| US10785350B2 (en) | Heartbeat in failover cluster | |
| JP6362119B2 (ja) | クラスタ・ブレイン分割後の調停処理方法、クォーラム記憶装置、およびシステム | |
| US8578204B1 (en) | Witness facility for distributed storage system | |
| WO2019085875A1 (zh) | 存储集群的配置修改方法、存储集群及计算机系统 | |
| US20130268590A1 (en) | System and method for reducing information loss in an aggregated information handling system | |
| CN101594383B (zh) | 一种双控制器存储系统的服务和控制器状态监控方法 | |
| CN104077199B (zh) | 基于共享磁盘的高可用集群的隔离方法和系统 | |
| CN102088490B (zh) | 数据存储方法、设备和系统 | |
| WO2017050254A1 (zh) | 热备方法、装置及系统 | |
| CN102868754A (zh) | 一种实现集群存储高可用性的方法、节点装置和系统 | |
| US11372557B2 (en) | Extra-resilient cache for resilient storage array | |
| CN113330426B (zh) | 一种备份数据的方法、装置和系统 | |
| CN108512753B (zh) | 一种集群文件系统中消息传输的方法及装置 | |
| CN102497288A (zh) | 一种双机备份方法和双机系统实现装置 | |
| WO2021238579A1 (zh) | 存储系统管理sata硬盘的方法及存储系统 | |
| CN103001787B (zh) | 用于数据处理中心容灾备份的系统及方法 | |
| CN109445984B (zh) | 一种业务恢复方法、装置、仲裁服务器以及存储系统 | |
| CN110620684A (zh) | 一种存储双控防脑裂方法、系统、终端及存储介质 | |
| WO2022218346A1 (zh) | 一种故障处理方法及装置 | |
| CN114499778B (zh) | 维护云平台双活的装置、方法、系统和存储介质 | |
| CN111414411A (zh) | 高可用度数据库系统 | |
| CN107197032A (zh) | 一种实时镜像的服务器数据在线备份方法 | |
| CN119576222A (zh) | 一种桌面云轻量化两副本存储集群部署方法与系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15899313 Country of ref document: EP Kind code of ref document: A1 |
|
| REEP | Request for entry into the european phase |
Ref document number: 2015899313 Country of ref document: EP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |