Active-active storage control method, device, equipment and non-volatile storage medium
By adopting an alternating distributed active-active volume strategy in the active-active storage system, the problem of storage service suspension caused by failure of the active-active primary site is solved, and rapid recovery and business continuity are achieved.
Patent Information
- Application Number
- CN202411088703.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2025-09-09
- Estimated Expiration
- 2044-08-09
AI Technical Summary
In an active-active storage system, if a site-level failure occurs at the active-active primary site, the entire storage system enters a silent state and cannot provide storage services. The recovery time is too long, affecting business continuity.
When creating an active-active storage system, adopt an alternating active-active volume distribution strategy. Deploy some active-active primary volumes at the active-active primary site and others at the active-active secondary site. In the event of a failure, the active-active secondary volumes are set as active-active primary volumes. After recovery, the initial distribution state is restored.
This reduces the storage service suspension time caused by active-active site failover, ensures rapid business recovery, shortens recovery time, and improves business continuity.
Smart Images
Figure CN118869456B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of storage technology, and in particular to a dual-active storage control method, device, equipment and non-volatile storage medium. Background Art
[0002] Active-active is a computer disaster recovery solution that implements a dual-core architecture where both primary and secondary data centers simultaneously handle user traffic. The two data centers act as backups for each other and perform real-time backups. Unlike other hot standby solutions, active-active achieves load balancing by having both primary and secondary data centers handle a portion of the traffic. Typically, the primary data center handles more traffic, perhaps 60-70%, while the secondary data center handles only 40-30%. This active-active mechanism ensures data can be transferred to the other data center in the event of a single storage node failure or a site-level failure in the data center.
[0003] However, when a site-level failure occurs at the active-active primary site, all active-active primary volumes belonging to that site will be displayed as offline. At this time, the entire active-active storage system enters a silent state, reporting that the volume path is offline and unable to provide storage services. Storage services can only be restored after all active-active primary volumes in the active-active primary site are switched to the surviving active-active slave site.
[0004] How to reduce the storage service suspension time caused by active-active site failover is a technical problem that those skilled in the art need to solve. Summary of the Invention
[0005] The object of the present invention is to provide a dual-active storage control method, device, equipment and non-volatile storage medium for reducing the storage service suspension time caused by dual-active site failover.
[0006] To solve the above technical problems, the present invention provides an active-active storage control method, which is applied to a storage control host and includes:
[0007] When creating an active-active storage system, alternately distributed active-active volumes are created at corresponding active-active primary sites and active-active secondary sites, so that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site, and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active secondary site.
[0008] If a failure occurs at the active-active master site or the active-active slave site, and if the corresponding failed volume is the active-active master volume, the active-active slave volume of the corresponding active-active volume is set as the active-active master volume;
[0009] After the failed volume is recovered, the corresponding active-active volume is restored to the initial alternating distribution state.
[0010] On the one hand, creating alternately distributed active-active volumes at corresponding active-active primary sites and active-active slave sites, so that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active slave site, includes:
[0011] Determining a master-slave volume distribution ratio of each of the active-active master site and the active-active slave site;
[0012] A storage node for deploying the active-active primary volume and a storage node for deploying the active-active slave volume are determined at the active-active primary site according to the master-slave volume distribution ratio to create the active-active volume.
[0013] On the other hand, determining the master-slave volume distribution ratio of each of the active-active master site and the active-active slave site includes:
[0014] If an input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio setting value is used as the master-slave volume distribution ratio;
[0015] If the input master-slave volume distribution ratio setting value is not received, the master-slave volume distribution ratio is adopted as that 50% of the active-active master volumes are deployed at both the active-active master site and the active-active slave site.
[0016] On the other hand, the active-active master site and the active-active slave site are both deployed with 50% of the active-active master volumes as the master-slave volume distribution ratio, including:
[0017] The active-active volumes are created sequentially according to the number of active-active volumes to be created in the active-active storage system, and when a command to create the active-active volume is issued to the processor core, storage nodes are cyclically selected from the active-active primary site and the active-active slave site to create an active-active primary volume of the active-active volume.
[0018] On the other hand, determining, at the active-active primary site, a storage node for deploying the active-active primary volume and a storage node for deploying the active-active slave volume according to the master-slave volume distribution ratio to create the active-active volume, includes:
[0019] Determining, based on the master-slave volume distribution ratio, a site where a dual-active master volume of each to-be-created dual-active volume of the active-active storage system is located and a site where a dual-active slave volume of each to-be-created dual-active volume is located;
[0020] Storage nodes are randomly selected at the site where the active-active primary volume of the active-active volume to be created is located and at the site where the active-active secondary volume of the active-active volume to be created is located to create the active-active primary volume and the active-active secondary volume for the active-active volume to be created.
[0021] On the other hand, the step of creating alternately distributed active-active volumes at the corresponding active-active primary site and active-active slave site, such that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active slave site, includes:
[0022] When the active-active primary site and the active-active slave site create the alternatingly distributed active-active volumes, if a preferred storage node exists at the site where the active-active primary volume of the active-active volume to be created is located, the active-active primary volume of the active-active volume to be created is preferentially deployed on the preferred storage node.
[0023] On the other hand, when creating the active-active storage system, creating alternately distributed active-active volumes at the corresponding active-active primary site and active-active slave site, so that the active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site, and the active-active primary volumes of another portion of the active-active volumes are deployed at the active-active slave site, including:
[0024] Determining the master-slave volume distribution ratio of the active-active master site and the active-active slave site according to the customized settings of the active-active storage system inputted through the user input interface;
[0025] If an input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio setting value is used as the master-slave volume distribution ratio;
[0026] If the input master-slave volume distribution ratio setting value is not received, the master-slave volume distribution ratio is set as follows: 50% of the active-active master volumes are deployed on both the active-active master site and the active-active slave site;
[0027] The active-active volumes are created sequentially according to the number of active-active volumes to be created in the active-active storage system, and when a command to create the active-active volumes is issued to the processor core, a storage node is selected from the active-active primary site or the active-active slave site according to the master-slave volume distribution ratio to create the active-active primary volume of the active-active volume, and a storage node is selected from another site to create the active-active slave volume of the active-active volume; wherein, if a preferred storage node exists at the active-active primary site or the active-active slave site, the preferred storage node is preferentially selected when the site selects the active-active primary volume;
[0028] If a failure occurs at the active-active master site or the active-active slave site, and if the corresponding failed volume is the active-active master volume, setting the active-active slave volume of the corresponding active-active volume as the active-active master volume includes:
[0029] If only the active-active primary volume of some of the active-active volumes fails, only the active-active slave volume corresponding to the failed volume is set as the active-active primary volume of the active-active volume, and the cluster view of the active-active storage system is updated;
[0030] If a site-level failure occurs at the active-active master site or the active-active slave site, the active-active slave volumes corresponding to the active-active master volume at the failed site at the other site are set as the active-active master volumes, and the cluster view of the active-active storage system is updated;
[0031] After the failed volume is recovered, restoring the corresponding active-active volume to an initial alternating distribution state includes:
[0032] After the failed volume is recovered, the corresponding active-active volume is restored to an initial alternating distribution state, and the cluster view of the active-active storage system is updated.
[0033] To solve the above technical problems, the present invention further provides an active-active storage control device, which is applied to a storage control host and includes:
[0034] A deployment unit is configured to create alternately distributed active-active volumes at corresponding active-active primary sites and active-active slave sites when creating an active-active storage system, so that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site, and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active slave site;
[0035] a failover unit configured to, if a failure occurs at the active-active master site or the active-active slave site, set the active-active slave volume of the corresponding active-active volume as the active-active master volume if the corresponding failed volume is the active-active master volume;
[0036] The fault recovery unit is used to restore the corresponding active-active volume to an initial alternating distribution state after the faulty volume is recovered.
[0037] To solve the above technical problems, the present invention further provides an active-active storage control device, comprising:
[0038] memory for storing computer programs;
[0039] A processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of the active-active storage control method as described in any one of the above items are implemented.
[0040] To solve the above technical problems, the present invention also provides a non-volatile storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the active-active storage control method as described in any one of the above items are implemented.
[0041] The active-active storage control method provided by the present invention has the beneficial effect that when the storage control host creates an active-active storage system, it creates alternatingly distributed active-active volumes at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a part of the active-active volumes are deployed at the active-active master site, and the active-active master volumes of the other part of the active-active volumes are deployed at the active-active slave site. If a failure occurs at the active-active master site or the active-active slave site, if the corresponding failed volume is the active-active master volume, the active-active slave volume of the corresponding active-active volume is set as the active-active master volume; after the failed volume is restored, the corresponding active-active volume is restored to the initial alternating distribution state. Therefore, when a site-level failure occurs at the active-active master site, there is no need to wait for all active-active master volumes to perform master-slave switching. The active-active master volume in the active-active volume deployed at the active-active slave site only needs to spend the time required for the silent process caused by the cluster view change caused by the failure to recover from the failure and become a single write, and resume business. Since the volume path of this part of the active-active volume is always online, the time for the volume to be offline and re-detected and put online is also reduced, and the active-active volume that needs master-slave switching can also be scheduled in time. Compared with the original mechanism in which the active-active primary volume is only deployed at the active-active primary site, when a site-level failure occurs, the storage service suspension time caused by a single active-active site failover can be significantly shortened.
[0042] The present invention also provides an active-active storage control device, equipment and non-volatile storage medium, which have the above-mentioned beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0044] Figure 1 This is a schematic diagram of traditional active-active synchronization;
[0045] Figure 2 A flowchart of a dual-active storage control method provided by an embodiment of the present invention;
[0046] Figure 3 A schematic diagram of active-active volume distribution in alternating mode provided by an embodiment of the present invention;
[0047] Figure 4 A schematic diagram of a dual-active primary site failure in alternating mode provided by an embodiment of the present invention;
[0048] Figure 5 A schematic diagram of a dual-active primary site failure recovery in alternating mode provided by an embodiment of the present invention;
[0049] Figure 6 A schematic structural diagram of an active-active storage control device provided by an embodiment of the present invention;
[0050] Figure 7 A schematic diagram of the structure of an active-active storage control device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0051] The core of the present invention is to provide a dual-active storage control method, device, equipment and non-volatile storage medium for reducing the storage service suspension time caused by dual-active site failure switching.
[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0053] To facilitate understanding of the technical solutions provided by the embodiments of the present invention, some key terms used in the embodiments of the present invention are first explained here.
[0054] Active-active is a computer disaster recovery solution that allows both primary and secondary data centers to handle user services simultaneously. The two data centers back up each other and perform real-time backup.
[0055] Active-active volumes (AA) use synchronous replication to synchronize data between two I / O groups, each of which is a separate site. Normally, the active-active primary volume provides data access. Data is synchronized within the cluster in real time using synchronous remote replication. Active-active secondary volumes are not mapped to the storage controller host and are normally offline. Synchronous replication relationships cannot be started or stopped; the storage system automatically switches between them.
[0056] Figure 1 This is a schematic diagram of traditional active-active synchronization.
[0057] like Figure 1 As shown in the figure, in a traditional active-active storage system, the storage control host manages the active-active storage system and the mirrored pairs between the active-active primary site and the active-active secondary site. Active-active primary volumes are deployed at the active-active primary site to provide storage services. Data in the active-active primary volumes is synchronously replicated in real time to active-active secondary volumes at the active-active secondary sites.
[0058] If a storage node-level failure occurs, it involves switching between multiple paths within the data input and output group and the storage control host. The active-active storage system will be temporarily silent and then recover. After recovery, only the business of the failed storage node will be affected, while the other active-active volume functions will not be affected. Figure 1 As shown, when a failure occurs at the active-active master site, the active-active master volume belonging to the site will be displayed as offline. The site-level failure of the active-active master site will cause the entire active-active storage system to enter a silent state, and the reported volume path will be offline, causing all tasks for the active-active storage system to be suspended. It is necessary to wait for the storage controller to switch the failed active-active master site to the surviving active-active slave site, that is, all active-active slave volumes in the active-active slave site are converted into master volumes, and the failed active-active master volume in the failed active-active master site is converted into a failed active-active slave volume. The new active-active master volume in the surviving active-active slave site simulates the logical unit number (LUN ID) of the failed active-active master volume, thereby achieving transparent access by upper-layer applications.
[0059] If the entire data input / output group fails, that is, encounters a site-level failure, all storage nodes at the site fail, the relevant volumes appear offline or in a copy offline state, and read / write operations on the storage control host are briefly suspended. The active-active storage system automatically performs a site switchover. For example, if the active-active primary site and the active-active secondary site each have two storage nodes, and a site-level failure occurs at the active-active primary site, the active-active primary volumes on the two storage nodes at the active-active primary site appear offline or in a synchronizing state. Data synchronization information can then be viewed. At this point, host data at the active-active primary site can be accessed through the storage nodes at the active-active secondary site. When data synchronization is complete, the cluster system page corresponding to the active-active storage system displays normal status. Before the failed site recovers, the active-active storage system is in single-write mode, with no storage nodes operating at the failed site and only the other site continuing to operate.
[0060] That is to say, the current failover logic of the active-active storage system is affected by the primary site where the active-active volumes are located. When the failed site is the active-active primary site, all active-active volumes must undergo an active-active master-slave switchover. This is a limitation of the current active-active technology. That is, when creating an active-active storage system, the site where all created active-active primary volumes are located is consistent with the site where the storage control host is located. In large-scale scenarios, since each active-active volume needs to undergo a master-slave switchover, this will result in a longer silent period when a site-level failure occurs at the active-active primary site of the active-active storage system. In addition, since each active-active volume needs to undergo a master-slave switchover, the time it takes for the volume to be offline and then re-detected and brought online will also affect the time it takes for data input and output to recover from the storage control host. This results in a very long time for host data input and output to drop to zero due to the failure of the active-active primary site, and the time the business is affected will also be prolonged. In other words, the time the storage business is affected increases with the number of active-active volumes.
[0061] In scenarios where disaster recovery protection is limited to the site level, the Recovery Time Objective (RTO) needs to be reduced. To address the issue of prolonged recovery time for active-active storage systems caused by site-level failures at a single active-active primary site, an embodiment of the present invention provides an active-active storage control solution. Instead of creating active-active primary volumes at the active-active primary site where the storage control host resides, this solution alternates between creating active-active primary volumes at both the active-active primary site and the active-active secondary site. This solution eliminates the need to wait for all active-active primary volumes to undergo a master-slave switchover in the event of a site-level failure at the active-active primary site. Active-active primary volumes deployed at the active-active secondary site can recover from the failure and resume services by switching to single write mode, simply by suspending the silent process caused by the cluster view change caused by the failure. Because the volume paths for these active-active volumes remain online, the time required to re-detect and bring the volumes back online after offline is reduced, allowing active-active volumes requiring a master-slave switchover to be scheduled promptly. Compared to the previous mechanism where active-active primary volumes are deployed only at the active-active primary site, this solution significantly shortens the storage service suspension time caused by a single active-active site failover in the event of a site-level failure.
[0062] Figure 2 A flowchart of a dual-active storage control method provided by an embodiment of the present invention; Figure 3 A schematic diagram of active-active volume distribution in alternating mode provided by an embodiment of the present invention; Figure 4 A schematic diagram of a dual-active primary site failure in alternating mode provided by an embodiment of the present invention; Figure 5 A schematic diagram of a dual-active primary site failure recovery in alternating mode is provided in an embodiment of the present invention.
[0063] like Figure 2 As shown, the active-active storage control method provided by the embodiment of the present invention, applied to a storage control host, includes:
[0064] S201: When creating an active-active storage system, create alternately distributed active-active volumes at the corresponding active-active primary site and active-active secondary site, so that the active-active primary volumes of some active-active volumes are deployed at the active-active primary site, and the active-active primary volumes of other active-active volumes are deployed at the active-active secondary site.
[0065] S202: If a failure occurs at the active-active master site or active-active slave site, and if the corresponding failed volume is the active-active master volume, the active-active slave volume of the corresponding active-active volume is set as the active-active master volume;
[0066] S203: After the failed volume is recovered, the corresponding active-active volume is restored to the initial alternating distribution state.
[0067] In an embodiment of the present invention, a dual-active volume alternating distribution mechanism is designed and implemented. This mode has more obvious beneficial effects in large-scale dual-active volume deployment scenarios. It can ensure business continuity when encountering site-level failures such as hardware failures, power failures, connection failures, or natural disasters such as fires and floods. Compared with dual-active storage systems in non-alternating mode, the recovery time is significantly shortened.
[0068] Simply put, the alternating mode of active-active volumes overcomes the current limitation of not being able to select the site where the active-active primary volume is located when creating active-active storage systems. That is, when creating active-active volumes in batches and selecting the alternating mode, the active-active primary volumes of some volumes are deployed at the active-active primary site, while the active-active primary volumes of other volumes are deployed at the active-active secondary site, so that the active-active primary volumes of the created active-active volumes are distributed across both sites.
[0069] For example, the active-active master volumes of half of the active-active volumes can be deployed at the active-active master site, and the active-active master volumes of the other half of the active-active volumes can be deployed at the active-active slave site. In this way, when a site-level failure occurs, only half of the active-active volumes need to perform master-slave switching, and the silent implementation of the active-active volumes will be significantly shortened. The site where the active-active master volumes of the other half of the active-active volumes are located has not failed, and the active-active master volumes of this part of the active-active volumes will not be offline, and there will be no loss of time for the volumes to be offline and then re-detected and brought online. This can significantly reduce the zero-drop time of data input and output of the storage control host. In addition, this part of the active-active volumes that do not need to be switched only needs to experience the cluster suspend (pend) and unsuspend (unpend) events caused by the site failure, and the degree of impact is only silent recovery. The state machine operation is very low time-consuming compared to the part that requires active-active switching, and can continue business processing for a short time after a failure.
[0070] In a specific implementation, for S201, the processor core of the storage control host can be configured to enable alternating mode by default in the creation command for the active-active storage system. Alternatively, a new "alternating mode" switch can be added to the active-active storage system customization settings on the user input interface, allowing the user to select whether to enable alternating mode. If alternating mode is enabled, when batches of active-active volumes are created, the active-active primary volumes are created alternately at the active-active primary site and the active-active secondary site.
[0071] In order to realize the alternating mode, it is necessary to configure in the processor core of the storage control host that the active-active volume is allowed to select the site where the active-active primary volume is located, rather than being created at the active-active primary site by default. At the same time, since the data input and output load balancing function configured in the active-active storage system will trigger the master-slave switching logic, that is, in the traditional active-active storage system, most of the business is allocated to the active-active primary site and a small part of the business is allocated to the active-active slave site for load balancing, if the data input and output load balancing function provided by the traditional active-active storage system is enabled at the same time as the alternating mode provided by the embodiment of the present invention, the active-active storage system will be affected by the data input and output load balancing switching logic, and will automatically switch the active-active primary volume back to the active-active primary site, resulting in the alternating mode being in name only. Therefore, in the embodiment of the present invention, after the alternating mode is enabled for the active-active storage system, the data input and output load balancing function of the active-active storage system itself is turned off.
[0072] For S202 and S203, the active-active storage control method provided by the embodiment of the present invention adds active-active volume switching logic compared to the traditional active-active storage system. In the traditional active-active storage system, when a site-level failure occurs at the active-active master site, the active-active master volume switches to the active-active slave site. After the original active-active master site is restored, the active-active master volume will not switch back. In the active-active storage control method provided by the embodiment of the present invention, when a new active-active volume encounters a site-level failure and a master-slave switch occurs, the active-active master volume switches back to the site where it was originally created. This ensures that each time a site-level failure occurs, only some active-active volumes need to be switched from master to slave, ensuring that the recovery time for each site-level failure is not particularly long.
[0073] like Figure 3 As shown, in this embodiment of the present invention, the storage control host also controls the active-active slave site to create an active-active master volume, so that when creating an active-active storage system, the active-active master volumes of the active-active volumes are alternately distributed on the active-active master site and the active-active slave site.
[0074] like Figure 4 As shown in the figure, when a site-level failure occurs at the active-active primary site, the active-active primary volume of active-active volume 1 is switched from the active-active primary site to the active-active slave site, and active-active volume 2 does not need to be switched from the primary site to the secondary site, thereby significantly shortening the silent period and enabling the switch to the single-write state in which all active-active volumes can resume services as quickly as possible.
[0075] like Figure 5 As shown in the figure, after the active-active primary site is restored, the active-active primary volume of active-active volume 1 is switched from the active-active slave site back to the active-active primary site, while active-active volume 2 remains unchanged, which also speeds up the recovery time to active-active storage.
[0076] The active-active storage control method provided by the embodiment of the present invention has the beneficial effect that when the storage control host creates an active-active storage system, it creates alternatingly distributed active-active volumes at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a part of the active-active volumes are deployed at the active-active master site, and the active-active master volumes of the other part of the active-active volumes are deployed at the active-active slave site. If a failure occurs at the active-active master site or the active-active slave site, if the corresponding failed volume is the active-active master volume, the active-active slave volume of the corresponding active-active volume is set as the active-active master volume; after the failed volume is restored, the corresponding active-active volume is restored to the initial alternating distribution state. Therefore, when a site-level failure occurs at the active-active master site, there is no need to wait for all active-active master volumes to perform master-slave switching. The active-active master volume in the active-active volume deployed at the active-active slave site only needs to spend the time required for the silent process caused by the cluster view change caused by the failure to recover from the failure and become a single write, and resume business. Since the volume path of this part of the active-active volume is always online, the time for the volume to be offline and re-detected and put online is also reduced, and the active-active volume that needs master-slave switching can be scheduled in time. Compared with the original mechanism in which the active-active primary volume is only deployed at the active-active primary site, when a site-level failure occurs, the storage service suspension time caused by a single active-active site failover can be significantly shortened.
[0077] Based on the above embodiments, in the active-active storage control method provided in an embodiment of the present invention, in S201, alternately distributed active-active volumes are created at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a part of the active-active volumes are deployed at the active-active master site, and the active-active master volumes of another part of the active-active volumes are deployed at the active-active slave site. It can include: determining the master-slave volume distribution ratio of the active-active master site and the active-slave site respectively; determining the storage nodes for deploying the active-active master volume and the storage nodes for deploying the active-active slave volume at the active-active master site according to the master-slave volume distribution ratio to create the active-active volume.
[0078] That is, in the customized settings of the active-active storage system created by the storage control host, a setting item for the master-slave volume distribution ratio can be added. During creation, it is first determined whether the master-slave volume distribution ratio setting exists, and then the information of the site where the active-active volume to be created is deployed is determined.
[0079] The master-slave volume distribution ratio of each of the active-active master site and the active-active slave site is determined, which may include: if an input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio is based on the master-slave volume distribution ratio setting value; if no input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio is based on 50% active-active master volumes deployed at both the active-active master site and the active-active slave site.
[0080] The master-slave volume distribution ratio is set to 50% for both the active-active master site and the active-active slave site. The method may include: sequentially creating active-active volumes according to the number of active-active volumes to be created in the active-active storage system, and cyclically selecting storage nodes from the active-active master site and the active-active slave site to create the active-active master volume of the active-active volume when issuing a command to create the active-active volume to the processor core.
[0081] In an embodiment of the present invention, the customized setting of the active-active storage system can be an option for batch creation of active-active volumes in the graphical user interface (GUI). As described in the above embodiment of the present invention, a new "alternating mode" switch can be added to this option to control whether to turn on the alternating mode. When batch creating active-active volumes and turning on the alternating mode, when the command to create active-active volumes is sent to the processor core, the active-active master volume is created in a loop for the specified surviving data input and output groups. For example, the active-active master volume of the first active-active volume is created in I / O Group 0, the active-active master volume of the second active-active volume is created in I / O Group 1, and the active-active master volume of the third active-active volume is created in I / O Group 0, and so on. In addition, a function for selecting an active-active master site can be added to the graphical user interface. The active-active master site and the active-active slave site can be recorded as site 1 and site 2, and the user can select site 1 as the site where the active-active master volume is located or site 2 as the site where the active-active master volume is located.
[0082] In some optional implementations of the embodiments of the present invention, the storage nodes for deploying active-active master volumes and the storage nodes for deploying active-active slave volumes are determined at the active-active master site according to the master-slave volume distribution ratio to create active-active volumes. This may include: determining the site where the active-active master volume of each to-be-created active-active volume and the site where the active-active slave volume of each to-be-created active-active volume are located in the active-active storage system according to the master-slave volume distribution ratio; randomly selecting storage nodes at the site where the active-active master volume of the to-be-created active-active volume and the site where the active-active slave volume of the to-be-created active-active volume are located to create active-active master volumes and active-active slave volumes for the to-be-created active-active volumes.
[0083] In some other optional implementations of the embodiments of the present invention, the processor core is configured to allow the active-active primary volume selected when creating an active-active volume to be located at a location other than the active-active primary site where the storage control host is located. A new function can also be added to the processor core in this scenario to allow the selection of a preferred storage node (preferNode) in the active-active slave site. The preferred storage node is the mirror pair storage node to which the active-active volume belongs.
[0084] Then, in S201, alternately distributed active-active volumes are created at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a part of the active-active volumes are deployed at the active-active master site, and the active-active master volumes of the other part of the active-active volumes are deployed at the active-active slave site. This may include: when creating alternately distributed active-active volumes at the active-active master site and the active-active slave site, if there is a preferred storage node at the site where the active-active master volume of the to-be-created active-active volume is located, the active-active master volume of the to-be-created active-active volume is preferentially deployed at the preferred storage node.
[0085] The preferred storage nodes may be specified by the user. For example, the user may specify some storage nodes with better storage performance as preferred storage nodes.
[0086] Alternatively, the preferred storage node can also be selected by the storage control host according to the storage capacity of each storage node. Then, in S201, alternately distributed active-active volumes are created at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a part of the active-active volumes are deployed at the active-active master site, and the active-active master volumes of the other part of the active-active volumes are deployed at the active-active slave site. It can also include: when creating alternately distributed active-active volumes at the active-active master site and the active-active slave site, the active-active master volume is deployed at a high-performance storage node with a storage capacity higher than that of the storage node where the active-active slave volume is located in the site. Storage capacity evaluation rules can be set, such as scoring each storage node based on indicators such as device computing power, storage, network, and load of the storage node, sorting the storage nodes in the site from high to low according to the score, and taking a preset proportion of storage nodes as preferred storage nodes for selection to create active-active master volumes.
[0087] Based on the above embodiment, in the active-active storage control method provided in an embodiment of the present invention, when creating an active-active storage system, in S201, active-active volumes are created that are alternately distributed at the corresponding active-active primary site and active-active secondary site, so that the active-active primary volumes of some active-active volumes are deployed at the active-active primary site, and the active-active primary volumes of other active-active volumes are deployed at the active-active secondary site. This method may include:
[0088] Determine the master-slave volume distribution ratio for each active-active primary site and active-active slave site based on the customized active-active storage system settings entered in the user input interface.
[0089] If the input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio setting value is used as the master-slave volume distribution ratio;
[0090] If the input master-slave volume distribution ratio setting value is not received, the master-slave volume distribution ratio is set to 50% for both the active-active primary site and the active-active secondary site.
[0091] Active-active volumes are created sequentially based on the number of active-active volumes to be created in the active-active storage system. When the command to create an active-active volume is sent to the processor core, a storage node is selected from the active-active primary site or the active-active secondary site based on the master-slave volume distribution ratio to create the active-active primary volume of the active-active volume, and a storage node is selected from the other site to create the active-active secondary volume of the active-active volume. If a preferred storage node exists at the active-active primary site or the active-active secondary site, the preferred storage node is selected first when selecting the active-active primary volume at the site.
[0092] In S202, if a failure occurs at the active-active master site or the active-active slave site, and if the corresponding failed volume is an active-active master volume, the active-active slave volume of the corresponding active-active volume is set as the active-active master volume, which may include: if only some active-active volumes of the active-active master volume fail, only the active-active slave volume corresponding to the failed volume is set as the active-active master volume of the active-active volume, and the cluster view of the active-active storage system is updated; if a site-level failure occurs at the active-active master site or the active-active slave site, all the active-active slave volumes corresponding to the active-active master volume in the failed site in the other site are set as active-active master volumes, and the cluster view of the active-active storage system is updated.
[0093] After the failed volume is recovered, S203 restores the corresponding active-active volume to the initial alternating distribution state, which may include: after the failed volume is recovered, restores the corresponding active-active volume to the initial alternating distribution state, and updates the cluster view of the active-active storage system.
[0094] The implementation of the embodiments of the present invention can refer to the introduction of the above embodiments.
[0095] It should be noted that in the embodiments of the active-active storage control method of the present invention, some of the steps or features may be ignored or not executed. The hardware or software functional modules are divided for convenience of description and are not the only implementation form of the active-active storage control method provided in the embodiments of the present invention.
[0096] The above describes in detail various embodiments corresponding to the active-active storage control method. On this basis, the present invention also discloses an active-active storage control device, equipment, non-volatile storage medium and computer program product corresponding to the above method.
[0097] Figure 6 A schematic diagram of the structure of an active-active storage control device provided by an embodiment of the present invention.
[0098] like Figure 6 As shown, the active-active storage control device provided by the embodiment of the present invention is applied to a storage control host and includes:
[0099] Deployment unit 601 is configured to create alternately distributed active-active volumes at corresponding active-active primary sites and active-active secondary sites when creating an active-active storage system, such that active-active primary volumes of some active-active volumes are deployed at the active-active primary site, and active-active primary volumes of other active-active volumes are deployed at the active-active secondary site.
[0100] A failover unit 602 is configured to, if a failure occurs at the active-active master site or the active-active slave site, set the active-active slave volume of the corresponding active-active volume as the active-active master volume if the corresponding failed volume is the active-active master volume;
[0101] The fault recovery unit 603 is configured to restore the corresponding active-active volume to an initial alternating distribution state after the faulty volume is recovered.
[0102] It should be noted that in each embodiment of the active-active storage control device provided by the embodiment of the present invention, the division of units is only a logical functional division, and other division methods can be used. The connection method between different units can adopt electrical, mechanical or other connection methods. Separated units can be located in the same physical location or distributed on multiple network nodes. Each unit can be implemented in the form of hardware or in the form of a software functional unit. That is, according to actual needs, some or all of the units provided in the embodiment of the present invention can be selected and the corresponding connection method or integration method can be adopted to achieve the purpose of the embodiment of the present invention.
[0103] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, and they will not be repeated here.
[0104] Figure 7 A schematic diagram of the structure of an active-active storage control device provided by an embodiment of the present invention.
[0105] like Figure 7 As shown, the active-active storage control device provided in an embodiment of the present invention includes: a memory 710 for storing a computer program 711; a processor 720 for executing the computer program 711. When the computer program 711 is executed by the processor 720, the steps of the active-active storage control method provided in any of the above embodiments are implemented.
[0106] The processor 720 may include one or more processing cores, such as a 3-core processor or an octa-core processor. The processor 720 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor 720 may also include a main processor and a coprocessor. The main processor is used to process data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 720 may integrate a graphics processing unit (GPU), which is responsible for rendering and drawing content required to be displayed on the display screen. In some embodiments, the processor 720 may also include an artificial intelligence (AI) processor, which is used to handle computational operations related to machine learning.
[0107] The memory 710 may include one or more non-volatile storage media, which may be non-transitory. The memory 710 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 710 is at least used to store the following computer program 711, wherein, after the computer program 711 is loaded and executed by the processor 720, it can implement the relevant steps in the active-active storage control method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 710 may also include an operating system 712 and data 713, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 712 may be Windows or other types of operating systems. The data 713 may include but is not limited to the data involved in the above method.
[0108] In some embodiments, the active-active storage control device may further include a display screen 730 , a power supply 740 , a communication interface 750 , an input / output interface 760 , a sensor 770 , and a communication bus 780 .
[0109] Those skilled in the art will understand that Figure 7 The structure shown in the figure does not constitute a limitation on the active-active storage control device, and may include more or fewer components than shown in the figure.
[0110] The active-active storage control device provided in an embodiment of the present invention includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the steps of the active-active storage control method provided in the above embodiment, and the effect is the same as above.
[0111] An embodiment of the present invention provides a non-volatile storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the active-active storage control method provided in any one of the above embodiments can be implemented.
[0112] The non-volatile storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., which can store program code.
[0113] For an introduction to the non-volatile storage medium provided in the embodiment of the present invention, please refer to the above method embodiment, and the effect thereof is the same as the active-active storage control method provided in the embodiment of the present invention, and the present invention will not elaborate on it here.
[0114] An embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the active-active storage control method provided in any one of the above embodiments.
[0115] For an introduction to the computer program product provided by the embodiment of the present invention, please refer to the above method embodiment, and the effect thereof is the same as the active-active storage control method provided by the embodiment of the present invention, and the present invention will not elaborate on it here.
[0116] The above is a detailed introduction to a dual-active storage control method, device, equipment and non-volatile storage medium provided by the present invention. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other. For the devices, equipment, non-volatile storage media and computer program products disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, the present invention can also be improved and modified in several ways, and these improvements and modifications also fall within the scope of protection of the present invention.
[0117] It should also be noted that, in this specification, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.
Claims
1. A dual-active storage control method, characterized in that: Applicable to storage control hosts, including: When creating an active-active storage system, alternately distributed active-active volumes are created at corresponding active-active primary sites and active-active secondary sites, so that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site, and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active secondary site. If a failure occurs at the active-active master site or the active-active slave site, and if the corresponding failed volume is the active-active master volume, the active-active slave volume of the corresponding active-active volume is set as the active-active master volume; After the failed volume is restored, restoring the corresponding active-active volume to an initial alternating distribution state; The step of creating alternately distributed active-active volumes at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a portion of the active-active volumes are deployed at the active-active master site and the active-active master volumes of another portion of the active-active volumes are deployed at the active-active slave site, includes: Determining a master-slave volume distribution ratio of each of the active-active master site and the active-active slave site; Determining, at the active-active primary site, a storage node for deploying the active-active primary volume and a storage node for deploying the active-active slave volume according to the distribution ratio of the active-active volumes, so as to create the active-active volume; Determining the master-slave volume distribution ratio of each of the active-active master site and the active-active slave site includes: If an input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio setting value is used as the master-slave volume distribution ratio; If the input master-slave volume distribution ratio setting value is not received, the master-slave volume distribution ratio is adopted as that 50% of the active-active master volumes are deployed at both the active-active master site and the active-active slave site.
2. The active-active storage control method according to claim 1, wherein: The active-active master site and the active-active slave site are both deployed with 50% of the active-active master volume as the master-slave volume distribution ratio, including: The active-active volumes are created sequentially according to the number of active-active volumes to be created in the active-active storage system, and when a command to create the active-active volume is issued to the processor core, storage nodes are cyclically selected from the active-active primary site and the active-active slave site to create an active-active primary volume of the active-active volume.
3. The active-active storage control method according to claim 1, wherein: Determining, based on the master-slave volume distribution ratio, a storage node for deploying the active-active master volume and a storage node for deploying the active-active slave volume at the active-active master site to create the active-active volume, including: Determining, based on the master-slave volume distribution ratio, a site where a dual-active master volume of each to-be-created dual-active volume of the active-active storage system is located and a site where a dual-active slave volume of each to-be-created dual-active volume is located; Storage nodes are randomly selected at the site where the active-active primary volume of the active-active volume to be created is located and at the site where the active-active secondary volume of the active-active volume to be created is located to create the active-active primary volume and the active-active secondary volume for the active-active volume to be created.
4. The active-active storage control method according to claim 1, wherein: The step of creating alternately distributed active-active volumes at the corresponding active-active master site and active-active slave site, so that active-active master volumes of a portion of the active-active volumes are deployed at the active-active master site and active-active master volumes of another portion of the active-active volumes are deployed at the active-active slave site, includes: When the active-active primary site and the active-active slave site create the alternatingly distributed active-active volumes, if a preferred storage node exists at the site where the active-active primary volume of the active-active volume to be created is located, the active-active primary volume of the active-active volume to be created is preferentially deployed on the preferred storage node.
5. The active-active storage control method according to claim 1, wherein: When creating the active-active storage system, creating alternately distributed active-active volumes at corresponding active-active primary sites and active-active slave sites, so that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site, and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active slave site, including: Determining the master-slave volume distribution ratio of the active-active master site and the active-active slave site according to the customized settings of the active-active storage system inputted through the user input interface; If an input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio setting value is used as the master-slave volume distribution ratio; If the input master-slave volume distribution ratio setting value is not received, the master-slave volume distribution ratio is set as follows: 50% of the active-active master volumes are deployed on both the active-active master site and the active-active slave site; The active-active volumes are created sequentially according to the number of active-active volumes to be created in the active-active storage system, and when a command to create the active-active volumes is issued to the processor core, a storage node is selected from the active-active primary site or the active-active slave site according to the master-slave volume distribution ratio to create the active-active primary volume of the active-active volume, and a storage node is selected from another site to create the active-active slave volume of the active-active volume; wherein, if a preferred storage node exists at the active-active primary site or the active-active slave site, the preferred storage node is preferentially selected when the site selects the active-active primary volume; If a failure occurs at the active-active master site or the active-active slave site, and if the corresponding failed volume is the active-active master volume, setting the active-active slave volume of the corresponding active-active volume as the active-active master volume includes: If only the active-active primary volume of some of the active-active volumes fails, only the active-active slave volume corresponding to the failed volume is set as the active-active primary volume of the active-active volume, and the cluster view of the active-active storage system is updated; If a site-level failure occurs at the active-active master site or the active-active slave site, the active-active slave volumes corresponding to the active-active master volume at the failed site at the other site are set as the active-active master volumes, and the cluster view of the active-active storage system is updated; After the failed volume is recovered, restoring the corresponding active-active volume to an initial alternating distribution state includes: After the failed volume is recovered, the corresponding active-active volume is restored to an initial alternating distribution state, and the cluster view of the active-active storage system is updated.
6. A dual-active storage control device, characterized in that: Applicable to storage control hosts, including: A deployment unit is configured to create alternately distributed active-active volumes at corresponding active-active primary sites and active-active slave sites when creating an active-active storage system, so that active-active primary volumes of a portion of the active-active volumes are deployed at the active-active primary site, and active-active primary volumes of another portion of the active-active volumes are deployed at the active-active slave site; a failover unit configured to, if a failure occurs at the active-active master site or the active-active slave site, set the active-active slave volume of the corresponding active-active volume as the active-active master volume if the corresponding failed volume is the active-active master volume; A fault recovery unit, configured to restore the corresponding active-active volume to an initial alternating distribution state after the faulty volume is recovered; The step of creating alternately distributed active-active volumes at the corresponding active-active master site and active-active slave site, so that the active-active master volumes of a portion of the active-active volumes are deployed at the active-active master site and the active-active master volumes of another portion of the active-active volumes are deployed at the active-active slave site, includes: Determining a master-slave volume distribution ratio of each of the active-active master site and the active-active slave site; Determining, at the active-active primary site, a storage node for deploying the active-active primary volume and a storage node for deploying the active-active slave volume according to the distribution ratio of the active-active volumes, so as to create the active-active volume; Determining the master-slave volume distribution ratio of each of the active-active master site and the active-active slave site includes: If an input master-slave volume distribution ratio setting value is received, the master-slave volume distribution ratio setting value is used as the master-slave volume distribution ratio; If the input master-slave volume distribution ratio setting value is not received, the master-slave volume distribution ratio is adopted as that 50% of the active-active master volumes are deployed at both the active-active master site and the active-active slave site.
7. A dual-active storage control device, characterized in that: include: Memory for storing computer programs; A processor is used to execute the computer program, and when the computer program is executed by the processor, the steps of the active-active storage control method according to any one of claims 1 to 5 are implemented.
8. A non-volatile storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the active-active storage control method according to any one of claims 1 to 5 are implemented.