Active-active storage system and data processing method thereof

Abstract

The present application provides an active-active storage system and a data processing method thereof, wherein the active-active storage system includes: a first storage site and a second storage site, and the second storage site is a backup storage site of the first storage site; a first resource pool is created in the first storage site, and the first resource pool is configured as a first redundancy strategy; a second resource pool is created in the second storage site, and the second resource pool is configured as a second redundancy strategy; a first logical volume is created in the first resource pool, and a second logical volume is created in the second resource pool, and the first logical volume and the second logical volume are configured as active-active volumes, and the active-active volumes are used to record placement group PG logs and provide data cache. This solution reduces the bandwidth usage of the distributed active-active storage system and improves system performance and reliability.

Description

Technical Field

[0001] The present application relates to the technical field of data storage, and in particular to an active-active storage system and a data processing method thereof. Background Art

[0002] As information technology becomes increasingly integrated into every industry and into people's daily lives, storage systems are playing an increasingly crucial role in critical operations across these sectors, leading to unprecedented demands for business continuity. This is particularly true in sectors such as communications, finance, healthcare, government offices, logistics, and e-commerce. Storage system outages can lead to the loss of critical data, significantly diminishing corporate credibility, and incurring significant economic losses. Therefore, ensuring business continuity is crucial for storage system development, and active-active technology has emerged in this context.

[0003] Active-active technology, commonly known as Active-Active, has gained widespread recognition in the storage industry. It provides users with flexible and powerful data disaster recovery capabilities, enabling real-time data synchronization and replication between two data centers, real-time business operation status monitoring, and failover. This ensures online cross-data center business switching and load balancing.

[0004] For example, traditional disaster recovery deployments typically involve a production center and a disaster recovery center. The disaster recovery center is usually inactive and only activated when a disaster occurs, paralyzing the production center. This type of disaster recovery system faces the following challenges: When the production center is hit by a disaster such as a flood, fire, man-made disaster, or earthquake, manual operations must be switched to the disaster recovery center. This results in prolonged business interruptions, typically with an RTO (Recovery Time Object) measured in hours, making it impossible to guarantee business continuity. The disaster recovery center remains idle year-round, resulting in low resource utilization and an increase in the overall TCO (Total Cost of Ownership). Summary of the Invention

[0005] The purpose of this application is to provide an active-active storage system and a data processing method thereof, so as to reduce the bandwidth occupancy of a distributed active-active storage system, thereby improving system performance and reliability.

[0006] In a first aspect, the present application provides an active-active storage system based on a distributed storage method, including:

[0007] A first storage site and a second storage site, wherein the second storage site is a backup storage site for the first storage site;

[0008] A first resource pool is created in the first storage site, and the first resource pool is configured as a first redundancy strategy;

[0009] A second resource pool is created in the second storage site, and the second resource pool is configured as a second redundancy strategy;

[0010] A first logical volume is created in the first resource pool, and a second logical volume is created in the second resource pool. The first logical volume and the second logical volume are configured as active-active volumes, which are used to record placement group PG logs and provide data cache.

[0011] A second aspect of the present application provides a data processing method, which is applied to the active-active storage system described in the first aspect. The method includes:

[0012] The first logical volume receives the first data sent by the first storage gateway and a processing result of the first data processed according to the Ceph index rule;

[0013] The first logical volume stores the first data in the first storage site according to a processing result of the first data, and records a PG log in the processing result, and the first storage site performs redundancy protection on the first data according to a first redundancy policy;

[0014] The first logical volume sends the first data and the processing results thereof to the second logical volume, so that the second logical volume stores the first data to the second storage site according to the processing results of the first data, and records the PG log in the processing results. The second storage site performs redundant protection on the first data according to the second redundancy strategy.

[0015] A third aspect of the present application provides a data processing method, which is applied to the active-active storage system described in the first aspect. The method includes:

[0016] The second logical volume receives the second data sent by the second storage gateway and a processing result of the second data processed according to the Ceph index rule;

[0017] The second logical volume locally caches the second data and records the PG log in the processing result;

[0018] The second logical volume sends the second data and the processing result thereof to the first logical volume, so that the first logical volume stores the second data in the first storage site according to the processing result of the second data and records the PG log in the processing result. The first storage site performs redundancy protection on the second data according to the first redundancy policy.

[0019] After receiving the control message sent by the first logical volume, the second logical volume stores the locally cached second data in the second storage site, and the second storage site performs redundancy protection on the second data according to the second redundancy policy.

[0020] Compared with the existing technology, the active-active storage system provided by this application has the following beneficial effects:

[0021] 1. Deploy two replicas of active-active volumes across clusters. This storage volume does not store actual data but only records metadata and can provide caching capabilities.

[0022] 2. Active-active volumes leverage the strong consistency of Ceph's two replicas to ensure cross-site data flow, enabling real-time cross-site data synchronization and automatic synchronization after failure recovery. This ensures that when both clusters are operating normally, data at the primary and backup sites are consistent in real time, with an RPO of 0.

[0023] 3. The number of complete copies of data stored at a single site, using complete redundant copies to ensure maximum data reliability.

[0024] 4. In this active-active storage system, each primary and backup site is configured with an independent data redundancy strategy, and the redundancy strategy can be flexibly selected. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0026] Figure 1 FIG2 is a schematic diagram of a cluster structure of an existing active-active storage system;

[0027] Figure 2 Shown Figure 1 Schematic diagram of the data writing operation process of the active-active storage system;

[0028] Figure 3 A schematic diagram of the cluster structure of an active-active storage system provided by the present application is shown;

[0029] Figure 4 A flow chart of a data processing method provided by the present application is shown;

[0030] Figure 5 A flowchart showing another data processing method provided by the present application is shown;

[0031] Figure 6 Shown Figure 3 Another data write operation flow diagram of the active-active storage system. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0033] It should be noted that, unless otherwise specified, the technical or scientific terms used in this application should have the common meanings understood by those skilled in the art to which this application belongs.

[0034] In addition, the terms "first" and "second" are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0035] To facilitate understanding, some technical terms in this application are first introduced.

[0036] Ceph (distributed storage system) is an open source project that provides a software-defined, unified storage solution with the advantages of large-scale scalability, high performance, and no single point of failure. When an application accesses a Ceph cluster and performs a write operation, the data is stored as an object in Ceph's Object Storage Device (OSD). The Ceph Monitor is responsible for the health of the entire cluster. Generally speaking, the Monitor node can be deployed independently on a physical host, or the Monitor node and storage nodes can be deployed on the same physical host. In a Ceph cluster, several Monitors are responsible for managing, maintaining, and publishing cluster status information.

[0037] In Ceph storage, data is stored in objects, each with a default size of 4MB. Several objects belong to a placement group (PG), which in turn belongs to an OSD (on-premises disk). Generally, one OSD corresponds to one disk. Ceph uses a hierarchical cluster map, which is user-defined, and OSDs are the leaf nodes of this hierarchical cluster map.

[0038] In a Ceph cluster, you can create several resource pools (Pool). When creating each Pool, you need to specify the number of PGs in the Pool. Pool is a logical concept.

[0039] Figure 1 The following is a schematic diagram of the cluster structure of an existing active-active storage system. Figure 1 The active-active storage system shown provides storage services across two data centers in the same city using a remote storage service cluster. The deployment is as follows:

[0040] 1. Taking the deployment of a 6-node storage cluster as an example, node1, node2, and node3 are deployed at storage site A on two racks; node4, node5, and node6 are deployed at storage site B on two racks. The arbitration server is deployed at site C.

[0041] 2. Storage gateways are deployed across sites to form a cluster, and any gateway can provide storage cluster services;

[0042] 3. The storage service cluster is deployed across sites to form a cluster. Taking the deployment of four replicas as an example, set the storage fault domain to the rack and the number of replicas to 4. That is, of these four replicas, the data of two replicas runs in site A, and the data of the other two replicas runs in site B.

[0043] 4. The storage control service monitor node (Monitor) is deployed in a three-node cluster. Mon1 is deployed on a server at site A, Mon2 is deployed on a server at site B, and Mon3 is deployed on the arbitration server at site C to prevent storage split-brain phenomenon, which may lead to failure of data storage function.

[0044] 5. If a disaster occurs at site A or site B, the cross-site cluster disaster recovery system of the storage system can achieve business failure recovery with RPO=0 and RTO≈0, ensuring that no stored data is lost and the storage system continues to operate without being perceived by the business.

[0045] Figure 2 Shown Figure 1 The data writing operation process of the active-active storage system is as follows:

[0046] 1. The host side (client) sends the data to be written and metadata information to the storage side through the gateway, and the gateway receives and processes the data.

[0047] 2. The gateway calculates the disk to which the data needs to be written according to certain index rules, such as Figure 2As shown: Assume that the disks to be written are: node3-HDD1, node2-HDD2, node4-HDD1, node5-HDD2, and the relationship between the four copies that need to be written is: node3-HDD1 is the primary copy, node2-HDD2, node4-HDD1, and node5-HDD2 are backup copies.

[0048] 3. The gateway writes the data to the storage service process where the primary replica node3-HDD1 is located through the network.

[0049] 4. The storage service process deployed on node3-HDD1 writes the data to the storage service processes on node2-HDD2, node4-HDD1, and node5-HDD2 simultaneously according to the data redundancy policy.

[0050] 5. The storage service process writes data to disk based on certain logic processing;

[0051] 6. After all four copies of data are written successfully, node3-HDD1 considers the data written successfully and returns the write success information to the host side. At this point, the data is written successfully;

[0052] From the above data write operation process, we can see that the existing active-active storage system has the following shortcomings:

[0053] Disadvantage 1: Host performance degrades: Since the number of replicas is 4, two copies of the same data need to be transmitted to site B and written to different disks, resulting in host performance degradation;

[0054] Disadvantage 2: Increased link construction costs: Transmitting redundant data requires doubling link bandwidth, wasting link resources and increasing construction costs.

[0055] Disadvantage 3: Reduced reliability. Site failures will cause both replicas to become unavailable, increasing the risk of business downtime.

[0056] Disadvantage 4: It only supports cross-cluster replication solutions and does not support erasure coding (EC) redundancy, which increases space usage.

[0057] Of course, the above solution can be simplified to 2 copies, but it will reduce data reliability. For example, if the number of data copies is set to 2, then Site A and Site B each have one copy. If Site A fails and Site B takes over the business, there will be only one copy providing storage services, which will pose a risk of single point failure. If the hard disk or server where the copy is located fails, the business will have no data storage capacity available, causing business downtime.

[0058] In view of this, an embodiment of the present application provides an active-active storage system and a data processing method thereof, which are described below with reference to the accompanying drawings.

[0059] Please refer to Figure 3 , which shows a cluster structure diagram of a dual-active storage system provided by some embodiments of the present application. The dual-active storage system is based on a distributed storage method, for example, it can be a Ceph method or other distributed storage methods, which is not limited by the present application.

[0060] like Figure 3 As shown, the active-active storage system includes: a first storage site 100 and a second storage site 200, and the second storage site 200 is a backup storage site of the first storage site 200;

[0061] A first resource pool 110 is created in the first storage site 100 and is configured as a first redundancy policy; a second resource pool 210 is created in the second storage site 200 and is configured as a second redundancy policy;

[0062] For example, Figure 3 As shown, the first resource pool 110 includes storage nodes node1, node2, and node3, and the second resource pool 210 includes storage nodes node4, node5, and node6. Each storage node includes two disks, and each disk corresponds to an object storage device OSD.

[0063] Specifically, the first redundancy strategy can be replica redundancy or erasure code redundancy, and the second redundancy strategy can be replica redundancy or erasure code redundancy. For example, there are three combinations: site 100 is configured with replica redundancy, and site 200 is configured with replica redundancy; site 100 is configured with replica redundancy, and site 200 is configured with erasure code redundancy; site 100 is configured with erasure code redundancy, and site 200 is configured with erasure code redundancy.

[0064] A first logical volume is created in the first resource pool 110, and a second logical volume is created in the second resource pool 210. The first logical volume and the second logical volume are configured as active-active volumes, which are used to record PG logs (PGlog) and provide data cache.

[0065] Specifically, the backend storage of the active-active volume may be a distributed cache, such as cache tier; or a distributed database, such as mondb.

[0066] For example, create a logical active-active pool, PoolAB1, and configure the redundancy policy to 2 replicas. This allows you to leverage the existing Crush algorithm to implement a 2-replica mechanism and strong data consistency. Based on the data download plan, you can set the Crush algorithm to specify the local primary. The Crush algorithm is used to determine which OSDs (on which OSDs) objects should be distributed.

[0067] Specifically, create a local resource pool PoolA1 at site 100, configure the redundancy policy as copy redundancy, and set the number of copies to 3. Create a local resource pool PoolB1 at site 200, configure the redundancy policy as copy redundancy, and set the number of copies to 2.

[0068] Create volume rbdA1 in site 100 / PoolA1 and volume rbdB1 in site 200 / PoolB1. Create an active-active relationship: Select 100 / PoolA1 / rbdA1 and 200 / PoolB1 / rbdB1 to create an active-active relationship in active-active pool PoolAB1. At this time, the active-active relationship object 100 / PoolA1 / rbdA1-200 / PoolB1 / rbdB1 will be generated in the PG object in the active-active pool. This will be used as the key value to record the PG log of subsequent write operations.

[0069] For write operations, the logical active-active pool provides a PG mechanism for the active-active relationship, which is used to implement a replica redundancy mechanism and ensure strong data consistency. However, it does not directly store data. Data that needs to be written is written to a specified resource space through an index relationship. Three types of data need to be stored:

[0070] The first type, the write-site resource pool, is an independent storage resource pool with customizable redundancy policies and levels. Write operations are dispatched from the objecter, which calculates the object name based on the volume name, LBA (Logical Block Address), and length. The object name is written to the primary OSD using the Crush algorithm, and then written to disk using the object's PG for redundancy protection. The objecter provides a unified interface for client read and write requests.

[0071] The second type is writing to the peer site resource pool. The PG in the active-active pool is responsible for sending write operations to the target site for processing. The PG at the target site indexes the data to the local resource 200 / PoolB1rbdB1 or 100 / PoolA1 / rbdA1 for write operations. The write operation is issued from the objector, and the object name is calculated based on the volume name, LBA, and length. It is written to the primary OSD through the Crush algorithm, and then written to the disk through the PG where the object is located for redundant protection. More efficient distributed caching technology can also be used for back-end devices to improve IO performance.

[0072] The third category is the active-active pool PGlog: used to record data changes. The main record keywords are volume name, LBA, length, and write sequence number. Since the active-active pool is a logical pool and does not actually store data, the location where the PGlog is written can be determined as needed, such as a distributed database, reusing the storage pool where the local resources of the active-active member volume are located, reusing other storage pools, establishing a separate copy storage pool, cache, distributed cache, etc.

[0073] In the active-active storage system provided by this application, when a site fails, data is written to a single site. At this time, the active-active pool will record PGlog. When both sites are restored, data recovery is performed based on PGlog, and data is read from the end with PGlog and synchronized to the other end site.

[0074] In one possible implementation, the active-active storage system provided in the present application further includes: an arbitration site 300; specifically, the first storage site 100 is deployed with a first monitor mon1, and the second storage site is deployed with a second monitor mon2; the arbitration site is deployed with an arbitration monitor mon3, which is used to provide arbitration services to the first monitor and the second monitor to prevent brain split.

[0075] like Figure 3 As shown, the first monitor mon1 is deployed on node2, the second monitor mon2 is deployed on node5, and the arbitration monitor mon3 is deployed on the arbitration server.

[0076] In one possible implementation, the above-mentioned active-active storage system provided in the present application also includes: a first storage gateway 120, which is used to receive the first data sent by the client, and process the first data according to the Ceph index rule to obtain a processing result, and send the processing result and the first data to the first logical volume, and the processing result includes PGlog and the stored object storage device OSD.

[0077] In one possible implementation, the above-mentioned active-active storage system provided in the present application also includes: a second storage gateway 220, which is used to receive the second data sent by the client, and process the second data according to the Ceph index rule to obtain a processing result, and send the processing result and the second data to the second logical volume.

[0078] In a possible implementation, in the active-active storage system provided in the present application, the first storage site 100 is an independent protection domain, and the second storage site 200 is another independent protection domain.

[0079] In this application, the Ceph cluster is divided into two protection domains, specifically site 100 as an independent protection domain and site 200 as an independent protection domain, to avoid cross-site data redundancy distribution of local sites. The protection domain is a logical concept set to improve the reliability of the cluster. A piece of data (including replicas or shards) only exists in one protection domain, and heartbeat detection is also within the protection domain.

[0080] Compared with the existing technology, the active-active storage system provided by this application has the following beneficial effects:

[0081] 1. Deploy two replicas of active-active volumes across clusters. This storage volume does not store actual data but only records metadata and can provide caching capabilities.

[0082] 2. Active-active volumes leverage the strong consistency of Ceph's two replicas to ensure cross-site data flow, enabling real-time cross-site data synchronization and automatic synchronization after failure recovery. This ensures that when both clusters are operating normally, data at the primary and backup sites are consistent in real time, with an RPO of 0.

[0083] 3. The number of complete copies of data stored at a single site, using complete redundant copies to ensure maximum data reliability.

[0084] 4. In this active-active storage system, each primary and backup site is configured with an independent data redundancy strategy, and the redundancy strategy can be flexibly selected.

[0085] In the above embodiment, a dual-active storage system is provided. Correspondingly, the present application also provides two data processing methods based on the above-mentioned dual-active storage system, one is a data processing method after the client's write operation is sent to the first storage gateway, and the other is a data processing method after the client's write operation is sent to the second storage gateway.

[0086] Specifically, after the client's write operation is sent to the first storage gateway, Figure 4 As shown, the data processing method includes the following steps:

[0087] S101: The first logical volume receives first data sent by a first storage gateway and a processing result of the first data processed according to a Ceph index rule;

[0088] S102: The first logical volume stores the first data in the first storage site according to the processing result of the first data, and records the PG log in the processing result. The first storage site performs redundancy protection on the first data according to the first redundancy policy.

[0089] S103. The first logical volume sends the first data and the processing results thereof to the second logical volume, so that the second logical volume stores the first data to the second storage site according to the processing results of the first data, and records the PG log in the processing results. The second storage site performs redundant protection on the first data according to the second redundancy strategy.

[0090] like Figure 3 As shown, the above data processing flow is as follows:

[0091] ① The business client sends a write operation to the first storage gateway, and the first storage gateway processes the first data to obtain a processing result;

[0092] ② The first storage gateway sends the first data and its processing results to the replica master (the first logical volume);

[0093] ③ The replica master caches the first data locally and records the PGlog according to the PG mechanism; the data at the first storage site is written and redundantly protected;

[0094] ④ The primary replica sends the first data and its processing results to the backup replica (second logical volume) for processing;

[0095] ⑤ The replica caches the first data locally and records the PGlog according to the PG mechanism to implement active-active data management logic;

[0096] ⑥ Data is written to the second storage site and redundantly protected. The replica master receives a write completion message and returns a write completion message to the client.

[0097] Specifically, after the client's write operation is sent to the second storage gateway, Figure 5 As shown, the data processing method includes the following steps:

[0098] S201: The second logical volume receives second data sent by the second storage gateway and a processing result of the second data processed according to the Ceph index rule;

[0099] S202: The second logical volume locally caches the second data and records the processing result in a PG log;

[0100] S203: The second logical volume sends the second data and the processing result thereof to the first logical volume, so that the first logical volume stores the second data in the first storage site according to the processing result of the second data and records the PG log in the processing result. The first storage site performs redundancy protection on the second data according to the first redundancy policy.

[0101] S204: After receiving the control message sent by the first logical volume, the second logical volume stores the locally cached second data in the second storage site, and the second storage site performs redundancy protection on the second data according to the second redundancy policy.

[0102] like Figure 6 As shown, the above data processing flow is as follows:

[0103] ① The business client sends a write operation to the second storage gateway, and the second storage gateway processes the second data to obtain a processing result;

[0104] ② The second storage gateway sends the second data and its processing results to the replica;

[0105] ③ The copy caches the second data locally and records the PGlog according to the PG mechanism;

[0106] ④ The backup replica sends the second data and its processing results to the primary replica for processing;

[0107] ⑤ The replica master caches the secondary data locally and records the PGlog according to the PG mechanism to implement active-active data management logic;

[0108] ⑥ The first storage site writes data and performs redundant protection, and sends a control message to the replica to write data;

[0109] ⑦ Data is written to the second storage site and redundantly protected. The primary replica receives a write completion message and returns a write completion message to the backup replica. The backup replica returns a write completion message to the client.

[0110] The data processing method of the above-mentioned active-active storage system of the present application realizes cross-site virtual machine replica protection and single-site independent data redundancy protection, and realizes cross-site active-active technology under distributed storage; based on the existing PG mechanism of Ceph, the cross-site active-active function is realized through the data active-active layer PG and the data storage layer PG. According to the active-active needs, the Crush algorithm of the active-active pool is set to realize the replica master at the desired site, improving the data reading and writing performance; cross-site data is copied once, and the active-active metadata is stored in a minimalist manner without occupying additional network resources and storage space; the replica protection mechanism between the original OSDs is abstracted to the client layer to retain the PGlog mechanism, and no real data is stored, so as to realize a cross-site data double-write strong consistency mechanism. Modification of the PG mechanism: when the replica master synchronizes data to the replica standby, it can choose to synchronize the real data or send a control message to the disk according to the data identifier, so as to realize efficient strong consistency of data between cross-site replicas.

[0111] Finally, it should be noted that the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment or part of the code, and the module, program segment or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0112] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, the indirect coupling or communication connection of the device or unit can be electrical, mechanical or other forms.

[0114] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and they should all be included in the scope of the claims and description of the present application.

Claims

1. A dual-active storage system based on distributed storage, characterized in that: include: A first storage site and a second storage site, wherein the second storage site is a backup storage site for the first storage site; A first resource pool is created in the first storage site, and the first resource pool is configured with a first redundancy strategy; the first resource pool is a local resource pool of the first storage site; A second resource pool is created in the second storage site, and the second resource pool is configured as a second redundancy strategy; the second resource pool is a local resource pool of the second storage site; A first logical volume is created in the first resource pool, and a second logical volume is created in the second resource pool. The first logical volume and the second logical volume are configured as active-active volumes, and the active-active volumes are used to record placement group PG logs and provide data cache. The active-active storage system further includes: A first storage gateway is configured to receive first data sent by a client, process the first data according to a Ceph index rule to obtain a processing result, and send the processing result and the first data to the first logical volume, wherein the processing result includes a PG log and a stored object storage device OSD; The second storage gateway is used to receive the second data sent by the client, process the second data according to the Ceph index rule to obtain a processing result, and send the processing result and the second data to the second logical volume.

2. The active-active storage system according to claim 1, wherein: The backend storage of the active-active volume is a distributed cache or a distributed database.

3. The active-active storage system according to claim 1, wherein: The first redundancy strategy is replica redundancy or erasure code redundancy.

4. The active-active storage system according to claim 1, wherein: The second redundancy strategy is replica redundancy or erasure code redundancy.

5. The active-active storage system according to claim 1, wherein: The active-active storage system further includes: an arbitration site; A first monitor is deployed at the first storage site, and a second monitor is deployed at the second storage site; an arbitration monitor is deployed at the arbitration site, and the arbitration monitor is used to provide arbitration services for the first monitor and the second monitor.

6. The active-active storage system according to claim 1, wherein: The first storage site is an independent protection domain, and the second storage site is another independent protection domain.

7. A data processing method, applied to the active-active storage system according to any one of claims 1 to 6, characterized in that: The method comprises: The first logical volume receives the first data sent by the first storage gateway and a processing result of the first data processed according to the Ceph index rule; The first logical volume stores the first data in the first storage site according to a processing result of the first data, and records a PG log in the processing result, and the first storage site performs redundancy protection on the first data according to a first redundancy policy; The first logical volume sends the first data and the processing results thereof to the second logical volume, so that the second logical volume stores the first data to the second storage site according to the processing results of the first data, and records the PG log in the processing results. The second storage site performs redundant protection on the first data according to the second redundancy strategy.

8. A data processing method, applied to the active-active storage system according to any one of claims 1 to 6, characterized in that: The method comprises: The second logical volume receives the second data sent by the second storage gateway and a processing result of the second data processed according to the Ceph index rule; The second logical volume locally caches the second data and records the PG log in the processing result; The second logical volume sends the second data and the processing result thereof to the first logical volume, so that the first logical volume stores the second data in the first storage site according to the processing result of the second data and records the PG log in the processing result. The first storage site performs redundancy protection on the second data according to the first redundancy policy. After receiving the control message sent by the first logical volume, the second logical volume stores the locally cached second data in the second storage site, and the second storage site performs redundancy protection on the second data according to the second redundancy policy.

Images