Cloud disaster recovery method and device across heterogeneous processor sites, equipment and storage medium

Abstract

The invention relates to a cloud disaster recovery method and device across heterogeneous processor sites, equipment and a storage medium. The method comprises the steps that production data of a production site are monitored, the change content of the production data is recognized according to a preset interval duration, the change content is recorded through a newly-built change data block, and the change position of the production data is recorded through a newly-built binary table; controlling the newly-built changed data block and the binary table to be backed up in the production site at each moment of the preset interval duration; obtaining an accumulated change rate of the binary table at the current moment, and judging whether the accumulated change rate of the binary table at the current moment is greater than a first threshold value or not; and when the accumulated change rate of the binary table at the current moment is greater than a first threshold value in response, sending the new changed data block at the current moment and the binary table to the disaster recovery station for backup, and setting the accumulated change rate at the next moment to be zero.

Description

Technical Field

[0001] The present application relates to the field of cloud computing technology, and in particular to a cloud disaster recovery method, apparatus, computer equipment and storage medium across heterogeneous processor sites. Background Art

[0002] As a computing power supply model that pursues cost-effectiveness, cloud computing is changing its processor upgrade, replacement and expansion from a single architecture to multiple heterogeneous architectures. In the case of differences in the functions, performance and reliability of multiple heterogeneous processors, in order to meet the technical requirements of high efficiency and stability, achieve low cost and free switching of applications across processors, avoid supply risks, and ensure the long-term stable operation of key businesses, "one cloud, multiple cores" has become an inevitable trend in the development of cloud computing.

[0003] In the one-cloud-multiple-core scenario, cloud computing systems face the problem of user business system reliability. Traditional cloud computing systems are based on Intel and AMD platforms, and the software and hardware systems are relatively mature and stable. Central processing units (CPUs) with inconsistent instruction sets, such as CPUs from different manufacturers and CPUs from the same manufacturer but different generations, can all be considered heterogeneous processors. However, in the one-cloud-multiple-core scenario, including multiple heterogeneous processors, it is more complicated to achieve unified resource pooling and scheduling management of servers equipped with heterogeneous processors, increasing the risk of data loss for user business applications. Summary of the invention

[0004] Based on this, a cloud disaster recovery method, apparatus, computer equipment and storage medium across heterogeneous processor sites are provided to solve the technical problem of low transmission efficiency of backup data and binary tables when current cloud disaster recovery uses heterogeneous processors.

[0005] In one aspect, a cloud disaster recovery method across heterogeneous processor sites is provided, the method comprising:

[0006] Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table;

[0007] Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0008] Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0009] In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

[0010] In one embodiment, obtaining the cumulative change rate of the binary table at the current moment includes:

[0011] Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup;

[0012] If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment;

[0013] Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

[0014] In one embodiment, the step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes:

[0015] Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero;

[0016] When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one;

[0017] Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment;

[0018] After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

[0019] In one embodiment, after sending the newly created changed data block and the binary table to the disaster recovery site for backup, the method further includes:

[0020] Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time;

[0021] The changed data blocks between the current time and the last backup time are merged with the backup data at the last backup time, and the binary table between the current time and the last backup time is merged with the binary table at the last backup time to save the latest backup data and binary table in the production site.

[0022] In one embodiment, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes:

[0023] A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table;

[0024] A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access (RDMA) channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

[0025] In one embodiment, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup further includes:

[0026] The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

[0027] In one embodiment, the method further comprises:

[0028] The same number of load test applications are respectively set in the production site and the disaster recovery site, and the load test applications include virtual machines, containers or target business application systems;

[0029] Running the load test application in the production site and the disaster recovery site, and obtaining performance scores of the production site and the disaster recovery site through performance testing;

[0030] Compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, adjust the number of load test applications set in the production site and the disaster recovery site according to the performance score difference, reduce the load test applications in the production site and / or increase the load test applications in the disaster recovery site when the performance score of the production site is high, and increase the load test applications in the production site and / or reduce the load test applications in the disaster recovery site when the performance score of the production site is low;

[0031] Obtaining, through performance testing, performance scores of the production site and the disaster recovery site after adjusting the number of load test applications, and cyclically adjusting the number of load test applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal;

[0032] Obtaining a ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal;

[0033] The ratio of the first mirror memory to the second mirror memory is adjusted according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

[0034] On the other hand, a cloud disaster recovery device across heterogeneous processor sites is provided, the device comprising:

[0035] A production data management module, used to monitor the production data of the production site, identify changes in the production data according to a preset interval, record the changes in the production data by creating a new change data block, and record the change position of the production data by creating a new binary table;

[0036] A production site backup module, used for controlling the backup of the newly created change data block and the binary table in the production site at each moment of the preset interval;

[0037] A binary table change rate monitoring module, used to obtain the cumulative change rate of the binary table at the current moment, and determine whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0038] The disaster recovery site backup module is used to send the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup in response to the cumulative change rate of the binary table at the current moment being greater than the first threshold, and set the cumulative change rate at the next moment to zero.

[0039] In another aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:

[0040] Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table;

[0041] Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0042] Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0043] In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

[0044] In another aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0045] Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table;

[0046] Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0047] Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0048] In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

[0049] The above-mentioned cloud disaster recovery method, device, computer equipment and storage medium across heterogeneous processor sites control the production site to identify the change content of the production data of the production site according to a preset interval time, and the change position of the production data is recorded by creating a new binary table, and the cumulative change rate of the binary table at each moment of the preset interval time is continuously judged. When the cumulative change rate of the binary table is greater than a first threshold, the binary table and backup data are sent to the disaster recovery site for backup, thereby reducing the file size of the binary table and significantly improving the transmission efficiency of the backup data and the binary table. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0051] Figure 1 This is an application environment diagram of a cloud disaster recovery method across heterogeneous processor sites in one embodiment of the present application;

[0052] Figure 2 A schematic diagram of a process flow of a cloud disaster recovery method across heterogeneous processor sites in one embodiment of the present application;

[0053] Figure 3 A schematic diagram of a step for comparing a binary table at a current moment with a binary table at a previous moment to obtain a current change rate of the binary table at the current moment in one embodiment of the present application;

[0054] Figure 4 A schematic diagram of a step of sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup in one embodiment of the present application;

[0055] Figure 5 A schematic diagram of making the performance scores of the production site and the disaster recovery site equal in one embodiment of the present application;

[0056] Figure 6 This is a structural block diagram of a cloud disaster recovery device across heterogeneous processor sites in one embodiment of the present application;

[0057] Figure 7 This is a diagram of the internal structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] The cloud disaster recovery method across heterogeneous processor sites provided in this application can be applied to Figure 1 In the application environment shown in the figure, the cloud computing system as a cross-heterogeneous processor site includes a production site and a disaster recovery site, business applications are set in the production site and the disaster recovery site to form CPU platform A and CPU platform B, the production site is used for production data and local backup file storage, and the disaster recovery site stores backup files as disaster recovery backup.

[0060] In one embodiment, Figure 2As shown, a cloud disaster recovery method across heterogeneous processor sites is provided, wherein the cross-heterogeneous processor sites include a production site and a disaster recovery site, and the cloud disaster recovery method includes the following steps:

[0061] Step S1, monitoring the production data of the production site, identifying the changes of the production data according to a preset interval, recording the changes by creating a change data block, and recording the change position of the production data by creating a binary table;

[0062] Step S2, controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0063] Step S3, obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0064] Step S4, in response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, and setting the accumulated change rate at the next moment to zero.

[0065] Among them, by controlling the production site to identify the change content of the production data of the production site according to the preset interval time, the change position of the production data is recorded by creating a new binary table, and the cumulative change rate of the binary table at each moment of the preset interval time is continuously judged. When the cumulative change rate of the binary table is greater than the first threshold, the binary table and the backup data are sent to the disaster recovery site for backup, which reduces the file size of the binary table and significantly improves the transmission efficiency of the backup data and the binary table.

[0066] Specifically, the first threshold is preferably 50%. The threshold is used to determine whether to generate a new backup file to solve the problem of continuous growth in the size of the initial backup file, and solves the problems of too large backup files, slow remote replication and insufficient reconstruction service performance in traditional methods.

[0067] like Figure 3 As shown, in this embodiment, obtaining the cumulative change rate of the binary table at the current moment includes:

[0068] Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup;

[0069] If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment;

[0070] Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

[0071] Among them, by comparing the binary tables of two adjacent moments with a preset interval time, the cumulative change rate of the binary table at the current moment can be obtained, and based on the comparison of the cumulative change rate with the first threshold, it is determined whether to divide it into small backup files and send them to the disaster recovery site for backup.

[0072] In other embodiments, obtaining the cumulative change rate of the binary table at the current moment includes:

[0073] At the time of obtaining the binary table sent to the disaster recovery site for backup, the accumulated change rate of all the binary tables sent to the disaster recovery site for backup is zero;

[0074] Obtain the binary table sent to the disaster recovery site for backup at the latest moment, compare the binary table at the current moment with the binary table sent to the disaster recovery site for backup at the latest moment, and obtain the change rate of the binary table at the current moment and the binary table sent to the disaster recovery site for backup at the latest moment as the cumulative change rate of the binary table at the current moment.

[0075] Among them, the binary table at the current moment is compared with the binary table sent to the disaster recovery site for backup at the latest moment, and the change rate of the binary table at the current moment and the binary table sent to the disaster recovery site for backup at the latest moment is obtained as the cumulative change rate of the binary table at the current moment. The cumulative change rate of each moment can be directly obtained without summing, and based on the comparison of the cumulative change rate and the first threshold, it is identified whether to split into small backup files to send to the disaster recovery site for backup. If the backup files are not split into small files and sent to the disaster recovery site for backup, the size of the backup files may continue to grow. For example, the initial backup file is only 10 units in size, but at time 6, the backup file has reached 28 units in size. The continuous growth of the size of a single backup file will significantly increase the complexity of storage space management.

[0076] like Figure 3 As shown, in this embodiment, the step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes:

[0077] Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero;

[0078] When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one;

[0079] Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment;

[0080] After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

[0081] Among them, the binary table can be a bitmap, and the value of each bit in the binary table is set to zero or one. Zero represents that the data of the production site is used as the comparison benchmark, and one represents that the data of the production site has been modified. Based on the value of each bit in the binary table, it can be distinguished whether the data of the production site has changed.

[0082] like Figure 3 As shown, in this embodiment, after sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, it also includes:

[0083] Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time;

[0084] In the production site, the changed data blocks between the current moment and the last backup moment are merged with the backup data at the last backup moment, and the binary table between the current moment and the last backup moment is merged with the binary table at the last backup moment, so as to save the latest backup data and binary table in the production site.

[0085] By merging the backup data and binary tables at all times in the production site, so as to save the latest backup data and binary tables in the production site, the space occupied by the storage data in the production site is reduced.

[0086] like Figure 4 As shown, in this embodiment, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes:

[0087] A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table;

[0088] A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access (RDMA) channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

[0089] Among them, Figure 4 As shown, in terms of hardware, compared with the traditional method of only configuring production storage (HDD), a new cache storage pool (HDD) and mirror memory are configured, and the data flow is production storage->first cache storage pool->first mirror memory->RDMA channel->second mirror memory->second cache storage pool->backup storage.

[0090] In terms of software, optimizations have been made in the following directions: 1) Business applications only write data to production storage and do not write data to backup storage synchronously, thereby improving write performance; 2) Accordingly, data changes are remapped from the production storage pool to the cache storage pool to generate backup data and corresponding binary tables; 3) The production site only saves the latest backup data and binary tables, and transmits the changed data to the disaster recovery site based on the binary tables; 4) The disaster recovery site retains the backup data and binary tables at all times; 5) The binary tables of the production site and the backup site have different record formats, where the binary table of the production site records the data change position at the latest moment, and the binary table of the backup site records the data change position at the cumulative moment; 6) Based on the binary table of the production site, the changed data is first written from the cache storage pool to the mirror memory, and then written to the mirror memory of the disaster recovery site at high speed through the remote direct data access (RDMA) channel.

[0091] In this embodiment, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup further includes:

[0092] The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

[0093] Among them, the backup data and binary tables of all times are stored in the backup storage in the disaster recovery site. In order to reduce historical data, the backup data and binary tables of all times over a long period of time can be merged to form disaster recovery backup data, thereby reducing the backup storage space occupied by the disaster recovery site.

[0094] like Figure 5 As shown, in this embodiment, the cloud disaster recovery method across heterogeneous processor sites also includes:

[0095] The same number of load test applications are respectively set in the production site and the disaster recovery site, and the load test applications include virtual machines, containers or target business application systems;

[0096] Running the load test application in the production site and the disaster recovery site, and obtaining performance scores of the production site and the disaster recovery site through performance testing;

[0097] Compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, adjust the number of load test applications set in the production site and the disaster recovery site according to the performance score difference, reduce the load test applications in the production site and / or increase the load test applications in the disaster recovery site when the performance score of the production site is high, and increase the load test applications in the production site and / or reduce the load test applications in the disaster recovery site when the performance score of the production site is low;

[0098] Obtaining, through performance testing, performance scores of the production site and the disaster recovery site after adjusting the number of load test applications, and cyclically adjusting the number of load test applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal;

[0099] Obtaining a ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal;

[0100] The ratio of the first mirror memory to the second mirror memory is adjusted according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

[0101] like Figure 5As shown, a virtual machine, container or specific business application system with a fixed CPU configuration is run on CPU platform A; standard performance testing tools such as Stream, 7-Zip, sysbench, etc. are run on the virtual machine, container or specific business application system on CPU platform A to obtain a performance score; a virtual machine, container or specific business application system with the same configuration as CPU platform A is run on CPU platform B; standard performance testing tools are run on the virtual machine, container or specific business application system on CPU platform B to obtain a performance score; the performance score on CPU platform B is compared with the performance score on CPU platform A, and the performance score is adjusted by continuously adjusting the hardware resources occupied by the virtual machine, container or specific business application system on CPU platform B until the same performance score as that on CPU platform A is obtained, and the hardware configuration occupied by the virtual machine, container or specific business application system on CPU platform B is recorded at this time.

[0102] Based on the above experiments, the hardware resource configurations required by virtual machines, containers, or specific business application systems on CPU platform A and CPU platform B respectively under given performance scores are obtained and recorded in the computing power database.

[0103] Based on this computing power database, when a virtual machine, container or business application system at the primary site fails, after the backup site is rebuilt, the cloud computing system will allocate corresponding hardware resources to the virtual machine, container or business application system to obtain the same performance as the primary site.

[0104] In the above-mentioned cloud disaster recovery method across heterogeneous processor sites, the production site is controlled to identify the changed content of the production data of the production site according to a preset interval, the changed position of the production data is recorded by creating a new binary table, and the cumulative change rate of the binary table at each moment of the preset interval is continuously judged. When the cumulative change rate of the binary table is greater than a first threshold, the binary table and the backup data are sent to the disaster recovery site for backup, thereby reducing the file size of the binary table and significantly improving the transmission efficiency of the backup data and the binary table.

[0105] In one embodiment, Figure 6 As shown, a cloud disaster recovery device 10 across heterogeneous processor sites is provided, including: a production data management module 1, a production site backup module 2, a binary table change rate monitoring module 3, and a disaster recovery site backup module 4.

[0106] The production data management module 1 is used to monitor the production data of the production site, identify the changes in the production data according to a preset interval, record the changes in the production data by creating a new change data block, and record the change position of the production data by creating a new binary table.

[0107] The production site backup module 2 is used to control the backup of the newly created changed data block and the binary table in the production site at each moment of the preset interval.

[0108] The binary table change rate monitoring module 3 is used to obtain the cumulative change rate of the binary table at the current moment, and determine whether the cumulative change rate of the binary table at the current moment is greater than a first threshold.

[0109] The disaster recovery site backup module 4 is used to send the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup in response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, and set the accumulated change rate at the next moment to zero.

[0110] In this embodiment, obtaining the cumulative change rate of the binary table at the current moment includes:

[0111] Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup;

[0112] If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment;

[0113] Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

[0114] In this embodiment, the step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes:

[0115] Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero;

[0116] When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one;

[0117] Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment;

[0118] After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

[0119] In this embodiment, after sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, the method further includes:

[0120] Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time;

[0121] The changed data blocks between the current time and the last backup time are merged with the backup data at the last backup time, and the binary table between the current time and the last backup time is merged with the binary table at the last backup time to save the latest backup data and binary table in the production site.

[0122] In this embodiment, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes:

[0123] A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table;

[0124] A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access (RDMA) channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

[0125] In this embodiment, sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup further includes:

[0126] The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

[0127] In this embodiment, if Figure 6 As shown, the cloud disaster recovery device 10 across heterogeneous processor sites also includes: a performance score testing module 5, a load balancing module 6 and a transmission efficiency control module 7.

[0128] The performance score testing module 5 is used to set up the same number of load testing applications in the production site and the disaster recovery site respectively, and the load testing applications include virtual machines, containers or target business application systems; run the load testing applications in the production site and the disaster recovery site, and obtain the performance scores of the production site and the disaster recovery site through performance testing.

[0129] The load balancing module 6 is used to compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, and adjust the number of load testing applications set in the production site and the disaster recovery site according to the performance score difference; when the performance score of the production site is high, reduce the load testing applications in the production site and / or increase the load testing applications in the disaster recovery site; when the performance score of the production site is low, increase the load testing applications in the production site and / or reduce the load testing applications in the disaster recovery site; obtain the performance scores of the production site and the disaster recovery site after adjusting the number of load testing applications through performance testing, and cyclically adjust the number of load testing applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal.

[0130] The transmission efficiency control module 7 is used to obtain the ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal; adjust the ratio of the first mirror memory and the second mirror memory according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

[0131] In the above-mentioned cloud disaster recovery device across heterogeneous processor sites, the production site is controlled to identify the changed content of the production data of the production site according to the preset interval time, the changed position of the production data is recorded by creating a new binary table, and the cumulative change rate of the binary table at each moment of the preset interval time is continuously judged. When the cumulative change rate of the binary table is greater than the first threshold, the binary table and the backup data are sent to the disaster recovery site for backup, which reduces the file size of the binary table and significantly improves the transmission efficiency of the backup data and the binary table.

[0132] For the specific definition of the cloud disaster recovery device across heterogeneous processor sites, please refer to the definition of the cloud disaster recovery method across heterogeneous processor sites above, which will not be repeated here. Each module in the above-mentioned cloud disaster recovery device across heterogeneous processor sites can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0133] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0134] Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table;

[0135] Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0136] Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0137] In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

[0138] In one embodiment, the computer program further implements the following steps when executed by a processor:

[0139] The step of obtaining the cumulative change rate of the binary table at the current moment includes:

[0140] Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup;

[0141] If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment;

[0142] Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

[0143] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0144] The step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes:

[0145] Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero;

[0146] When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one;

[0147] Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment;

[0148] After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

[0149] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0150] After sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, the method further includes:

[0151] Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time;

[0152] The changed data blocks between the current time and the last backup time are merged with the backup data at the last backup time, and the binary table between the current time and the last backup time is merged with the binary table at the last backup time to save the latest backup data and binary table in the production site.

[0153] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0154] The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes:

[0155] A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table;

[0156] A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access (RDMA) channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

[0157] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0158] The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup also includes:

[0159] The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

[0160] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0161] The same number of load test applications are respectively set in the production site and the disaster recovery site, and the load test applications include virtual machines, containers or target business application systems;

[0162] Running the load test application in the production site and the disaster recovery site, and obtaining performance scores of the production site and the disaster recovery site through performance testing;

[0163] Compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, adjust the number of load test applications set in the production site and the disaster recovery site according to the performance score difference, reduce the load test applications in the production site and / or increase the load test applications in the disaster recovery site when the performance score of the production site is high, and increase the load test applications in the production site and / or reduce the load test applications in the disaster recovery site when the performance score of the production site is low;

[0164] Obtaining, through performance testing, performance scores of the production site and the disaster recovery site after adjusting the number of load test applications, and cyclically adjusting the number of load test applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal;

[0165] Obtaining a ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal;

[0166] The ratio of the first mirror memory to the second mirror memory is adjusted according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

[0167] For specific limitations on the steps implemented when a computer program is executed by a processor, please refer to the above limitations on the method for cloud disaster recovery across heterogeneous processor sites, which will not be repeated here.

[0168] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store cloud disaster recovery data across heterogeneous processor sites. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a cloud disaster recovery method across heterogeneous processor sites is implemented.

[0169] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0170] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0171] Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table;

[0172] Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0173] Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0174] In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

[0175] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0176] The step of obtaining the cumulative change rate of the binary table at the current moment includes:

[0177] Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup;

[0178] If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment;

[0179] Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

[0180] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0181] The step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes:

[0182] Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero;

[0183] When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one;

[0184] Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment;

[0185] After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

[0186] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0187] After sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, the method further includes:

[0188] Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time;

[0189] The changed data blocks between the current time and the last backup time are merged with the backup data at the last backup time, and the binary table between the current time and the last backup time is merged with the binary table at the last backup time to save the latest backup data and binary table in the production site.

[0190] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0191] The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes:

[0192] A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table;

[0193] A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access (RDMA) channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

[0194] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0195] The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup also includes:

[0196] The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

[0197] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0198] The same number of load test applications are respectively set in the production site and the disaster recovery site, and the load test applications include virtual machines, containers or target business application systems;

[0199] Running the load test application in the production site and the disaster recovery site, and obtaining performance scores of the production site and the disaster recovery site through performance testing;

[0200] Compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, adjust the number of load test applications set in the production site and the disaster recovery site according to the performance score difference, reduce the load test applications in the production site and / or increase the load test applications in the disaster recovery site when the performance score of the production site is high, and increase the load test applications in the production site and / or reduce the load test applications in the disaster recovery site when the performance score of the production site is low;

[0201] Obtaining, through performance testing, performance scores of the production site and the disaster recovery site after adjusting the number of load test applications, and cyclically adjusting the number of load test applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal;

[0202] Obtaining a ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal;

[0203] The ratio of the first mirror memory to the second mirror memory is adjusted according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

[0204] For specific limitations on the steps implemented when the processor executes the computer program, please refer to the limitations on the method for cloud disaster recovery across heterogeneous processor sites mentioned above, which will not be repeated here.

[0205] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0206] Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table;

[0207] Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval;

[0208] Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold;

[0209] In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

[0210] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0211] The step of obtaining the cumulative change rate of the binary table at the current moment includes:

[0212] Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup;

[0213] If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment;

[0214] Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

[0215] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0216] The step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes:

[0217] Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero;

[0218] When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one;

[0219] Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment;

[0220] After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

[0221] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0222] After sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, the method further includes:

[0223] Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time;

[0224] The changed data blocks between the current time and the last backup time are merged with the backup data at the last backup time, and the binary table between the current time and the last backup time is merged with the binary table at the last backup time to save the latest backup data and binary table in the production site.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0226] The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes:

[0227] A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table;

[0228] A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access (RDMA) channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

[0229] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0230] The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup also includes:

[0231] The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

[0232] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0233] The same number of load test applications are respectively set in the production site and the disaster recovery site, and the load test applications include virtual machines, containers or target business application systems;

[0234] Running the load test application in the production site and the disaster recovery site, and obtaining performance scores of the production site and the disaster recovery site through performance testing;

[0235] Compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, adjust the number of load test applications set in the production site and the disaster recovery site according to the performance score difference, reduce the load test applications in the production site and / or increase the load test applications in the disaster recovery site when the performance score of the production site is high, and increase the load test applications in the production site and / or reduce the load test applications in the disaster recovery site when the performance score of the production site is low;

[0236] Obtaining, through performance testing, performance scores of the production site and the disaster recovery site after adjusting the number of load test applications, and cyclically adjusting the number of load test applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal;

[0237] Obtaining a ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal;

[0238] The ratio of the first mirror memory to the second mirror memory is adjusted according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

[0239] For specific limitations on the steps implemented when a computer program is executed by a processor, please refer to the above limitations on the method for cloud disaster recovery across heterogeneous processor sites, which will not be repeated here.

[0240] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0241] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0242] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A cloud disaster recovery method across heterogeneous processor sites, characterized in that: The cross-heterogeneous processor site includes a production site and a disaster recovery site, and the cloud disaster recovery method includes: Monitoring the production data of the production site, identifying changes in the production data according to a preset interval, recording the changes in the production data by creating a new change data block, and recording the change position of the production data by creating a new binary table; Controlling to back up the newly created changed data block and the binary table in the production site at each moment of the preset interval; Obtaining the cumulative change rate of the binary table at the current moment, and determining whether the cumulative change rate of the binary table at the current moment is greater than a first threshold; In response to the accumulated change rate of the binary table at the current moment being greater than the first threshold, the newly created changed data block and the binary table at the current moment are sent to the disaster recovery site for backup, and the accumulated change rate at the next moment is set to zero.

2. The cloud disaster recovery method across heterogeneous processor sites according to claim 1, characterized in that: The step of obtaining the cumulative change rate of the binary table at the current moment includes: Determine whether the binary table at the previous moment is sent to the disaster recovery site for backup; If so, the binary table at the next moment is controlled not to be compared with the binary table at the previous moment; Otherwise, compare the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment, and sum the current change rate with the cumulative change rate of the binary table at the previous moment to obtain the cumulative change rate of the binary table at the current moment.

3. The cloud disaster recovery method across heterogeneous processor sites according to claim 2, characterized in that: The step of comparing the binary table at the current moment with the binary table at the previous moment to obtain the current change rate of the binary table at the current moment includes: Setting the data storage location of each bit in the binary table for the production site, and initially setting the value of each bit in the binary table to zero; When the data of the target data storage location of the production site is changed, the value of the corresponding target bit in the binary table is modified to one; Compare the values ​​of all bits of the binary table at the current moment with the values ​​of all bits of the binary table at the previous moment, and obtain the change rate of the values ​​of all bits of the binary table as the current change rate of the binary table at the current moment; After the binary table is sent to the disaster recovery site for backup, the value of each bit in the binary table at the next moment is set to zero.

4. The cloud disaster recovery method across heterogeneous processor sites according to claim 1, characterized in that: After sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup, the method further includes: Obtain the last backup time when the binary table was sent to the disaster recovery site for backup, and obtain the backup data and the binary table at the last backup time; In the production site, the changed data blocks between the current moment and the last backup moment are merged with the backup data at the last backup moment, and the binary table between the current moment and the last backup moment is merged with the binary table at the last backup moment, so as to save the latest backup data and binary table in the production site.

5. The cloud disaster recovery method across heterogeneous processor sites according to claim 1, characterized in that: The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup includes: A first cache storage pool and a first mirror memory are set in the production site, the first cache storage pool is used to back up the newly created changed data block and the binary table, and the first mirror memory is used to transmit the changed data block to the disaster recovery site based on the binary table; A second cache storage pool and a second mirror memory are set in the disaster recovery site, and a remote direct data access channel is formed between the first mirror memory and the second mirror memory to transmit the binary table and the changed data block. The second mirror memory is used to receive the binary table and the changed data block sent by the first mirror memory, and the second cache storage pool is used to save the changed data block and the binary table.

6. The cloud disaster recovery method across heterogeneous processor sites according to claim 5, characterized in that: The sending the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup also includes: The changed data blocks and the binary table stored in the second cache storage pool are merged to form disaster recovery backup data.

7. The cloud disaster recovery method across heterogeneous processor sites according to claim 1, characterized in that: The method further comprises: The same number of load test applications are respectively set in the production site and the disaster recovery site, and the load test applications include virtual machines, containers or target business application systems; Running the load test application in the production site and the disaster recovery site, and obtaining performance scores of the production site and the disaster recovery site through performance testing; Compare the performance scores of the production site and the disaster recovery site to obtain a performance score difference, adjust the number of load test applications set in the production site and the disaster recovery site according to the performance score difference, reduce the load test applications in the production site and / or increase the load test applications in the disaster recovery site when the performance score of the production site is high, and increase the load test applications in the production site and / or reduce the load test applications in the disaster recovery site when the performance score of the production site is low; Obtaining, through performance testing, performance scores of the production site and the disaster recovery site after adjusting the number of load test applications, and cyclically adjusting the number of load test applications set in the production site and the disaster recovery site to make the performance scores of the production site and the disaster recovery site equal; Obtaining a ratio of the number of load test applications set in the production site and the disaster recovery site when the performance scores of the production site and the disaster recovery site are equal; The ratio of the first mirror memory to the second mirror memory is adjusted according to the ratio of the number of load test applications set in the production site and the disaster recovery site, so that the rate at which the first mirror memory sends the change data block and the binary table is equal to the rate at which the second mirror memory receives the change data block and the binary table.

8. A cloud disaster recovery device across heterogeneous processor sites, characterized in that: The cross-heterogeneous processor site includes a production site and a disaster recovery site, and the device includes: A production data management module, used to monitor the production data of the production site, identify changes in the production data according to a preset interval, record the changes in the production data by creating a new change data block, and record the change position of the production data by creating a new binary table; A production site backup module, used for controlling the backup of the newly created change data block and the binary table in the production site at each moment of the preset interval; A binary table change rate monitoring module, used to obtain the cumulative change rate of the binary table at the current moment, and determine whether the cumulative change rate of the binary table at the current moment is greater than a first threshold; The disaster recovery site backup module is used to send the newly created changed data block and the binary table at the current moment to the disaster recovery site for backup in response to the cumulative change rate of the binary table at the current moment being greater than the first threshold, and set the cumulative change rate at the next moment to zero.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images