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

Abstract

The application relates to a cloud disaster recovery method, device and equipment across heterogeneous processor sites and a storage medium. The method comprises the following steps: monitoring production data of a production site, identifying change content of the production data according to a preset interval length, recording the change content through a newly created change data block, and recording a change position of the production data through a newly created binary table; controlling backup of the newly created change data block and the binary table in the production site at each time of the preset interval length; acquiring an accumulated change rate of the binary table at a current time, judging whether the accumulated change rate of the binary table at the current time is greater than a first threshold value; and in response to the accumulated change rate of the binary table at the current time being greater than the first threshold value, sending the newly created change data block and the binary table at the current time to the disaster recovery site for backup, and setting an accumulated change rate at a next time as zero.

Description

Technical Field

[0001] This 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 Technology

[0002] As a computing power supply model that pursues cost-effectiveness, cloud computing is shifting its processor upgrades, replacements, and expansions from a single architecture to a diverse and heterogeneous architecture. Given the differences in functionality, performance, and reliability among these diverse and heterogeneous processors, "one cloud, multiple chips" has become an inevitable trend in cloud computing development to meet the technical requirements of high efficiency and stability, achieve low-cost and free switching of applications across processors, mitigate supply risks, and ensure the long-term stable operation of critical businesses.

[0003] In a "one cloud, multiple processors" scenario, cloud computing systems face the challenge of ensuring the reliability of user business systems. Traditional cloud computing systems are implemented based on Intel and AMD platforms, with relatively mature and stable hardware and software systems. Central processing units (CPUs) with incompletely consistent instruction sets, such as CPUs from different manufacturers or CPUs from the same manufacturer but different generations, can be considered heterogeneous processors. However, in a "one cloud, multiple processors" scenario, the inclusion of multiple heterogeneous processors makes the unified resource pooling and scheduling management of servers with heterogeneous processor configurations more complex, 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 using heterogeneous processors for current cloud disaster recovery.

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

[0006] Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables;

[0007] The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval.

[0008] Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold.

[0009] When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

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

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

[0012] If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step;

[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, 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] Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero;

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

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

[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 change data block and the binary table to the disaster recovery site for backup, the method further includes:

[0020] Get the last backup time when the binary table was last sent to the disaster recovery site for backup, and get the backup data and 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, so as to save the latest backup data and binary table in the production site.

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

[0023] A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change 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 up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table.

[0025] In one embodiment, sending the newly created modified data block and the binary table 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 includes:

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

[0029] The load testing application is run on the production site and the disaster recovery site, and the performance scores of the production site and the disaster recovery site are obtained through performance testing.

[0030] The performance scores of the production site and the disaster recovery site are compared to obtain the performance score difference. The number of load test applications set in the production site and the disaster recovery site is adjusted according to the performance score difference. When the performance score of the production site is high, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is decreased.

[0031] The performance scores of the production site and the disaster recovery site are obtained by performance testing after adjusting the number of load test applications. The number of load test applications set in the production site and the disaster recovery site is adjusted cyclically to make the performance scores of the production site and the disaster recovery site equal.

[0032] The ratio of the number of load test applications set up 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] The production data management module is used to monitor the production data of the production station, identify the changes in the production data according to a preset interval, and record the changes by creating new change data blocks and the location of the changes in the production data by creating new binary tables.

[0036] The production site backup module is used to control the backup of the newly created change data block and the binary table in the production site at each time interval specified in the preset time interval.

[0037] The binary table change rate monitoring module is used to obtain the cumulative change rate of the binary table at the current time and determine whether the cumulative change rate of the binary table at the current time 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 to the disaster recovery site for backup when the cumulative change rate of the binary table at the current time is greater than a first threshold, and set the cumulative change rate to zero at the next time.

[0039] In another aspect, 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 executes the computer program to perform the following steps:

[0040] Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables;

[0041] The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval.

[0042] Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold.

[0043] When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

[0044] In another aspect, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0045] Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables;

[0046] The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval.

[0047] Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold.

[0048] When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

[0049] The aforementioned cloud disaster recovery method, apparatus, computer equipment, and storage medium across heterogeneous processor sites control the production site to identify changes in production data at preset intervals. The location of the changes in production data is recorded by creating a new binary table. The cumulative change rate of the binary table is continuously judged at each moment of the preset interval. When the cumulative change rate of the binary table exceeds a first threshold, the binary table and backup data are sent to the disaster recovery site for backup. This reduces the file size of the binary table and significantly improves the transmission efficiency of backup data and the binary table. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

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

[0052] Figure 2 This is a flowchart illustrating a cloud disaster recovery method across heterogeneous processor sites in one embodiment of this application.

[0053] Figure 3 This is a schematic diagram illustrating the principle of the step in one embodiment of this application 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;

[0054] Figure 4 This is a schematic diagram illustrating the principle of sending the newly created modified data block and the binary table to the disaster recovery site for backup in one embodiment of this application;

[0055] Figure 5 This is a schematic diagram illustrating how the performance scores of the production site and the disaster recovery site are equal in one embodiment of this application.

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

[0057] Figure 7 This is an internal structural diagram of a computer device in one embodiment of this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

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

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

[0061] Step S1: Monitor the production data of the production station, identify the changes in the production data according to a preset interval, record the changes by creating a new change data block, and record the location of the changes in the production data by creating a new binary table.

[0062] Step S2: Control the creation of the new change data block and the binary table in the production site at each time interval specified in the preset time interval.

[0063] Step S3: Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than the first threshold.

[0064] Step S4: In response to the fact that the cumulative change rate of the binary table at the current time is greater than the first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

[0065] Specifically, by controlling the production site to identify changes in production data at preset intervals, the location of changes in production data is recorded by creating a new binary table. The cumulative change rate of the binary table is continuously judged at each moment of the preset interval. When the cumulative change rate of the binary table exceeds a first threshold, the binary table and backup data are sent to the disaster recovery site for backup. This reduces the file size of the binary table and significantly improves the transmission efficiency of backup data and the binary table.

[0066] Specifically, the preferred first threshold is 50%. This threshold is used to determine whether to generate a new backup file, thus addressing the problem of continuously increasing initial backup file size and resolving issues such as excessively large backup files, slow remote copying, and insufficient business performance during reconstruction, common in traditional methods.

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

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

[0069] If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step;

[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, the method of obtaining the cumulative change rate of two adjacent time points by comparing the binary tables of two adjacent time points according to the preset time interval can obtain the cumulative change rate of the binary table at the current time. Based on the comparison of the cumulative change rate with the first threshold, it can be identified 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 time includes:

[0073] The time when the binary table is sent to the disaster recovery site for backup is obtained, and the cumulative change rate of all binary tables sent to the disaster recovery site for backup is zero.

[0074] Obtain the binary table that was sent to the disaster recovery site for backup at the latest time. Compare the binary table at the current time with the binary table sent to the disaster recovery site for backup at the latest time. Obtain the change rate of the binary table at the current time and the binary table sent to the disaster recovery site for backup at the latest time as the cumulative change rate of the binary table at the current time.

[0075] The process involves comparing the current binary table with the latest binary table sent to the disaster recovery site for backup. The change rate between the current and latest binary tables is used as the cumulative change rate of the binary table at the current time. This cumulative change rate can be obtained directly at each time point without summation. Based on this cumulative change rate, a first threshold is compared to determine whether to split the backup into smaller files for transmission to the disaster recovery site. Failure to split the backup into smaller files may lead to a continuous increase in the size of the backup files. For example, an initial backup file might be only 10 units in size, but by time point 6, it could have reached 28 units. This continuous increase in the size of individual backup files significantly increases 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] Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero;

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

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

[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] The binary table can be a bitmap. The value of each bit in the binary table is set to zero or one. Zero means that the data of the production site is the comparison base, and one means that the data of the production site has been modified. The value of each bit in the binary table can be used to distinguish whether the data of the production site has changed.

[0082] like Figure 3 As shown, in this embodiment, after sending the newly created change data block and the binary table to the disaster recovery site for backup, the method further includes:

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

[0084] In the production site, 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, so as to save the latest backup data and binary table in the production site.

[0085] In this way, by merging backup data and binary tables from all times in the production site, the latest backup data and binary tables are stored in the production site, thereby reducing the storage space occupied by the production site.

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

[0087] A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change 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 up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table.

[0089] Among them, such as Figure 4 As shown, in terms of hardware, compared to the traditional method of configuring only production storage (HDD), a new configuration of cache storage pool (HDD) and mirror memory is adopted. 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] On the software side, optimizations were made in the following areas: 1) Business applications only write data to production storage and not synchronously to backup storage, thereby improving write performance; 2) Correspondingly, data changes are remapped from the production storage pool to the cache storage pool, generating backup data and corresponding binary tables; 3) The production site only stores 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 backup data and binary tables at all times; 5) The binary tables at the production site and the backup site have different record formats, with the production site's binary table recording the latest data change position and the backup site's binary table recording the cumulative data change position; 6) Based on the production site's binary table, the changed data is first written from the cache storage pool to the mirror memory, and then written at high speed to the disaster recovery site's mirror memory through the Remote Direct Data Access (RDMA) channel.

[0091] In this embodiment, sending the newly created modified data block and the binary table 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] The backup storage at the disaster recovery site stores backup data and binary tables from all points in time. To reduce historical data, backup data and binary tables from all points in time that are very old can be merged to form disaster recovery backup data, thereby reducing the space occupied by the backup storage at the disaster recovery site.

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

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

[0096] The load testing application is run on the production site and the disaster recovery site, and the performance scores of the production site and the disaster recovery site are obtained through performance testing.

[0097] The performance scores of the production site and the disaster recovery site are compared to obtain the performance score difference. The number of load test applications set in the production site and the disaster recovery site is adjusted according to the performance score difference. When the performance score of the production site is high, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is decreased.

[0098] The performance scores of the production site and the disaster recovery site are obtained by performance testing after adjusting the number of load test applications. The number of load test applications set in the production site and the disaster recovery site is adjusted cyclically to make the performance scores of the production site and the disaster recovery site equal.

[0099] The ratio of the number of load test applications set up 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, and sysbench, are run on the virtual machine, container, or specific business application system on CPU platform A to obtain performance scores. 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 performance scores. The performance scores on CPU platform B are compared with those on CPU platform A. The performance scores are 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 on CPU platform A is obtained. The hardware configuration occupied by the virtual machine, container, or specific business application system on CPU platform B at this time is recorded.

[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 under a given performance score are obtained and recorded in the computing power database.

[0103] Based on this computing power database, when the virtual machines, containers, or business application systems of the primary site fail, after the backup site is rebuilt, the cloud computing system will allocate corresponding hardware resources to the virtual machines, containers, or business application systems to achieve the same performance as the primary site.

[0104] In the cloud disaster recovery method for cross-heterogeneous processor sites described above, the production site is controlled to identify changes in the production data at preset intervals. The location of the changes in the production data is recorded by creating a new binary table. The cumulative change rate of the binary table is continuously judged at each moment of the preset interval. 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. This reduces the file size of the binary table and significantly improves the transmission efficiency of the backup data and the binary table.

[0105] In one embodiment, such as Figure 6 As shown, a cloud disaster recovery device 10 for 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 station, identify the changes in the production data according to a preset interval, and record the changes by creating a new change data block and the location of the changes in 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 change data block and the binary table in the production site at each time interval specified in the preset time 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 time and determine whether the cumulative change rate of the binary table at the current time is greater than the first threshold.

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

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

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

[0112] If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step;

[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, 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] Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero;

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

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

[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 modified data block and the binary table to the disaster recovery site for backup, the method further includes:

[0120] Get the last backup time when the binary table was last sent to the disaster recovery site for backup, and get the backup data and 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, so as to save the latest backup data and binary table in the production site.

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

[0123] A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change 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 up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table.

[0125] In this embodiment, sending the newly created modified data block and the binary table 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, as 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 test applications in the production site and the disaster recovery site respectively. The load test applications include virtual machines, containers or target business application systems; run the load test 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 the performance score difference, and adjust the number of load test 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, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is reduced. The performance scores of the production site and the disaster recovery site after adjusting the number of load test applications are obtained through performance testing, and the number of load test applications set in the production site and the disaster recovery site is adjusted cyclically 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; and to 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 changed data block and the binary table is equal to the rate at which the second mirror memory receives the changed data block and the binary table.

[0131] In the aforementioned cloud disaster recovery device across heterogeneous processor sites, the production site is controlled to identify changes in its production data at preset intervals. The location of the changes in the production data is recorded by creating a new binary table. The cumulative change rate of the binary table is continuously judged at each moment of the preset interval. 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. This reduces the file size of the binary table and significantly improves the transmission efficiency of the backup data and the binary table.

[0132] Specific limitations regarding cloud disaster recovery devices across heterogeneous processor sites can be found in the above description of cloud disaster recovery methods across heterogeneous processor sites, and will not be repeated here. Each module in the aforementioned cloud disaster recovery device across heterogeneous processor sites can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0133] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0134] Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables;

[0135] The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval.

[0136] Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold.

[0137] When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

[0138] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

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

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

[0141] If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step;

[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, it further performs the following steps:

[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] Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero;

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

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

[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, it further performs the following steps:

[0150] After sending the newly created modified data block and the binary table to the disaster recovery site for backup, the process also includes:

[0151] Get the last backup time when the binary table was last sent to the disaster recovery site for backup, and get the backup data and 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, so as 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, it further performs the following steps:

[0154] The step of sending the newly created modified data block and the binary table to the disaster recovery site for backup includes:

[0155] A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change 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 up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table.

[0157] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0158] The step of sending the newly created modified data block and the binary table 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, it further performs the following steps:

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

[0162] The load testing application is run on the production site and the disaster recovery site, and the performance scores of the production site and the disaster recovery site are obtained through performance testing.

[0163] The performance scores of the production site and the disaster recovery site are compared to obtain the performance score difference. The number of load test applications set in the production site and the disaster recovery site is adjusted according to the performance score difference. When the performance score of the production site is high, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is decreased.

[0164] The performance scores of the production site and the disaster recovery site are obtained by performance testing after adjusting the number of load test applications. The number of load test applications set in the production site and the disaster recovery site is adjusted cyclically to make the performance scores of the production site and the disaster recovery site equal.

[0165] The ratio of the number of load test applications set up 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 limitations on cloud disaster recovery methods across heterogeneous processor sites mentioned above, which will not be repeated here.

[0168] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores cloud disaster recovery data across heterogeneous processor sites. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a cloud disaster recovery method across heterogeneous processor sites.

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

[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 executes the computer program to perform the following steps:

[0171] Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables;

[0172] The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval.

[0173] Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold.

[0174] When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

[0175] In one embodiment, the processor, when executing a computer program, also performs 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 from the previous moment was sent to the disaster recovery site for backup;

[0178] If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step;

[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, the processor, when executing a computer program, also performs 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] Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero;

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

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

[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, the processor, when executing a computer program, also performs the following steps:

[0187] After sending the newly created modified data block and the binary table to the disaster recovery site for backup, the process also includes:

[0188] Get the last backup time when the binary table was last sent to the disaster recovery site for backup, and get the backup data and 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, so as to save the latest backup data and binary table in the production site.

[0190] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0191] The step of sending the newly created modified data block and the binary table to the disaster recovery site for backup includes:

[0192] A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change 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 up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table.

[0194] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0195] The step of sending the newly created modified data block and the binary table 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, the processor, when executing a computer program, also performs the following steps:

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

[0199] The load testing application is run on the production site and the disaster recovery site, and the performance scores of the production site and the disaster recovery site are obtained through performance testing.

[0200] The performance scores of the production site and the disaster recovery site are compared to obtain the performance score difference. The number of load test applications set in the production site and the disaster recovery site is adjusted according to the performance score difference. When the performance score of the production site is high, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is decreased.

[0201] The performance scores of the production site and the disaster recovery site are obtained by performance testing after adjusting the number of load test applications. The number of load test applications set in the production site and the disaster recovery site is adjusted cyclically to make the performance scores of the production site and the disaster recovery site equal.

[0202] The ratio of the number of load test applications set up 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 a processor takes when executing a computer program, please refer to the limitations on cloud disaster recovery methods across heterogeneous processor sites mentioned above, which will not be repeated here.

[0205] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0206] Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables;

[0207] The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval.

[0208] Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold.

[0209] When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero.

[0210] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

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

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

[0213] If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step;

[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, it further performs the following steps:

[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] Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero;

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

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

[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, it further performs the following steps:

[0222] After sending the newly created modified data block and the binary table to the disaster recovery site for backup, the process also includes:

[0223] Get the last backup time when the binary table was last sent to the disaster recovery site for backup, and get the backup data and 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, so as 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, it further performs the following steps:

[0226] The step of sending the newly created modified data block and the binary table to the disaster recovery site for backup includes:

[0227] A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change 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 up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table.

[0229] In one embodiment, when the computer program is executed by a processor, it further performs the following steps:

[0230] The step of sending the newly created modified data block and the binary table 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, it further performs the following steps:

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

[0234] The load testing application is run on the production site and the disaster recovery site, and the performance scores of the production site and the disaster recovery site are obtained through performance testing.

[0235] The performance scores of the production site and the disaster recovery site are compared to obtain the performance score difference. The number of load test applications set in the production site and the disaster recovery site is adjusted according to the performance score difference. When the performance score of the production site is high, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is decreased.

[0236] The performance scores of the production site and the disaster recovery site are obtained by performance testing after adjusting the number of load test applications. The number of load test applications set in the production site and the disaster recovery site is adjusted cyclically to make the performance scores of the production site and the disaster recovery site equal.

[0237] The ratio of the number of load test applications set up 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 limitations on cloud disaster recovery methods across heterogeneous processor sites mentioned above, which will not be repeated here.

[0240] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, 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. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0241] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A cloud disaster recovery method across heterogeneous processor sites, characterized in that, The cross-heterogeneous processor site includes production sites and disaster recovery sites, and the cloud disaster recovery method includes: Monitor the production data of the production station, identify the changes in the production data at preset intervals, record the changes by creating new change data blocks, and record the location of the changes in the production data by creating new binary tables; The newly created change data block and the binary table are backed up in the production site at each time interval specified in the preset time interval. Obtain the cumulative change rate of the binary table at the current time, and determine whether the cumulative change rate of the binary table at the current time is greater than a first threshold. When the cumulative change rate of the binary table at the current time is greater than a first threshold, the newly created changed data block and the binary table at the current time are sent to the disaster recovery site for backup, and the cumulative change rate at the next time is set to zero. The step of sending the newly created modified data block and the binary table to the disaster recovery site for backup includes: A first cache storage pool and a first mirror memory are set up in the production site. The first cache storage pool is used to back up the newly created change data block and the binary table. The first mirror memory is used to transfer the change data block to the disaster recovery site based on the binary table. A second cache storage pool and a second mirror memory are set up in the disaster recovery site. 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. The second cache storage pool is used to store the changed data block and the binary table. The cloud disaster recovery method also includes: The same number of load testing applications are set up in the production site and the disaster recovery site, and the load testing applications include virtual machines, containers or target business application systems. The load testing application is run on the production site and the disaster recovery site, and the performance scores of the production site and the disaster recovery site are obtained through performance testing. The performance scores of the production site and the disaster recovery site are compared to obtain the performance score difference. The number of load test applications set in the production site and the disaster recovery site is adjusted according to the performance score difference. When the performance score of the production site is high, the number of load test applications in the production site is reduced and / or the number of load test applications in the disaster recovery site is increased. When the performance score of the production site is low, the number of load test applications in the production site is increased and / or the number of load test applications in the disaster recovery site is decreased. The performance scores of the production site and the disaster recovery site are obtained by performance testing after adjusting the number of load test applications. The number of load test applications set in the production site and the disaster recovery site is adjusted cyclically to make the performance scores of the production site and the disaster recovery site equal. The ratio of the number of load test applications set up 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.

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 from the previous moment was sent to the disaster recovery site for backup; If so, then control the binary table of the next time step not to be compared with the binary table of the previous time step; 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: Set the data storage location of each bit in the binary table for the production site, and initialize the value of each bit in the binary table to zero; When the data at the target data storage location of the production site changes, the value of the corresponding target bit in the binary table is modified to one. Compare the values ​​of all bits in the binary table at the current time with the values ​​of all bits in the binary table at the previous time, and obtain the change rate of the values ​​of all bits in the binary table as the current change rate of the binary table at the current time. 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 modified data block and the binary table to the disaster recovery site for backup, the process also includes: Get the last backup time when the binary table was last sent to the disaster recovery site for backup, and get the backup data and binary table at the last backup time; In the production site, 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, 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 step of sending the newly created modified data block and the binary table 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.

6. A cloud disaster recovery device across heterogeneous processor sites, characterized in that, A cloud disaster recovery method for cross-heterogeneous processor sites according to any one of claims 1 to 5, wherein the cross-heterogeneous processor sites include production sites and disaster recovery sites, the apparatus comprising: The production data management module is used to monitor the production data of the production station, identify the changes in the production data according to a preset interval, and record the changes by creating new change data blocks and the location of the changes in the production data by creating new binary tables. The production site backup module is used to control the backup of the newly created change data block and the binary table in the production site at each time interval specified in the preset time interval. The binary table change rate monitoring module is used to obtain the cumulative change rate of the binary table at the current time and determine whether the cumulative change rate of the binary table at the current time 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 to the disaster recovery site for backup when the cumulative change rate of the binary table at the current time is greater than a first threshold, and set the cumulative change rate to zero at the next time.

7. 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, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images