Data migration performance monitoring method and device, computer device and storage medium

By obtaining timestamps during the data migration process to calculate latency and performance metrics, adjusting concurrency levels, and generating alarm notifications, the problem of lack of visual monitoring in data migration tools is solved, thus improving data migration efficiency.

CN116561103BActive Publication Date: 2025-10-24INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202310542682.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-05-15
Publication Date
2025-10-24
Estimated Expiration
2043-05-15

AI Technical Summary

Technical Problem

Existing data migration tools lack visual performance monitoring capabilities, making it impossible for users to intuitively understand data migration performance metrics such as latency, success rate, and migration speed.

Method used

By obtaining upload and download timestamps during the data migration process, latency and performance metrics are calculated. When performance metrics are abnormal, the number of concurrent data migrations is adjusted, and alarm notifications are generated, enabling visualized monitoring of data migration performance.

Benefits of technology

It enables real-time visual monitoring of the performance metrics of data migration tools, automatically adjusts the data concurrency to improve data migration efficiency, and solves the problem that users cannot intuitively understand the performance metrics.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116561103B_ABST
    Figure CN116561103B_ABST
Patent Text Reader

Abstract

The application relates to a data migration performance monitoring method and device, computer equipment and a storage medium. It relates to the technical field of computers and can be used in the field of financial technology and other related fields. The method comprises the following steps: in a data migration process, uploading time stamps and downloading time stamps of each message data are acquired; a time delay index and a performance index of the message data are determined according to the uploading time stamps and the downloading time stamps of the message data; if the performance index exceeds a preset performance threshold, the data migration concurrency is updated according to the time delay index and a time delay threshold; and an alarm notification is output according to the updated data migration concurrency and / or the performance index. The method can realize real-time visual monitoring of the performance index of a data migration tool, and can automatically adjust the data concurrency when the data migration performance is poor, so as to improve the data migration efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and in particular to a data migration performance monitoring method and device, a computer device, and a storage medium. BACKGROUND

[0002] In a disaster scenario, it is often necessary to use a data migration tool to perform data migration work. For example, the data migration tool can be a cross-cluster synchronization tool (MirrorMaker) for migrating data between different Kafka clusters. Therefore, it is often necessary to verify the disaster resistance of the data migration tool by using performance indicators during data migration.

[0003] However, the current data migration tool does not have a visual performance monitoring function, which causes the user to be unable to intuitively understand the performance of data migration (such as data migration latency, success rate, migration rate, etc.). SUMMARY

[0004] Therefore, it is necessary to provide a data migration performance monitoring method and device that can realize visual monitoring of data migration performance, a computer device, and a storage medium.

[0005] In a first aspect, the present application provides a data migration performance monitoring method. The method comprises:

[0006] In the data migration process, the upload timestamp and the download timestamp of each message data are obtained;

[0007] According to the upload timestamp and the download timestamp of each message data, the latency indicator and the performance indicator of the message data are determined;

[0008] If the performance indicator exceeds the preset performance threshold, the data migration concurrency is updated according to the latency indicator and the latency threshold;

[0009] According to the updated data migration concurrency and / or performance indicator, an alarm notification is output.

[0010] In one embodiment, if the performance indicator exceeds the preset performance threshold, the data migration concurrency is updated according to the latency indicator and the latency threshold, comprising:

[0011] If the performance indicator exceeds the preset performance threshold, the required new concurrency of each message data is determined according to the latency indicator and the latency threshold;

[0012] The data migration concurrency is updated according to the new concurrency.

[0013] In one of the embodiments, if the performance index exceeds the preset performance threshold, the required new concurrency of each message data is determined according to the time delay index and the time delay threshold, including:

[0014] If the performance index exceeds the preset performance threshold, the current usage of the local processor, the current usage of the local memory and the current data migration concurrency are obtained;

[0015] The temporary concurrency supported by the processor is determined according to the current usage of the local processor and the preset processor usage threshold;

[0016] The temporary concurrency supported by the memory is determined according to the current usage of the local memory and the preset memory usage threshold;

[0017] The temporary concurrency supported by the message is determined according to the data migration concurrency and the concurrency threshold;

[0018] The required temporary concurrency of the message is determined according to the time delay index, the time delay threshold and the delay change value between the current time and the historical time;

[0019] If the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message and the required temporary concurrency of the message are all greater than zero, the required temporary concurrency of the message is determined as the required new concurrency of each message data.

[0020] In one of the embodiments, the time delay index and the performance index of each message data are determined according to the upload timestamp and the download timestamp of each message data, including:

[0021] The time delay index in the preset period is determined according to the upload timestamp and the download timestamp of each message data;

[0022] The performance index is determined according to the time delay index in the preset period, the total number of message data and the number of successfully migrated message data.

[0023] In one of the embodiments, the time delay index in the preset period is determined according to the upload timestamp and the download timestamp of each message data, including:

[0024] The successfully migrated message data in the preset period is determined according to the upload timestamp and the download timestamp of each message data;

[0025] The time delay index in the preset period is determined according to the upload timestamp and the download timestamp of the successfully migrated message data.

[0026] In one of the embodiments, the performance index is determined according to the time delay index in the preset period, the total number of message data and the number of successfully migrated message data, including at least one of the following:

[0027] According to the time delay index in the preset period, and the total number of message data in the preset period, the average time delay in the performance index is determined;

[0028] According to the time delay index in the preset period, the peak time delay in the performance index is determined;

[0029] According to the total number of message data in the preset period and the preset time length, the migration rate in the performance index is determined;

[0030] According to the number of successful message data migration in the preset period and the total number of message data, the successful migration rate in the performance index is determined. In one embodiment,

[0031] In one embodiment, if the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold, including:

[0032] If the performance index exceeds the preset performance threshold, and the duration of exceeding the performance threshold meets the preset time length, the data migration concurrency is updated according to the time delay index and the time delay threshold.

[0033] In one embodiment, the method further comprises:

[0034] If the performance index does not exceed the preset performance threshold, it is determined whether the current data migration concurrency has been updated;

[0035] If it has been updated, it is determined whether the performance index is lower than the average of the performance index in the historical preset period;

[0036] If it is lower, the data migration concurrency is updated according to the historical update data of the data migration concurrency.

[0037] Secondly, the application also provides a data migration performance monitoring device. The device comprises:

[0038] The time acquisition module is configured to acquire the upload timestamp and the download timestamp of each message data during the data migration process;

[0039] The index determination module is configured to determine the time delay index and the performance index of the message data according to the upload timestamp and the download timestamp of each message data;

[0040] The concurrency update module is configured to update the data migration concurrency according to the time delay index and the time delay threshold if the performance index exceeds the preset performance threshold;

[0041] The alarm module is configured to output an alarm notification according to the updated data migration concurrency and / or the performance index.

[0042] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor. The memory stores a computer program. The processor implements the following steps when executing the computer program:

[0043] In the data migration process, the upload timestamp and the download timestamp of each message data are acquired;

[0044] According to the upload timestamp and the download timestamp of each message data, the time delay index and the performance index of the message data are determined;

[0045] If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold;

[0046] According to the updated data migration concurrency and / or the performance index, an alarm notification is output.

[0047] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the following steps:

[0048] In the data migration process, the upload timestamp and the download timestamp of each message data are acquired;

[0049] According to the upload timestamp and the download timestamp of each message data, the time delay index and the performance index of the message data are determined;

[0050] If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold;

[0051] According to the updated data migration concurrency and / or the performance index, an alarm notification is output.

[0052] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program. The computer program is executed by a processor to implement the following steps:

[0053] In the data migration process, the upload timestamp and the download timestamp of each message data are acquired;

[0054] According to the upload timestamp and the download timestamp of each message data, the time delay index and the performance index of the message data are determined;

[0055] If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold;

[0056] According to the updated data migration concurrency and / or the performance index, an alarm notification is output.

[0057] The data migration performance monitoring method, device, computer device and storage medium provided by the present embodiment, by obtaining the upload timestamp and download timestamp of the message data in the data migration process, and calculating the time delay index and performance index based on the obtained upload timestamp and download timestamp, judging whether the performance of the data migration tool is abnormal by setting the performance threshold, and adjusting the data migration concurrency number through the time delay index and time delay threshold after the performance index is abnormal, and generating an alarm notification to send to the user, so that the user can visually monitor the performance index of the data migration tool in real time through the alarm notification, thereby solving the problem that the user cannot intuitively understand the performance index of the data migration tool. In addition, the present embodiment can automatically adjust the data concurrency number when the data migration performance is poor, so as to improve the efficiency of data migration. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 An application environment diagram of the data migration performance monitoring method provided by the present embodiment is shown in the following figure:

[0059] Figure 2 A flowchart of the first data migration performance monitoring method provided by the present embodiment is shown in the following figure:

[0060] Figure 3 A flowchart of updating the concurrency number provided by the present embodiment is shown in the following figure:

[0061] Figure 4 A flowchart of determining the time delay index and performance index provided by the present embodiment is shown in the following figure:

[0062] Figure 5 A flowchart of monitoring the data migration performance provided by the present embodiment is shown in the following figure:

[0063] Figure 6 A flowchart of the second data migration performance monitoring method provided by the present embodiment is shown in the following figure:

[0064] Figure 7 A structural block diagram of the first data migration performance monitoring device provided by the present embodiment is shown in the following figure:

[0065] Figure 8 A structural block diagram of the second data migration performance monitoring device provided by the present embodiment is shown in the following figure:

[0066] Figure 9 A structural block diagram of the third data migration performance monitoring device provided by the present embodiment is shown in the following figure:

[0067] Figure 10 A structural block diagram of the fourth data migration performance monitoring device provided by the present embodiment is shown in the following figure:

[0068] Figure 11An internal structure diagram of a computer device is provided for the embodiment. DETAILED DESCRIPTION

[0069] For the purpose, technical solutions and advantages of the present application to be clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0070] The data migration performance monitoring method provided by the embodiment of the present application can be applied in an application environment as shown in Figure 1 In an embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 1 The computer device includes a processor, a memory and a network interface connected through a system bus. 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 operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store message data, time stamps, latency indicators, performance indicators, concurrent numbers and alarm notifications and the like. The network interface of the computer device is used to communicate with an external terminal through a network connection to transmit alarm notifications to the external terminal. The computer program is executed by the processor to implement a data migration performance monitoring method.

[0071] The embodiment provides a data migration performance monitoring method. In the data migration process, the upload time stamps and the download time stamps of each message data are obtained, and the latency indicators and the performance indicators of the message data are determined according to the upload time stamps and the download time stamps of each message data. If the performance indicators exceed a preset performance threshold, the data migration concurrent number is updated according to the latency indicators and a latency threshold, and an alarm notification is output according to the updated data migration concurrent number and / or the performance indicators.

[0072] In an embodiment, as shown in Figure 2 A data migration performance monitoring method is provided. Taking a server in Figure 1 as an example, the method can be applied to a data migration tool installed in the server, i.e., the data migration performance monitoring method provided by the embodiment is executed by the data migration tool installed in the server, which includes the following steps:

[0073] S201 In the data migration process, the upload time stamps and the download time stamps of each message data are obtained.

[0074] Wherein, data migration can be an operation of migrating data. Optionally, data migration can be a process of migrating data between different cluster devices (such as servers), or between different folders in the same cluster device, which is not limited in this application.

[0075] The message data may be data that needs to be migrated. Optionally, the message data may be all message data in the cluster device that needs to be migrated, or part of the message data that is manually set.

[0076] The upload timestamp may be a timestamp generated during the process of uploading the message data to the target cluster device (i.e., the cluster device receiving the message data). Optionally, the upload timestamp may include an upload start timestamp (i.e., the time when the message data starts uploading) and an upload completion timestamp (i.e., the time when the message data upload is completed).

[0077] The download timestamp may be a timestamp generated during the download process of the message data from the source cluster device (i.e., the cluster device to which the message data needs to be migrated). Optionally, the download timestamp may include a download start timestamp (i.e., the time when the message data starts downloading) and a download completion timestamp (i.e., the time when the message data download is completed).

[0078] Optionally, during the process of data migration using the data migration tool, the interceptor in the data migration tool will obtain in real time the download timestamps generated during the download process of each message data from the source cluster device, that is, the download start timestamp and the download completion timestamp. At the same time, the interceptor will also obtain in real time the upload timestamps generated during the upload process of the message data to the target cluster device, that is, the upload start timestamp and the upload completion timestamp.

[0079] It should be noted that during data migration using the data migration tool, the tool can also set an initial concurrent migration count, allowing multiple message data to be migrated simultaneously based on the initial concurrent migration count, thereby improving the efficiency of the data migration tool. The concurrent migration count represents the number of message data that can be migrated simultaneously.

[0080] S202 determines the delay index and performance index of the message data according to the upload timestamp and download timestamp of each message data.

[0081] The time delay index can be an index representing a delay time of the message data in the data migration process. Alternatively, the time delay index can include an upload time delay index, a download time delay index, and a migration time delay index. The upload time delay index can be an index generated in the process of uploading the message data to the target cluster device, the download time delay index can be an index generated in the process of downloading the message data from the source cluster device, and the migration time delay index can be an index generated in the process of migrating the message data from the source cluster device to the target cluster device.

[0082] The performance index can be an index representing the performance of the data migration tool in migrating the message data. Alternatively, the performance index can include a time delay average, a time delay peak, a migration rate, and a migration success rate. The time delay average can be an average of all time delay indexes generated in the data migration process within a preset period, the time delay peak can be a maximum value of all time delay indexes generated in the data migration process within a preset period, the migration rate can be an efficiency of migrating the message data in the data migration process within a preset period, and the migration success rate can be a success rate of completing the data migration within a preset period.

[0083] Alternatively, the optional manner of determining the time delay index and the performance index of the message data according to the upload timestamp and the download timestamp of each message data can be calculating a difference value between the upload timestamp and the download timestamp according to the upload timestamp and the download timestamp of each message data, and taking the difference value as the time delay index of the message data, and simultaneously searching for the performance index corresponding to the time delay index in a pre-set performance index table according to the time delay index; or inputting the upload timestamp and the download timestamp of each message data into a pre-trained index model, and the index model will calculate the upload timestamp and the download timestamp of the message data to finally obtain the time delay index and the performance index corresponding to the message data.

[0084] S203If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold.

[0085] Alternatively, if the obtained performance index exceeds the performance threshold, it is proved that the time delay of the message data in the data migration process is longer, and the data migration speed of the message data needs to be improved. Therefore, the data migration concurrency at the current moment is calculated according to the time delay index and the time delay threshold through the pre-set concurrency calculation logic, the data migration concurrency is updated according to the data migration concurrency at the current moment, and the migration of the message data is continued through the updated data migration concurrency.

[0086] Preferably, when the performance index temporarily exceeds the performance threshold and returns to the normal level, the data migration tool still updates the data migration concurrency number because the data migration tool has determined that the performance index exceeds the performance threshold, but after the data migration concurrency number is updated, too many data migration concurrency numbers can cause too much resource waste, therefore, to reduce resource waste, the embodiment can introduce a preset time length to avoid the data migration concurrency number update caused by the performance index temporarily exceeding the performance threshold. Specifically, if the performance index exceeds the preset performance threshold and the duration of exceeding the performance threshold meets the preset time length, the data migration concurrency number is updated according to the latency index and the latency threshold. That is, if the performance index exceeds the preset performance threshold, a timer is started to determine whether the performance index continuously exceeds the performance threshold within the preset time length, if not, the data migration concurrency number is not updated, and if yes, the data migration concurrency number is updated according to the latency index and the latency threshold.

[0087] S204 outputs an alarm notification according to the updated data migration concurrency number and / or the performance index.

[0088] Optionally, when the performance index temporarily exceeds the performance threshold but the duration of exceeding the performance threshold does not meet the preset time length, it is considered that the performance index only temporarily exceeds the performance threshold and does not affect the efficiency of data migration, therefore, the alarm notification can be generated only according to the performance index exceeding the performance threshold, and the alarm notification is output through the terminal; when the performance index temporarily exceeds the performance threshold and the duration of exceeding the performance threshold meets the preset time length, it is considered that the performance index exceeds the performance threshold and affects the efficiency of data migration, therefore, the alarm notification can be generated only according to the updated data migration concurrency number, and the alarm notification is output through the terminal, or the alarm notification can be generated according to the updated data migration concurrency number and the performance index exceeding the performance threshold, and the alarm notification is output through the terminal. The specific data required for generating the alarm notification can be determined according to the user's setting.

[0089] The data migration performance monitoring method, device, computer device and storage medium described above, by acquiring the upload timestamp and download timestamp of the message data in the data migration process, calculating the latency index and performance index based on the acquired upload timestamp and download timestamp, judging whether the performance of the data migration tool is abnormal by setting the performance threshold, and adjusting the data migration concurrency number through the latency index and the latency threshold after the performance index is abnormal, and generating an alarm notification to send to the user, so that the user can visually monitor the performance index of the data migration tool in real time through the alarm notification, thereby solving the problem that the user cannot intuitively understand the performance index of the data migration tool. In addition, the present scheme can automatically adjust the data concurrency data when the data migration performance is poor to improve the efficiency of data migration.

[0090] Figure 3 A flowchart for updating the concurrency number in an embodiment. In this embodiment, when the performance index exceeds the performance threshold, it proves that the time delay of message data migration in the data migration process is longer, i.e., the speed of data migration is slower, so it is crucial to improve the speed of data migration. This embodiment introduces the update of the concurrency number to enable more message data to be migrated simultaneously, further improving the speed of data migration. Therefore, this embodiment gives an optional way to update the concurrency number, including the following steps:

[0091] S301 If the performance index exceeds the preset performance threshold, determine the newly added concurrency number required by each message data according to the time delay index and the time delay threshold.

[0092] The newly added concurrency number can be the concurrency number determined according to the message data that needs to be increased.

[0093] Optionally, if the performance index exceeds the preset performance threshold, the current usage of the local processor, the current usage of the local memory, and the current data migration concurrency number are obtained. According to the current usage of the local processor and the preset processor usage threshold, the temporary concurrency number supported by the processor is determined. According to the current usage of the local memory and the preset memory usage threshold, the temporary concurrency number supported by the memory is determined. According to the data migration concurrency number and the concurrency number threshold, the temporary concurrency number supported by the message is determined. According to the time delay index, the time delay threshold, and the delay change value between the current time and the historical time, the temporary concurrency number required by the message is determined. If the temporary concurrency number supported by the processor, the temporary concurrency number supported by the memory, the temporary concurrency number supported by the message, and the temporary concurrency number required by the message are all greater than zero, the temporary concurrency number required by the message is determined as the newly added concurrency number required by each message data.

[0094] The local processor can be the processor of the server where the data migration tool is located. The temporary concurrency number supported by the processor can be the maximum value of the concurrency number that the processor can add at the current time. The local memory can be the memory of the server where the data migration tool is located. The temporary concurrency number supported by the memory can be the maximum value of the concurrency number that the memory can add at the current time. The temporary concurrency number supported by the message can be the maximum value of the concurrency number that the message data can add at the current time. The temporary concurrency number required by the message can be the number of concurrency numbers that need to be added at the current time.

[0095] Specifically, if the performance index exceeds the preset performance threshold, the current usage of the local processor, the current usage of the local memory, and the current data migration concurrency are obtained, and the processor difference value between the current usage of the local processor and the preset processor usage threshold is calculated. Then, the processor quotient value between the processor difference value and the local processor usage required by a single message data is calculated, and the processor quotient value is taken as the determined temporary concurrency supported by the processor. The memory difference value between the current usage of the local memory and the preset memory usage threshold is calculated, and the memory quotient value between the memory difference value and the local memory usage required by a single message data is calculated, and the memory quotient value is taken as the temporary concurrency supported by the memory. The concurrency difference value between the migration concurrency at the current time and the concurrency threshold is calculated, and the concurrency difference value is taken as the temporary concurrency supported by the message. The delay difference value between the delay index and the delay threshold is calculated, and the delay change value between the delay index at the current time and the delay index at the preset historical time is calculated. Finally, the demand quotient value between the delay difference value and the delay change value is calculated, and the demand quotient value is taken as the temporary concurrency required by the message. Based on the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message, it is judged whether the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message are all greater than zero. If not, the update of the data migration concurrency is not allowed. If yes, the temporary concurrency required by the message is taken as the new concurrency required by each message data.

[0096] For example, the calculation method of the temporary concurrency supported by the processor can be: temporary concurrency supported by processor=(processor usage threshold-current usage of local processor) / local processor usage required by single message data. The calculation method of the temporary concurrency supported by the memory can be: temporary concurrency supported by memory=(memory usage threshold-current usage of local memory) / local memory usage required by single message data. The calculation method of the temporary concurrency supported by the message can be: temporary concurrency supported by message=concurrency threshold-migration concurrency at current time. The calculation method of the temporary concurrency required by the message can be: temporary concurrency required by message=(delay threshold-delay index) / (delay index at current time-delay index at historical time).

[0097] S302 updates the data migration concurrency according to the new concurrency.

[0098] Optionally, according to the obtained new concurrency, the sum value between the new concurrency and the initial concurrency is calculated, and the sum value is taken as the data migration concurrency, so as to complete the update of the data migration concurrency.

[0099] The above updating concurrent quantity method proves that the efficiency of data migration at the current moment is low if the performance index exceeds the preset performance threshold, and thus the required new concurrent quantity of each message data can be determined according to the time delay index and the time delay threshold, and the data migration concurrent quantity is updated according to the new concurrent quantity, that is, by increasing the concurrent quantity, more message data can be simultaneously subjected to data migration, and the efficiency of data migration is further improved.

[0100] Figure 4 A flowchart for determining the time delay index and the performance index in an embodiment is shown. In order to ensure the efficiency and accuracy of data migration, how to accurately obtain the time delay index and the performance index is crucial, and thus, on the basis of the above embodiment, an optional way of determining the time delay index and the performance index is given, including the following steps:

[0101] S401 determining the time delay index in a preset period according to the upload timestamp and the download timestamp of each message data.

[0102] Optionally, there are various ways of determining the time delay index in a preset period according to the upload timestamp and the download timestamp of each message data, which are not limited in the present application.

[0103] One of the optional implementation manners can be calculating the difference between the upload timestamp and the download timestamp according to the upload timestamp and the download timestamp of each message data, and taking the difference as the time delay index of the message data.

[0104] Another optional implementation manner can be determining the successfully migrated message data in a preset period according to the upload timestamp and the download timestamp of each message data, and determining the time delay index in a preset period according to the upload timestamp and the download timestamp of the successfully migrated message data. Specifically, it is determined whether the upload timestamp and the download timestamp of each message data are complete, that is, the message data should carry the four timestamps of the upload start timestamp, the upload completion timestamp, the download start timestamp and the download completion timestamp. If yes, it proves that the message data is successfully migrated, and if no, it proves that the message data is not successfully migrated. The number of the successfully migrated message data in a preset period (such as 1 minute) is determined. Meanwhile, the upload difference between the upload start timestamp and the upload completion timestamp of the obtained successfully migrated message data is calculated, and the upload difference is taken as the upload time delay index in the time delay index; the download difference between the download start timestamp and the download completion timestamp of the message data is calculated, and the download difference is taken as the download time delay index in the time delay index; the migration difference between the upload start timestamp and the download completion timestamp of the message data is calculated, and the migration difference is taken as the migration time delay index in the time delay index.

[0105] For example, the upload latency indicator can be calculated as upload completion timestamp - upload start timestamp, the download latency indicator can be calculated as download completion timestamp - download start timestamp, and the migration latency indicator can be calculated as download completion timestamp - upload start timestamp.

[0106] At S402, the performance indicator is determined according to the latency indicator, the total number of message data, and the number of successfully migrated message data in the preset period.

[0107] The total number of message data can be the number of all message data that are subjected to the data migration operation in the preset period.

[0108] The number of successfully migrated message data can be the number of message data that are subjected to the data migration operation and successfully migrated in the preset period.

[0109] Optionally, there are various ways to determine the performance indicator according to the latency indicator, the total number of message data, and the number of successfully migrated message data in the preset period, which are not limited in the present application.

[0110] One optional implementation can be that the latency indicator, the total number of message data, and the number of successfully migrated message data in the preset period are input into a pre-trained performance indicator model, the performance indicator model analyzes the latency indicator, the total number of message data, and the number of successfully migrated message data in the preset period, and obtains the performance indicator.

[0111] Another optional implementation can be that the average latency in the performance indicator is determined according to the latency indicator in the preset period and the total number of message data in the preset period, the peak latency in the performance indicator is determined according to the latency indicator in the preset period, the migration rate in the performance indicator is determined according to the total number of message data in the preset period and the preset time length, and the success rate in the performance indicator is determined according to the number of successfully migrated message data in the preset period and the total number of message data. Specifically, the average latency in the performance indicator is calculated as the quotient of the latency indicator in the preset period and the total number of message data in the preset period, the peak latency in the performance indicator is selected as the maximum value from all the latency indicators in the preset period, the migration rate in the performance indicator is calculated as the quotient of the total number of message data in the preset period and the preset time length (e.g., 60 seconds), and the success rate in the performance indicator is calculated as the quotient of the number of successfully migrated message data in the preset period and the total number of message data.

[0112] For example, the time delay average can be calculated as time delay index / message data total number, the migration rate can be calculated as message data total number / 60, and the migration success rate can be calculated as migration success message data number / message data total number.

[0113] The above method for determining the time delay index and the performance index can more accurately determine the time delay index in the preset time period according to the upload time stamp and the download time stamp of each message data, and can more reasonably determine the performance index according to the time delay index in the preset time period, the message data total number and the message data migration success number, considering the influence of various factors on the performance index, so as to facilitate the user to monitor the data migration performance and provide data support and guarantee for subsequent judgment of whether the data migration concurrency needs to be updated.

[0114] Figure 5 A flowchart for monitoring the data migration performance in an embodiment is shown. In this embodiment, after the performance index of the data migration is determined, the relationship between the performance index and the performance threshold value is determined to determine how to adjust the data migration concurrency, so that the efficiency and accuracy of the data migration are ensured while the local device loss is small. Specifically, this embodiment provides an optional way of monitoring the data migration performance, including the following steps:

[0115] S501In the data migration process, the upload time stamp and the download time stamp of each message data are obtained.

[0116] S502The upload time stamp and the download time stamp of each message data are obtained.

[0117] S503It is judged whether the performance index exceeds the preset performance threshold value. If yes, step S504 is executed, and if no, step S505 is executed.

[0118] S504If the performance index exceeds the preset performance threshold value, the data migration concurrency is updated according to the time delay index and the time delay threshold value, and an alarm notification is output according to the updated data migration concurrency and / or the performance index.

[0119] S505If the performance index does not exceed the preset performance threshold value, it is judged whether the current data migration concurrency has been updated. If yes, step S506 is executed, and if no, the operation of obtaining the upload time stamp and the download time stamp of each message data is returned.

[0120] Optionally, when the performance index does not exceed the preset performance threshold, it is proved that the current data migration efficiency is high, at this time, it is needed to judge whether the data migration concurrency has been updated, if not, it is proved that the data migration concurrency has not been increased, the data migration concurrency is within a reasonable range, and there is no possibility of resource waste, and the operation of obtaining the upload timestamp and the download timestamp of each message data is returned to be executed; if yes, it is proved that the data migration concurrency has been updated, that is, the data migration concurrency at the current time is obtained on the basis of the initial concurrency by adding the new concurrency, therefore, there may be resource waste, and step S506 is continued to be executed in order to judge whether the data migration concurrency needs to be adjusted.

[0121] S506 if updated, it is judged whether the performance index is lower than the average of the performance index in the historical preset period, if yes, step S507 is executed, if not, the operation of obtaining the upload timestamp and the download timestamp of each message data is returned to be executed.

[0122] Optionally, if the data migration concurrency has been updated, it is proved that the data migration concurrency at the current time may cause resource waste, therefore, it is further needed to judge whether the performance index at the current time is lower than the average of the performance index in the historical preset period, if not, it is proved that the data migration concurrency at the current time can not only meet the requirement of keeping high efficiency of data migration, but also will not cause more resource waste, therefore, the operation of obtaining the upload timestamp and the download timestamp of each message data is returned to be executed; if yes, it is proved that the performance index at the current time is lower than the average of the historical performance index, that is, the data migration efficiency at the current time is high, but it will cause certain resource waste, therefore, in order to reduce resource waste, the data migration concurrency should be adjusted, that is, step S507 is executed.

[0123] S507 if lower, the data migration concurrency is updated according to the historical update data of the data migration concurrency.

[0124] The historical update data can be the data migration concurrency increased or decreased when the data migration concurrency is updated.

[0125] Optionally, if the performance index is lower than the average of the performance index in the historical preset period, it is proved that the data migration at the current time will cause certain resource waste, therefore, the number of the data migration concurrency needs to be reduced, that is, the difference between the data migration concurrency at the current time and the historical update data is calculated, and the difference is taken as the data migration concurrency at the current time, so as to complete the update of the data migration concurrency.

[0126] If the performance index does not exceed the preset performance threshold, it is proved that the data migration efficiency at the current moment meets the preset requirement, and it is further determined whether the data migration has resource waste, that is, whether the current data migration concurrency has been updated. If the data migration concurrency has been updated, it is proved that the data migration concurrency at the current moment has been increased, and therefore, resource waste is possible. Therefore, it is further determined whether the data migration at the current moment definitely has resource waste, that is, whether the performance index is lower than the average of the performance index in the historical preset period. If it is lower, it is proved that the data migration at the current moment definitely has resource waste. Therefore, the data migration concurrency is updated according to the historical update data of the data migration concurrency, that is, the current data migration concurrency is reduced, so as to reduce more resource waste without reducing the efficiency of the data migration.

[0127] In one embodiment, an optional method for monitoring data migration performance is given. The method is applied to a server as an example for illustration. As shown in Figure 6 The method comprises the following steps:

[0128] S601 In the data migration process, the upload timestamp and the download timestamp of each message data are obtained.

[0129] S602 The migration successful message data in the preset period are determined according to the upload timestamp and the download timestamp of each message data.

[0130] S603 The time delay index in the preset period is determined according to the upload timestamp and the download timestamp of the migration successful message data.

[0131] S604 The time delay average in the performance index is determined according to the time delay index in the preset period and the total number of message data in the preset period.

[0132] S605 The time delay peak value in the performance index is determined according to the time delay index in the preset period.

[0133] S606 The migration rate in the performance index is determined according to the total number of message data in the preset period and the preset time length.

[0134] S607 The migration success rate in the performance index is determined according to the number of migration successful message data in the preset period and the total number of message data.

[0135] S608 It is determined whether the performance index exceeds the performance threshold. If yes, step S609 is executed, and if no, step S617 is executed.

[0136] S609 If the performance index exceeds the preset performance threshold, the current usage rate of the local processor, the current usage rate of the local memory and the current data migration concurrency are obtained.

[0137] S610 determining the temporary concurrency supported by the processor according to the current usage rate of the local processor and the preset processor usage rate threshold.

[0138] S611 determining the temporary concurrency supported by the memory according to the current usage rate of the local memory and the preset memory usage rate threshold.

[0139] S612 determining the temporary concurrency supported by the message according to the data migration concurrency and the concurrency threshold.

[0140] S613 determining the temporary concurrency required by the message according to the latency index, the latency threshold, and the delay change value between the current time and the historical time.

[0141] S614 if the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message are all greater than zero, determining the temporary concurrency required by the message as the new concurrency required by each message data.

[0142] S615 updating the data migration concurrency according to the new concurrency.

[0143] S616 outputting an alarm notification according to the updated data migration concurrency and / or the performance index.

[0144] S617 if the performance index does not exceed the preset performance threshold, determining whether the current data migration concurrency has been updated, if yes, executing step S618, and if no, returning to execute the operation of obtaining the upload timestamp and the download timestamp of each message data.

[0145] S618 if the performance index is lower than the average of the performance index in the historical preset period, executing step S619, and if not, returning to execute the operation of obtaining the upload timestamp and the download timestamp of each message data.

[0146] S619 if lower, updating the data migration concurrency according to the historical update data of the data migration concurrency.

[0147] It should be understood that although the steps in the flowcharts involved in the embodiments described above are shown in sequence according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the embodiments described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the steps or stages is not necessarily sequential, but can be alternately executed with other steps or steps or stages in at least part of other steps.

[0148] Based on the same inventive concept, the embodiments of the present application also provide a data migration performance monitoring device for implementing the above-mentioned data migration performance monitoring method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more data migration performance monitoring device embodiments provided below can refer to the limitations of the data migration performance monitoring method described above, which will not be repeated here.

[0149] In one embodiment, as shown in Figure 7 , a data migration performance monitoring device 1 is provided, comprising: a time acquisition module 10, an index determination module 11, a concurrent update module 12 and an alarm module 13, wherein:

[0150] The time acquisition module 10 is configured to acquire upload timestamps and download timestamps of each message data during the data migration process.

[0151] The index determination module 11 is configured to determine a time delay index and a performance index of the message data according to the upload timestamps and the download timestamps of each message data.

[0152] The concurrent update module 12 is configured to update the data migration concurrency according to the time delay index and a time delay threshold if the performance index exceeds a preset performance threshold.

[0153] The alarm module 13 is configured to output an alarm notification according to the updated data migration concurrency and / or the performance index.

[0154] In one embodiment, as shown in Figure 8 , Figure 7 , the concurrent update module 12 in the

[0155] The new determination unit 120 is configured to determine the required new concurrency of each message data according to the time delay index and the time delay threshold if the performance index exceeds the preset performance threshold.

[0156] The concurrency update unit 121 is used to update the data migration concurrency number according to the newly added concurrency number.

[0157] In one embodiment, Figure 7 The newly added determining unit 120 includes:

[0158] The data acquisition subunit is used to obtain the current usage rate of the local processor, the current usage rate of the local memory and the current number of concurrent data migrations if the performance indicator exceeds a preset performance threshold.

[0159] The processor concurrency determination subunit determines the temporary concurrency supported by the processor based on the current usage of the local processor and a preset processor usage threshold.

[0160] The memory concurrency determination subunit determines the temporary concurrency supported by the memory based on the current usage of the local memory and a preset memory usage threshold.

[0161] The message concurrency determination subunit determines the temporary concurrency supported by messages based on the data migration concurrency and the concurrency threshold.

[0162] The required concurrency determination subunit determines the temporary concurrency required for the message based on the delay index, delay threshold, and the delay change value between the current time and the historical time.

[0163] A newly added concurrency determination subunit: if the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message are all greater than zero, the temporary concurrency required by the message is determined as the newly added concurrency required for each message data.

[0164] In one embodiment, Figure 9 As shown, Figure 7 The indicator determination module 11 includes:

[0165] The delay determination unit 110 is configured to determine a delay index within a preset time period according to the upload timestamp and download timestamp of each message data.

[0166] The performance determination unit 111 is configured to determine a performance indicator according to a delay indicator, a total number of message data, and a number of successful message data migrations within a preset time period.

[0167] In one embodiment, Figure 9 The delay determination unit 110 in the embodiment includes:

[0168] The migration success sub-unit is used to determine the message data that has been successfully migrated within a preset time period according to the upload timestamp and download timestamp of each message data.

[0169] The delay determination subunit is used to determine the delay index within a preset time period according to the upload timestamp and download timestamp of the successfully migrated message data.

[0170] In one embodiment, Figure 9 The performance determination unit 111 in the embodiment includes:

[0171] The mean value determination subunit is used to determine the delay mean value in the performance indicator according to the delay indicator in the preset time period and the total number of message data in the preset time period.

[0172] The peak determination subunit is used to determine the delay peak value in the performance indicator according to the delay indicator within a preset time period.

[0173] The rate determination subunit is used to determine the migration rate in the performance indicator according to the total number of message data in a preset time period and a preset duration.

[0174] The success rate determination subunit is used to determine the migration success rate in the performance indicator according to the number of successful message data migrations and the total number of message data within a preset time period.

[0175] In one embodiment, Figure 7 The concurrent update module 12 is also used to update the data migration concurrency number according to the delay indicator and the delay threshold if the performance indicator exceeds the preset performance threshold and the duration of exceeding the performance threshold meets the preset duration.

[0176] In one embodiment, Figure 10 As shown, Figure 7 The data migration performance monitoring device 1 further includes:

[0177] The update judgment module 14 is configured to judge whether the current concurrent number of data migrations has been updated if the performance indicator does not exceed a preset performance threshold.

[0178] The indicator comparison module 15 is used to determine whether the performance indicator is lower than the average value of the performance indicator in the historical preset time period if an update has been performed.

[0179] The concurrency adjustment module 16 is configured to update the data migration concurrency number according to the historical update data of the data migration concurrency number if it is lower than .

[0180] Each module in the aforementioned data migration performance monitoring device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0181] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. 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 and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a data migration performance monitoring method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0182] Those skilled in the art will understand that Figure 11 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0183] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0184] During the data migration process, obtain the upload and download timestamps of each message data;

[0185] Determine the latency and performance indicators of the message data based on the upload and download timestamps of each message data;

[0186] If the performance indicator exceeds the preset performance threshold, the number of concurrent data migrations is updated based on the latency indicator and latency threshold.

[0187] Output alarm notifications based on the updated data migration concurrency number and / or performance indicators.

[0188] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0189] If the performance indicator exceeds the preset performance threshold, the number of additional concurrent requests required for each message data is determined based on the latency indicator and latency threshold;

[0190] According to the new concurrency number, the data migration concurrency number is updated.

[0191] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0192] If the performance index exceeds the preset performance threshold, the current usage of the local processor, the current usage of the local memory, and the current data migration concurrency number are obtained;

[0193] According to the current usage of the local processor and the preset processor usage threshold, the processor supports a temporary concurrency number;

[0194] According to the current usage of the local memory and the preset memory usage threshold, the memory supports a temporary concurrency number;

[0195] According to the data migration concurrency number and the concurrency threshold, the message supports a temporary concurrency number;

[0196] According to the latency index, the latency threshold, and the delay change value between the current time and the historical time, the message required temporary concurrency number is determined;

[0197] If the processor supports a temporary concurrency number, the memory supports a temporary concurrency number, the message supports a temporary concurrency number, and the message required temporary concurrency number are all greater than zero, the message required temporary concurrency number is determined as the new concurrency number required by each message data.

[0198] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0199] According to the upload timestamp and the download timestamp of each message data, the latency index in the preset period is determined;

[0200] According to the latency index in the preset period, the total number of message data, and the number of message data migration success, the performance index is determined.

[0201] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0202] According to the upload timestamp and the download timestamp of each message data, the message data migrated successfully in the preset period is determined;

[0203] According to the upload timestamp and the download timestamp of the message data migrated successfully, the latency index in the preset period is determined.

[0204] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0205] According to the latency index in the preset period, and the total number of message data in the preset period, the latency average in the performance index is determined;

[0206] determining a time delay peak value in the performance index according to the time delay index within the preset period;

[0207] determining a migration rate in the performance index according to the total number of message data within the preset period and the preset time length;

[0208] determining a migration success rate in the performance index according to the number of successful message data migration and the total number of message data within the preset period.

[0209] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0210] If the performance index exceeds the preset performance threshold, and the duration of exceeding the performance threshold meets the preset time length, then updating the data migration concurrency according to the time delay index and the time delay threshold.

[0211] In one embodiment, the processor, when executing the computer program, also implements the following steps:

[0212] If the performance index does not exceed the preset performance threshold, then determining whether the current data migration concurrency has been updated;

[0213] If it has been updated, then determining whether the performance index is lower than the average of the performance index within the historical preset period;

[0214] If it is lower, then updating the data migration concurrency according to the historical update data of the data migration concurrency.

[0215] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed by a processor, implements the following steps:

[0216] In the data migration process, obtaining the upload timestamp and the download timestamp of each message data;

[0217] determining the time delay index and the performance index of the message data according to the upload timestamp and the download timestamp of each message data;

[0218] If the performance index exceeds the preset performance threshold, then updating the data migration concurrency according to the time delay index and the time delay threshold;

[0219] outputting an alarm notification according to the updated data migration concurrency and / or the performance index.

[0220] In one embodiment, the computer program, when executed by the processor, also implements the following steps:

[0221] If the performance index exceeds the preset performance threshold, then determining the required additional concurrency of each message data according to the time delay index and the time delay threshold.

[0222] updating the data migration concurrency according to the added concurrency.

[0223] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0224] if the performance index exceeds the preset performance threshold, obtaining the current usage of the local processor, the current usage of the local memory, and the current data migration concurrency;

[0225] determining the temporary concurrency supported by the processor according to the current usage of the local processor and the preset processor usage threshold;

[0226] determining the temporary concurrency supported by the memory according to the current usage of the local memory and the preset memory usage threshold;

[0227] determining the temporary concurrency supported by the message according to the data migration concurrency and the concurrency threshold;

[0228] determining the temporary concurrency required by the message according to the latency index, the latency threshold, and the delay change value between the current time and the historical time;

[0229] if the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message are all greater than zero, determining the temporary concurrency required by the message as the added concurrency required by each message data.

[0230] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0231] determining the latency index in the preset period according to the upload timestamp and the download timestamp of each message data;

[0232] determining the performance index according to the latency index in the preset period, the total number of message data, and the number of successfully migrated message data.

[0233] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0234] determining the successfully migrated message data in the preset period according to the upload timestamp and the download timestamp of each message data;

[0235] determining the latency index in the preset period according to the upload timestamp and the download timestamp of the successfully migrated message data.

[0236] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0237] According to the time delay index in the preset period, and the total number of message data in the preset period, a time delay average in the performance index is determined;

[0238] According to the time delay index in the preset period, a time delay peak in the performance index is determined;

[0239] According to the total number of message data in the preset period and the preset time length, a migration rate in the performance index is determined;

[0240] According to the number of successful message data migration in the preset period and the total number of message data, a migration success rate in the performance index is determined.

[0241] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0242] If the performance index exceeds the preset performance threshold, and the duration of exceeding the performance threshold meets the preset time length, the data migration concurrency is updated according to the time delay index and the time delay threshold.

[0243] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0244] If the performance index does not exceed the preset performance threshold, it is judged whether the current data migration concurrency has been updated;

[0245] If it has been updated, it is judged whether the performance index is lower than the average of the performance index in the historical preset period;

[0246] If it is lower, the data migration concurrency is updated according to the historical update data of the data migration concurrency.

[0247] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0248] In the data migration process, the upload timestamp and the download timestamp of each message data are obtained;

[0249] According to the upload timestamp and the download timestamp of each message data, the time delay index and the performance index of the message data are determined;

[0250] If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold;

[0251] According to the updated data migration concurrency, and / or the performance index, an alarm notification is output.

[0252] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0253] If the performance index exceeds the preset performance threshold, the newly added concurrency required by each message data is determined according to the time delay index and the time delay threshold;

[0254] The data migration concurrency is updated according to the newly added concurrency.

[0255] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0256] If the performance index exceeds the preset performance threshold, the current usage of the local processor, the current usage of the local memory, and the current data migration concurrency are obtained;

[0257] The temporary concurrency supported by the processor is determined according to the current usage of the local processor and the preset processor usage threshold;

[0258] The temporary concurrency supported by the memory is determined according to the current usage of the local memory and the preset memory usage threshold;

[0259] The temporary concurrency supported by the message is determined according to the data migration concurrency and the concurrency threshold;

[0260] The temporary concurrency required by the message is determined according to the time delay index, the time delay threshold, and the delay change value between the current time and the historical time;

[0261] If the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message are all greater than zero, the temporary concurrency required by the message is determined as the newly added concurrency required by each message data.

[0262] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0263] The time delay index in the preset period is determined according to the upload timestamp and the download timestamp of each message data;

[0264] The performance index is determined according to the time delay index in the preset period, the total number of message data, and the number of successfully migrated message data.

[0265] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0266] The successfully migrated message data in the preset period is determined according to the upload timestamp and the download timestamp of each message data;

[0267] The time delay index in the preset period is determined according to the upload timestamp and the download timestamp of the successfully migrated message data.

[0268] In one embodiment, the computer program, when executed by the processor, further implements the following steps:

[0269] According to the time delay index in the preset period, and the total number of message data in the preset period, a time delay average in the performance index is determined;

[0270] According to the time delay index in the preset period, a time delay peak in the performance index is determined;

[0271] According to the total number of message data in the preset period and the preset time length, a migration rate in the performance index is determined;

[0272] According to the number of successful message data migration in the preset period and the total number of message data, a migration success rate in the performance index is determined.

[0273] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0274] If the performance index exceeds the preset performance threshold, and the duration of exceeding the performance threshold meets the preset time length, the data migration concurrency is updated according to the time delay index and the time delay threshold.

[0275] In one embodiment, the computer program is executed by the processor to further implement the following steps:

[0276] If the performance index does not exceed the preset performance threshold, it is determined whether the current data migration concurrency has been updated;

[0277] If it has been updated, it is determined whether the performance index is lower than the average of the performance index in the historical preset period;

[0278] If it is lower, the data migration concurrency is updated according to the historical update data of the data migration concurrency.

[0279] It should be noted that the data involved in the present application (including but not limited to data for analysis, stored data, displayed data, etc.) are all information and data authorized by the user or fully authorized by all parties.

[0280] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0281] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0282] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for monitoring data migration performance, the method comprising: The method comprises: In the data migration process, the upload timestamp and the download timestamp of each message data are acquired; According to the upload timestamp and the download timestamp of each message data, the time delay index and the performance index of the message data are determined; If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold; According to the updated data migration concurrency and / or the performance index, an alarm notification is outputted; If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold, which comprises: If the performance index exceeds the preset performance threshold, the current usage of the local processor, the current usage of the local memory and the current data migration concurrency are acquired; According to the current usage of the local processor and the preset processor usage threshold, the temporary concurrency supported by the processor is determined; According to the current usage of the local memory and the preset memory usage threshold, the temporary concurrency supported by the memory is determined; According to the data migration concurrency and the concurrency threshold, the temporary concurrency supported by the message is determined; According to the time delay index, the time delay threshold and the delay change value between the current time and the historical time, the temporary concurrency required by the message is determined; If the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message and the temporary concurrency required by the message are all greater than zero, the temporary concurrency required by the message is determined as the new concurrency required by each message data; According to the new concurrency, the data migration concurrency is updated.

2. The method of claim 1, wherein, According to the upload timestamp and the download timestamp of each message data, the time delay index and the performance index of the message data are determined, which comprises: According to the upload timestamp and the download timestamp of each message data, the time delay index in the preset period is determined; According to the time delay index in the preset period, the total number of message data and the number of successfully migrated message data, the performance index is determined.

3. The method of claim 2, wherein, According to the upload timestamp and the download timestamp of each message data, the time delay index in the preset period is determined, which comprises: According to the upload timestamp and the download timestamp of each message data, the successfully migrated message data in the preset period is determined; According to the upload timestamp and the download timestamp of the successfully migrated message data, the time delay index in the preset period is determined.

4. The method of claim 2, wherein, According to the time delay index in the preset period, the total number of message data in the preset period and the number of successfully migrated message data, the performance index is determined, which comprises at least one of the following: According to the time delay index in the preset period and the total number of message data in the preset period, the time delay average in the performance index is determined; According to the time delay index in the preset period, the time delay peak in the performance index is determined; According to the total number of message data in the preset period and the preset time length, the migration rate in the performance index is determined; According to the number of successfully migrated message data in the preset period and the total number of message data, the migration success rate in the performance index is determined.

5. The method of claim 1, wherein, If the performance index exceeds the preset performance threshold, the data migration concurrency is updated according to the time delay index and the time delay threshold, which comprises: If the performance index exceeds a preset performance threshold, and a duration of exceeding the performance threshold meets a preset duration, the data migration concurrency is updated according to the time delay index and a time delay threshold.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: If the performance index does not exceed a preset performance threshold, it is determined whether the current data migration concurrency has been updated; If the performance index has been updated, it is determined whether the performance index is lower than an average of performance indexes in a historical preset time period; If the performance index is lower than the average, the data migration concurrency is updated according to historical update data of the data migration concurrency.

7. A data migration performance monitoring apparatus, characterized by comprising: The device comprises: a time acquisition module configured to acquire upload timestamps and download timestamps of each message data in a data migration process; an index determination module configured to determine a time delay index and a performance index of the message data according to the upload timestamps and the download timestamps of the each message data; a concurrency update module configured to update the data migration concurrency according to the time delay index and a time delay threshold if the performance index exceeds a preset performance threshold; an alarm module configured to output an alarm notification according to the updated data migration concurrency and / or the performance index; The concurrency update module is specifically configured to: If the performance index exceeds a preset performance threshold, acquire a current usage rate of a local processor, a current usage rate of a local memory, and a current data migration concurrency; determine a temporary concurrency supported by a processor according to the current usage rate of the local processor and a preset processor usage rate threshold; determine a temporary concurrency supported by a memory according to the current usage rate of the local memory and a preset memory usage rate threshold; determine a temporary concurrency supported by a message according to the data migration concurrency and a concurrency threshold; determine a temporary concurrency required by the message according to the time delay index, a time delay threshold, and a delay change value between a current time and a historical time; If the temporary concurrency supported by the processor, the temporary concurrency supported by the memory, the temporary concurrency supported by the message, and the temporary concurrency required by the message are all greater than zero, determine the temporary concurrency required by the message as a new concurrency required by each message data; update the data migration concurrency according to the new concurrency.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Citation Information

Patent Citations

  • Data migration method and system, computing equipment and storage medium

    CN113468143A

  • Table-based InfluxDB data migration method

    CN113515503A