Link Condition Awareness Method, Apparatus and Computer Device

Abstract

The link condition awareness method, device and computer equipment provided by this application can, when performing awareness tasks on multiple link awareness points in a to-be-tested area, first determine the target resource pool and the probing strategy corresponding to each link awareness point. In this way, the cloud storage link between each link awareness point and its corresponding target resource pool can be probed according to the probing strategy of each link awareness point, so as to obtain the probing result of each link awareness point. Then, this application can analyze the link quality of the cloud storage link between each link awareness point and its corresponding target resource pool according to the probing result of each link awareness point, and sense the link conditions of each link awareness point in the to-be-tested area according to the analysis result. In this way, when the coverage of the link awareness points is sufficient, the link conditions can be accurately evaluated, and scheduling suggestions can be provided for the scheduling system.

Description

Technical Field

[0001] The present application relates to the field of cloud storage technology, and in particular to a link status perception method, device and computer equipment. Background Art

[0002] Cloud storage is an online storage model that stores data on multiple virtual servers usually hosted by a third party, rather than on dedicated servers. Hosting companies operate large data centers, and people who need data storage hosting can meet their data storage needs by purchasing or renting storage space from them. Data center operators prepare storage virtualization resources at the back end based on customer needs and provide them in the form of storage resource pools, which customers can then use to store files or objects.

[0003] At present, with the increasing traffic of equipment, the problem of cloud storage upload is gradually emerging. Due to the huge equipment links, the complicated network conditions of various users, provinces, cities, storage pools, etc., the bandwidth load, delay and other information of each link cannot be mastered in detail, and the equipment cannot be reasonably scheduled according to the conditions of each link, resulting in problems such as cloud storage failure to upload and frame loss after some equipment is scheduled. At the same time, due to the lack of refined link dialing, the background cannot intuitively display and warn the details of the link. Once the link is abnormal, the operation and maintenance personnel cannot discover and schedule the traffic in time, which eventually leads to cloud storage abnormality and affects the business. Summary of the invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect that the bandwidth load, delay and other information of each link in the prior art cannot be timely grasped, resulting in cloud storage anomalies and affecting business.

[0005] The present application provides a link status perception method, the method comprising:

[0006] When multiple link sensing points in the area to be tested perform sensing tasks, determine the target resource pool and dialing strategy corresponding to each link sensing point;

[0007] According to the dialing test strategy of each link sensing point, the cloud storage link between each link sensing point and its corresponding target resource pool is respectively dialed to obtain the dialing test result of each link sensing point;

[0008] The link quality of the cloud storage link between each link perception point and its corresponding target resource pool is analyzed according to the dialing test result of each link perception point, and the link status of each link perception point in the test area is sensed according to the analysis result.

[0009] Optionally, determining a target resource pool and a dialing test strategy for each link sensing point includes:

[0010] Determine whether the target resource pool and the probing strategy of each locally pre-configured link sensing point need to be updated;

[0011] If not, obtain the target resource pool and the probing strategy of each locally pre-configured link sensing point from the local;

[0012] If so, reconfigure the target resource pool and the probing strategy of each link sensing point.

[0013] Optionally, the configuration process of the target resource pool corresponding to each link sensing point includes:

[0014] Obtain a preset normalization rule table, where the normalization rule table includes a cloud storage scheduling rule table and a service planning rule table;

[0015] Configure a first resource pool corresponding to each link sensing point according to the cloud storage scheduling rule table;

[0016] Configure a second resource pool corresponding to each link sensing point according to the service planning rule table;

[0017] Aggregate the first resource pool and the second resource pool to form the target resource pool corresponding to each link sensing point.

[0018] Optionally, the method further includes:

[0019] Judge whether the configuration time of the target resource pool corresponding to each link sensing point is within the effective detection time range of the temporary demand rule table, where the temporary demand rule table contains a temporary resource pool and the corresponding temporary sensing points;

[0020] If so, use the temporary sensing points in the temporary demand rule table as the link sensing points of the area to be measured, and use the temporary resource pool in the temporary demand rule table as the target resource pool corresponding to this link sensing point;

[0021] If not, continue to execute the step of probing the cloud storage link between each link sensing point and its corresponding target resource pool according to the preset probing strategy.

[0022] Optionally, the configuration process of the probing strategy corresponding to each link sensing point includes:

[0023] Configure the global strategy corresponding to each link sensing point, where the global strategy at least includes the probing period, the probing method, the number of probing times for each probing method, the submission strategy of the probing results, and the exception handling method;

[0024] Configure the specified policies corresponding to each link perception point, where the specified policies support configuring specific high-priority policies for specified link perception points, target resource pools, geographical regions, and time access ranges;

[0025] Use the global policy or the global policy and the specified policy as the probing policies corresponding to each link perception point.

[0026] Optionally, analyze the link quality of the cloud storage link between each link perception point and its corresponding target resource pool according to the probing results of each link perception point to obtain analysis results, including:

[0027] According to the probing results of each link perception point, calculate the link scoring results of the cloud storage link between each link perception point and its corresponding target resource pool per unit time within a preset period;

[0028] For each link perception point, if the number of times the link scoring result of this link perception point is lower than the first preset scoring threshold within the preset period is not less than the first preset number threshold, or the number of times the link scoring result of this link perception point is continuously lower than the second preset scoring threshold within the preset period is not less than the second preset number threshold, then determine that there is an abnormality in the cloud storage link between this link perception point and its corresponding target resource pool, and issue a warning for the abnormal cloud storage link;

[0029] For the link scoring results of each link perception point per unit time within the preset period, if the link scoring result is lower than the historical link scoring result at the same unit time and the decrease ratio of the link scoring result is not less than the preset ratio threshold, then determine that there is an abnormality in the cloud storage link between this link perception point and its corresponding target resource pool, and issue a warning for the abnormal cloud storage link.

[0030] Optionally, calculating the link scoring results of the cloud storage link between each link perception point and its corresponding target resource pool per unit time within a preset period according to the probing results of each link perception point includes:

[0031] For the cloud storage link between each link perception point and its corresponding target resource pool:

[0032] Calculate the file upload efficiency, file download efficiency, file deletion efficiency, and link request success rate of this cloud storage link per unit time within a preset period according to the probing results of this link perception point;

[0033] Score the file upload efficiency, file download efficiency, and file deletion efficiency of this cloud storage link respectively according to a preset scoring policy to obtain their respective scoring results;

[0034] Calculate the link score result of the cloud storage link based on the link request success rate, file upload efficiency, file download efficiency, file deletion efficiency of the cloud storage link, and their respective scoring results.

[0035] Optionally, the method further includes:

[0036] Synchronize the ping test results of each link perception point according to the link conditions of the cloud storage links between each link perception point and its corresponding target resource pool.

[0037] This application also provides a link condition perception device, including:

[0038] A task determination module, configured to determine the target resource pool and ping test strategy corresponding to each link perception point when performing perception tasks on multiple link perception points in a to-be-tested area;

[0039] A link ping test module, configured to perform ping tests on the cloud storage links between each link perception point and its corresponding target resource pool respectively according to the ping test strategy of each link perception point, and obtain the ping test results of each link perception point;

[0040] A condition perception module, configured to analyze the link quality of the cloud storage links between each link perception point and its corresponding target resource pool according to the ping test results of each link perception point, and perceive the link conditions of each link perception point in the to-be-tested area according to the analysis results.

[0041] This application also provides a computer device, including: one or more processors, and a memory;

[0042] Computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the one or more processors, the steps of the link condition perception method described in any one of the above embodiments are executed.

[0043] It can be seen from the above technical solutions that the embodiments of this application have the following advantages:

[0044] The link condition perception method, device, and computer device provided by this application can, when performing perception tasks on multiple link perception points in a to-be-tested area, first determine the target resource pool and probing strategy corresponding to each link perception point. In this way, the cloud storage link between each link perception point and its corresponding target resource pool can be probed according to the probing strategy of each link perception point, so as to obtain the probing result of each link perception point. Then, this application can analyze the link quality of the cloud storage link between each link perception point and its corresponding target resource pool based on the probing result of each link perception point, and perceive the link conditions of each link perception point in the to-be-tested area according to the analysis result. In this way, when the coverage of the link perception points is sufficient, the link conditions can be accurately evaluated, and scheduling suggestions can be provided for the scheduling system, so that when the scheduling system monitors that there are abnormal cloud storage-related behaviors of users in a certain area, the user cloud storage in this area can be scheduled to a resource pool with better links. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 It is a schematic flowchart of a link condition perception method provided by an embodiment of this application;

[0047] Figure 2 It is a schematic structural diagram of a cloud storage link perception system provided by an embodiment of this application;

[0048] Figure 3 It is a schematic structural diagram of a link condition perception device provided by an embodiment of this application;

[0049] Figure 4 It is a schematic internal structural diagram of a computer device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the drawings in the embodiments of this application. Obviously, the described embodiments are only some embodiments of this application, rather than all embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of this application.

[0051] Currently, while the device traffic is increasing day by day, the problem of cloud storage upload is gradually emerging. Due to the huge device links, the network conditions of each user, province, city, storage pool, etc. are intricate. Information such as the bandwidth load and delay of each link cannot be detailedly grasped, and the device cannot be reasonably scheduled according to the conditions of each link, resulting in problems such as the inability to upload cloud storage and frame loss during upload after some devices are scheduled. At the same time, due to the lack of refined link dial testing, the background cannot intuitively display and warn about the link details. Once the link is abnormal, the operation and maintenance personnel cannot discover and perform traffic scheduling in time, ultimately leading to abnormal cloud storage and affecting the business.

[0052] Based on this, the present application proposes the following technical solutions, which are specifically described below:

[0053] In one embodiment, as Figure 1 shown, Figure 1 is a flowchart of a method for perceiving link conditions provided by an embodiment of the present application; the present application provides a method for perceiving link conditions, and the method may include:

[0054] S110: When performing a perception task on multiple link perception points in a region to be measured, determine the target resource pool and dial testing strategy corresponding to each link perception point.

[0055] In this step, when performing a perception task on multiple link perception points in the region to be measured, the target resource pool and dial testing strategy corresponding to each link perception point can be determined, so that the cloud storage link between each link perception point and its corresponding target resource pool can be dial tested according to the dial testing strategy to obtain a dial testing result.

[0056] Among them, the region to be measured in the present application refers to the region where the link conditions are to be perceived. This region can be within the scope of the whole country, within the scope of the whole province, or within the scope of the whole city or district. Of course, one or more target resource pools can also be used as the region to be measured to perceive the link conditions of the cloud storage links under the one or more target resource pools.

[0057] The link perception point in the present application refers to a detection node preset in the region to be measured. This detection node has the characteristics of stable environment and sufficient bandwidth, so a standardized evaluation can be formed; the dial testing strategy in the present application refers to the dial testing method used when dial testing the cloud storage link between the link perception point and its corresponding target resource pool. This dial testing method can include a global strategy or a specified strategy. Among them, the global strategy can include the dial testing period, dial testing method, the number of dial testing times for each dial testing method, the submission strategy of the dial testing result, and the exception handling method, etc. The specified strategy can support configuring specific high-priority strategies for specified link perception points, target resource pools, geographical regions, and time access ranges.

[0058] Further, the target resource pools and the probing strategies corresponding to each link perception point in this application may be the same or different. For example, when probing the link perception points in the whole region, there may be one or more target resource pools corresponding to this region, while the number of link perception points in this region is much larger than the number of target resource pools. Therefore, there will be a situation where one target resource pool corresponds to multiple link perception points, and there are certain differences in the devices, regions, etc. corresponding to each link perception point. Therefore, the probing strategies corresponding to each link perception point may also have certain differences.

[0059] S120: Probe the cloud storage link between each link perception point and its corresponding target resource pool according to the probing strategy of each link perception point, and obtain the probing result of each link perception point.

[0060] In this step, after determining the target resource pool and the probing strategy corresponding to each link perception point through S110, this application can probe the cloud storage link between each link perception point and its corresponding target resource pool according to the probing strategy of each link perception point, and obtain the probing result of each link perception point.

[0061] For example, when the probing period, probing method, the number of probing times for each probing method, the submission strategy of the probing result, and the exception handling method of a certain link perception point are set in the probing strategy of this application, the cloud storage link between this link perception point and its corresponding target resource pool can be probed when the probing period arrives. When probing, it can be carried out according to the specific probing method. For example, uploading one file at a time, uploading files in slices, downloading, parallel downloading, deleting, etc. The specific number of probing times can be carried out according to the number of probing times set under this probing method, including the amount of data uploaded in a single task, the number of data uploads, the number of data downloads, the number of deletions, etc. When the probing is completed, the data submission strategy can be submitting after accumulating a certain number of times, submitting when an exception occurs, submitting at a certain period, etc. Further, when an abnormal situation occurs, such as supporting enhanced testing when a certain test is abnormal. Thus, the probing result of each link perception point can be obtained.

[0062] S130: Analyze the link quality of the cloud storage link between each link perception point and its corresponding target resource pool according to the probing result of each link perception point, and perceive the link conditions of each link perception point in the area to be tested according to the analysis result.

[0063] In this step, through S120, the cloud storage link between each link sensing point and its corresponding target resource pool is respectively tested according to the testing strategy of each link sensing point. After obtaining the testing results of each link sensing point, the present application can analyze the link quality of the cloud storage link between each link sensing point and its corresponding target resource pool according to the testing results of each link sensing point, and sense the link conditions of each link sensing point in the area to be tested according to the analysis results. In this way, the link conditions can be evaluated timely, accurately and intuitively, and scheduling suggestions can be provided for the scheduling system.

[0064] In a specific implementation manner, when the present application analyzes the link quality of the cloud storage link, it can be analyzed from multiple dimensions. For example, the present application can analyze the link quality of the cloud storage link from aspects such as the link request success rate, file upload efficiency, file download efficiency, and file deletion efficiency of the cloud storage link. After obtaining the analysis results of each link sensing point, the link conditions of each link sensing point in the area to be tested can be sensed according to the analysis results.

[0065] Furthermore, when the present application senses the link conditions of each link sensing point in the area to be tested according to the analysis results, it can construct a link sensing network according to each link sensing point in the area to be tested, the target resource pool corresponding to each link sensing point, and the cloud storage link, and mark different colors for each cloud storage link according to the link quality of each cloud storage link, so that users can directly obtain the link conditions of the area to be tested through this link sensing network. In addition, when it is detected that there are abnormal cloud storage-related behaviors of users in a certain area, the scheduling system can call this link sensing network, obtain the link conditions of the cloud storage link corresponding to this area in this link sensing network, and then schedule the user cloud storage in this area to the target resource pool with better links according to the link quality of each cloud storage link, so as to optimize the scheduling and reduce the impact on services caused by cloud storage anomalies.

[0066] Furthermore, the present application can implement the technical solution of the above link condition sensing method through a cloud storage link sensing system. Specifically, as Figure 2 shown, Figure 2 is a schematic structural diagram of the cloud storage link sensing system provided by the embodiment of the present application; Figure 2In the cloud storage link perception system, it consists of five major modules: the link perception center, the link perception measurement point, the link data analysis center, the link alarm, and the data middle platform. Among them, the link perception center mainly provides functions such as link data query (page view, large screen view), management control, link diagnosis, full-link troubleshooting, and link recommendation. The management control function realizes the task configuration of the measurement points and the detailed execution configuration of each measurement point; the link data query function obtains data by accessing the data analysis center, supports data query according to time dimension, province dimension, measurement nodes, etc., and provides various display forms, including basic data view, large screen display, etc.; the timing diagnosis function performs timing polling analysis on link data and provides abnormal link diagnosis results; the full-link troubleshooting function provides troubleshooting capabilities in combination with other log data; the link recommendation function provides province-pool link recommendations by analyzing link historical data.

[0067] The link perception measurement point, that is, the link perception point in this application, mainly provides three major functions: flexible and configurable measurement strategies, data reporting, and various detection methods. The link perception measurement point dynamically obtains relevant configurations by accessing the link perception center, including configurable measurement frequency, period, task grouping, etc.; the measurement link rule is that the regular measurement only measures the scheduling links that may occur in this area, and users can also customize other scheduling links according to needs; after the measurement is completed, the link perception measurement point can also achieve data synchronization, and the measurement data outputs logs in a certain format, and the data is synchronized in real time through log synchronization.

[0068] The link data analysis center in the cloud storage link perception system can realize the aggregation analysis and persistent storage of data by reading the big data cluster of the data middle platform, provide access APIs, and output relevant analysis results. The data middle platform can set various types of clusters, such as KAFKA clusters, ES clusters, etc., for storing the measurement plasticizers reported by the link perception measurement points; while the link alarm center is mainly responsible for the alarm push of the link diagnosis results of the link perception center, and can manage alarm methods, alarm personnel / system groups, etc.

[0069] In the above embodiments, when performing sensing tasks on multiple link sensing points in the area to be measured, the target resource pool and the probing strategy corresponding to each link sensing point can be determined first. In this way, the cloud storage link between each link sensing point and its corresponding target resource pool can be probed according to the probing strategy of each link sensing point, so as to obtain the probing result of each link sensing point. Then, the present application can analyze the link quality of the cloud storage link between each link sensing point and its corresponding target resource pool according to the probing result of each link sensing point, and sense the link conditions of each link sensing point in the area to be measured according to the analysis result. In this way, when the coverage of the link sensing points is sufficient, the link conditions can be accurately evaluated, and scheduling suggestions can be provided for the scheduling system, so that when the scheduling system monitors that there are abnormal cloud storage-related behaviors of users in a certain area, the user cloud storage in this area can be scheduled to a resource pool with better links.

[0070] In one embodiment, determining the target resource pool and the probing strategy for each link sensing point in S110 may include:

[0071] S111: Determine whether the target resource pool and the probing strategy for each link sensing point pre-configured locally need to be updated; if not, execute S112; if so, execute S113.

[0072] S112: Obtain the target resource pool and the probing strategy for each link sensing point pre-configured locally.

[0073] S113: Re-configure the target resource pool and the probing strategy for each link sensing point.

[0074] In this embodiment, when determining the target resource pool and the probing strategy for each link sensing point, the present application can first determine whether the target resource pool and the probing strategy for each link sensing point pre-configured locally need to be updated. If so, re-configure the target resource pool and the probing strategy for each link sensing point. If not, directly obtain the target resource pool and the probing strategy for each link sensing point pre-configured locally.

[0075] It can be understood that when each link sensing point in the area to be measured needs to perform a sensing task, each link sensing point can dynamically obtain from the link sensing center whether there are changes in the target resource pool and the probing strategy. If there are changes, re-configure the target resource pool and the probing strategy through the link sensing center, and synchronously update the target resource pool and the probing strategy saved locally. If there are no changes, directly obtain the target resource pool and the probing strategy from the local.

[0076] Furthermore, when determining the target resource pool for each link perception point in this application, since the scheduling system controls the cloud storage link between the link perception point and the target resource pool and allocates one or more resource pools nearby according to the region to which the device belongs, when allocating multiple resource pools, the allocation process also refers to the dynamic traffic volume in each region, whether the local pool can meet the requirements, whether the link can meet the requirements, etc. Therefore, this strategy is dynamically changing, which leads to the dynamic change of the target resource pool corresponding to the link perception point every time the perception task is executed. When there is a change, it is necessary to reconfigure the corresponding target resource pool and the dial test strategy to adapt to the current business requirements, etc.

[0077] In one embodiment, the configuration process of the target resource pool corresponding to each link perception point may include:

[0078] S101: Obtain a preset normalization rule table, where the normalization rule table includes a cloud storage scheduling rule table and a business planning rule table.

[0079] S102: Configure the first resource pool corresponding to each link perception point according to the cloud storage scheduling rule table.

[0080] S103: Configure the second resource pool corresponding to each link perception point according to the business planning rule table.

[0081] S104: Aggregate the first resource pool and the second resource pool to form the target resource pool corresponding to each link perception point.

[0082] In this embodiment, when configuring the target resource pool corresponding to each link perception point, a preset normalization rule table can be obtained. The normalization rule table includes a cloud storage scheduling rule table and a business rule table. This application can configure the first resource pool corresponding to each link perception point according to the cloud storage scheduling rule table, and configure the second resource pool corresponding to each link perception point according to the business planning rule table, and aggregate the first resource pool and the second resource pool to form the target resource pool corresponding to each link perception point.

[0083] In a specific example, the cloud storage scheduling rule table of the present application mainly records the scheduling relationship between regional devices and resource pools. Therefore, according to this cloud storage scheduling rule table, a corresponding set S1 [pool, region] between multiple resource pools and regions can be obtained; while the service planning rule table of the present application records the relationship between resource pools and preset writable regions. Therefore, through this service planning rule table, a corresponding set S2 [pool, region] between multiple resource pools and regions can also be obtained. Among them, the service planning rule table of the present application is for a preset link, and the preset link represents a link planned according to the service, including the priority order of the link, the backup link in case of emergency, etc. When constructing the preset rule, the province can be selected first, that is, the detection node representing the province, and then the write pool can be selected. Generally, the local province pool is selected. When it is estimated that the resources of the local province pool are insufficient, the adjacent province pool or the backup large pool is selected as the backup. Finally, according to the selected province and the selected write pool, the preset rule is constructed and written into the service planning rule table. After obtaining S1 and S2, the present application can aggregate S1 and S2 and determine the target resource pool corresponding to each link sensing point according to the area to be measured.

[0084] In one embodiment, the method may further include:

[0085] S105: Determine whether the configuration time of the target resource pool corresponding to each link sensing point is within the effective detection time range of the temporary demand rule table, where the temporary demand rule table contains a temporary resource pool and the corresponding temporary sensing point; if so, execute S106; if not, execute S107.

[0086] S106: Use the temporary sensing point in the temporary demand rule table as the link sensing point of the area to be measured, and use the temporary resource pool in the temporary demand rule table as the target resource pool corresponding to this link sensing point.

[0087] S107: Continue to execute the step of performing cloud storage link detection between each link sensing point and its corresponding target resource pool according to the preset detection strategy.

[0088] In this embodiment, when setting the target resource pool corresponding to each link sensing point, the present application may also determine whether the configuration time of the target resource pool corresponding to each link sensing point is within the effective detection time range of the temporary demand rule table. If so, use the temporary sensing point in the temporary demand rule table as the link sensing point of the area to be measured, and use the temporary resource pool in the temporary demand rule table as the target resource pool corresponding to this link sensing point. If not, continue to execute the step of S120.

[0089] Among them, the temporary requirement rule table of the present application can be used to configure a temporary link. The temporary link represents a link with a certain life cycle set under temporary requirements and is not a normal link. When setting a temporary link, a temporary resource pool can be selected first. The selection can be made in a multi-level manner, including by region > provinces within the region > pools within the region. For example, selecting a region means selecting all pools within that region; selecting a province means selecting all pools within that province; selecting a pool means selecting one or more selected pools. Then, the detection nodes during probing can be selected. All detection nodes can be filtered and used as temporary sensing points. Finally, the effective detection time range of the temporary link can be set, and the custom rules and time range can be stored in the database to form the temporary requirement rule table.

[0090] In one embodiment, the configuration process of the probing strategy corresponding to each link sensing point may include:

[0091] S1001: Configure the global strategy corresponding to each link sensing point. The global strategy at least includes the probing period, the probing method, the number of probing times for each probing method, the submission strategy for probing results, and the exception handling method.

[0092] S1002: Configure the specified strategy corresponding to each link sensing point. The specified strategy supports configuring specific high-priority strategies for specified link sensing points, target resource pools, geographical regions, and time access ranges.

[0093] S1003: Use the global strategy or the global strategy and the specified strategy as the probing strategy corresponding to each link sensing point.

[0094] In this embodiment, the probing strategy refers to the probing method used when probing the cloud storage link between a link sensing point and its corresponding target resource pool. This probing method may include a global strategy or a specified strategy. Among them, the global strategy may include the probing period, the probing method, the number of probing times for each probing method, the submission strategy for probing results, and the exception handling method, etc. The specified strategy supports configuring specific high-priority strategies for specified link sensing points, target resource pools, geographical regions, and time access ranges.

[0095] Therefore, when configuring the dial test policy corresponding to the link awareness point, the global policy of the link awareness point can be configured first. In addition to supporting the dial test period (start, end, interval frequency), dial test methods (including multiple types: uploading one file at a time, uploading files in slices, downloading, parallel downloading, deleting, etc.), the number of dial test times for each dial test method (the amount of data uploaded in a single task, the number of data uploads, the number of data downloads, the number of deletions), and the submission policy of the dial test results (submitting after accumulating a certain number of times, submitting when an exception occurs, submitting at a certain period), it also supports configuring the exception handling method (such as strengthening the test when a certain test is abnormal). Further, in addition to the global policy, this application also supports configuring specific high-priority policies for specified link awareness points, target resource pools, geographical regions, and time access ranges. In this way, the dial test policy of the link awareness point can be determined through the global policy, or the dial test policy of the link awareness point can be determined through the global policy and the specified policy.

[0096] In one embodiment, in S130, based on the dial test results of each link awareness point, the link quality of the cloud storage link between each link awareness point and its corresponding target resource pool is analyzed to obtain an analysis result, which may include:

[0097] S131: According to the dial test results of each link awareness point, calculate the link score result of the cloud storage link between each link awareness point and its corresponding target resource pool per unit time within a preset time period.

[0098] S132: For each link awareness point, if the number of times the link score result of this link awareness point is lower than the first preset score threshold within the preset time period is not less than the first preset number threshold, or the number of times the link score result of this link awareness point is continuously lower than the second preset score threshold within the preset time period is not less than the second preset number threshold, it is determined that there is an abnormality in the cloud storage link between this link awareness point and its corresponding target resource pool, and a warning is issued for the abnormal cloud storage link.

[0099] S133: For the link score result of each link awareness point per unit time within the preset time period, if this link score result is lower than the historical link score result at the same unit time, and the decrease ratio of this link score result is not less than the preset ratio threshold, it is determined that there is an abnormality in the cloud storage link between this link awareness point and its corresponding target resource pool, and a warning is issued for the abnormal cloud storage link.

[0100] In this embodiment, when analyzing the link quality of the cloud storage link between each link perception point and its corresponding target resource pool, the link score result of the cloud storage link between each link perception point and its corresponding target resource pool per unit time within a preset period can be calculated first according to the dial test result of each link perception point. Then, for each link perception point, the present application can count the number of times that the link score result of this link perception point is lower than the first preset score threshold within the preset period, and determine whether this number is not less than the first preset number threshold. If it is not less than, it means that there is an abnormality in the cloud storage link between this link perception point and its corresponding target resource pool. At this time, a warning can be issued for the abnormal cloud storage link through the link warning module. Of course, the present application can also count the number of times that the link score result of this link perception point is continuously lower than the second preset score threshold within the preset period, and determine whether this number is not less than the second preset number threshold. If it is not less than, it means that there is an abnormality in the cloud storage link between this link perception point and its corresponding target resource pool. At this time, a warning can also be issued for the abnormal cloud storage link through the link warning module.

[0101] Next, for the link score result of each link perception point per unit time within the preset period, the present application can also count whether this link score result is lower than the historical link score result at the same unit time. If it is lower, it is determined whether there is an abnormality in this cloud storage link according to whether the decrease ratio of this link score result is less than the preset ratio threshold. If the decrease ratio is less than the preset ratio threshold, there may be an abnormality, and a warning can be issued for the abnormal cloud storage link.

[0102] Among them, the historical link score result at the same unit time mentioned above can be the link score result at the same unit time within the historical period relatively close to the current preset period.

[0103] In one embodiment, calculating the link score result of the cloud storage link between each link perception point and its corresponding target resource pool per unit time within a preset period according to the dial test result of each link perception point in S131 may include:

[0104] S1311: For the cloud storage link between each link perception point and its corresponding target resource pool: calculate the file upload efficiency, file download efficiency, file deletion efficiency, and link request success rate of this cloud storage link per unit time within the preset period according to the dial test result of this link perception point.

[0105] S1312: Score the file upload efficiency, file download efficiency, and file deletion efficiency of this cloud storage link respectively according to the preset scoring strategy, and obtain their respective score results.

[0106] S1313: Calculate the link score result of the cloud storage link based on the link request success rate, file upload efficiency, file download efficiency, file deletion efficiency of the cloud storage link, and their respective scoring results.

[0107] In this embodiment, when calculating the link score result of each cloud storage link between each link perception point and its corresponding target resource pool per unit time within a preset period, for each cloud storage link, the file upload efficiency, file download efficiency, file deletion efficiency, and link request success rate of the cloud storage link per unit time within the preset period can be calculated according to the dial test result of the link perception point, and then the file upload efficiency, file download efficiency, and file deletion efficiency of the cloud storage link are scored respectively according to the preset scoring strategy, and their respective scoring results are obtained. Finally, the link score result of the cloud storage link is calculated based on the link request success rate, file upload efficiency, file download efficiency, file deletion efficiency of the cloud storage link, and their respective scoring results.

[0108] For example, in this application, t0 to t1 can be taken as the unit time T. When calculating the link score result Sij and link request success rate Rij of the link perception point i accessing the target resource pool j, the following steps can be performed:

[0109] (1) The file upload efficiency s1 can be represented by the average upload speed Vup within the T time period, and the file upload efficiency s1 is scored according to the set threshold range to obtain w1;

[0110] (2) The file download efficiency s2 can be represented by the average download speed Vdown within the T time period, and the file download efficiency s2 is scored according to the set threshold range to obtain w2.

[0111] (3) The file deletion efficiency s3 can be determined according to the request response time, and scored through the interval corresponding to the request response time to obtain w3.

[0112] (4) Link request success rate Rij:

[0113]

[0114] (5) Link score result Sij:

[0115]

[0116] The link score result of the cloud storage link in this application can be calculated through the above five steps.

[0117] In one embodiment, the method may further include:

[0118] S140: Synchronize the test results of each link sensing point based on the link conditions of the cloud storage links between each link sensing point and its corresponding target resource pool.

[0119] In this embodiment, after sensing the link conditions of each link sensing point in the area to be tested according to the analysis results, the present application can synchronize the test results of each link sensing point based on the link conditions of the cloud storage links between each link sensing point and its corresponding target resource pool.

[0120] Specifically, when there is no abnormality in the cloud storage link between the link sensing point and its corresponding target resource pool, data can be synchronized regularly or quantitatively according to the synchronization policy. Here, "regularly" refers to the time frequency interval for collecting logs or a fixed time point, and "quantitatively" refers to a certain number of data rows or data bytes. When there is an abnormality in the cloud storage link between the link sensing point and its corresponding target resource pool, an abnormal synchronization policy can be configured, such as reporting data immediately when the test speed fails to meet the standard N times or the average success rate is lower than a certain threshold after testing M times.

[0121] Next, the link condition sensing device provided by the embodiments of the present application will be described. The link condition sensing device described below can be correspondingly referred to the link condition sensing method described above.

[0122] In one embodiment, as Figure 3 shown, Figure 3 is a schematic structural diagram of a link condition sensing device provided by an embodiment of the present application; the present application also provides a link condition sensing device, which may include a task determination module 210, a link test module 220, and a condition sensing module 230, specifically including the following:

[0123] The task determination module 210 is configured to determine the target resource pool and the test policy corresponding to each link sensing point when performing a sensing task on multiple link sensing points in the area to be tested.

[0124] The link test module 220 is configured to test the cloud storage links between each link sensing point and its corresponding target resource pool respectively according to the test policy of each link sensing point, and obtain the test results of each link sensing point.

[0125] The condition sensing module 230 is configured to analyze the link quality of the cloud storage links between each link sensing point and its corresponding target resource pool according to the test results of each link sensing point, and sense the link conditions of each link sensing point in the area to be tested according to the analysis results.

[0126] In the above embodiments, when performing sensing tasks on multiple link sensing points in the area to be measured, the target resource pool and the dial test policy corresponding to each link sensing point can be determined first. In this way, the cloud storage link between each link sensing point and its corresponding target resource pool can be dial tested according to the dial test policy of each link sensing point, so as to obtain the dial test result of each link sensing point. Then, the present application can analyze the link quality of the cloud storage link between each link sensing point and its corresponding target resource pool according to the dial test result of each link sensing point, and sense the link conditions of each link sensing point in the area to be measured according to the analysis result. In this way, when the coverage of the link sensing points is sufficient, the link conditions can be accurately evaluated, and scheduling suggestions can be provided for the scheduling system, so that when the scheduling system monitors that there are abnormal cloud storage related behaviors of users in a certain area, the user cloud storage in this area can be scheduled to a resource pool with better links.

[0127] In one embodiment, the present application further provides a computer device, including: one or more processors, and a memory.

[0128] The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the link condition sensing method described in any one of the above embodiments are executed.

[0129] Schematically, as Figure 4 shown, Figure 4 is an internal structural diagram of a computer device provided by an embodiment of the present application. The computer device 300 can be provided as a server. Referring to Figure 4 , the computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by the memory 301 for storing instructions executable by the processing component 302, such as application programs. The application programs stored in the memory 301 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the link condition sensing method of any of the above embodiments.

[0130] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 can operate based on an operating system stored in the memory 301, such as WindowsServer TM, Mac OS XTM, Unix TM, Linux TM, Free BSDTM or the like.

[0131] Those skilled in the art can understand, Figure 4The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. Specifically, the computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0132] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0133] The various embodiments in this specification are described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0134] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for sensing link conditions, characterized in that, The method includes: When performing sensing tasks on multiple link sensing points in the area to be measured, determining the target resource pool and the probing policy corresponding to each link sensing point; Probing the cloud storage link between each link sensing point and its corresponding target resource pool according to the probing policy of each link sensing point, and obtaining the probing result of each link sensing point; Analyzing the link quality of the cloud storage link between each link sensing point and its corresponding target resource pool according to the probing result of each link sensing point, and sensing the link conditions of each link sensing point in the area to be measured according to the analysis result; The analyzing the link quality of the cloud storage link between each link sensing point and its corresponding target resource pool according to the probing result of each link sensing point includes: According to the probing result of each link sensing point, calculating the link scoring result of the cloud storage link between each link sensing point and its corresponding target resource pool per unit time within a preset time period; For each link sensing point, if the number of times that the link scoring result of this link sensing point is lower than the first preset scoring threshold within the preset time period is not less than the first preset number threshold, or the number of times that the link scoring result of this link sensing point is continuously lower than the second preset scoring threshold within the preset time period is not less than the second preset number threshold, it is determined that there is an abnormality in the cloud storage link between this link sensing point and its corresponding target resource pool; For the link scoring result of each link sensing point per unit time within the preset time period, if this link scoring result is lower than the historical link scoring result at the same unit time and the decrease ratio of this link scoring result is not less than the preset ratio threshold, it is determined that there is an abnormality in the cloud storage link between this link sensing point and its corresponding target resource pool; Issuing a warning for the abnormal cloud storage link.

2. The method for sensing link conditions according to claim 1, characterized in that, The determining the target resource pool and the probing policy corresponding to each link sensing point includes: Determining whether the target resource pool and the probing policy of each link sensing point pre-configured locally need to be updated; If not, obtaining the target resource pool and the probing policy of each link sensing point pre-configured locally; If so, re-configuring the target resource pool and the probing policy of each link sensing point.

3. The method for sensing link conditions according to claim 2, characterized in that, The configuration process of the target resource pool corresponding to each link sensing point includes: Obtaining a preset normalization rule table, where the normalization rule table includes a cloud storage scheduling rule table and a service planning rule table; Configuring a first resource pool corresponding to each link sensing point according to the cloud storage scheduling rule table; Configuring a second resource pool corresponding to each link sensing point according to the service planning rule table; Aggregating the first resource pool and the second resource pool to form the target resource pool corresponding to each link sensing point.

4. The method for sensing link conditions according to claim 3, characterized in that, The method further includes: Judging whether the configuration time of the target resource pool corresponding to each link sensing point is within the effective detection time range of the temporary demand rule table, where the temporary demand rule table contains a temporary resource pool and the corresponding temporary sensing points; If it exists, use the temporary sensing points in the temporary requirement rule table as the link sensing points of the area to be measured, and use the temporary resource pool in the temporary requirement rule table as the target resource pool corresponding to the link sensing point; If it does not exist, continue to execute the step of performing ping tests on the cloud storage links between each link sensing point and its corresponding target resource pool according to the ping test strategy of each link sensing point.

5. The method for sensing link conditions according to claim 2, characterized in that, The configuration process of the ping test strategies corresponding to the respective link sensing points includes: Configure the global strategy corresponding to each link sensing point, where the global strategy includes at least the ping test period, ping test method, number of ping tests for each ping test method, submission strategy for ping test results, and exception handling method; Configure the specified strategy corresponding to each link sensing point, where the specified strategy supports configuring specific high-priority strategies for specified link sensing points, target resource pools, geographical regions, and time access ranges; Use the global strategy or the global strategy and the specified strategy as the ping test strategies corresponding to the respective link sensing points.

6. The method for sensing link conditions according to claim 1, characterized in that, The calculating of the link score results for each unit time within a preset period for the cloud storage link between each link sensing point and its corresponding target resource pool according to the ping test results of each link sensing point includes: For the cloud storage link between each link sensing point and its corresponding target resource pool: Calculate the file upload efficiency, file download efficiency, file deletion efficiency, and link request success rate of the cloud storage link for each unit time within the preset period according to the ping test results of the link sensing point; Score the file upload efficiency, file download efficiency, and file deletion efficiency of the cloud storage link according to the preset scoring strategy respectively, and obtain their respective scoring results; Calculate the link score result of the cloud storage link based on the link request success rate, file upload efficiency, file download efficiency, file deletion efficiency of the cloud storage link, and their respective scoring results.

7. The method for sensing link conditions according to claim 1, characterized in that, The method further includes: Synchronize the data of the ping test results of each link sensing point according to the link conditions of the cloud storage links between each link sensing point and its corresponding target resource pool.

8. A link condition awareness device, characterized in that, It includes: A task determination module, configured to determine the target resource pool and ping test strategy corresponding to each link sensing point when performing sensing tasks on multiple link sensing points of the area to be measured; A link ping test module, configured to perform ping tests on the cloud storage links between each link sensing point and its corresponding target resource pool according to the ping test strategy of each link sensing point, and obtain the ping test results of each link sensing point; The situation sensing module is further configured to analyze the link quality of the cloud storage links between each link sensing point and its corresponding target resource pool according to the ping test results of each link sensing point, and sense the link conditions of each link sensing point in the area to be measured according to the analysis results; the situation sensing module is configured to calculate the link score results for each unit time within a preset period for the cloud storage link between each link sensing point and its corresponding target resource pool according to the ping test results of each link sensing point; For each link perception point, if the number of times that the link score result of this link perception point is lower than the first preset score threshold within the preset time period is not less than the first preset number threshold, or, if the number of times that the link score result of this link perception point is continuously lower than the second preset score threshold within the preset time period is not less than the second preset number threshold, it is determined that there is an abnormality in the cloud storage link between this link perception point and its corresponding target resource pool; For the link score result of each link perception point at each unit time within the preset time period, if this link score result is lower than the historical link score result at the same unit time, and the decrease ratio of this link score result is not less than the preset ratio threshold, it is determined that there is an abnormality in the cloud storage link between this link perception point and its corresponding target resource pool; Send a warning for the abnormal cloud storage link.

9. A computer device, characterized in that, Including: One or more processors, and a memory; Computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the one or more processors, the steps of the link condition perception method according to any one of claims 1 to 7 are executed.

Images