Resource recycling methods, apparatus, equipment, media and process products
By establishing a four-dimensional comprehensive resource health scoring system, different levels of resource recycling processes are determined based on the scores, which solves the problem of low efficiency in cloud network resource recycling in existing technologies and realizes differentiated recycling and efficient utilization of cloud network resources.
Patent Information
- Application Number
- CN202611413848.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-11
- Publication Date
- 2026-11-17
AI Technical Summary
In existing technologies, cloud network resource recycling solutions use a uniform waiting period and recycling steps for resources with different hardware performance and aging levels. This results in aging, low-performance hardware occupying the recycling isolation domain and public resource pool space for a long time, making it impossible to achieve differentiated and rapid release. Consequently, the resource pool space is ineffectively occupied, and the overall recycling efficiency is low.
By establishing a four-dimensional resource health comprehensive scoring system, a comprehensive score is given from four dimensions: hardware basic health, performance degradation degree, historical fault records, and network connectivity quality. Based on the score, different levels of resource recycling processes are determined, including rapid recycling, standard recycling, prudent recycling, and scrap recycling, so as to achieve differentiated recycling of cloud network resources.
It enables differentiated recycling of cloud network resources, reduces recycling cycle and hardware monitoring consumption, and improves resource recycling efficiency.
Smart Images

Figure CN123123288A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of computer software technology, and in particular to a resource recycling method, apparatus, equipment, medium, and program product. Background Technology
[0002] With the continuous development of cloud-network convergence technology and the rapid expansion of data center resources, efficient recycling and reuse of cloud and network resources has become the key to cost reduction and efficiency improvement in the industry.
[0003] In existing technologies, the homogeneous periodic cloud network resource recycling solution identifies and marks the resources to be recycled and moves them into the recycling isolation domain. Then, it waits in a static state according to a preset waiting period. After the waiting period expires, it sequentially performs business disconnection, permission stripping, data erasure, and resource status reset operations, and finally releases the resources to be recycled and returns them to the public resource pool for business rescheduling.
[0004] However, the above solution uses a uniform preset waiting period to wait for the resources to be recycled, so that resources with different hardware performance and different aging levels perform the same recycling steps and waiting period. Aging and low-performance hardware occupies the recycling isolation domain and public resource pool space for a long time, which cannot achieve differentiated and rapid release, resulting in the ineffective occupation of resource pool space and low overall cloud network resource recycling efficiency. Summary of the Invention
[0005] This application provides a resource recycling method, apparatus, equipment, medium, and program product for improving the recycling efficiency of cloud network resources.
[0006] In a first aspect, embodiments of this application provide a resource reclamation method, which includes: obtaining a health score for each cloud network resource dimension corresponding to the cloud network resource, wherein the cloud network resource dimension includes at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension; performing a weighted summation of the health scores for each cloud network resource dimension to obtain a reclamation score, and determining the health level of the cloud network resource according to the reclamation score; different health levels correspond to different resource reclamation processes; and reclaiming the cloud network resource based on the health level and using the resource reclamation process corresponding to the health level.
[0007] The technical solution provided in this application brings at least the following beneficial effects: By establishing a four-dimensional comprehensive resource health scoring system, a comprehensive score is given from four dimensions: hardware basic health, performance degradation degree, historical fault records, and network connectivity quality. Based on the recycling score, different resource recycling processes are implemented for cloud network resources. The recycling cycle, hardware detection method, and confirmation time are different for different levels of cloud network resources, thereby achieving differentiated recycling of all recyclable resources, reducing the recycling cycle and hardware monitoring resource consumption, thus greatly improving the recycling efficiency of cloud network resources.
[0008] One possible implementation is to reclaim cloud network resources based on the health level and using the resource reclamation process corresponding to the health level. This includes: determining the resource reclamation process as a fast reclamation process when the health level is at the first level; performing indicator sampling and verification on the cloud network resources; and if the cloud network resources pass the indicator sampling and verification, then reclaiming the cloud network resources to the resource reclamation pool corresponding to the first level.
[0009] Another possible implementation is to reclaim cloud network resources based on the health level and using the resource reclamation process corresponding to the health level. This includes: determining the resource reclamation process as a standard reclamation process when the health level is level two; performing full-component routine verification on all resources in the cloud network; and if the cloud network resources pass the full-component routine verification, then reclaiming the cloud network resources to the resource reclamation pool corresponding to level two.
[0010] Another possible implementation is to reclaim cloud network resources based on the health level and using the corresponding resource reclamation process. This includes: determining the resource reclamation process as a prudent reclamation process when the health level is level three; performing a first verification on all resources in the cloud network, which includes: full component deep detection, bad block masking, and firmware upgrade; and if the cloud network resources pass the first verification, then reclaiming the cloud network resources to the resource reclamation pool corresponding to level three.
[0011] Another possible implementation is to recycle cloud network resources based on the health level and using the resource recycling process corresponding to the health level. This includes: when the health level is level four, determining that the resource recycling process is an approval recycling process; performing a second verification on all resources in the cloud network, which includes: resource obsolescence detection and dismantling of usable components; if the cloud network resources pass the second verification, then recycling the cloud network resources to the resource recycling pool corresponding to level four.
[0012] Another possible implementation, after the above-mentioned resource reclamation process based on health level to reclaim cloud network resources, further includes: when a first service is detected, determining the service execution priority of the first service based on the service attribute information of the first service; determining a first resource reclamation pool that matches the service execution priority based on the service execution priority corresponding to the first service; and allocating cloud network resources corresponding to the service execution requirement information from the first resource reclamation pool for the first service based on the service execution requirement information of the first service.
[0013] Secondly, embodiments of this application provide a resource scheduling apparatus, including: an acquisition module, a processing module, and a recycling module. The acquisition module is used to acquire a health score for each cloud network resource dimension, wherein the cloud network resource dimension includes at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension. The processing module is used to perform a weighted summation of the health scores for each cloud network resource dimension to obtain a recycling score, and determine the health level of the cloud network resource according to the recycling score; different health levels correspond to different resource recycling processes. The recycling module is used to recycle the cloud network resource based on the health level and using the resource recycling process corresponding to the health level.
[0014] One possible implementation is that the aforementioned processing module is specifically used to determine that the resource recycling process is a fast recycling process when the health level is at the first level; and to perform indicator sampling and verification on the cloud network resources; if the cloud network resources pass the indicator sampling and verification, then the cloud network resources are recycled to the resource recycling pool corresponding to the first level.
[0015] Another possible implementation is that the aforementioned processing module is specifically used to determine the resource recycling process as a standard recycling process when the health level is level two; and to perform a full-component routine check on all resources in the cloud network resources; if the cloud network resources pass the full-component routine check, then the cloud network resources are recycled to the resource recycling pool corresponding to level two.
[0016] Another possible implementation is that the above processing module is specifically used to determine that the resource recycling process is a prudent recycling process when the health level is level three; and to perform a first verification on all resources in the cloud network resources, which includes: full component deep detection, bad block masking processing and firmware upgrade; if the cloud network resources pass the first verification, the cloud network resources are recycled to the resource recycling pool corresponding to level three.
[0017] Another possible implementation is that the above processing module is specifically used to determine the resource recycling process as an approval recycling process when the health level is level four; and to perform a second verification on all resources in the cloud network resources, the second verification including: resource scrap detection and dismantling of usable components; if the cloud network resources pass the second verification, the cloud network resources are recycled to the resource recycling pool corresponding to level four.
[0018] In another possible implementation, the resource recycling device further includes a determining module, which is used to recycle cloud network resources based on the health level and the corresponding resource recycling process. After recycling the cloud network resources, if a first service is detected, the module determines the service execution priority of the first service based on the service attribute information of the first service; and determines a first resource recycling pool that matches the service execution priority based on the service execution priority of the first service. The processing module is also used to allocate cloud network resources corresponding to the service execution requirement information from the first resource recycling pool to the first service based on the service execution requirement information of the first service.
[0019] Thirdly, this application provides an electronic device comprising: a processor and a memory; the memory stores a program or instructions executable on the processor, wherein the program or instructions, when executed by the processor, implement the method of the first aspect described above.
[0020] Fourthly, this application provides a readable storage medium on which a program or instructions are stored, which, when executed by a computer, implement the method of the first aspect described above.
[0021] Fifthly, this application provides a computer program product stored in a storage medium, which, when executed by a computer, implements the method described in the first aspect.
[0022] In a sixth aspect, embodiments of this application provide a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.
[0023] The beneficial effects of the second to sixth aspects mentioned above are described in the corresponding description of the first aspect and will not be repeated here. Attached Figure Description
[0024] Figure 1 A schematic diagram of the network architecture for an application of a resource recycling method provided in this application embodiment;
[0025] Figure 2 A schematic flowchart of a resource recycling method provided in an embodiment of this application;
[0026] Figure 3A schematic flowchart illustrating another resource recycling method provided in an embodiment of this application;
[0027] Figure 4 A schematic flowchart illustrating another resource recycling method provided in this application embodiment;
[0028] Figure 5 A schematic flowchart illustrating another resource recycling method provided in this application embodiment;
[0029] Figure 6 A schematic flowchart illustrating another resource recycling method provided in this application embodiment;
[0030] Figure 7 A schematic flowchart illustrating another resource recycling method provided in this application embodiment;
[0031] Figure 8 This is a schematic diagram of the structure of a resource recycling system provided in an embodiment of this application;
[0032] Figure 9 This is a schematic diagram of the structure of a resource recycling device provided in an embodiment of this application;
[0033] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0034] The resource recovery method, apparatus, equipment, medium, and procedure products provided in this application will now be described in detail with reference to the accompanying drawings.
[0035] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0036] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0037] The terms "at least one," "at least one of," etc., used in the specification and claims of this application refer to any one, any two, or a combination of two or more of the included items. For example, at least one of a, b, and c can mean: "a," "b," "c," "a and b," "a and c," "b and c," and "a, b, and c," where a, b, and c can be single or multiple. Similarly, "at least two" refers to two or more items, and its meaning is similar to that of "at least one."
[0038] In the description of this application, unless otherwise stated, "a plurality of" means two or more.
[0039] The resource recycling method, apparatus, equipment, medium, and program products provided in this application embodiment can be applied to cloud network resource recycling scenarios.
[0040] With the deepening development of cloud-network convergence, the resource scale of data centers is growing exponentially. The recycling and reuse of cloud and network resources has become an important technical means for operators and cloud vendors to reduce costs and increase efficiency. How to achieve efficient and reasonable recycling and redistribution of cloud and network resources has also become a research focus in this field.
[0041] In existing technologies, cloud network resource recycling solutions mainly identify idle resources based on resource operation index thresholds, and clean up expired and zombie resources through scheduled tasks. At the same time, they combine application operation status and device health status to determine the timing of recycling, and complete the hierarchical recycling scheduling of storage resources based on storage cluster metadata and topology. The recycled resources are uniformly included in the public resource pool for business calls and reuse.
[0042] However, the aforementioned existing technologies have a relatively singular assessment dimension for resource health, making it difficult to fully represent the actual operating status of resources; the recycling process adopts a uniform processing mode, which cannot take into account both recycling efficiency and recycling security; after recycling, resources are not differentiated and are put into the public resource pool, which can easily lead to resource mismatch; at the same time, there is a lack of a closed-loop management mechanism for recycling effect evaluation and self-optimization, and recycling-related parameters and rules cannot be iteratively adjusted according to actual operating conditions, resulting in poor overall recycling and reuse effect of cloud network resources.
[0043] To address the aforementioned technical issues, this application provides a resource recycling method, apparatus, equipment, medium, and program product. By establishing a four-dimensional comprehensive resource health scoring system, a comprehensive score is given from four dimensions: hardware basic health, performance degradation degree, historical fault records, and network connectivity quality. Based on the recycling score, different resource recycling processes are implemented for cloud network resources. The recycling cycle, hardware detection method, and confirmation time are different for different levels of cloud network resources, thereby achieving differentiated recycling of all recyclable resources, reducing the recycling cycle and hardware monitoring resource consumption, and thus greatly improving the recycling efficiency of cloud network resources.
[0044] The resource recycling methods, apparatus, equipment, media, and program products provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0045] Figure 1 The network architecture for a resource recycling method application provided in an embodiment of this application is illustrated. For example... Figure 1 As shown, the network architecture includes a resource recycling device 101 and a terminal device 102. The resource recycling device 101 and the terminal device 102 are interconnected.
[0046] In some embodiments, the resource recycling device 101 may be a server, a computer, or a processor or processing unit within a server or computer. The server may be a single server or a server cluster comprising multiple servers. It should be noted that the embodiments of this application do not limit the specific device form of the resource recycling device 101. Figure 1 The resource recycling device 101 is used as an example of a single server.
[0047] In some embodiments, the terminal device may be a mobile phone, tablet computer, laptop computer, handheld computer, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, personal computer (PC), ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., and the embodiments of this application do not specifically limit it. Figure 1 The example shown is a mobile phone, with terminal device 102 as an example.
[0048] In some embodiments, terminal device 102 sends cloud network resources to resource recycling device 101, and resource recycling device 101 receives the cloud network resources sent by terminal device 102; resource recycling device 101 obtains the health score of each cloud network resource dimension corresponding to the cloud network resources, wherein the cloud network resource dimension includes at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension; resource recycling device 101 performs a weighted summation of the health scores of each cloud network resource dimension to obtain a recycling score, and determines the health level of the cloud network resources according to the recycling score; different health levels correspond to different resource recycling processes; resource recycling device 101 recycles the cloud network resources based on the health level and adopts the resource recycling process corresponding to the health level.
[0049] It should be noted that the network architecture described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As network architectures evolve, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.
[0050] See Figure 2 This is a schematic flowchart of a resource recycling method provided in an embodiment of this application. Figure 2 As shown, the resource recycling method provided in this application embodiment can be implemented by the above-mentioned resource recycling device, specifically including the following steps 201 to 203.
[0051] Step 201: The resource recycling device obtains the health score of each cloud network resource dimension corresponding to the cloud network resource.
[0052] In some embodiments, the cloud network resource dimensions mentioned above include at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension.
[0053] In some embodiments, the above-mentioned hardware health dimensions are used to characterize the degree of aging and wear of the hardware corresponding to the cloud network resources, the in-situ status of components, and the abnormal status of hardware alarms, reflecting the basic hardware operating health status of the cloud network resources.
[0054] In some embodiments, the above-mentioned performance degradation dimension is used to characterize the degree of degradation of key performance indicators such as central processing unit (CPU), memory, and disk input / output (I / O) during the operation of cloud network resources, and reflects the real-time performance operation status of cloud network resources.
[0055] In some embodiments, the aforementioned historical fault record dimension is used to characterize the past fault types, fault occurrence frequency, and fault repair record information of cloud network resources, reflecting the long-term operational stability of cloud network resources.
[0056] In some embodiments, the above-mentioned network connectivity quality dimension is used to characterize the network latency, packet loss rate, and link connectivity stability corresponding to cloud network resources, reflecting the network transmission service capabilities of cloud network resources.
[0057] In some embodiments, the resource recycling device can score the health of various indicators based on hardware health, performance degradation, historical fault records, and network connectivity quality.
[0058] In some embodiments, the above-mentioned indicators include at least one of the following: computing resource indicators, storage resource indicators, and network resource indicators.
[0059] In some embodiments, the resource recycling device can pre-configure the indicator weights, optimal benchmark values and worst benchmark values for each sub-indicator of the resource indicators, storage resource indicators and network resource indicators under the hardware health dimension, and collect the actual indicator values of the cloud network resources to be evaluated. Based on the indicator values of the above sub-indicators, the individual score of the sub-indicator is calculated. If the sub-indicator is a positive indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (1).
[0060] Score = (Actual value - Worst baseline value) / (Best baseline value - Worst baseline value) × 100 (1)
[0061] If the sub-indicator is a reverse indicator, the specific calculation process of the sub-indicator's individual score is shown in formula (2).
[0062] Score = (Optimal benchmark value - Actual value) / (Optimal benchmark value - Worst benchmark value) × 100 (2)
[0063] The health score of the cloud network resource hardware health dimension is obtained by multiplying the individual scores of each sub-indicator by their corresponding weights and then summing the results.
[0064] Among them, the above positive indicators are sub-indicators in which the larger the value of the indicator belongs to the cloud network resource dimension, the higher the health score of the cloud network resource in that dimension; the above negative indicators are sub-indicators in which the larger the value of the indicator belongs to the cloud network resource dimension, the lower the health score of the cloud network resource in that dimension.
[0065] In some embodiments, the optimal benchmark value is the reference value corresponding to the optimal operating state of the sub-indicator, and the worst benchmark value is the reference value corresponding to the unacceptable deterioration of the operating state of the sub-indicator. All benchmark values are taken from the nominal value of the equipment at the factory and the industry-standard threshold. The actual values of all indicators are truncated with upper and lower limits.
[0066] In some embodiments, the weights of the sub-indicators configured above can be preset by the resource recycling device; or, user-defined. The specific weights can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.
[0067] For example, the weight of the above sub-indicators can be 0.5, 0.4 or 0.3, etc.
[0068] In some embodiments, the optimal benchmark value of the above-mentioned sub-indicators can be preset by the resource recycling device; or, user-defined. The specific value can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.
[0069] In some embodiments, the worst-case benchmark value of the above-mentioned sub-indicators can be preset by the resource recycling device; or, user-defined. The specific value can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.
[0070] In some embodiments, the computing resource sub-indicators of the above hardware health dimension include at least one of the following: service life, number of CPU / memory hardware defects, power supply or fan health status, etc.
[0071] In some embodiments, the storage resource sub-indicators of the above hardware health dimension include at least one of the following: service life, number of bad sectors using Self-Monitoring, Analysis and Reporting Technology (SMART), and health status of the storage controller.
[0072] In some embodiments, the storage resource sub-indicators of the above hardware health dimension include at least one of the following: optical module service life, port hardware bit error rate, board health status, etc.
[0073] In some embodiments, the resource recycling device can pre-configure the indicator weights, optimal benchmark values, and worst benchmark values for each sub-indicator of the resource indicators, storage resource indicators, and network resource indicators under the performance degradation dimension, and collect the actual indicator values of the cloud network resources to be evaluated. Based on the indicator values of the above sub-indicators, the individual score of the sub-indicator is calculated. If the sub-indicator is a positive indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (1). If the sub-indicator is a negative indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (2). The individual scores of each sub-indicator are multiplied by their corresponding weights and then weighted and summed to obtain the health score of the above cloud network resource performance degradation dimension.
[0074] In some embodiments, the computing resource sub-indicators of the above-mentioned performance degradation dimension include at least one of the following: CPU computing power baseline degradation rate and memory read / write bandwidth degradation rate, etc.
[0075] In some embodiments, the storage resource sub-metrics of the above-mentioned performance degradation dimension include at least one of the following: disk input / output operations per second (IOPS) degradation rate and throughput degradation rate, etc.
[0076] In some embodiments, the storage resource sub-metrics of the above-mentioned performance degradation dimension include at least one of the following: port throughput degradation rate and forwarding latency increment, etc.
[0077] In some embodiments, the resource recycling device can pre-configure the indicator weights, optimal benchmark values, and worst benchmark values for each sub-indicator of the resource indicators, storage resource indicators, and network resource indicators under the historical fault record dimension, and collect the actual indicator values of the cloud network resources to be evaluated. Based on the indicator values of the above sub-indicators, the individual score of the sub-indicator is calculated. If the sub-indicator is a positive indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (1). If the sub-indicator is a negative indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (2). The individual scores of each sub-indicator are multiplied by their corresponding weights and then weighted and summed to obtain the health score of the above cloud network resource historical fault record dimension.
[0078] In some embodiments, the computing resource sub-indicators of the above-mentioned historical fault record dimension include at least one of the following: number of hardware failures in the past 12 months, mean time between failures, and percentage of serious failures.
[0079] In some embodiments, the storage resource sub-metrics of the above-mentioned historical fault record dimension include at least one of the following: the number of disk failures in the past 12 months and the downtime of the storage cluster, etc.
[0080] In some embodiments, the storage resource sub-metrics of the above-mentioned historical fault record dimension include at least one of the following: the number of port outages and the duration of link interruptions in the past 12 months.
[0081] In some embodiments, the resource recycling device can pre-configure the indicator weights, optimal benchmark values, and worst benchmark values for each sub-indicator of the resource indicators, storage resource indicators, and network resource indicators under the network connectivity quality dimension, and collect the actual indicator values of the cloud network resources to be evaluated. Based on the indicator values of the above sub-indicators, the individual score of the sub-indicator is calculated. If the sub-indicator is a positive indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (1). If the sub-indicator is a negative indicator, the specific calculation process of the individual score of the sub-indicator is shown in formula (2). The individual scores of each sub-indicator are multiplied by their corresponding weights and then weighted and summed to obtain the health score of the above cloud network resource network connectivity quality dimension.
[0082] In some embodiments, the computational resource sub-indicators of the above-mentioned network connectivity quality dimension include at least one of the following: average uplink port latency, packet loss rate, jitter, and bit error rate.
[0083] In some embodiments, the storage resource sub-indicators of the above-mentioned network connectivity quality dimension include at least one of the following: storage front-end link latency and packet loss rate, etc.
[0084] In some embodiments, the storage resource sub-indicators of the above-mentioned network connectivity quality dimension include at least one of the following: port latency, packet loss rate, and link availability.
[0085] Step 202: The resource recycling device performs a weighted summation of the health scores for each cloud network resource dimension to obtain a recycling score, and determines the health level of the cloud network resource according to the recycling score.
[0086] In some embodiments, different health levels correspond to different resource recycling processes.
[0087] In some embodiments, the resource recycling device can normalize and weight the health score of each cloud network resource dimension to obtain a recycling score, and determine the health level of the cloud network resource according to the preset mapping relationship between the level and the recycling score interval. The specific recycling score calculation process is shown in formula (3).
[0088] Recovery score = Health score of hardware health dimension × 30% + Health score of performance degradation dimension × 30% + Health score of historical fault record dimension × 20% + Health score of network connectivity quality dimension × 20% (3)
[0089] In some embodiments, the resource recycling device can pre-configure multiple resource levels based on the hardware status, performance capabilities, and reusability value of cloud network resources, and set corresponding recycling score threshold ranges for each resource level to obtain a preset mapping relationship between the levels and recycling score ranges. The device then compares the comprehensive recycling score of the cloud network resources with the recycling score threshold ranges corresponding to each resource level, and classifies the cloud network resources into the corresponding resource levels based on the threshold range into which the comprehensive recycling score falls.
[0090] In some embodiments, the resource levels described above can be preset by the resource recycling device or user-defined. The specific level can be determined according to actual usage requirements, and this application embodiment does not impose any limitations. The recycling scoring threshold ranges corresponding to each resource level can be preset by the resource recycling device or user-defined. The specific level can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.
[0091] For example, the resource levels and the corresponding recycling score threshold ranges for each resource level can be: 90-100 points: Level A; 70-89 points: Level B; 50-69 points: Level C; <50 points: Level D.
[0092] Step 203: Based on the health level, the resource recycling device uses the resource recycling process corresponding to the health level to recycle cloud network resources.
[0093] In some embodiments, the resource recycling device can match the corresponding recycling process according to the health level of the cloud network resource, notify the tenant, lock the resource after the tenant has no objection, erase the data, detect and repair the hardware where the cloud network resource is located, and then return the resource to the pool.
[0094] In some embodiments, the above-described recycling process includes at least one of the following: a rapid recycling process, a standard recycling process, a prudent recycling process, and an end-of-life recycling process.
[0095] For example, when the resource level is A, a fast recycling process is executed; when the resource level is B, a standard recycling process is executed; when the resource level is C, a prudent recycling process is executed; and when the resource level is D, an end-of-life recycling process is executed.
[0096] In some embodiments, the resource recycling device may send a recycling notice to the tenant to which the resource belongs and start a tenant confirmation countdown.
[0097] In some embodiments, the countdown timer confirmed by the tenant can be that of a resource recycling device; or, it can be user-defined. The specific duration can be determined based on actual usage needs, and this application embodiment does not impose any limitations.
[0098] For example, the countdown duration confirmed by the tenant can be 24h, 48h, or 72h, etc.
[0099] In some embodiments, the resource recycling device can listen for tenant feedback during the confirmation period. When the confirmation period ends and no objection instruction is received from the tenant, the resource recycling device cuts off the service access link of the cloud network resource, releases the calling relationship between the upper layer service and the cloud network resource, and realizes resource locking.
[0100] In some embodiments, the resource reclamation device can clear the tenant-specific Virtual Local Area Network (VLAN), Virtual Extensible LAN-Network Identifier (VXLAN VNI), security group, and Access Control List (ACL) policy configurations on the corresponding ports of the cloud network resources, and reclaim network service resources such as Internet Protocol (IP) addresses, Network Address Translation (NAT) mappings, and load balancing nodes allocated for the tenant's services.
[0101] In some embodiments, the resource recycling device can place the recycled cloud network resources into a resource pool corresponding to the health level of the cloud network resources.
[0102] In some embodiments, the resource pool described above may be a resource recycling device; or, it may be user-defined. The specific configuration can be determined based on actual usage requirements, and this application embodiment does not impose any limitations.
[0103] For example, the resource pool mentioned above can be a Class A resource pool, a Class B resource pool, and a Class C resource pool, etc. When the resource level is A, it is recycled to the Class A resource pool; when the resource level is B, it is recycled to the Class B resource pool; when the resource level is C, it is recycled to the Class C resource pool; and when the resource level is D, it is recycled to the scrap resource repository.
[0104] In some embodiments, the resource recycling device can update the network topology ledger after the resource recycling is completed, and mark the service ports corresponding to the cloud network resources as pending reuse.
[0105] In the resource recycling method provided in this application embodiment, a health score for each cloud network resource dimension is obtained. The cloud network resource dimensions include at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension. The health scores for each cloud network resource dimension are weighted and summed to obtain a recycling score. Based on the recycling score, the health level of the cloud network resource is determined. Different health levels correspond to different resource recycling processes. Based on the health level, the corresponding resource recycling process is used to recycle the cloud network resource. In this solution, a four-dimensional comprehensive resource health scoring system is established, comprehensively scoring from four dimensions: basic hardware health, performance degradation degree, historical fault record, and network connectivity quality. Different resource recycling processes are implemented for cloud network resources based on the recycling score. The recycling cycle, hardware detection method, and confirmation time are different for different levels of cloud network resources, thereby achieving differentiated recycling of all recyclable resources, reducing the recycling cycle and hardware monitoring resource consumption, and thus greatly improving the recycling efficiency of cloud network resources.
[0106] In some embodiments, combined with Figure 2 ,like Figure 3 As shown, step 203 above can be implemented through steps 301 and 303 as follows.
[0107] Step 301: When the health level is at Level 1, the resource recycling device determines the resource recycling process to be a rapid recycling process.
[0108] In some embodiments, the first level mentioned above is a high health level of cloud network resources.
[0109] In some embodiments, a fast recycling process can be characterized as a simplified recycling process performed on cloud network resources with high health levels to be recycled.
[0110] In some embodiments, the resource recycling device is pre-configured with a mapping relationship between the health level of cloud network resources and the resource recycling process. The resource recycling device can determine the resource recycling process corresponding to the cloud network resource as a fast recycling process based on the target health level of the cloud network resource to be recycled and the preset mapping relationship between the health level and the recycling process.
[0111] Step 302: The resource recycling device performs random checks and verifications on the cloud network resources.
[0112] In some embodiments, the resource recycling device can perform rapid power-on self-test and random sampling of key indicators for the cloud network resources to be recycled.
[0113] In some embodiments, the resource recycling device can issue a power-on self-test command to the cloud network resources to be recycled, wake up the cloud network resource hardware unit to power on and run, collect the first operating parameters of all hardware components under the instantaneous power-on condition, and compare the collected first operating parameters at the instantaneous power-on with the preset normal hardware threshold to obtain the rapid power-on self-test result.
[0114] For example, if the first operating parameters of each hardware component at the moment of power-on all meet the normal hardware threshold, the cloud network resource is determined to have passed the fast power-on self-test; if the first operating parameter of any hardware component at the moment of power-on exceeds the normal hardware threshold, the cloud network resource is determined to have failed the fast power-on self-test, and a hardware abnormality alarm message is output.
[0115] In some embodiments, the aforementioned "all components" can be characterized as all hardware components included in the cloud network resources.
[0116] In some embodiments, the above-mentioned components include at least one of the following: power module, cooling fan, disk component, motherboard, optical module, and service port device.
[0117] In some embodiments, the first operating parameters of the entire component can be characterized as quantitative parameters that are collected at the moment of power-on self-test and reflect the real-time working performance of each hardware component at the moment of power-on.
[0118] In some embodiments, the first operating parameters of the above-mentioned components include at least one of the following: component operating temperature at power-on, component load rate at power-on, disk read / write error count at power-on, optical module transmit optical power at power-on, optical module receive optical power at power-on, fan speed at power-on, and power supply output voltage at power-on.
[0119] In some embodiments, the aforementioned hardware normal threshold can be preset by the resource recycling device; or, it can be user-defined. The specific threshold can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.
[0120] For example, the above-mentioned normal hardware thresholds can be that the operating temperature of the component at the moment of power-on is not greater than 65 degrees Celsius, the disk read / write error count is equal to zero, and the fan speed is not less than 3,000 revolutions per minute.
[0121] In some embodiments, the resource recycling device may select some key sub-indicators under the resource type of the cloud network resource as sampling inspection objects, collect the actual operating values of the sampling inspection objects, compare the actual operating values with the preset sampling inspection qualification threshold, and obtain the indicator sampling inspection results.
[0122] For example, if all sampled objects meet the sampling pass threshold, the sampling of the key indicators of the cloud network resource is deemed to have passed; if any sampled object exceeds the sampling pass threshold, the sampling of the key indicators of the cloud network resource is deemed to have failed, and a resource anomaly prompt message is output.
[0123] In some embodiments, the aforementioned key sub-indicators are core monitoring parameters for verifying the operational health status of cloud network resources.
[0124] In some embodiments, the aforementioned key sub-indicators include at least one of the following: CPU utilization, memory utilization, and mean time between failures (MTBF).
[0125] Step 303: If the cloud network resources pass the indicator sampling and verification, the resource recycling device will recycle the cloud network resources to the resource recycling pool corresponding to the first level.
[0126] In some embodiments, the resource recycling device may modify the resource status marker of the cloud network resource verified by indicator sampling to a schedulable reuse status, and register the resource registration information of the cloud network resource to the resource recycling pool corresponding to the first level; update the resource statistics list of the resource recycling pool, and complete the registration of the cloud network resource into the pool.
[0127] In some embodiments, the resource status of cloud network resources can be characterized as a status marker used to record the current working stage of the cloud network resources.
[0128] In some embodiments, the resource status of cloud network resources may include at least one of the following: pending recycling status, recycling confirmation status, pending reuse status, pooled and schedulable status, fault unavailable status, etc.
[0129] In some embodiments, the resource registration information of the cloud network resources described above can be used to characterize descriptive data used for registering, managing and scheduling cloud network resources.
[0130] In some embodiments, the resource registration information of the cloud network resources may include at least one of the following: unique identifier of cloud network resources, resource level identifier, resource type, hardware parameter information, resource status, resource recycling pool number, etc.
[0131] In some embodiments, the cloud network resource unique identifier is used to uniquely identify a single cloud network resource, the resource level identifier is used to mark the health level to which the cloud network resource belongs, the resource type indicates whether the cloud network resource belongs to computing, storage or network resources, the hardware parameter information records the hardware specifications of the cloud network resource, the resource status records the current working status of the cloud network resource, and the resource recycling pool number is used to mark the target resource recycling pool to which the cloud network resource belongs.
[0132] In this way, by establishing a fast recycling channel for cloud network resources with high health levels, redundant hardware deep detection processes are eliminated, the tenant recycling confirmation cycle is shortened, and recycling processing time is reduced. This allows cloud network resources in good health to be quickly released back to the resource recycling pool, improving the turnover and reuse efficiency of cloud network resources.
[0133] In some embodiments, combined with Figure 2 ,like Figure 4 As shown, step 203 above can be implemented through steps 401 and 403 as follows.
[0134] Step 401: When the health level is Level 2, the resource recycling device determines the resource recycling process to be the standard recycling process.
[0135] In some embodiments, the second level is a medium health level of cloud network resources.
[0136] In some embodiments, a standard recycling process can be characterized as a standardized recycling process performed on cloud network resources to be recycled for a medium health level.
[0137] In some embodiments, the resource recycling device is pre-configured with a mapping relationship between the health level of cloud network resources and the resource recycling process. The resource recycling device can determine the resource recycling process corresponding to the cloud network resource as a standard recycling process based on the target health level of the cloud network resource to be recycled and in combination with the preset mapping relationship between the health level and the recycling process.
[0138] Step 402: The resource recycling device performs a full-component routine check on all resources in the cloud network.
[0139] In some embodiments, the above-mentioned routine monitoring can be characterized as a standardized collection and threshold comparison verification operation of the working status and second operating parameters of each hardware component. The monitoring objects of routine monitoring include component power supply status, component operating temperature, component fault alarm signal, and component performance parameters.
[0140] In some embodiments, the resource recycling device can traverse all hardware components within the cloud network resources to be recycled, and sequentially issue status collection instructions to each hardware component, and collect the second operating parameters and hardware status information of all components respectively, and compare the collected second operating parameters of each component with the preset normal operating threshold of the component respectively.
[0141] For example, if the second operating parameters of all hardware components meet the normal operating threshold of the components, the normal verification of all components is determined to be passed; if the second operating parameter of any hardware component exceeds the normal operating threshold of the components, the normal verification of all components is determined to be failed, the abnormal component identifier is recorded and the hardware abnormal alarm information is output.
[0142] In some embodiments, the second operating parameter of the entire component can be characterized as a quantitative parameter reflecting the real-time working performance of each hardware component, which is steady-state quantitative data collected under continuous operating conditions.
[0143] In some embodiments, the second operating parameters of the entire component include at least one of the following: component operating temperature, component load rate, disk read / write error count, optical module transmit optical power, optical module receive optical power, fan speed, and power supply output voltage.
[0144] In some embodiments, the hardware status information described above can be characterized as status identification information indicating whether a hardware component has malfunctioned.
[0145] Step 403: If the cloud network resources pass the routine full component verification, the resource recycling device will recycle the cloud network resources to the resource recycling pool corresponding to the second level.
[0146] In some embodiments, the resource recycling device may modify the resource status mark of the cloud network resource through the routine full-component verification to a schedulable reuse status, and register the resource registration information of the cloud network resource to the resource recycling pool corresponding to the second level; update the resource statistics list of the resource recycling pool, and complete the registration of the cloud network resource into the pool.
[0147] In this way, the selection criteria for recycling medium-health resources will be used, and the operating parameters and hardware status information of each hardware component will be collected through a complete traversal to comprehensively investigate potential hidden hardware faults. This will prevent cloud network resources with potential problems from directly flowing into the resource recycling pool. Compared with the lightweight sampling inspection mode of the rapid recycling process, this can improve the reliability of recycling and reusing medium-health cloud network resources.
[0148] In some embodiments, combined with Figure 2 ,like Figure 5 As shown, step 203 above can be implemented through steps 501 and 503 as follows.
[0149] Step 501: When the health level is Level 3, the resource recycling device determines the resource recycling process to be a prudent recycling process.
[0150] In some embodiments, the third level mentioned above is a low health level of cloud network resources.
[0151] In some embodiments, a prudent recycling process can be characterized as a prudent recycling process performed on cloud network resources with low health levels to be recycled.
[0152] In some embodiments, the resource recycling device may be pre-configured with a mapping relationship between the health level of cloud network resources and the resource recycling process. The resource recycling device may determine the resource recycling process corresponding to the cloud network resource as a prudent recycling process based on the target health level of the cloud network resource to be recycled and in combination with the preset mapping relationship between the health level and the recycling process.
[0153] Step 502: The resource recycling device performs a first verification on all resources in the cloud network. The first verification includes: full component deep detection, bad block masking processing, and firmware upgrade.
[0154] In some embodiments, the resource recycling device sends deep detection commands to each hardware component of the cloud network resource to be recycled, triggering the hardware to complete multi-dimensional functional verification, and continuously collecting the second operating parameters and hardware status information of all components for a long time. Then, it conducts stress simulation tests, applies simulated business loads to the cloud network resource, and obtains the performance of the hardware components under load conditions. The steady-state parameters and parameters under stress conditions corresponding to the cloud network resource are extracted respectively, and the steady-state parameters and parameters under stress conditions are compared with the preset depth detection qualification threshold to obtain the depth detection results of all components.
[0155] For example, if all hardware components meet the depth detection qualification threshold under steady-state and pressure conditions, the depth detection of all components is deemed to have passed; if any hardware component does not meet the depth detection qualification threshold, the depth detection of all components is deemed to have failed, and the location and type of the abnormal component are recorded.
[0156] In some embodiments, the above-mentioned multi-dimensional functional verification can be characterized as a comprehensive verification operation performed by the hardware component on its own basic hardware functions, circuit paths, and register states.
[0157] In some embodiments, the above-mentioned multi-dimensional functional verification includes at least one of the following: component in-situ identification verification, register verification, loop connectivity detection, read / write loopback test, and fault flag bit reading verification.
[0158] In some embodiments, the aforementioned service load can be characterized as simulated service pressure exerted by real services running on simulated cloud network resources.
[0159] In some embodiments, the above-mentioned service load includes at least one of the following: computing power load, disk read / write input / output (I / O) load, and network port traffic load, etc.
[0160] In some embodiments, the performance of hardware components under the above-mentioned load conditions can be characterized as various feedback results output during the process of hardware bearing simulated service load.
[0161] In some embodiments, the performance of the hardware components under the above-mentioned load conditions includes at least one of the following: component operating temperature under load, service processing latency, service packet loss, IO response time, and component error events.
[0162] In some embodiments, the above-mentioned steady-state parameters can be characterized as hardware operating parameters collected when the cloud network resources are in an idle and stable operating state without being subjected to simulated service loads.
[0163] In some embodiments, the above-mentioned steady-state parameters include at least one of the following: idle component temperature, idle fan speed, idle power supply output voltage, and idle optical module optical power, etc.
[0164] In some embodiments, the parameters under the aforementioned stress conditions can be characterized as hardware operating parameters collected when cloud network resources apply simulated service loads and are in a stress test running state.
[0165] In some embodiments, the parameters under the above-mentioned pressure conditions include at least one of the following: peak component temperature after pressurization, high load fan speed fluctuation, high load power supply voltage fluctuation, and optical module optical power offset under high flow rate.
[0166] In some embodiments, the resource recycling device can read the disk bad block scan results, locate the physical and logical bad block addresses of the cloud network resource disk media, write the bad block addresses into a mask list to prohibit reading and writing to them, and synchronously update the disk registration information.
[0167] For example, when the number of bad blocks exceeds a preset upper limit threshold, the repair is deemed invalid and a disk failure message is output.
[0168] In some embodiments, the disk medium described above can be characterized as a hardware carrier that performs data storage functions within cloud network resources.
[0169] In some embodiments, the disk media mentioned above include hard disk drives (HDDs) and solid-state drives (SSDs).
[0170] In some embodiments, the aforementioned bad blocks on the disk can be characterized as storage units in the disk storage medium that cannot complete read / write operations normally.
[0171] In some embodiments, the aforementioned bad blocks on the disk include physical bad blocks, logical bad blocks, etc.
[0172] In some embodiments, the aforementioned mask list may be characterized as a list of addresses maintained locally by the disk, used to record the storage addresses of bad blocks that need to be isolated, and the disk may skip read and write requests for the corresponding addresses based on the list.
[0173] In some embodiments, the disk registration information described above can be characterized as resource ledger information that registers the disk hardware status.
[0174] In some embodiments, the disk registration information may include at least one of the following: disk model, disk capacity, number of masked bad blocks, bad block address range, and disk health markers.
[0175] In some embodiments, the resource recycling device can read the current firmware version of the cloud network resource, retrieve the matching target firmware and complete packet verification, issue an instruction to burn the firmware and then restart the hardware to upgrade the current firmware version.
[0176] In some embodiments, the current firmware version can be characterized as the firmware version identifier currently running on the cloud network resource hardware component.
[0177] In some embodiments, the firmware version includes a major version number, a minor version number, and a revision number.
[0178] In some embodiments, the resource recycling device can index the firmware version library based on the hardware model of the cloud network resource and filter the target firmware package that is compatible with the hardware model.
[0179] Step 503: If the cloud network resources pass the first verification, the resource recycling device will recycle the cloud network resources to the resource recycling pool corresponding to the third level.
[0180] In some embodiments, the resource recycling device may modify the resource status marker that has passed the first verification to a schedulable reuse status, and register the resource registration information of the cloud network resource to the resource recycling pool corresponding to the third level; update the resource statistics list of the resource recycling pool, and complete the registration of the cloud network resource into the pool.
[0181] Thus, after completing in-depth testing of all components, bad block masking, and firmware upgrade verification, the beneficial effects of modifying the cloud network resource status to reusable can be characterized as follows: ensuring that hardware faults are investigated and repaired, firmware runs to a compliant version, avoiding the reuse and deployment of resources with potential risks, reducing the probability of subsequent tenant business failures, and improving the security and stability of resource recycling and reuse.
[0182] In some embodiments, combined with Figure 2 ,like Figure 6 As shown, step 203 above can be implemented through steps 601 and 603 as follows.
[0183] Step 601: When the health level is level four, the resource recycling device determines the resource recycling process to be the reporting and approval recycling process.
[0184] In some embodiments, the fourth level mentioned above is the cloud network resource failure and degradation health level.
[0185] In some embodiments, the reporting and recycling process can be characterized as a reporting and recycling process performed on cloud network resources to be recycled with a medium health level.
[0186] In some embodiments, the resource recycling device is pre-configured with a mapping relationship between the health level of cloud network resources and the resource recycling process. The resource recycling device can determine the resource recycling process corresponding to the cloud network resource as the reporting and recycling process based on the target health level of the cloud network resource to be recycled and the preset mapping relationship between the health level and the recycling process.
[0187] Step 602: The resource recycling device performs a second verification on all resources in the cloud network resources. The second verification includes: resource obsolescence detection and dismantling of usable components.
[0188] In some embodiments, the resource recycling device can perform scrap detection on cloud network resources, identify usable and failed components, disassemble usable components and register component information, mark failed components as scrapped, and complete the classification and disposal.
[0189] In some embodiments, the above-mentioned available components can be characterized as hardware components in cloud network resources whose performance indicators meet the reuse standard, and the above-mentioned failed components can be characterized as hardware components that are severely damaged by faults and cannot be repaired and reused.
[0190] In some embodiments, the aforementioned component information may be characterized as ledger record information of the disassembled hardware components.
[0191] In some embodiments, the component information may include component model, component number, test results, component health level, and component status markers.
[0192] In some embodiments, the resource recycling device can read cloud network resource detection data and resource registration information, compare them with the scrapping judgment threshold, and comprehensively consider the hardware failure situation to obtain the detection results of each component. The device can then compare the component operating parameters with the reuse threshold to obtain the usable components that meet the performance standards and the failed components that exceed the failure standards.
[0193] In some embodiments, the aforementioned cloud network resource detection data is collected from the hardware operating status reported by the cloud network resource itself.
[0194] In some embodiments, the cloud network resource detection data described above can be characterized as the detection and collection data output by each hardware component of the cloud network resource.
[0195] In some embodiments, the cloud network resource detection data may include at least one of the following: component operating parameters and component error records.
[0196] In some embodiments, the resource registration information described above can be characterized as ledger information that records the hardware attributes of cloud network resources.
[0197] In some embodiments, the resource registration information may include at least one of the following: hardware model, component number, historical health level, and historical processing records.
[0198] In some embodiments, the aforementioned hardware failure can be characterized as an abnormal state of various hardware components of the cloud network resources.
[0199] In some embodiments, the aforementioned hardware failure conditions may include at least one of the following: component error, excessive bad blocks, firmware anomaly, substandard performance, and hardware damage.
[0200] In some embodiments, the resource recycling device may issue a dismantling instruction to perform isolated dismantling of the selected available components, read the inherent parameters of the components, enter the component information, and update the component status to be put into storage.
[0201] In some embodiments, the aforementioned component-specific parameters can be characterized as inherent attribute identifiers that come with the hardware component at the factory.
[0202] In some embodiments, the inherent parameters of the aforementioned component may include at least one of the following: component model, hardware serial number, factory version, and hardware specifications.
[0203] In some embodiments, the above component information may be characterized as component file information created after disassembly.
[0204] In some embodiments, the above component information may include at least one of the following: component inherent parameters, component inspection results, disassembly time, component health level, and pending warehousing status markers, etc.
[0205] Step 603: If the cloud network resources pass the second verification, the resource recycling device will recycle the cloud network resources to the resource recycling pool corresponding to the fourth level.
[0206] In some embodiments, the resource recycling device may modify the resource status marker that has passed the second verification to a schedulable reuse status, and register the resource registration information of the cloud network resource to the resource recycling pool corresponding to the fourth level; update the resource statistics list of the resource recycling pool, and complete the registration of the cloud network resource into the pool.
[0207] In some embodiments, the resource recycling pool corresponding to the fourth level is a waste resource repository.
[0208] In this way, conducting scrapping inspections and dismantling usable components for Level 4 cloud network resources can separate reusable components from scrapped components, making the best use of hardware resources, reducing hardware waste, and completing the compliant scrapping of failed components, thereby reducing the overall resource operation and maintenance costs.
[0209] In some embodiments, combined with Figure 2 ,like Figure 7 As shown, after step 203 above, the resource recycling method provided in this application embodiment may further include the following steps 701 to 703.
[0210] Step 701: Upon detecting the first service, the resource recycling device determines the service execution priority of the first service based on the service attribute information of the first service.
[0211] In some embodiments, the aforementioned service attribute information may be characterized as descriptive information related to the type of service carried by the cloud network resources.
[0212] In some embodiments, the aforementioned business attribute information includes business ownership identifier, business usage record, resource allocation record, business unbinding flag, and business exception log, etc.
[0213] In some embodiments, the above-mentioned business execution priorities include: core production level (S1), important business level (S2), ordinary business level (S3), and test development level (S4), etc.
[0214] In some embodiments, the resource recycling device can determine the execution priority of the first service by looking up a mapping table between the service attribute information and the service execution priority based on the service attribute information of the first service.
[0215] In some embodiments, the mapping table between the above-mentioned business attribute information and business execution priority can be preset by the resource recycling device; or, it can be user-defined. The specific mapping can be determined according to actual usage requirements, and this application embodiment does not impose any limitations.
[0216] For example, core production level is used to carry core transaction-related businesses with high data sensitivity; important business level is used to carry routine production businesses with a wide impact; ordinary business level is used to carry office and operation-related non-core businesses; and test and development level is used to carry testing, development, and offline computing businesses.
[0217] Step 702: The resource recycling device determines the first resource recycling pool that matches the business execution priority based on the business execution priority corresponding to the first business.
[0218] In some embodiments, the resource recycling device can acquire resources from different resource pools based on rigid matching rules according to the business execution priority of the business.
[0219] For example, S1 level services are only allowed to be allocated resources from the A level resource pool; S2 level services are given priority to allocate resources from the B level pool, and can apply for overflow resources from the A level pool if there are insufficient resources; S3 / S4 level services are only allowed to allocate resources from the C level and below, and are prohibited from occupying high-level pools.
[0220] Step 703: The resource recycling device can allocate cloud network resources corresponding to the business execution requirement information of the first business from the first resource recycling pool.
[0221] In some embodiments, the resource recycling device can receive the service execution requirement information of the first service, parse the resource specifications, traverse the first resource recycling pool to filter and match cloud network resources, complete the resource allocation, and return the allocation result to the first service.
[0222] In some embodiments, the above resource specifications can be characterized as the hardware capability parameters of cloud network resources required for the first service to carry out business operations.
[0223] In some embodiments, the above resource specifications include at least one of the following: storage capacity, computing power specifications, hardware type, and health level.
[0224] In this way, different levels of services correspond to independent resource pools, realizing hierarchical matching between services and cloud network resources. Higher-level services have priority to obtain high-quality resources, and resources between services do not compete for each other, ensuring the quality of service operation, while simplifying resource scheduling and operation and maintenance management.
[0225] The resource recycling method of this application will be described below through specific embodiments.
[0226] The implementation process of the resource recycling method provided in this application includes the following steps S1 to S4.
[0227] S1. The resource recycling device performs four-dimensional detection and classification of cloud network resources to assess their health.
[0228] For example, the evaluation of three types of heterogeneous resources—computing, storage, and network—can be implemented, and the above-mentioned S1 can be specifically implemented by S11 to S13.
[0229] S11. Resource recycling device obtains four-dimensional indicators.
[0230] For example, the four-dimensional indicators are shown in Table 1.
[0231] Table 1
[0232]
[0233] S12, Calculate the comprehensive score for the resource recycling device.
[0234] For example, the overall score = hardware fundamentals score × 30% + performance degradation score × 30% + fault reliability score × 20% + network quality score × 20%
[0235] All metrics are normalized and mapped to a score of 0-100: Positive metrics (higher values are better, such as mean time between failures): Score = (Actual value - Worst baseline) / (Best baseline - Worst baseline) × 100; Negative metrics (lower values are better, such as failure rate, latency): Score = (Best baseline - Actual value) / (Best baseline - Worst baseline) × 100. Baseline values are taken from the equipment's factory specifications and industry-standard thresholds. All metrics have upper and lower limits to prevent distortion from extreme values.
[0236] S13. Resource recycling devices are graded based on comprehensive scores.
[0237] For example, 90-100 points: Grade A; 70-89 points: Grade B; 50-69 points: Grade C; <50 points: Grade D; Disqualification items: Resources that have experienced serious failures such as data loss or irreversible hardware damage will be directly judged as Grade D.
[0238] S2. The resource recycling device performs graded and differentiated recycling.
[0239] For example, all levels of resource reclamation follow a unified process, with only the parameters differing at each stage. When storage resources are reclaimed, the system automatically coordinates with the network management plane to synchronously clear the tenant-specific Virtual Local Area Network (VLAN), Virtual Extensible LAN (VXLAN) network identifier (VNI), security group, and Access Control List (ACL) policy configurations for the corresponding ports of the resource; unbind the dedicated bandwidth slice and Quality of Service (QoS) priority quota occupied by the resource and release them to the network public resource pool; reclaim the network service resources allocated to the service, such as Internet Protocol (IP), Network Address Translation (NAT) mapping, and load balancing nodes; update the network topology ledger, mark the ports as pending reuse, and synchronize with the storage resource pool level to avoid fragmented and idle network resources.
[0240] For example, the above S2 can be implemented by S21 to S26.
[0241] S21. The resource recycling device is graded.
[0242] For example, the corresponding recycling channel is matched according to the health level.
[0243] S22. The resource recycling unit informs the tenants.
[0244] For example, a recycling notice is pushed to the tenant to which the resource belongs, and a confirmation countdown is started.
[0245] S23, The resource recycling device locks in the resources.
[0246] For example, after the confirmation period ends and the tenant has no objection, the service access is disconnected.
[0247] S24. The resource recycling device erases the data.
[0248] For example, data erasure is performed.
[0249] S25. Hardware testing and repair of the resource recycling device.
[0250] For example, hardware detection and firmware repair are performed at the corresponding depth according to the level.
[0251] S26. The resource recycling device returns the resources to the pool.
[0252] For example, resources that pass the test are assigned to the corresponding level resource pool, and the global resource ledger is updated.
[0253] For example, the above-mentioned graded differential recycling method is specifically shown in Table 2.
[0254] Table 2
[0255]
[0256] S3. The resource recycling device performs dynamic water level control of the graded resource pool.
[0257] For example, to balance resource supply elasticity and the principle of hierarchical isolation, a dynamic upgrade / downgrade mechanism between resource pools is set up. Lowest water level triggers upgrade: When the available capacity of a single-level resource pool falls below 15%, resources in the top 10% of health from the next lower-level resource pool are automatically selected, re-inspected, and upgraded to the current level resource pool to supplement capacity. Automatic downgrade due to declining health: Resources within a resource pool are periodically re-inspected; those whose health falls below the current level threshold are automatically downgraded to the corresponding level resource pool. Expansion priority: If a high-level resource pool is still insufficient after upgrades, a new hardware procurement process is triggered; when a low-level resource pool is insufficient, priority is given to supplementing from surplus resources downgraded from higher-level pools before considering new procurement. Highest water level limit: When the available capacity of a single-level resource pool exceeds 80%, resource replenishment to that pool is suspended, and demand is diverted to other pools.
[0258] S4. The resource recycling device performs health degradation prediction and assessment.
[0259] For example, based on the monthly health time-series data of the past 6 months, the Holt Linear Trend Model (Holt) with double exponential smoothing is used to predict the health trend for the next 3 months, outputting monthly prediction scores and confidence intervals. Based on the prediction results, health degradation warnings and migration suggestions are pushed to tenants in advance. The effectiveness of data recovery is regularly evaluated, including: efficiency indicators (timeliness rate, average recovery duration); quality indicators (false positive rate, false negative rate, data erasure success rate); and benefit indicators (resource reuse rate, cost savings rate, business failure rate).
[0260] Thus, by establishing a four-dimensional comprehensive resource health scoring system, a comprehensive score is given from four dimensions: hardware basic health, performance degradation degree, historical fault records, and network connectivity quality. Based on the recycling score, different resource recycling processes are implemented for cloud network resources. The recycling cycle, hardware detection method, and confirmation time are different for different levels of cloud network resources, thereby achieving differentiated recycling of all recyclable resources, reducing the recycling cycle and hardware monitoring resource consumption, and thus greatly improving the recycling efficiency of cloud network resources.
[0261] It should be noted that the descriptions of each step S1 to S4 in this embodiment can be found in the descriptions in the above embodiments, and will not be repeated here.
[0262] It should be noted that the above-described method embodiments, or the various possible implementations of the method embodiments, can be executed individually, or, provided there is no conflict, they can be combined with each other. The specific implementation can be determined according to actual usage requirements, and this application embodiment does not impose any restrictions on this.
[0263] Figure 8 This is a schematic diagram of a resource recycling system provided in an embodiment of this application. Figure 8 As shown, the resource recycling system 800 may include: a resource health detection module 801, a differentiated recycling module 802, and a hierarchical resource pool management module 803.
[0264] The resource health detection module 801 is used for computing resource detection, storage resource detection and network resource detection, and is applied to the relevant scheme in step 203 above.
[0265] The differentiated recycling module 802 is used for recycling channel matching, data erasure, hardware repair and cloud network linkage recycling, and is applied to the relevant schemes of steps 701 and 702 above.
[0266] The hierarchical resource pool management module 803 is used for service level agreement (SLA) classification, matching degree calculation and inter-pool upgrade and downgrade, and is applied to the relevant schemes in step 703 above.
[0267] It should be noted that for a detailed explanation of the steps performed by each module and their beneficial effects, please refer to the description in the above embodiments, which will not be repeated here.
[0268] As can be seen, the above mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, the embodiments of this application provide corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the modules and algorithm steps of the various examples described in the embodiments disclosed herein, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0269] This application embodiment can divide the resource recycling device into functional modules according to the above method example. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.
[0270] In some embodiments, this application also provides a resource recycling apparatus. The resource recycling apparatus may include one or more functional modules for implementing the resource recycling method of the above method embodiments.
[0271] For example, Figure 9 This is a schematic diagram of a resource recycling device provided in an embodiment of this application. Figure 9 As shown, the resource recycling device 900 includes: an acquisition module 901, a processing module 902, and a recycling module 903.
[0272] The acquisition module 901 is used to acquire the health score of each cloud network resource dimension, whereby the cloud network resource dimensions include at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension. The processing module 902 is used to perform a weighted summation of the health scores for each cloud network resource dimension to obtain a recycling score, and to determine the health level of the cloud network resource according to the recycling score; different health levels correspond to different resource recycling processes. The recycling module 903 is used to recycle the cloud network resources based on the health level and using the resource recycling process corresponding to the health level.
[0273] The resource recycling device provided in this application establishes a four-dimensional resource health comprehensive scoring system, which comprehensively scores the resources from four dimensions: hardware basic health, performance degradation degree, historical fault records, and network connectivity quality. Based on the recycling score, different resource recycling processes are implemented for cloud network resources. The recycling cycle, hardware detection method, and confirmation time are different for different levels of cloud network resources, thereby achieving differentiated recycling of all recyclable resources, reducing the recycling cycle and hardware monitoring resource consumption, and thus greatly improving the recycling efficiency of cloud network resources.
[0274] In some embodiments, the processing module 902 is specifically used to determine that the resource recycling process is a fast recycling process when the health level is the first level; and to perform indicator sampling and verification on the cloud network resources; if the cloud network resources pass the indicator sampling and verification, the cloud network resources are recycled to the resource recycling pool corresponding to the first level.
[0275] In other embodiments, the processing module 902 is specifically used to determine that the resource recycling process is a standard recycling process when the health level is the second level; and to perform full component routine testing on all resources in the cloud network resources; if the cloud network resources pass the full component routine test, then the cloud network resources are recycled to the resource recycling pool corresponding to the second level.
[0276] In some other embodiments, the processing module 902 is specifically used to determine that the resource recycling process is a prudent recycling process when the health level is level 3; and to perform a first verification on all resources in the cloud network resources, the first verification including: full component deep detection, bad block masking processing and firmware upgrade; if the cloud network resources pass the first verification, the cloud network resources are recycled to the resource recycling pool corresponding to level 3.
[0277] In some other embodiments, the processing module 902 is specifically used to determine that the resource recycling process is an approval recycling process when the health level is level four; and to perform a second verification on all resources in the cloud network resources, the second verification including: resource scrapping detection and dismantling of usable components; if the cloud network resources pass the second verification, the cloud network resources are recycled to the resource recycling pool corresponding to level four.
[0278] In some other embodiments, the resource recycling device further includes a determining module, which is used to recycle cloud network resources based on a health level and using a resource recycling process corresponding to the health level. After the cloud network resources are recycled, if a first service is detected, the module determines the service execution priority of the first service based on the service attribute information of the first service; and determines a first resource recycling pool that matches the service execution priority based on the service execution priority of the first service. The processing module 902 is also used to allocate cloud network resources corresponding to the service execution requirement information from the first resource recycling pool to the first service based on the service execution requirement information of the first service.
[0279] It should be noted that the resource recycling device can implement all the processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.
[0280] In the case where the functions of the integrated modules described above are implemented in hardware, this application provides a possible structural schematic diagram of the electronic device involved in the above embodiments. For example... Figure 10 As shown, the electronic device 90 includes: a processor 92, a communication interface 93, and a bus 94. Optionally, the electronic device 90 may also include a memory 91.
[0281] Processor 92 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 92 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.
[0282] Communication interface 93 is used to connect with other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.
[0283] The memory 91 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.
[0284] As one possible implementation, the memory 91 can exist independently of the processor 92. The memory 91 can be connected to the processor 92 via a bus 94 and is used to store instructions or program code. When the processor 92 calls and executes the instructions or program code stored in the memory 91, it can implement the resource reclamation method provided in the embodiments of this application.
[0285] In another possible implementation, memory 91 can also be integrated with processor 92.
[0286] Bus 94 can be an Extended Industry Standard Architecture (EISA) bus, etc. Bus 94 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0287] Through the above description of the implementation methods, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the service calling device can be divided into different functional modules to complete all or part of the functions described above.
[0288] This application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described resource recycling method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0289] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.
[0290] This application also provides a readable storage medium storing a program or instructions that, when executed by a computer, implement the resource reclamation method provided in the above embodiments. It is understood that all or part of the processes in the above method embodiments can be executed by computer instructions instructing related hardware; the readable storage medium can be any of the foregoing embodiments or memory; the readable storage medium can also be an external storage device of the service invocation device, such as a plug-in hard drive, Smart MediaCard (SMC), Secure Digital (SD) card, flash card, etc., equipped on the service invocation device. Further, the readable storage medium can include both internal storage units of the service invocation device and external storage devices. The readable storage medium is used to store the computer program and other programs and data required by the service invocation device. The readable storage medium can also be used to temporarily store data that has been output or will be output.
[0291] This application also provides a computer program product, which is stored in a storage medium and implements the resource recycling method provided in the above embodiments when the computer program product is executed by a computer.
[0292] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0293] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.
[0294] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
Claims
1. A resource recycling method, characterized in that, include: Obtain the health score for each cloud network resource dimension corresponding to the cloud network resource, wherein the cloud network resource dimension includes at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension; The health scores for each cloud network resource dimension are weighted and summed to obtain a recycling score, and the health level of the cloud network resource is determined according to the recycling score; different health levels correspond to different resource recycling processes. Based on the health level, the cloud network resources are reclaimed using the resource reclamation process corresponding to the health level.
2. The resource recycling method according to claim 1, characterized in that, The process of reclaiming cloud network resources based on the health level and using the corresponding resource reclamation procedure includes: If the health level is at level one, the resource recycling process is determined to be a rapid recycling process; The cloud network resources are subject to random sampling and verification of indicators; If the cloud network resources pass the sampling inspection of the indicators, the cloud network resources will be recycled to the resource recycling pool corresponding to the first level.
3. The resource recycling method according to claim 1, characterized in that, The process of reclaiming cloud network resources based on the health level and using the corresponding resource reclamation procedure includes: If the health level is Level 2, the resource recycling process is determined to be a standard recycling process. Perform full-component routine verification on all resources in the cloud network resources; If the cloud network resources pass the routine verification of all components, the cloud network resources will be recycled to the resource recycling pool corresponding to the second level.
4. The resource recycling method according to claim 1, characterized in that, The process of reclaiming cloud network resources based on the health level and using the corresponding resource reclamation procedure includes: If the health level is level three, the resource recycling process is determined to be a prudent recycling process. A first verification is performed on all resources in the cloud network resources. The first verification includes: full component deep detection, bad block masking processing, and firmware upgrade. If the cloud network resource passes the first verification, the cloud network resource will be recycled to the resource recycling pool corresponding to the third level.
5. The resource recycling method according to claim 1, characterized in that, The process of reclaiming cloud network resources based on the health level and using the corresponding resource reclamation procedure includes: If the health level is level four, the resource recycling process is determined to be an approval-based recycling process. A second verification is performed on all resources in the cloud network resources. The second verification includes: resource obsolescence detection and disassembly of usable components. If the cloud network resource passes the second verification, the cloud network resource will be recycled to the resource recycling pool corresponding to the fourth level.
6. The resource recycling method according to any one of claims 1 to 5, characterized in that, After reclaiming the cloud network resources based on the health level and using the resource reclamation process corresponding to the health level, the method further includes: Upon detecting the first service, the service execution priority of the first service is determined based on the service attribute information of the first service; Based on the business execution priority corresponding to the first business, a first resource recycling pool matching the business execution priority is determined; Based on the service execution requirement information of the first service, cloud network resources corresponding to the service execution requirement information are allocated from the first resource recycling pool for the first service.
7. A resource scheduling apparatus, characterized in that, The resource scheduling device includes: an acquisition module, a processing module, and a recycling module; The acquisition module is used to acquire the health score of each cloud network resource dimension corresponding to the cloud network resource, wherein the cloud network resource dimension includes at least one of the following: hardware health dimension, performance degradation dimension, historical fault record dimension, and network connectivity quality dimension. The processing module is used to perform a weighted summation of the health scores for each cloud network resource dimension to obtain a recycling score, and to determine the health level of the cloud network resource according to the recycling score; different health levels correspond to different resource recycling processes. The recycling module is used to recycle the cloud network resources based on the health level and using the resource recycling process corresponding to the health level.
8. The resource recycling device according to claim 7, characterized in that, The processing module is specifically used to determine that the resource recycling process is a fast recycling process when the health level is the first level. And perform random sampling and verification of the cloud network resources; If the cloud network resources pass the sampling inspection of the indicators, the cloud network resources will be recycled to the resource recycling pool corresponding to the first level.
9. The resource recycling device according to claim 7, characterized in that, The processing module is specifically used to determine that the resource recycling process is a standard recycling process when the health level is the second level. And perform full-component routine verification on all resources in the cloud network resources; If the cloud network resources pass the routine verification of all components, the cloud network resources will be recycled to the resource recycling pool corresponding to the second level.
10. The resource recycling device according to claim 7, characterized in that, The processing module is specifically used to determine that the resource recycling process is a prudent recycling process when the health level is level three. The first verification is performed on all resources in the cloud network resources, including: full component deep detection, bad block masking processing, and firmware upgrade; If the cloud network resource passes the first verification, the cloud network resource will be recycled to the resource recycling pool corresponding to the third level.
11. The resource recycling device according to claim 7, characterized in that, The processing module is specifically used to determine that the resource recycling process is an approval and recycling process when the health level is level four. A second verification is performed on all resources in the cloud network resources. The second verification includes: resource obsolescence detection and disassembly of usable components. If the cloud network resource passes the second verification, the cloud network resource will be recycled to the resource recycling pool corresponding to the fourth level.
12. The resource recycling device according to any one of claims 7 to 11, the resource recycling device further comprising a determining module, the determining module being configured to, based on the health level and using the resource recycling process corresponding to the health level, recycle the cloud network resources, and, upon detecting the first service, determine the service execution priority of the first service based on the service attribute information of the first service; Based on the business execution priority corresponding to the first business, a first resource recycling pool matching the business execution priority is determined; The processing module is further configured to allocate cloud network resources corresponding to the service execution requirement information from the first resource recycling pool to the first service based on the service execution requirement information of the first service.
13. An electronic device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the resource recycling method as described in any one of claims 1-6.
14. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a computer, implement the resource recycling method as described in any one of claims 1-6.
15. A computer program product, characterized in that, The computer program product is stored in a storage medium, and when executed by a computer, the computer program product implements the resource recycling method as described in any one of claims 1-6.
