Cloud host service availability evaluation method and device, storage medium and electronic equipment
By combining the internal operation indicators of cloud hosts and external detection indicators, comprehensive analysis and evaluation of the availability of cloud hosts is solved, and the problem of inaccurate judgment and insufficient real-timeness in the existing technology is improved, and the accuracy and completeness of cloud host service availability is improved.
Patent Information
- Application Number
- CN202411190724.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-06
AI Technical Summary
The existing cloud host availability evaluation method is relatively single, mainly relying on network connectivity or system log judgment, which leads to inaccurate availability judgment of the current status of cloud hosts and is difficult to ensure the real-time and timeliness of the evaluation.
By combining the internal operation indicator data of the cloud host and external detection indicator data, the disk I/O status, computing resource status and network status indicators are extracted, and the current availability of the cloud host is comprehensively analyzed and evaluated, including obtaining internal operation indicator data and external detection indicator data. , and use this data to calculate service availability rates.
It improves the accuracy and completeness of cloud host service availability, solves the problems of incompleteness and inaccurate evaluation models in traditional evaluation methods, and achieves more accurate and real-time availability evaluation.
Smart Images

Figure CN119088659A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of cloud computing technology, and in particular to a cloud host service availability evaluation method, device, storage medium and electronic device. Background Art
[0002] In the field of cloud computing, the service availability of cloud hosts represents the quality level of cloud host services provided by public or private clouds. The service availability of cloud hosts is usually calculated and evaluated by the ratio of the cloud host's unavailable time to the total service time during the service cycle. The availability of cloud hosts is affected by many factors, such as system status, network firewall policy, and system disk status.
[0003] However, the existing cloud host availability determination criteria are relatively simple, either only determined by network connectivity or only determined by system logs, resulting in inaccurate availability determination of the current status of the cloud host.
[0004] Therefore, how to accurately evaluate the current service availability of the cloud host has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention
[0005] In view of the above problems, the present invention provides a cloud host service availability evaluation method, device, storage medium and electronic device that overcome the above problems or at least partially solve the above problems. The technical solution is as follows:
[0006] A cloud host service availability evaluation method, comprising:
[0007] Obtaining internal operating indicator data of the cloud host, wherein the internal operating indicator data is internal operating data collected from inside the cloud host about its own operating status;
[0008] Obtaining external detection indicator data of the cloud host, wherein the external detection indicator data is external evaluation data obtained by detecting the cloud host;
[0009] Using the internal operation indicator data, obtaining disk I / O status indicator data, computing resource status indicator data and network status indicator data of the cloud host;
[0010] The current availability evaluation index data of the cloud host is obtained by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data.
[0011] Optionally, after obtaining the external detection indicator data of the cloud host, the method further includes:
[0012] Using the external detection indicator data, obtaining the total service time and unavailable service time of the cloud host within a preset service period;
[0013] The total service duration and the unavailable service duration are used to obtain the service availability rate of the cloud host within the preset service period.
[0014] Optionally, the external detection indicator data includes the cloud host instance external connectivity indicator data, the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data.
[0015] Optionally, the obtaining the current availability evaluation index data of the cloud host by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data includes:
[0016] When the status results of each of the disk I / O status indicator data, the computing resource status indicator data, the network status indicator data, and the instance external connectivity indicator data are all in normal state, setting the current availability evaluation indicator data of the cloud host to normal state;
[0017] When the status result of any one of the disk I / O status indicator data, the computing resource status indicator data, the network status indicator data and the instance external connectivity indicator data is an abnormal state, the current availability evaluation indicator data of the cloud host is set to an abnormal state.
[0018] Optionally, the using the external detection indicator data to obtain the total service duration and unavailable service duration of the cloud host within a preset service period includes:
[0019] Using the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data, counting the normal service duration and abnormal service duration of the cloud host within a preset service cycle, and confirming the abnormal service duration as the unavailable service duration of the cloud host within the preset service cycle;
[0020] The normal service duration is subtracted from the period duration of the preset service period to obtain the total service duration of the cloud host in the preset service period.
[0021] Optionally, the internal operating indicator data include the number of IO times completed by the system disk read of the cloud host, the number of IO times completed by the system disk write, the number of IO times in the system disk waiting queue, the waiting time for physical CPU resource requests, the number of lost packets received by the network card, the number of lost packets sent by the network card, the total number of packets received by the cloud host, and the total number of packets sent by the cloud host.
[0022] Optionally, the using the internal operation indicator data to obtain disk I / O status indicator data, computing resource status indicator data, and network status indicator data of the cloud host includes:
[0023] Obtain disk I / O status indicator data of the cloud host by using the number of IOs completed by the system disk read, the number of IOs completed by the system disk write, and the number of IOs in the system disk waiting queue;
[0024] Obtain computing resource status indicator data of the cloud host by using the waiting physical CPU resource request time and a preset request time threshold;
[0025] The network status indicator data of the cloud host is obtained by using the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host and the total number of messages sent by the cloud host.
[0026] A cloud host service availability evaluation device comprises: an internal operation index data acquisition unit, an external detection index data acquisition unit, a status index data acquisition unit and an availability evaluation index data acquisition unit.
[0027] The internal operation index data obtaining unit is used to obtain the internal operation index data of the cloud host, wherein the internal operation index data is the internal operation data collected from the cloud host about its own operation status;
[0028] The external detection indicator data obtaining unit is used to obtain the external detection indicator data of the cloud host, wherein the external detection indicator data is the external evaluation data obtained by detecting the cloud host;
[0029] The status indicator data obtaining unit is used to obtain the disk I / O status indicator data, computing resource status indicator data and network status indicator data of the cloud host by using the internal operation indicator data;
[0030] The availability evaluation index data obtaining unit is used to obtain the current availability evaluation index data of the cloud host by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data.
[0031] A computer-readable storage medium stores a program, wherein when the program is executed by a processor, the method for evaluating the availability of a cloud host service described in any one of the above is implemented.
[0032] An electronic device comprises at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; and the processor is used to call program instructions in the memory to execute any of the cloud host service availability evaluation methods described above.
[0033] By means of the above technical scheme, the cloud host service availability evaluation method, device, storage medium and electronic device provided by the present invention are applied to the field of cloud computing technology, and the method comprises: obtaining internal operation index data of the cloud host, wherein the internal operation index data is internal operation data collected from the inside of the cloud host about its own operation status; obtaining external detection index data of the cloud host, wherein the external detection index data is external evaluation data obtained by detecting the cloud host; using the internal operation index data, obtaining the disk I / O state index data, computing resource state index data and network state index data of the cloud host; using the disk I / O state index data, computing resource state index data, network state index data and external detection index data, obtaining the current availability evaluation index data of the cloud host. The present invention can accurately evaluate the current service availability of the cloud host by combining multiple factors including the internal operation index data and external detection index data of the cloud host for comprehensive analysis and evaluation, thereby effectively improving the accuracy and completeness of the cloud host service availability.
[0034] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:
[0036] Figure 1 A schematic diagram showing a flow chart of an implementation of a method for evaluating the availability of a cloud host service provided by an embodiment of the present invention;
[0037] Figure 2 A flow chart showing another implementation of a method for evaluating the availability of a cloud host service provided by an embodiment of the present invention;
[0038] Figure 3 A schematic diagram showing the structure of a cloud host service availability evaluation device provided by an embodiment of the present invention;
[0039] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0040] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.
[0041] Service availability refers to the ability of a system or service to operate normally and provide services within a specified period of time. High availability means that the service can respond to requests at any time when users need it, and the downtime or service interruption caused by failure is as short as possible. Service availability is a key indicator to measure service reliability, continuity and stability.
[0042] In the field of cloud computing, the service availability of cloud hosts represents the quality level of cloud host services provided by public or private clouds. The service availability of cloud hosts is usually calculated and evaluated by the ratio of the cloud host's unavailable time to the total service time during the service cycle. The availability of cloud hosts is affected by many factors, such as system status, network firewall policy, and system disk status.
[0043] At present, most public cloud and private cloud service providers will provide availability commitments for cloud host services. When evaluating the availability of a cloud host, two dimensions are usually considered: the single instance dimension (for the availability of a single cloud host) and the single-region multi-availability zone dimension (for the availability of instances). The present invention mainly evaluates the availability of the cloud host in two different stages under the single instance dimension: the first stage is the availability determination of the current state of the cloud host, and the second stage is the calculation of the cloud host availability rate within the cycle.
[0044] There are two main solutions for determining the availability of a single cloud host in its current state: Solution 1: Under the premise that the cloud host is configured with TCP or UDP protocol security rules, determine the connectivity between the cloud host and any IP address from the network level to evaluate the availability of the service. Solution 2: Determine whether the service is available based on the cloud host system log. This is a method for evaluating the availability of cloud host services from within the system.
[0045] In the network-level assessment, it is necessary to consider the impact of the cloud host's own security policy on the service availability determination; in the system-level assessment, it is necessary to analyze the impact of the failure on the current system based on system failure logs at different levels, and evaluate the availability of the cloud host service accordingly.
[0046] When calculating the cloud host availability rate within a period, the cloud host unavailability duration will be counted based on the above determination results. In some cases, the administrator needs to intervene to count and define the unavailability duration of the cloud host service within the period; in most cases, the abnormal status of the cloud host will be recorded through the monitoring system, and finally, within the settlement period, the cloud host availability rate of the current period will be calculated through the ratio of the cloud host unavailability duration to the total service duration.
[0047] However, the existing cloud host availability evaluation methods have certain limitations in the above two stages:
[0048] In the first stage, the existing technical solutions have relatively simple criteria for determining the availability of cloud hosts, either only through network connectivity or only through system logs, resulting in inaccurate availability determination of the current state of the cloud host, and may also be affected by the cloud host's network security policy.
[0049] In the second stage, i.e., the calculation process of the availability rate within a cycle, existing solutions usually perform calculations based on the full cloud host availability records. The computing tasks are relatively concentrated, which requires that the statistical data within the computing cycle must be complete. It is also difficult to ensure the real-time and timeliness of the cloud host availability evaluation.
[0050] Based on this, in an embodiment of the present invention, a method for evaluating the availability of a cloud host service is provided. First, internal operating indicator data of the cloud host that reflects its own operating status is collected. At the same time, external detection indicator data obtained by detecting the cloud host is obtained. Based on the internal operating indicator data, the disk I / O status, computing resource status, and network status indicators of the cloud host are extracted. Finally, the current availability of the cloud host is evaluated by combining the disk I / O status, computing resource status, network status indicators, and external detection data. It can be seen that the present invention can improve the accuracy and completeness of the cloud host service availability by combining a comprehensive evaluation with multi-factor analysis, and effectively solves the problems of incompleteness and inaccurate evaluation models in traditional cloud host availability evaluation methods.
[0051] like Figure 1 As shown, a flow chart of an implementation of a method for evaluating the availability of a cloud host service provided by an embodiment of the present invention is provided. The method may include:
[0052] S100: Obtain internal operation index data of the cloud host, wherein the internal operation index data is internal operation data collected from inside the cloud host about its own operation status.
[0053] Specifically, the embodiment of the present invention can periodically pull the internal operating index data of the cloud host from the Exporter through the Prometheus server. Exporter is an agent instance deployed inside the cloud host, responsible for collecting various index data inside the cloud host system, and publicizing the index data through the API (Application Programming Interface), and the Prometheus server can obtain these index data through the API.
[0054] The indicator data collected by Exporter include the current IO indicator of the cloud host's system disk, the packet loss indicator of the cloud host network card, the CPU preemption indicator, and the system error indicator, etc. These indicator data will be collected in real time through Node Exporter and pushed to the Prometheus time series database.
[0055] Optionally, the internal operation indicator data may include the number of IO times completed by the cloud host's system disk reads (NodeDiskReadsCompletedTotal), the number of IO times completed by the system disk writes (NodeDiskWritesCompletedTotal), the number of IO times in the system disk waiting queue (NodeDiskIOTimeWeightedSecondsTotal), the waiting time for physical CPU resource requests (NodeCPUSecon dsSteal), the number of packets lost by the network card (NodeNetworkReceiveDropTotal), the number of packets lost by the network card (NodeNetworkTransmitDropTotal), the total number of packets received by the cloud host (NodeNetworkReceivePacketsTotal) and the total number of packets sent by the cloud host (NodeNetworkTransmitPacketsTotal).
[0056] S110: Obtain external detection indicator data of the cloud host, wherein the external detection indicator data is external evaluation data obtained by detecting the cloud host.
[0057] Specifically, the embodiment of the present invention can periodically check the connectivity status of the cloud host and its power status in the cloud environment through the external detection system, and generate corresponding external detection indicator data. The external detection indicator data is then pushed to the server through the PushGateway interface of Prometheus.
[0058] Among them, the external detection system runs outside the cloud host system and is used to monitor and evaluate the connectivity, response time, status (such as power status) and service accessibility of the cloud host.
[0059] Optionally, the external detection indicator data includes the cloud host's instance external connectivity indicator data (NodeInstanceProbeStatus), the current cloud environment instance status indicator data (NodeInstanceCloudStatus), and the current cloud environment mounted disk status indicator data (NodeDiskCloudStatus).
[0060] Among them, the instance external connectivity indicator data represents the detection status of the cloud host instance. This indicator is usually used to monitor the accessibility or health of the cloud host instance. Through regular detection (Probe), it can be determined whether the instance is running normally, whether it can respond to requests, and whether there are network connection problems. If the detection status is abnormal, it may mean that the instance is unavailable or there is a network problem.
[0061] The current cloud environment instance status indicator data indicates the status of the cloud host instance in the cloud environment (eg, power status).
[0062] The current cloud environment mounted disk status indicator data indicates the status of the cloud host disk in the cloud environment (eg, operation and maintenance status).
[0063] Specifically, the embodiment of the present invention can determine the connectivity of the cloud host through network detection, such as sending ICMP and TCPSYNC network messages to confirm the network reachability of the cloud host and generate corresponding instance external connectivity indicator data. At the same time, the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data of the cloud host are obtained through the API provided by the cloud environment to eliminate errors that may affect the calculation of service availability and ensure that the service duration calculation of the cloud host is accurate.
[0064] S120. Using the internal operation indicator data, obtain the disk I / O status indicator data, computing resource status indicator data, and network status indicator data of the cloud host.
[0065] Among them, the disk I / O status indicator data (NodeDiskIOStatus) is used to reflect the disk storage availability of the cloud host, determine whether the current disk read and write of the cloud host is normal, and whether the disk queue is backlogged.
[0066] The embodiment of the present invention can extract first target indicator data related to the disk storage availability of the cloud host from the internal operation indicator data, and count the increments of these first target indicator data within a specified time range, so as to determine the disk I / O status indicator data of the cloud host.
[0067] Among them, the computing resource status indicator data (NodeInstanceCloudStatus) is used to reflect the computing resource availability of the cloud host and determine whether the current cloud host waiting time for physical CPU resource requests is reasonable.
[0068] The embodiment of the present invention can extract second target indicator data related to the computing resource availability of the cloud host from the internal operation indicator data, and determine the computing resource status indicator data of the cloud host by judging whether the current cloud host waiting time for physical CPU resource request is reasonable.
[0069] Among them, the network status indicator data (NodeNetworkStatus) is used to reflect the network availability of the cloud host and determine whether the number of bidirectional packet loss of the cloud host network card network is reasonable.
[0070] The embodiment of the present invention can extract third target indicator data related to the network availability of the cloud host from the internal operation indicator data, and determine the network status indicator data of the cloud host by determining whether the number of bidirectional packet loss of the cloud host network card network is reasonable.
[0071] S130. Obtain current availability evaluation index data of the cloud host using disk I / O status index data, computing resource status index data, network status index data, and external detection index data.
[0072] Specifically, the embodiment of the present invention can comprehensively analyze and integrate the disk I / O status indicator data, computing resource status indicator data, network status indicator data and external detection indicator data to obtain the current availability evaluation indicator data of the cloud host. For example, the embodiment of the present invention can standardize the disk I / O status indicator data, computing resource status indicator data, network status indicator data and external detection indicator data, and then perform weighted comprehensive processing according to the weights corresponding to different indicator data to obtain the current availability evaluation indicator data of the cloud host.
[0073] The present invention provides a method for evaluating the availability of cloud host services, the method comprising: obtaining internal operating index data of the cloud host, wherein the internal operating index data is internal operating data collected from the inside of the cloud host about its own operating status; obtaining external detection index data of the cloud host, wherein the external detection index data is external evaluation data obtained by detecting the cloud host; using the internal operating index data, obtaining disk I / O status index data, computing resource status index data and network status index data of the cloud host; using the disk I / O status index data, computing resource status index data, network status index data and external detection index data, obtaining current availability evaluation index data of the cloud host. The present invention can accurately evaluate the current service availability of the cloud host by combining multiple factors including the internal operating index data and external detection index data of the cloud host for comprehensive analysis and evaluation, thereby effectively improving the accuracy and completeness of the cloud host service availability.
[0074] Optional, based on Figure 1 The method shown, such as Figure 2 As shown, a flow chart of another implementation of a cloud host service availability evaluation method provided by an embodiment of the present invention is shown. After step S110, the method may further include:
[0075] S200: Utilize external detection indicator data to obtain the total service duration and unavailable service duration of the cloud host within a preset service period.
[0076] Specifically, the embodiments of the present invention can utilize the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data to count the normal service duration and abnormal service duration of the cloud host within a preset service cycle, and confirm the abnormal service duration as the unavailable service duration of the cloud host within the preset service cycle; subtract the normal service duration from the cycle duration of the preset service cycle to obtain the total service duration of the cloud host within the preset service cycle.
[0077] The embodiment of the present invention may use the Counter function to count the available time of the cloud host within a preset service cycle, thereby calculating the total service time and unavailable service time of the cloud host within the preset service cycle.
[0078] Among them, the total service time refers to the time data of the cloud host online status within the preset service cycle. When calculating the availability of the cloud host, the embodiment of the present invention can use an accumulator to count the total service time of the cloud host. At this time, the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data in the external detection indicator data are used to filter out the duration data of the non-service cycle to ensure that only the duration within the actual service cycle is calculated. For example: assuming that the preset service cycle is half a year, and the cloud host is marked as normal (i.e. "1") in the current cloud environment instance status indicator data every minute, and the disk is marked as normal (i.e. "1") in the current cloud environment mounted disk status indicator data every minute, then the calculation formula for the total service time of the cloud host within the preset service cycle is "Total service time = 180 × 24 × 60-count (NodeInstanceCloudStatus! = 1and NodeDiskCl oudStatus! = 1)".
[0079] Among them, the unavailable service duration refers to the duration data of the abnormal state of the cloud host within the preset service cycle. When calculating the availability of the cloud host, the embodiment of the present invention can use an accumulator to count the unavailable service duration of the cloud host. At this time, the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data in the external detection indicator data are used to filter out the duration data of the non-service cycle to ensure that only the unavailable duration within the service cycle is recorded. For example: assuming that the preset service cycle is half a year, and the cloud host is marked as an abnormal state (i.e., "0") in the current cloud environment instance status indicator data every minute, and the disk is marked as an abnormal state (i.e., "0") in the current cloud environment mounted disk status indicator data every minute, then the calculation formula for the unavailable service duration of the cloud host within the preset service cycle is "unavailable service duration = count (NodeInstanceCloudStatus = 0 and NodeDiskCloudStatus = 0)".
[0080] S210: Obtain the service availability rate of the cloud host within a preset service period by using the total service duration and the unavailable service duration.
[0081] Specifically, in the embodiment of the present invention, the total service time of the cloud host minus the unavailable service time can be used to obtain the available service time of the cloud host in a preset statistical period. Then, the available service time is divided by the total service time to obtain the availability rate of the cloud host in the entire statistical period. Finally, in order to express it as a percentage, this result is multiplied by 100%. That is, "service availability rate = (total service time - unavailable service time) / total service time × 100%".
[0082] In the process of calculating the service availability of the cloud host, the embodiment of the present invention calculates the total service time and unavailable service time of the cloud host in the statistical period based on the previously evaluated active status of the cloud host. During the calculation, the current power status and operation and maintenance status of the cloud host are also considered to optimize and reduce the error in the availability calculation, thereby obtaining a more accurate availability evaluation.
[0083] Optional, in the above Figure 1 On the basis of one or more corresponding embodiments, in another optional embodiment provided by the embodiment of the present invention, the current availability evaluation indicator data of the cloud host is obtained by using the disk I / O status indicator data, the computing resource status indicator data, the network status indicator data and the external detection indicator data, which may specifically include:
[0084] When the status results of each item in the disk I / O status indicator data, the computing resource status indicator data, the network status indicator data, and the instance external connectivity indicator data are all in normal state, the current availability evaluation indicator data of the cloud host is set to normal state.
[0085] When the status result of any one of the disk I / O status indicator data, computing resource status indicator data, network status indicator data and instance external connectivity indicator data is abnormal, the current availability evaluation indicator data of the cloud host is set to an abnormal state.
[0086] Specifically, the current availability evaluation index data of the cloud host can be judged by the following logic: if the values of the cloud host's disk I / O status index data, computing resource status index data, network status index data, and instance external connectivity index data are all 1, it means that the cloud host is currently available, and the value of the current availability evaluation index data is 1; if any state is not 1, it means that the cloud host is currently unavailable, and the value of the current availability evaluation index data is 0. That is, "current availability evaluation index data = 1 if (NodeDiskIOStatus == 1 and NodeComputeStatus == 1 and NodeNetworkStatus == 1) and (NodeInstanceProbeStatus == 1) else 0".
[0087] The embodiment of the present invention ensures that the cloud host is considered available only when all relevant states are normal by simultaneously checking the disk input and output status, computing status, network status and instance detection status, thereby avoiding misjudgment and effectively improving the accuracy of cloud host service availability.
[0088] Optional, in the above Figure 1On the basis of one or more corresponding embodiments, another optional embodiment provided by the embodiment of the present invention uses internal operation indicator data to obtain disk I / O status indicator data, computing resource status indicator data, and network status indicator data of the cloud host, which may specifically include:
[0089] The disk I / O status indicator data of the cloud host is obtained by using the number of IOs completed by the system disk read, the number of IOs completed by the system disk write, and the number of IOs in the system disk waiting queue.
[0090] Specifically, the embodiment of the present invention can use the Increase function to calculate the number of IOs completed by the system disk read within the specified time range, the number of IOs completed by the system disk write, and the increment of the number of IOs in the system disk waiting queue, and determine whether the disk of the cloud host has not completed any read operation and write operation within the specified time range, and there is still an I / O time record. If yes, the disk I / O status indicator data of the cloud host is set to an abnormal state, and if not, the disk I / O status indicator data of the cloud host is set to a normal state. For example: assuming that the specified time range is 2 minutes, "NodeDiskIOStatus = 0if(Increase(NodeDiskReadsCompletedTotal[2m])==0)and(Increase(NodeDiskWritesCompletedTotal[2m])==0))and(Increase(NodeDiskIOTimeWeightedSecondsTotal[2m])!=0)else 1".
[0091] The embodiment of the present invention can effectively monitor the disk I / O status of the cloud host within a specified time range by utilizing the number of IO times completed by the system disk read, the number of IO times completed by the system disk write and the number of IO times in the system disk waiting queue, thereby obtaining accurate disk I / O status indicator data, which is conducive to accurately evaluating the current service availability of the cloud host and improving the accuracy and completeness of the cloud host service availability.
[0092] The computing resource status indicator data of the cloud host is obtained by using the waiting time for physical CPU resource requests and the preset request time threshold.
[0093] Specifically, the embodiment of the present invention can set the computing resource status indicator data of the cloud host to an abnormal state when the waiting time for the physical CPU resource request is greater than the preset request time threshold. When the waiting time for the physical CPU resource request is less than or equal to the preset request time threshold, the computing resource status indicator data of the cloud host is set to a normal state. For example: assuming that the preset request time threshold is 0.6, then "NodeComputeStatus = 0if(NodeCPUSecondsSteal>0.6else 1".
[0094] The embodiment of the present invention evaluates the computing resource status of the cloud host by utilizing the waiting time for physical CPU resource requests and the preset request time threshold, and can flexibly evaluate the computing resource status indicator data of the cloud host, thereby obtaining accurate computing resource status indicator data, which is conducive to accurately evaluating the current service availability of the cloud host and improving the accuracy and completeness of the cloud host service availability.
[0095] The network status indicator data of the cloud host is obtained by using the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host, and the total number of messages sent by the cloud host.
[0096] Specifically, the embodiments of the present invention can use the Increase function to calculate the increment of the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host, and the total number of messages sent by the cloud host, and then calculate the ratio between the total number of discarded data packets and the total number of processed data packets, that is, the discard rate. If the discard rate is greater than the preset discard ratio threshold, the network status indicator data of the cloud host is set to an abnormal state; if the discard rate is less than or equal to the preset discard ratio threshold, the network status indicator data of the cloud host is set to a normal state. For example: Assuming that the preset discard ratio threshold is 0.5, "NodeNetworkStatus = 0if(Increase(NodeNetworkReceiveDropTotal)+Increase(NodeNetworkTransmitDropTotal)) / (Increase(NodeNetworkReceivePacketsTotal)+Increase(NodeNetworkTransmitPacketsTotal))>0.5Else 1".
[0097] The embodiment of the present invention calculates the network packet loss rate by the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host, and the total number of messages sent by the cloud host. It can accurately evaluate the network status of the cloud host, thereby obtaining accurate network status indicator data, which is conducive to accurately evaluating the current service availability of the cloud host and improving the accuracy and completeness of the cloud host service availability.
[0098] Although operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.
[0099] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.
[0100] Corresponding to the above method embodiment, the embodiment of the present invention also provides a cloud host service availability evaluation device, whose structure is as follows: Figure 3 As shown, it may include: an internal operation indicator data obtaining unit 10, an external detection indicator data obtaining unit 20, a state indicator data obtaining unit 30 and an availability evaluation indicator data obtaining unit 40.
[0101] The internal operation index data obtaining unit 10 is used to obtain the internal operation index data of the cloud host, wherein the internal operation index data is the internal operation data collected from the inside of the cloud host about its own operation status.
[0102] The external detection indicator data obtaining unit 20 is used to obtain the external detection indicator data of the cloud host, wherein the external detection indicator data is the external evaluation data obtained by detecting the cloud host.
[0103] The status indicator data obtaining unit 30 is used to obtain the disk I / O status indicator data, computing resource status indicator data and network status indicator data of the cloud host using the internal operation indicator data.
[0104] The availability evaluation index data obtaining unit 40 is used to obtain the current availability evaluation index data of the cloud host by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data.
[0105] Optionally, the cloud host service availability evaluation device may further include: a service duration obtaining unit and a service availability rate obtaining unit.
[0106] The service duration obtaining unit is used for the external detection indicator data obtaining unit 20, which is used to obtain the external detection indicator data of the cloud host and then use the external detection indicator data to obtain the total service duration and unavailable service duration of the cloud host within a preset service period.
[0107] The service availability acquisition unit is used to obtain the service availability of the cloud host within a preset service period by using the total service duration and the unavailable service duration.
[0108] Optionally, the external detection indicator data includes the cloud host instance external connectivity indicator data, the current cloud environment instance status indicator data, and the current cloud environment mounted disk status indicator data.
[0109] Optionally, the availability evaluation index data obtaining unit 40 can be specifically used to set the current availability evaluation index data of the cloud host to a normal state when the status results of each item among the disk I / O status index data, the computing resource status index data, the network status index data, and the instance external connectivity index data are all in a normal state. When the status result of any item among the disk I / O status index data, the computing resource status index data, the network status index data, and the instance external connectivity index data is an abnormal state, the current availability evaluation index data of the cloud host is set to an abnormal state.
[0110] Optionally, the service duration acquisition unit can be used to use the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data to count the normal service duration and abnormal service duration of the cloud host within the preset service cycle, and confirm the abnormal service duration as the unavailable service duration of the cloud host within the preset service cycle. The normal service duration is subtracted from the cycle duration of the preset service cycle to obtain the total service duration of the cloud host within the preset service cycle.
[0111] Optionally, the internal operation indicator data includes the number of IO times completed by the cloud host's system disk read, the number of IO times completed by the system disk write, the number of IO times in the system disk waiting queue, the waiting time for physical CPU resource requests, the number of lost packets received by the network card, the number of lost packets sent by the network card, the total number of packets received by the cloud host, and the total number of packets sent by the cloud host.
[0112] Optionally, the status indicator data obtaining unit 30 can be specifically used to obtain the disk I / O status indicator data of the cloud host by utilizing the number of IO times completed by the system disk read, the number of IO times completed by the system disk write and the number of IO times in the system disk waiting queue; to obtain the computing resource status indicator data of the cloud host by utilizing the waiting time for physical CPU resource request and the preset request time threshold; and to obtain the network status indicator data of the cloud host by utilizing the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host and the total number of messages sent by the cloud host.
[0113] The cloud host service availability evaluation device provided by the present invention is used to: obtain the internal operation index data of the cloud host, wherein the internal operation index data is the internal operation data collected from the inside of the cloud host about its own operation status; obtain the external detection index data of the cloud host, wherein the external detection index data is the external evaluation data obtained by detecting the cloud host; use the internal operation index data to obtain the disk I / O status index data, computing resource status index data and network status index data of the cloud host; use the disk I / O status index data, computing resource status index data, network status index data and external detection index data to obtain the current availability evaluation index data of the cloud host. The present invention can accurately evaluate the current service availability of the cloud host by combining multiple factors including the internal operation index data and external detection index data of the cloud host for comprehensive analysis and evaluation, thereby effectively improving the accuracy and completeness of the cloud host service availability.
[0114] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.
[0115] The cloud host service availability evaluation device includes a processor and a memory. The internal operation indicator data acquisition unit 10, the external detection indicator data acquisition unit 20, the status indicator data acquisition unit 30 and the availability evaluation indicator data acquisition unit 40 are all stored in the memory as program units, and the processor executes the above program units stored in the memory to realize corresponding functions.
[0116] The processor contains a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set. By adjusting the kernel parameters, a comprehensive analysis and evaluation of multiple factors including the internal operating index data of the cloud host and the external detection index data can be performed to accurately evaluate the current service availability of the cloud host and improve the accuracy and completeness of the cloud host service availability.
[0117] An embodiment of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, the cloud host service availability evaluation method is implemented.
[0118] An embodiment of the present invention provides a processor, which is used to run a program, wherein the cloud host service availability evaluation method is executed when the program is running.
[0119] like Figure 4As shown, an embodiment of the present invention provides an electronic device 1000, which includes at least one processor 1001, at least one memory 1002 connected to the processor 1001, and a bus 1003; wherein the processor 1001 and the memory 1002 communicate with each other through the bus 1003; the processor 1001 is used to call the program instructions in the memory 1002 to execute the above-mentioned cloud host service availability evaluation method. The electronic device in this article can be a server, a PC, a PAD, a mobile phone, etc.
[0120] The present invention also provides a computer program product, which, when executed on an electronic device, is suitable for executing a program that initializes the steps of a cloud host service availability assessment method.
[0121] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatuses, electronic devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable device to generate a machine, so that the instructions executed by the processor of the computer or other programmable device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0122] In a typical configuration, an electronic device includes one or more processors (CPU), a memory, and a bus. The electronic device may also include an input / output interface, a network interface, and the like.
[0123] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
[0124] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0125] In the description of the present invention, it should be understood that the terms "up", "down", "front", "back", "left" and "right" etc. indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the positions or elements referred to must have specific directions, be constructed and operate in specific directions. Therefore, they should not be understood as limitations of the present invention.
[0126] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be noted that the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0127] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0128] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims
1. A method for evaluating the availability of a cloud host service, characterized in that: include: Obtaining internal operating indicator data of the cloud host, wherein the internal operating indicator data is internal operating data collected from inside the cloud host about its own operating status; Obtaining external detection indicator data of the cloud host, wherein the external detection indicator data is external evaluation data obtained by detecting the cloud host; Using the internal operation indicator data, obtaining disk I / O status indicator data, computing resource status indicator data and network status indicator data of the cloud host; The current availability evaluation index data of the cloud host is obtained by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data.
2. The method according to claim 1, characterized in that After obtaining the external detection indicator data of the cloud host, the method further includes: Using the external detection indicator data, obtaining the total service time and unavailable service time of the cloud host within a preset service period; The total service duration and the unavailable service duration are used to obtain the service availability rate of the cloud host within the preset service period.
3. The method according to claim 2, characterized in that The external detection indicator data includes the cloud host instance external connectivity indicator data, the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data.
4. The method according to claim 3, characterized in that The obtaining of current availability evaluation index data of the cloud host by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data includes: When the status results of each of the disk I / O status indicator data, the computing resource status indicator data, the network status indicator data, and the instance external connectivity indicator data are all in normal state, setting the current availability evaluation indicator data of the cloud host to normal state; When the status result of any one of the disk I / O status indicator data, the computing resource status indicator data, the network status indicator data and the instance external connectivity indicator data is an abnormal state, the current availability evaluation indicator data of the cloud host is set to an abnormal state.
5. The method according to claim 3, characterized in that: The obtaining of the total service duration and unavailable service duration of the cloud host within a preset service period by using the external detection indicator data includes: Using the current cloud environment instance status indicator data and the current cloud environment mounted disk status indicator data, counting the normal service duration and abnormal service duration of the cloud host within a preset service cycle, and confirming the abnormal service duration as the unavailable service duration of the cloud host within the preset service cycle; The normal service duration is subtracted from the period duration of the preset service period to obtain the total service duration of the cloud host in the preset service period.
6. The method according to claim 1, characterized in that The internal operation indicator data includes the number of IO times completed by the system disk of the cloud host for reading, the number of IO times completed by the system disk for writing, the number of IO times in the system disk waiting queue, the waiting time for physical CPU resource requests, the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host, and the total number of messages sent by the cloud host.
7. The method according to claim 6, characterized in that The method of using the internal operation indicator data to obtain disk I / O status indicator data, computing resource status indicator data, and network status indicator data of the cloud host includes: Obtain disk I / O status indicator data of the cloud host by using the number of IOs completed by the system disk read, the number of IOs completed by the system disk write, and the number of IOs in the system disk waiting queue; Obtain computing resource status indicator data of the cloud host by using the waiting physical CPU resource request time and a preset request time threshold; The network status indicator data of the cloud host is obtained by using the number of lost messages received by the network card, the number of lost messages sent by the network card, the total number of messages received by the cloud host and the total number of messages sent by the cloud host.
8. A cloud host service availability evaluation device, characterized in that: include: Internal operation indicator data acquisition unit, external detection indicator data acquisition unit, status indicator data acquisition unit and availability evaluation indicator data acquisition unit, The internal operation index data obtaining unit is used to obtain the internal operation index data of the cloud host, wherein the internal operation index data is the internal operation data collected from the cloud host about its own operation status; The external detection indicator data obtaining unit is used to obtain the external detection indicator data of the cloud host, wherein the external detection indicator data is the external evaluation data obtained by detecting the cloud host; The status indicator data obtaining unit is used to obtain the disk I / O status indicator data, computing resource status indicator data and network status indicator data of the cloud host by using the internal operation indicator data; The availability evaluation index data obtaining unit is used to obtain the current availability evaluation index data of the cloud host by using the disk I / O status index data, the computing resource status index data, the network status index data and the external detection index data.
9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the cloud host service availability evaluation method according to any one of claims 1 to 7 is implemented.
10. An electronic device, characterized in that: The electronic device includes at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the cloud host service availability evaluation method as described in any one of claims 1 to 7.
