A server reliability testing method, device, storage medium and product

Abstract

The embodiment of the present invention provides a server reliability testing method, device, storage medium and product, which obtain historical fault information of a preset server and the reliability requirement of the server; based on the historical fault information, determine the historical probability of occurrence of server faults; based on the historical probability of occurrence of faults, determine the test weight of the server; based on the reliability requirement and the historical probability of occurrence, determine the number of tests to be met by the server in the event that the server fails during a preset reliability test; based on the test weight and the number of tests required, determine the target number of tests for the server; based on the target number of tests, perform a target reliability test on the server, thereby providing theoretical support for the design of the number of tests for repeated tests in accelerated aging tests.

Description

Technical Field

[0001] The present invention relates to the technical field of servers, and in particular to a server reliability testing method, equipment, storage medium and product. Background Art

[0002] The reliability of a server refers to the time during which the server can operate normally within a specific period of time. In the related art, the reliability of a server can be tested by means of accelerated aging test. Accelerated aging test refers to repeated tests with extremely short intervals. It can shorten the time required for the server aging process by increasing the intensity of the test conditions, thereby testing the reliability of the server in a shorter period of time. However, the accelerated aging test lacks theoretical support for the number of tests for repeated tests, and there is no clear theoretical framework to guide the design of the number of tests. Summary of the invention

[0003] The embodiments of the present invention provide a server reliability testing method, a computer device, a computer-readable storage medium, and a computer program product to solve the problem that the number of tests for repeated tests and accelerated aging tests lack theoretical support and there is no clear theoretical framework to guide the design of the number of tests.

[0004] The embodiment of the present invention discloses a method for testing server reliability, the method comprising:

[0005] Obtaining historical failure information of a preset server and reliability requirements of the server;

[0006] Based on the historical failure information, determining a historical occurrence probability of a failure of the server;

[0007] Determining a test weight of the server based on a historical probability of occurrence of the fault;

[0008] Based on the reliability requirement and the historical occurrence probability, determining a test number requirement to be met by the server in the event that the server fails during a preset reliability test process;

[0009] Determining a target number of tests for the server based on the test weight and the test number requirement;

[0010] Based on the target test number, a target reliability test of the server is performed.

[0011] Optionally, the determining, based on the reliability requirement and the historical occurrence probability, a test number requirement to be met by the server when a failure occurs in the server during a preset reliability test process includes:

[0012] Determine a single failure probability of the server based on the historical occurrence probability of the failure; the single failure probability refers to the probability of the server failing in any single test during the reliability test;

[0013] Based on the reliability requirement and the single failure probability, the test times requirement for the server is determined.

[0014] Optionally, the determining the test number requirement of the server based on the reliability requirement and the single failure probability includes:

[0015] Based on the reliability requirement, determining the failure probability requirement of the server; the failure probability requirement refers to the probability requirement of the server having a target number of failures to be met during the target reliability test;

[0016] Based on the failure probability requirement and the single failure probability, the test times requirement for the server is determined.

[0017] Optionally, the determining the test times requirement of the server based on the failure probability requirement and the single failure probability includes:

[0018] Based on the failure probability requirement and the single failure probability, a test number calculation formula is used to determine the number of tests included in the test number requirement;

[0019] The test number calculation formula is:

[0020]

[0021] Wherein, N is the number of tests, p is the single failure probability, and q is the probability of the target number of failures to be met.

[0022] Optionally, determining a target number of tests for the server based on the test weight and the test number requirement includes:

[0023] A target test number for the server is determined based on the test weight and the test number included in the test number requirement.

[0024] Optionally, determining a target test number of the server based on the test weight and the test number included in the test number requirement includes:

[0025] Using a preset target test number calculation formula to determine the target test number of the server;

[0026] The target test number calculation formula is:

[0027] SN=N*K

[0028] Wherein, K is the test weight, and SN is the target test number.

[0029] Optionally, the method comprises:

[0030] Based on a preset failure probability calculation formula, the test number calculation formula is obtained; the failure probability calculation formula is a calculation formula for the probability of the server having a target number of failures during the target reliability test;

[0031] The failure probability calculation formula is:

[0032] P=1-(1-p) N

[0033] Wherein, P is the probability of the server failing a target number of times.

[0034] Optionally, the method comprises:

[0035] Based on the result of the target reliability test, it is determined whether the server meets the reliability requirement; if the server does not fail during the target reliability test, the server meets the reliability requirement.

[0036] Optionally, determining the test weight of the server based on the historical occurrence probability of the fault includes:

[0037] Obtaining a test purpose of the server;

[0038] The test weight of the server is determined based on the historical occurrence probability of the fault and / or the test purpose.

[0039] Optionally, the acquiring historical fault information of a preset server and reliability requirements of the server includes:

[0040] Obtaining quality requirements of the server;

[0041] The reliability requirement of the server is determined according to the quality requirement of the server.

[0042] Optionally, the server includes at least one server unit to be tested; the server unit is a hardware device and / or a software system; and the obtaining of historical fault information of a preset server and reliability requirements of the server includes:

[0043] Acquire historical fault information of the server unit and reliability requirements of the server unit;

[0044] The determining, based on the historical fault information, a historical occurrence probability of a fault of the server includes:

[0045] Based on the historical failure information of the server unit, a historical occurrence probability of failure of the server unit is determined.

[0046] Optionally, the determining, based on the reliability requirement and the historical occurrence probability, a test number requirement to be met by the server when a failure occurs in the server during a preset reliability test process includes:

[0047] Based on the historical occurrence probability of failure of the server unit, determining the single failure probability of the server unit; the single failure probability of the server unit refers to the probability of failure of the server unit for any single test in the reliability test process;

[0048] Based on the reliability requirement of the server unit, determining the failure probability requirement of the server unit; the failure probability requirement of the server unit refers to the probability requirement of the server unit having a target number of failures to be met during the target reliability test;

[0049] The test times requirement of the server unit is determined based on the failure probability requirement and the single failure probability of the server unit.

[0050] An embodiment of the present invention further discloses a computer device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the above method when executed by the processor.

[0051] The embodiment of the present invention further discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described above is implemented.

[0052] An embodiment of the present invention further discloses a computer program product, including a computer program, wherein the computer program implements the above method when executed by a processor.

[0053] The embodiments of the present invention include the following advantages:

[0054] In an embodiment of the present invention, historical failure information of a preset server and reliability requirements of the server are obtained. Based on the historical failure information, the historical probability of occurrence of server failures is determined; based on the historical probability of occurrence of failures, the test weight of the server is determined; based on the reliability requirements and the historical probability of occurrence, the number of tests required for the server to be met when a server fails during a preset reliability test is determined. Based on the test weight and the number of tests required, the target number of tests for the server can be determined, and based on the target number of tests, the target reliability test of the server is performed, which provides theoretical support for the design of the number of tests for repeated tests in accelerated aging tests, and provides a clear theoretical framework to guide the design of the number of tests. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of the steps of a method for testing server reliability provided in an embodiment of the present invention;

[0056] Figure 2 It is a structural block diagram of a server reliability testing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] To facilitate understanding of the technical solutions and technical effects of the embodiments of the present invention, the prior art of the present invention is briefly described below.

[0059] In related technologies, "X nines" is a standard used to measure server reliability. X is a number, usually between 3 and 6. "X nines" can mean the ratio of the time a server can operate normally to the total time within a year of operation; "X nines" can also mean the time a server may be down within a year of operation. It should be noted that if a server is down, the business conducted by the server will be interrupted. The MTBF (Mean Time Between Failures) value for stable operation of a server usually needs to be no less than 50,000 hours, or 5.7 years.

[0060] If X is 3, the server availability is 0.999. The maximum possible downtime of the server within one year of operation is calculated as follows:

[0061] (1-99.9%)*365*24=8.76(hours)=525.6(minutes)

[0062] If X is 4, the server availability is 0.9999. The maximum possible downtime of the server within one year of operation is calculated as follows:

[0063] (1-99.99%)*365*24=0.876(hours)=52.6(minutes)

[0064] If X is 5, the server availability is 0.99999. The maximum possible downtime of the server within one year of operation is calculated as follows:

[0065] (1-99.999%)*365*24=0.0876(hours)=5.26(minutes)

[0066] If X is 6, the server availability is 0.999999. The maximum possible downtime of the server within one year of operation is calculated as follows:

[0067] (1-99.9999%)*365*24=0.00876(hours)=0.526(minutes)=31(seconds)

[0068] In summary, the maximum downtime of a server corresponding to "3 nines" in one year is 525.6 minutes, the maximum downtime of a server corresponding to "4 nines" in one year is 52.6 minutes, the maximum downtime of a server corresponding to "5 nines" in one year is 5.26 minutes, and the maximum downtime of a server corresponding to "6 nines" in one year is 0.526 minutes. If the maximum downtime of a server corresponding to "3 nines", "4 nines", "5 nines" and "6 nines" is considered to be 500 minutes, 50 minutes, 5 minutes and 0.5 minutes respectively, the availability of the server corresponding to "X nines", the number of nines and the annual downtime can be shown in Table 1 below.

[0069] Table 1: Example of server availability, number of 9s, and annual downtime corresponding to "X nines"

[0070]

[0071] In the related art, the reliability of the server is usually tested by running a long and stable test. Running a long and stable test means running the server continuously for a long time to observe whether it is stable and reliable under continuous working conditions. However, the reliability of the server usually refers to whether the server can run stably for a long time, even up to 50,000 hours. Therefore, the time cost of testing the reliability of the server by running a long and stable test is relatively high.

[0072] In the related art, the reliability of the server can also be tested by aging test. Aging test is a test method that simulates the performance degradation of the server after long-term use. It accelerates the aging process of the server in a short period of time to predict the reliability and expected life of the server under actual use conditions. However, when the reliability of the server is tested by aging test, the time cost of the test is also very high.

[0073] In the related art, the reliability of the server can also be tested by accelerated aging test. Accelerated aging test refers to a repetitive test with very short intervals. It can shorten the time required for the server aging process by increasing the intensity of the test conditions, so as to test the reliability of the server in a shorter time. However, for the number of tests of the repetitive test, the accelerated aging test lacks theoretical support, there is no clear theoretical framework to guide the design of the number of tests and the analysis of the test results, and no specific test completion standard is set, so that the evaluation of the test results lacks a unified standard. In addition, in the accelerated aging test, the probability of problems or failures is low, and the test needs to be repeated many times, and potential problems can only be observed after a certain period. Specifically, when the reliability of the light bulb is verified by the accelerated aging test method, it is necessary to verify the reliability of the light bulb by repeatedly starting and shutting down the light bulb to determine how many times the light bulb fails after switching. If a light bulb manufacturer claims that its product can withstand 10,000 switching operations without failure, this statement may not be rigorous enough because it may not be based on a scientific test method to design the number of tests to draw such a conclusion.

[0074] The related technology also provides the following methods to test the reliability of the server:

[0075] 1) By updating the basic software information and hardware information of the server under test, the server under test is controlled to run based on the test content, and the test information of the server under test is obtained, and the basic information and test information are compared to obtain the test results. This method can standardize and streamline the reliability test of the server, thereby significantly improving the efficiency and accuracy of the test. However, this method does not establish a clear standard for the number of tests to support the quantitative evaluation of reliability indicators.

[0076] 2) In response to the server being fully equipped with processors, the server is powered on, and a test function script is generated for verifying the system configuration and checking the error status register. The system is soft restarted multiple times, and the test function script is executed and the test results are recorded after each restart. Next, the system is shut down multiple times and powered on again using the power button, and the test function script is also executed and the test results are recorded after each power-on. In addition, the system is hard reset multiple times, using the reset button to reset, and the test function script is executed and the test results are recorded after each reset. The system is stress tested for the processor, and multiple iterations are performed, and the test function script is executed and the test results are recorded after each iteration. If no errors are found in all the above test results, it is determined that the server has passed the reliability test. However, this test method can only verify the reliability of the system for one application scenario.

[0077] 3) Perform performance tests on N server systems to determine the M performance scores and M weight coefficients corresponding to the M target performance indicators of these N server systems. Using L preset business models, M performance scores and M weight coefficients, calculate N preliminary performance scores of the N server systems and their corresponding N confidence levels. According to the target business processing requirements of the target users, the target server for processing the target business is selected based on these N preliminary performance scores and N confidence levels, thereby achieving the technical goal of improving the accuracy of server evaluation mechanism and resource allocation. This method is for the evaluation of server system performance, but does not provide a theoretical basis for the verification of comprehensive reliability indicators of server systems.

[0078] Reference Figure 1 , shows a flow chart of the steps of a server reliability testing method provided in an embodiment of the present invention, which may specifically include the following steps:

[0079] Step 101, obtaining historical fault information of a preset server and reliability requirements of the server;

[0080] In an embodiment of the present invention, a historical problem data table of the server can be obtained based on the historical usage of the server. The historical problem data table records the historical fault information of the server during the historical project and market operation of the server. The historical fault information refers to the information of the server fault during the historical use of the server.

[0081] In an embodiment of the present invention, the reliability requirement of the server can be obtained. Specifically, the reliability requirement can be expressed as "X nines". X is a number, usually between 3 and 6; "X nines" can represent the ratio of the time that the server can operate normally to the total time within 1 year of operation. If X is 3, the availability of the server is 0.999; if X is 4, the availability of the server is 0.9999; if X is 5, the availability of the server is 0.99999; if X is 6, the availability of the server is 0.999999. Therefore, the larger the number of X, the higher the reliability requirement of the server.

[0082] In some embodiments of the present invention, the obtaining of historical fault information of a preset server and reliability requirements of the server includes:

[0083] Obtaining quality requirements of the server;

[0084] The reliability requirement of the server is determined according to the quality requirement of the server.

[0085] Specifically, when obtaining the reliability requirements of the server, the quality requirements of the server may be obtained first. When the server is applied to different countries, regions, and industries, it usually has different quality requirements. According to the quality requirements of the server, the reliability requirements of the server may be determined.

[0086] Step 102, determining a historical occurrence probability of a failure of the server based on the historical failure information;

[0087] In the embodiment of the present invention, the historical occurrence probability of the server failure can be determined based on the acquired historical failure information. Specifically, the historical occurrence probability of the server failure can be 1% (percent sign), that is, 0.01.

[0088] Step 103, determining a test weight of the server based on the historical occurrence probability of the fault;

[0089] In an embodiment of the present invention, the test weight of the server can be determined based on the historical probability of occurrence of the fault. For example, in a real network environment, the server often has a link disconnection fault. This fault usually occurs when there is a problem with the switch or optical module of the server. Within one hour of the problem, thousands of link disconnection faults caused by bit errors may occur. In order to test this situation more accurately, the test weight of the server can be increased.

[0090] In some embodiments of the present invention, determining the test weight of the server based on the historical occurrence probability of the fault includes:

[0091] Obtaining a test purpose of the server;

[0092] The test weight of the server is determined based on the historical occurrence probability of the fault and / or the test purpose.

[0093] Specifically, when determining the test weight of a server, the test purpose of the server can be first obtained, and the test weight of the server can be determined based on the historical probability of failure and / or the test purpose. For example, if the purpose of the server test is to upgrade the CCU (Communication Control Unit), the test weight of the server can be reduced because the CCU version is usually upgraded once every few months or even two years in the current network environment.

[0094] In an embodiment of the present invention, if the server test is targeted at components that are not frequently upgraded, since the components that are not frequently upgraded are less likely to change in the existing network environment and therefore have a relatively low risk of causing problems, the server test weight can be reduced to improve the efficiency of the server test.

[0095] In an embodiment of the present invention, if the historical probability of failure of a server is high, the test weight of the server can be increased to increase the number of tests of the server, and the test weight of the server can also be determined based on the test purpose of the server to better evaluate and ensure the stability and reliability of the server.

[0096] Step 104, based on the reliability requirement and the historical occurrence probability, determining the number of tests required to be met by the server when a failure occurs in the server during a preset reliability test process;

[0097] In an embodiment of the present invention, based on the reliability requirements of the server and the historical probability of failure of the server, it is possible to determine the number of tests that the server needs to meet when a failure occurs during the reliability test, that is, the number of tests that the server has performed during the reliability test must meet the number of tests that the server needs to meet when a failure occurs.

[0098] In some embodiments of the present invention, the step of determining, based on the reliability requirement and the historical occurrence probability, a test number requirement to be met by the server when a failure occurs in the server during a preset reliability test, includes:

[0099] Determine a single failure probability of the server based on the historical occurrence probability of the failure; the single failure probability refers to the probability of the server failing in any single test during the reliability test;

[0100] Based on the reliability requirement and the single failure probability, the test times requirement for the server is determined.

[0101] In an embodiment of the present invention, when determining the number of tests to be met by the server in the event that the server fails during the reliability test, the single failure probability of the server can be determined based on the historical probability of failure of the server. Specifically, the historical probability of failure of the server can be used as the single failure probability of the server. The single failure probability can refer to the probability of failure of the server for any single test in the reliability test process. For example: if the historical probability of failure of the server is 1%, the single failure probability of the server is 0.01.

[0102] In an embodiment of the present invention, the reliability test process of the server includes at least one single test. For any single test, the server has two results: failure and no failure, and the single test result of the server conforms to the "0-1 distribution". It should be noted that the result of each single test of the server is random. If event A is used to indicate that the result of a single test is a server failure, the following formula can be used to represent the test result of the reliability test of the server:

[0103]

[0104] Where i represents the number of single tests, i can be 1, 2, ..., n; X i Indicates the i-th single test. 0 means that in the i-th single test, event A did not occur, that is, the result of the i-th single test was that the server did not fail; 1 means that in the i-th single test, event A occurred, that is, the result of the i-th single test was that the server failed. X1,X2,X3,…,X n Indicates that the single tests in different orders are independent random variable sequences, that is, the single tests are independent of each other and do not affect each other. If the probability of event A occurring is p, X i The probability of event A occurring and not occurring is P i Indicates that, according to the binomial distribution, the distribution law of the server reliability test is shown in Table 2 below.

[0105] Table 2: Distribution of server reliability tests

[0106]

[0107] In the embodiment of the present invention, based on the reliability requirement and single failure probability of the server, the test times requirement of the server can be determined.

[0108] In some embodiments of the present invention, determining the test times requirement of the server based on the reliability requirement and the single failure probability includes:

[0109] Based on the reliability requirement, determining the failure probability requirement of the server; the failure probability requirement refers to the probability requirement of the server having a target number of failures to be met during the target reliability test;

[0110] Based on the failure probability requirement and the single failure probability, the test times requirement for the server is determined.

[0111] In an embodiment of the present invention, when determining the test times requirement of the server based on the reliability requirement of the server and the probability of a single failure, the failure probability requirement of the server can be determined based on the reliability requirement of the server. The failure probability requirement refers to the requirement on the probability of a target number of failures that the server needs to meet during the target reliability test. Among them, the target number of times can be at least once. If the reliability requirement is "3 nines", the failure probability requirement refers to the requirement that the server needs to meet the probability of at least one failure being 99.9% during the target reliability test, that is, the probability of a target number of failures that the server needs to meet is the availability corresponding to "X nines".

[0112] In the embodiment of the present invention, based on the failure probability requirement and single failure probability of the server, the test times requirement of the server can be determined.

[0113] In some embodiments of the present invention, determining the test times requirement of the server based on the failure probability requirement and the single failure probability includes:

[0114] Based on the failure probability requirement and the single failure probability, a test number calculation formula is used to determine the number of tests included in the test number requirement;

[0115] The test number calculation formula is:

[0116]

[0117] Wherein, N is the number of tests, p is the single failure probability, and q is the probability of the target number of failures to be met.

[0118] In the embodiment of the present invention, the number of tests included in the test number requirement may be determined based on the failure probability requirement and the single failure probability by using a test number calculation formula.

[0119] The formula for calculating the number of tests can be:

[0120]

[0121] Where N is the number of tests, p is the probability of a single failure, and q is the probability of a target number of failures to be met.

[0122] In the embodiment of the present invention, according to the quality requirements of the server and in combination with the probability distribution calculation method, a reasonable calculation formula is provided for designing the test times of the repeated test in the accelerated aging test.

[0123] In some embodiments of the invention, the method comprises:

[0124] Based on a preset failure probability calculation formula, the test number calculation formula is obtained; the failure probability calculation formula is a calculation formula for the probability of the server having a target number of failures during the target reliability test;

[0125] The failure probability calculation formula is:

[0126] P=1-(1-p) N

[0127] Wherein, P is the probability of the server failing a target number of times.

[0128] In the embodiment of the present invention, if p is used to represent the probability of a single failure of the server, and p is 0.01, then during a single test of 1 / p, the server will fail once. The probability that no failure occurs in a single test of the server is 1-p. If P is used to represent the probability of a server failure during a single test of 1 / p, then the calculation formula for the probability of a server failure during a single test of 1 / p is:

[0129]

[0130] Therefore, if p is 0.01, the probability of a server failure occurring once in 100 single tests is 63.40%.

[0131] According to the calculation formula of the probability of a server failure during a single test of 1 / p, a failure probability calculation formula can be obtained. The failure probability calculation formula is a calculation formula for the probability of a server failure occurring a target number of times during a target reliability test. The target number of times can be at least once.

[0132] The failure probability calculation formula is:

[0133] P=1-(1-p) N

[0134] The failure probability calculation formula can also be:

[0135] P≤1-(1-p) N

[0136] Among them, P is the probability of the server failing the target number of times during the target reliability test, N is the number of tests, and p is the probability of a single failure.

[0137] In the embodiment of the present invention, based on the failure probability calculation formula, a test number calculation formula can be converted.

[0138] Specifically, the probability of the target number of failures to be met by the server during the target reliability test corresponds to the probability of the target number of failures to be met by the server during the target reliability test. If q is used to represent the probability of the target number of failures to be met by the server during the target reliability test, the calculation formula for the number of tests included in the number of tests to be met by the server is:

[0139]

[0140] Where N is the number of tests, p is the probability of a single failure, and q is the probability of the target number of failures to be met. If p is 0.01 and q is 0.99, then N≥458; if p is 0.01 and q is 0.999, then N≥687; if p is 0.01 and q is 0.9999, then N≥916; if p is 0.01 and q is 0.99999, then N≥1145; if p is 0.01 and q is 0.999999, then N≥1374.

[0141] Step 105, determining a target test number of the server based on the test weight and the test number requirement;

[0142] In the embodiment of the present invention, based on the test weight of the server and the test number requirement to be met by the server, the target test number of the server can be determined.

[0143] In some embodiments of the present invention, determining the target number of tests for the server based on the test weight and the test number requirement includes:

[0144] A target test number for the server is determined based on the test weight and the test number included in the test number requirement.

[0145] In the embodiment of the present invention, based on the test weight of the server and the number of tests included in the test number requirement, the target number of tests for the server can be determined.

[0146] In some embodiments of the present invention, determining the target number of tests for the server based on the test weight and the number of tests included in the test number requirement includes:

[0147] Using a preset target test number calculation formula to determine the target test number of the server;

[0148] The target test number calculation formula is:

[0149] SN=N*K

[0150] Wherein, K is the test weight, and SN is the target test number.

[0151] In the embodiment of the present invention, the target test times calculation formula is adopted to determine the target test times of the server.

[0152] The target number of tests is calculated as follows:

[0153] SN=N*K

[0154] Among them, K is the test weight and SN is the target number of tests.

[0155] In an embodiment of the present invention, additional weighted calculation is performed on the calculation result of the test number calculation formula according to the historical probability of occurrence of failures and the test purpose of the server, which provides a scientific basis for the design of server reliability testing, helps to discover server failure problems and achieve controllable server research project plans.

[0156] Step 106: Perform a target reliability test on the server based on the target test number.

[0157] In the embodiment of the present invention, based on the target test times, a target reliability test of the server can be performed. According to the test result of the target reliability of the server, it can be determined whether the server meets the reliability requirement.

[0158] In some embodiments of the invention, the method comprises:

[0159] Based on the result of the target reliability test, it is determined whether the server meets the reliability requirement; if the server does not fail during the target reliability test, the server meets the reliability requirement.

[0160] In the embodiment of the present invention, based on the result of the target reliability test, it can be determined whether the server meets the reliability requirement. Specifically, if the server does not fail during the target reliability test, the server meets the reliability requirement. For example, if the target test number is 1374 times, after 1374 single tests, if the server does not fail, the server meets the reliability requirement.

[0161] In an embodiment of the present invention, based on the result of the target reliability test, it is determined whether the server meets the reliability requirements. If the server does not fail during the target reliability test, the server meets the reliability requirements, thereby realizing the analysis of the test results and setting specific test completion standards for repeated tests in accelerated aging tests.

[0162] In some embodiments of the present invention, the server includes at least one server unit to be tested; the server unit is a hardware device and / or a software system; the obtaining of historical fault information of a preset server and reliability requirements of the server includes:

[0163] Acquire historical fault information of the server unit and reliability requirements of the server unit;

[0164] The determining, based on the historical fault information, a historical occurrence probability of a fault of the server includes:

[0165] Based on the historical failure information of the server unit, a historical occurrence probability of failure of the server unit is determined.

[0166] In an embodiment of the present invention, the server includes at least one server unit to be tested. The server unit may be a hardware device and / or a software system. Historical fault information of the server unit and reliability requirements of the server unit may be obtained. Based on the historical fault information, the historical probability of occurrence of the fault of the server unit may be determined. Based on the historical probability of occurrence of the fault, the test weight of the server unit may be determined. Based on the reliability requirements and the historical probability of occurrence, the number of test requirements to be met by the server in the event that the server unit fails during a preset reliability test process may be determined. Based on the test weight and the number of test requirements, the target number of tests for the server unit may be determined, and based on the target number of tests, the target reliability test of the server unit may be performed.

[0167] In some embodiments of the present invention, the step of determining, based on the reliability requirement and the historical occurrence probability, a test number requirement to be met by the server when a failure occurs in the server during a preset reliability test, includes:

[0168] Based on the historical occurrence probability of failure of the server unit, determining the single failure probability of the server unit; the single failure probability of the server unit refers to the probability of failure of the server unit for any single test in the reliability test process;

[0169] Based on the reliability requirement of the server unit, determining the failure probability requirement of the server unit; the failure probability requirement of the server unit refers to the probability requirement of the server unit having a target number of failures to be met during the target reliability test;

[0170] The test times requirement of the server unit is determined based on the failure probability requirement and the single failure probability of the server unit.

[0171] In an embodiment of the present invention, based on the historical probability of occurrence of failures of the server unit, the single failure probability of the server unit can be determined. The single failure probability of the server unit refers to the probability of failure of the server unit for any single test in the reliability test process. Based on the reliability requirements of the server unit, the failure probability requirements of the server unit can be determined; the failure probability requirements of the server unit refer to the requirements for the probability of a target number of failures that the server unit needs to meet during the target reliability test. Based on the failure probability requirements and the single failure probability of the server unit, the test number requirements of the server unit can be determined.

[0172] In an embodiment of the present invention, historical fault information of a preset server and reliability requirements of the server are obtained. Based on the historical fault information, the historical probability of occurrence of the server fault is determined; based on the historical probability of occurrence of the fault, the test weight of the server is determined; based on the reliability requirements and the historical probability of occurrence, the number of tests to be met by the server in the case of a failure in the preset reliability test process is determined. Based on the test weight and the number of tests required, the target number of tests for the server can be determined, and based on the target number of tests, the target reliability test of the server is performed, which provides theoretical support for the design of the number of tests for repeated tests in accelerated aging tests, and provides a clear theoretical framework to guide the design of the number of tests. According to the quality requirements of the server, combined with the probability distribution calculation method, a reasonable calculation formula is provided for the design of the number of tests for repeated tests in accelerated aging tests, and an additional weighted calculation is performed on the calculation result of the test number calculation formula according to the historical probability of occurrence of the fault and the test purpose of the server, which provides a scientific basis for the design of server reliability testing, helps to discover server failure problems and realize the controllability of server research project plans.

[0173] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0174] Reference Figure 2 , shows a structural block diagram of a server reliability testing device provided in an embodiment of the present invention, which may specifically include the following modules:

[0175] The information acquisition module 201 is used to acquire historical fault information of a preset server and reliability requirements of the server;

[0176] A historical occurrence probability determination module 202, configured to determine a historical occurrence probability of a failure of the server based on the historical failure information;

[0177] A test weight determination module 203, configured to determine a test weight of the server based on the historical occurrence probability of the fault;

[0178] A test number requirement determination module 204, configured to determine, based on the reliability requirement and the historical occurrence probability, a test number requirement to be met by the server in the event that the server fails during a preset reliability test process;

[0179] A target test times determination module 205, configured to determine a target test times of the server based on the test weight and the test times requirement;

[0180] The test performing module 206 is configured to perform a target reliability test on the server based on the target test number.

[0181] In an optional embodiment of the present invention, the test number requirement determination module includes:

[0182] A single failure probability determination submodule, used to determine the single failure probability of the server based on the historical occurrence probability of the failure; the single failure probability refers to the probability of the server failing for any single test in the reliability test process;

[0183] The test number requirement determination submodule is used to determine the test number requirement of the server based on the reliability requirement and the single failure probability.

[0184] In an optional embodiment of the present invention, the test number requirement determination submodule includes:

[0185] A failure probability requirement determination unit, configured to determine a failure probability requirement of the server based on the reliability requirement; the failure probability requirement refers to a requirement on the probability of a target number of failures to be met by the server during the target reliability test;

[0186] The test number requirement determining unit is used to determine the test number requirement of the server based on the failure probability requirement and the single failure probability.

[0187] In an optional embodiment of the present invention, the test number requirement determining unit includes:

[0188] A test number determination subunit, used to determine the number of tests included in the test number requirement based on the failure probability requirement and the single failure probability by using a test number calculation formula;

[0189] The test number calculation formula is:

[0190]

[0191] Wherein, N is the number of tests, p is the single failure probability, and q is the probability of the target number of failures to be met.

[0192] In an optional embodiment of the present invention, the target test number determination module includes:

[0193] The target test number determination submodule is used to determine the target test number of the server based on the test weight and the test number included in the test number requirement.

[0194] In an optional embodiment of the present invention, the target test number determination submodule includes:

[0195] A target test number determination unit, configured to determine the target test number of the server using a preset target test number calculation formula;

[0196] The target test number calculation formula is:

[0197] SN=N*K

[0198] Wherein, K is the test weight, and SN is the target test number.

[0199] In an optional embodiment of the present invention, the device comprises:

[0200] A test number calculation formula acquisition module is used to acquire the test number calculation formula based on a preset failure probability calculation formula; the failure probability calculation formula is a calculation formula for the probability of the server having a target number of failures during the target reliability test;

[0201] The failure probability calculation formula is:

[0202] P=1-(1-p) N

[0203] Wherein, P is the probability of the server failing a target number of times.

[0204] In an optional embodiment of the present invention, the device comprises:

[0205] The judgment module is used to judge whether the server meets the reliability requirement based on the result of the target reliability test; if the server does not fail during the target reliability test, the server meets the reliability requirement.

[0206] In an optional embodiment of the present invention, the test weight determination module includes:

[0207] A test purpose acquisition submodule, used to acquire the test purpose of the server;

[0208] A test weight determination submodule is used to determine the test weight of the server based on the historical occurrence probability of the fault and / or the test purpose.

[0209] In an optional embodiment of the present invention, the information acquisition module includes:

[0210] A quality requirement acquisition submodule, used to acquire the quality requirements of the server;

[0211] The reliability requirement determination submodule is used to determine the reliability requirement of the server according to the quality requirement of the server.

[0212] In an optional embodiment of the present invention, the server includes at least one server unit to be tested; the server unit is a hardware device and / or a software system; the information acquisition module includes:

[0213] An information acquisition submodule, used to acquire historical fault information of the server unit and reliability requirements of the server unit;

[0214] The historical occurrence probability determination module includes:

[0215] The historical occurrence probability determination submodule is used to determine the historical occurrence probability of the failure of the server unit based on the historical failure information of the server unit.

[0216] In an optional embodiment of the present invention, the test number requirement determination module includes:

[0217] A single failure probability determination submodule, used to determine the single failure probability of the server unit based on the historical occurrence probability of the failure of the server unit; the single failure probability of the server unit refers to the probability of the server unit failing for any single test in the reliability test process;

[0218] A failure probability requirement determination submodule is used to determine the failure probability requirement of the server unit based on the reliability requirement of the server unit; the failure probability requirement of the server unit refers to the probability requirement of the target number of failures to be met by the server unit during the target reliability test;

[0219] The test times requirement determination submodule is used to determine the test times requirement of the server unit based on the failure probability requirement and the single failure probability of the server unit.

[0220] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0221] Some embodiments of the present invention further provide a computer program product, including a computer program, which implements the above-mentioned server reliability testing method when executed by a processor.

[0222] Some embodiments of the present invention further provide a computer device, comprising a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the above-mentioned server reliability testing method when executed by the processor.

[0223] Some embodiments of the present invention further provide a computer-readable storage medium storing a computer program, which implements the server reliability testing method as described above when executed by a processor.

[0224] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0225] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of 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 embodiments of 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.

[0226] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the 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 the 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 data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal 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.

[0227] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0228] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0229] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0230] Finally, 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. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal 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, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the above elements.

[0231] The above is a detailed introduction to a server reliability testing method, device, storage medium and product provided. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for testing server reliability, characterized in that: The method comprises: Obtaining historical failure information of a preset server and reliability requirements of the server; Based on the historical failure information, determining a historical occurrence probability of a failure of the server; Determining a test weight of the server based on a historical probability of occurrence of the fault; Based on the reliability requirement and the historical occurrence probability, determining a test number requirement to be met by the server in the event that the server fails during a preset reliability test process; Determining a target number of tests for the server based on the test weight and the test number requirement; Based on the target test number, performing a target reliability test on the server; Wherein, the determining, based on the reliability requirement and the historical occurrence probability, of the number of tests to be met by the server when a failure occurs in the server during a preset reliability test process includes: Determine a single failure probability of the server based on the historical occurrence probability of the failure; the single failure probability refers to the probability of the server failing for any single test in the reliability test process; Determining the test times requirement for the server based on the reliability requirement and the single failure probability; Wherein, determining the test number requirement of the server based on the reliability requirement and the single failure probability includes: Based on the reliability requirement, determining the failure probability requirement of the server; the failure probability requirement refers to the probability requirement of the server having a target number of failures to be met during the target reliability test; Determining the test times requirement for the server based on the failure probability requirement and the single failure probability; Wherein, determining the test times requirement of the server based on the failure probability requirement and the single failure probability includes: Based on the failure probability requirement and the single failure probability, a test number calculation formula is used to determine the number of tests included in the test number requirement; The test number calculation formula is: Wherein, N is the number of tests, p is the single failure probability, and q is the probability of the target number of failures to be met.

2. The method according to claim 1, characterized in that The determining a target number of tests for the server based on the test weight and the test number requirement includes: A target test number for the server is determined based on the test weight and the test number included in the test number requirement.

3. The method according to claim 2, characterized in that The determining a target test number of the server based on the test weight and the test number included in the test number requirement includes: Using a preset target test number calculation formula to determine the target test number of the server; The target test number calculation formula is: SN=N*K Wherein, K is the test weight, and SN is the target test number.

4. The method according to claim 1, characterized in that: The method comprises: Based on a preset failure probability calculation formula, the test number calculation formula is obtained; the failure probability calculation formula is a calculation formula for the probability of the server having a target number of failures during the target reliability test; The failure probability calculation formula is: P=1-(1-p) N Wherein, P is the probability of the server failing a target number of times.

5. The method according to claim 1, characterized in that The method comprises: Based on the result of the target reliability test, it is determined whether the server meets the reliability requirement; if the server does not fail during the target reliability test, the server meets the reliability requirement.

6. The method according to claim 1, characterized in that The determining the test weight of the server based on the historical occurrence probability of the fault includes: Obtaining a test purpose of the server; The test weight of the server is determined based on the historical occurrence probability of the fault and / or the test purpose.

7. The method according to claim 1, characterized in that The obtaining of historical fault information of a preset server and reliability requirements of the server includes: Obtaining quality requirements of the server; The reliability requirement of the server is determined according to the quality requirement of the server.

8. The method according to claim 1, characterized in that The server includes at least one server unit to be tested; the server unit is a hardware device and / or a software system; the obtaining of historical fault information of a preset server and reliability requirements of the server includes: Acquire historical fault information of the server unit and reliability requirements of the server unit; The determining, based on the historical fault information, a historical occurrence probability of a fault of the server includes: Based on the historical failure information of the server unit, a historical occurrence probability of failure of the server unit is determined.

9. The method according to claim 8, characterized in that The determining, based on the reliability requirement and the historical occurrence probability, a test number requirement to be met by the server when a failure occurs in the server during a preset reliability test, includes: Based on the historical occurrence probability of failure of the server unit, determining the single failure probability of the server unit; the single failure probability of the server unit refers to the probability of failure of the server unit for any single test in the reliability test process; Based on the reliability requirement of the server unit, determining the failure probability requirement of the server unit; the failure probability requirement of the server unit refers to the probability requirement of the server unit having a target number of failures to be met during the target reliability test; The test times requirement of the server unit is determined based on the failure probability requirement and the single failure probability of the server unit.

10. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 9 when executed by the processor.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

12. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 9.

Images