WO2019052208A1 - 一种内存评估的方法及装置 - Google Patents

一种内存评估的方法及装置 Download PDF

Info

Publication number
WO2019052208A1
WO2019052208A1 PCT/CN2018/087360 CN2018087360W WO2019052208A1 WO 2019052208 A1 WO2019052208 A1 WO 2019052208A1 CN 2018087360 W CN2018087360 W CN 2018087360W WO 2019052208 A1 WO2019052208 A1 WO 2019052208A1
Authority
WO
WIPO (PCT)
Prior art keywords
memory
health
evaluated
factor
operating parameter
Prior art date
Application number
PCT/CN2018/087360
Other languages
English (en)
French (fr)
Inventor
叶铮
张飞
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP18855251.7A priority Critical patent/EP3712773B1/en
Priority to EP23158131.5A priority patent/EP4220409A3/en
Publication of WO2019052208A1 publication Critical patent/WO2019052208A1/zh
Priority to US16/816,597 priority patent/US11354183B2/en
Priority to US17/741,765 priority patent/US11868201B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
    • G06F11/0766—Error or fault reporting or storing
    • G06F11/0772—Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3037—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a memory, e.g. virtual memory, cache
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/008—Reliability or availability analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
    • G06F11/0706—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment
    • G06F11/073—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment in a memory management context, e.g. virtual memory or cache management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
    • G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
    • G06F11/0751—Error or fault detection not based on redundancy
    • G06F11/0754—Error or fault detection not based on redundancy by exceeding limits
    • G06F11/076—Error or fault detection not based on redundancy by exceeding limits by exceeding a count or rate limit, e.g. word- or bit count limit
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
    • G06F11/321—Display for diagnostics, e.g. diagnostic result display, self-test user interface
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3447—Performance evaluation by modeling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3452—Performance evaluation by statistical analysis
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
    • G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
    • G11C29/08—Functional testing, e.g. testing during refresh, power-on self testing [POST] or distributed testing
    • G11C29/12—Built-in arrangements for testing, e.g. built-in self testing [BIST] or interconnection details
    • G11C29/44—Indication or identification of errors, e.g. for repair
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
    • G11C7/04—Arrangements for writing information into, or reading information out from, a digital store with means for avoiding disturbances due to temperature effects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • G06F11/3419—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment by assessing time
    • G06F11/3423—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment by assessing time where the assessed time is active or idle time
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C29/00—Checking stores for correct operation ; Subsequent repair; Testing stores during standby or offline operation
    • G11C29/04—Detection or location of defective memory elements, e.g. cell constructio details, timing of test signals
    • G11C2029/0409—Online test

Definitions

  • the embodiments of the present invention relate to the field of computer technologies, and in particular, to a method and an apparatus for memory evaluation.
  • the problem is that the prior art determines whether the memory can work normally based on whether the memory is faulty or not, and the memory failure has already affected the normal operation of the server. For example, when it is judged that the memory is not available, the memory has caused serious downtime such as server downtime, business damage, and even data loss.
  • the present application provides a memory evaluation method and device for evaluating the health of a memory in a server, and prompting a user to replace the memory when the memory is not faulty and has low health, so that the memory can support the memory.
  • the server is running normally.
  • a method for memory evaluation comprising: determining a health assessment model of a memory to be evaluated, wherein the health assessment model is a health of a memory to be evaluated with respect to at least one health influence factor of a memory to be evaluated Relationship, a health influencing factor corresponds to an operating parameter and a failure rate parameter, and a health influencing factor corresponds to a weight, the weight is a constant; obtaining at least one health influencing factor corresponding to each health influencing factor At least one operating parameter value corresponding to one of the operating parameters; matching at least one operating parameter value corresponding to each health influencing factor to the health assessment model to obtain the health of the memory to be evaluated According to the health of the memory to be evaluated, the health indication information of the memory to be evaluated is output, and the health indication information of the memory to be evaluated is used to indicate to the user whether the memory to be evaluated needs to be replaced.
  • the present application provides a health assessment model that describes the relationship between the health of the memory to be evaluated and the change of at least one health impact factor of the memory to be evaluated, so that the device for memory evaluation can be based on the health of the memory to be evaluated.
  • the evaluation model obtains the health of the memory to be evaluated. Therefore, the device for memory evaluation can generate the health indication information of the memory to be evaluated according to the value of the health of the memory to be evaluated. That is to say, the device for memory evaluation can determine whether the memory to be evaluated is replaced before the memory to be evaluated fails due to the health of the memory to be evaluated.
  • the device for memory evaluation may output the health indication information of the memory to be evaluated if the memory does not fail and the health of the memory is low, so as to prompt the user to replace the memory, so that the memory can support the server. run.
  • the weight corresponding to the health impact factor may indicate the degree of influence of the health influence factor on the health of the memory to be evaluated, and the health impact factors of different weights have different effects on the health of the memory. For example, the greater the weight corresponding to a health impact factor, the greater the impact of the health impact factor on the health of the memory being evaluated.
  • the weight of each health influencing factor in the health assessment model provided by the present application may indicate the influence of each health influencing factor on the health of the memory to be evaluated, so that the health assessment model is for the memory to be evaluated.
  • the degree of influence of different health assessment factors is more in line with the memory to be evaluated, which is helpful for accurately assessing the health of the memory to be evaluated.
  • the at least one operating parameter value corresponding to each health impact factor is matched to the health assessment model, and the health of the memory to be evaluated may include: each health impact factor Corresponding at least one operating parameter value is respectively matched to the first sub-model of the corresponding health influencing factor in the health assessment model, and the fitness loss value corresponding to each health influencing factor is obtained; the health assessment model includes a second sub-model, and a first sub-model corresponding to each health-influencing factor, a first sub-model of a health-influencing factor is a fitness-related impairment value corresponding to the health-influencing factor corresponding to the health-influencing factor The relationship between the operating parameter and the failure rate parameter; the second sub-model is the health of the memory to be evaluated, the health loss value corresponding to each health factor and the weight value corresponding to each health factor Relationship; the fitness loss value corresponding to each health factor, the weight corresponding to each health factor, and Two sons model healthy degree of memory to be assessed.
  • the device for memory evaluation may obtain the health degree of the memory to be evaluated corresponding to each health influencing factor according to the first sub-model corresponding to each health influencing factor in the health assessment model.
  • the value of the loss is used to indicate the impact of each health factor on the health of the memory being evaluated.
  • different health assessment models can be generated for different memory to be evaluated, which is beneficial to improve the accuracy of the health of the memory to be evaluated obtained according to the health assessment model.
  • the at least one health impact factor includes one or more of the following: a memory operating temperature factor, a memory service load factor, a total memory running time factor, a memory plugging factor, and a memory correctable error CE. Frequency factor, memory uncorrectable error UCE frequency factor and memory performance attenuation factor.
  • the health assessment model provided by the present application presets a plurality of health influence factors, so that the user can select corresponding health influence factors for different memory to be evaluated, so that the health assessment model is for the memory to be evaluated.
  • the health assessment factor is more in line with the memory to be evaluated, which is helpful for accurately assessing the health of the memory to be evaluated.
  • the running parameter corresponding to the memory running temperature factor is an operating temperature of the memory to be evaluated; the operating parameter corresponding to the memory service load factor is the number of charging and discharging of the memory to be evaluated; and the total running time factor of the memory
  • the corresponding running parameter is the total running time of the memory to be evaluated; the running parameter corresponding to the memory plugging factor is the number of times of the memory to be evaluated; the operating parameter corresponding to the memory CE frequency factor is the number of CEs to be evaluated and / or the CE frequency of the memory to be evaluated; the operating parameter corresponding to the memory UCE frequency factor is the UCE number of the memory to be evaluated and/or the UCE frequency of the memory to be evaluated; the operating parameter corresponding to the memory performance attenuation factor is to be Evaluate the amount of performance degradation of the memory.
  • the device for memory evaluation may store data describing the relationship between the operating parameter and the failure rate parameter corresponding to each health impact factor, such as describing the failure rate parameter of the memory to be evaluated with respect to the corresponding operating parameter change. Curve.
  • the curve of the failure rate parameter of the above-mentioned memory to be evaluated with respect to the corresponding operation parameter change is pre-statisticd data. In this way, the memory evaluation device can evaluate the health of the memory to be evaluated that has not failed based on the data obtained from the existing statistics.
  • each of the at least one health impact factor included in the health assessment model corresponds to an algorithm, and the algorithm may be addition and/or multiplication.
  • the above “according to the fitness loss value corresponding to each health factor, the weight corresponding to each health factor and the second sub-model, and obtaining the health of the memory to be evaluated” may include factors according to each health factor. Corresponding health loss value, weight corresponding to each health factor and second sub-model, and an algorithm corresponding to each health factor affecting the health of the memory to be evaluated.
  • the memory evaluation device quantifies the health of the memory according to the weight corresponding to each health influence factor of the memory.
  • the degree of influence of each health influence factor on the health of the memory can be further quantified. In this way, it is beneficial to improve the accuracy of the health of the memory to be evaluated.
  • the outputting the health indication information of the memory to be evaluated according to the health of the memory to be evaluated may include: if the value of the health of the memory to be evaluated is within the first preset value interval And outputting the first health degree indication information, where the first health degree indication information is used to prompt the user that the memory to be evaluated does not need to be replaced; and when the value of the health of the memory to be evaluated is within the second preset value interval, outputting the second The health indicator information is used to prompt the user that the memory to be evaluated can be replaced. If the value of the health of the memory to be evaluated is within the third preset value range, the third health indicator information is output. The third health degree indication information is used to prompt the user that the memory to be evaluated needs to be replaced.
  • the memory evaluation device may display different health for the memory to be evaluated with different health values. Degree indication information. In this way, in the case that the memory to be evaluated does not fail and the memory is low in health (the health value is small), the memory evaluation device prompts the user to replace the memory to be evaluated, so that the memory to be evaluated supports the server. normal operation.
  • the determining the health assessment model of the memory to be evaluated includes: receiving at least one health influence factor set by the user; determining at least one health influence factor set by the user as the health of the memory to be evaluated Evaluating a health-influencing factor included in the model; determining a corresponding first sub-model according to at least one health-influencing factor; receiving a weight and an algorithm corresponding to each health-influencing factor of the at least one health-influencing factor set by the user; The weights and algorithms corresponding to the health influence factors determine the second submodel.
  • the devices for memory evaluation may determine a first sub-model corresponding to each health impact factor of different memory to be evaluated and a second sub-model of the memory to be evaluated, that is, determine Different health assessment models for the memory to be evaluated.
  • the health assessment model provided by the embodiment of the present invention can be made to conform to the memory to be evaluated, which is beneficial to improving the accuracy of the health of the memory to be evaluated obtained according to the health assessment model.
  • the method for memory evaluation provided by the present application before generating the health indication information of the memory to be evaluated according to the health of the memory to be evaluated, further includes: receiving a first preset value set by the user. The interval, the second preset value interval, and the third preset value interval.
  • the user may set different preset value intervals for different memory to be evaluated, so that the memory evaluation device obtains the health indication of the memory to be evaluated according to the preset value interval.
  • the information is more in line with the memory to be evaluated, which helps to more accurately prompt the user whether the memory to be evaluated needs to be replaced.
  • the method for memory evaluation inputs the operating parameter values corresponding to each health impact factor into the health assessment model to obtain the health of the memory to be evaluated, and further The method includes: receiving an update of the template data of the user to be evaluated, where the template data includes at least one or more of the following: at least one health impact factor, an operational parameter corresponding to each health impact factor of the at least one health impact factor, a weight corresponding to each health influence factor, an algorithm corresponding to each health influence factor, a first preset value interval, a second preset value interval, and a third preset value interval; according to the updated memory to be evaluated Template data, update the health assessment model.
  • the memory evaluation device obtains the health of the memory to be evaluated according to the updated health assessment model.
  • the memory to be evaluated helps to more accurately prompt the user whether the memory to be evaluated needs to be replaced.
  • the present application provides an apparatus for memory evaluation, the apparatus comprising: a determining module, an obtaining module, a matching module, and an output module.
  • the determining module is configured to determine a health assessment model of the memory to be evaluated, where the health assessment model is a relationship between the health of the memory to be evaluated and the change of at least one health influence factor of the memory to be evaluated, and a health influence factor.
  • Corresponding to one operating parameter and one failure rate parameter, and one health factor affecting factor corresponds to one weight, and the weight is constant.
  • the obtaining module is configured to obtain at least one operating parameter value corresponding to each health influencing factor of the at least one health influencing factor determined by the determining module, and the at least one running parameter value corresponds to one operating parameter.
  • the matching module is configured to match the at least one operating parameter value corresponding to each health impact factor obtained by the obtaining module to the health assessment model to obtain the health of the memory to be evaluated.
  • the output module is configured to output the health indication information of the memory to be evaluated according to the health of the memory to be evaluated obtained by the matching module, where the health indication information of the memory to be evaluated is used to indicate to the user whether the memory to be evaluated needs to be replaced.
  • the matching module is specifically configured to match at least one operating parameter value corresponding to each health impact factor to a first sub-model of a corresponding health impact factor in the health assessment model.
  • the fitness loss value corresponding to each health factor is obtained;
  • the health assessment model includes a second sub-model, and a first sub-model corresponding to each health-influencing factor, and a health-influencing factor first
  • the sub-model is the relationship between the health-related impairment value corresponding to the health-influencing factor and the operating parameter and the failure rate parameter corresponding to the health-influencing factor;
  • the second sub-model is the health of the memory to be evaluated with respect to each health degree.
  • the relationship between the fitness loss value corresponding to the influencing factor and the weight change corresponding to each health influencing factor; the fitness loss value corresponding to each health influencing factor, the weight corresponding to each health influencing factor, and The second sub-model obtains the health of the memory to be evaluated.
  • the at least one health impact factor includes one or more of the following: a memory operating temperature factor, a memory service load factor, a total memory running time factor, a memory plugging factor, and a memory correctable error CE. Frequency factor, memory uncorrectable error UCE frequency factor and memory performance attenuation factor.
  • the running parameter corresponding to the memory running temperature factor is an operating temperature of the memory to be evaluated; the operating parameter corresponding to the memory service load factor is the number of charging and discharging of the memory to be evaluated; and the total running time factor of the memory
  • the corresponding running parameter is the total running time of the memory to be evaluated; the running parameter corresponding to the memory plugging factor is the number of times of the memory to be evaluated; the operating parameter corresponding to the memory CE frequency factor is the number of CEs to be evaluated and / or the CE frequency of the memory to be evaluated; the operating parameter corresponding to the memory UCE frequency factor is the UCE number of the memory to be evaluated and/or the UCE frequency of the memory to be evaluated; the operating parameter corresponding to the memory performance attenuation factor is to be Evaluate the amount of performance degradation of the memory.
  • each of the at least one health impact factor included in the health assessment model corresponds to an algorithm, and the algorithm may be addition and/or multiplication.
  • the matching module is further configured to: according to the fitness loss value corresponding to each health influencing factor, the weight corresponding to each health influencing factor, and the second sub-model, and an algorithm corresponding to each health influencing factor, The health of the memory to be evaluated.
  • the output module is configured to output a first health degree indication information, where the value of the health of the memory to be evaluated is within a first preset value interval, where the first health indicator is The information is used to prompt the user that the memory to be evaluated does not need to be replaced; if the value of the health of the memory to be evaluated is within the second preset value interval, the second health degree indication information is output, and the second health degree indication information is used for prompting
  • the memory to be evaluated by the user may be replaced; if the value of the health of the memory to be evaluated is within the third preset value interval, the third health degree indication information is output, and the third health degree indication information is used to prompt the user to evaluate the memory requirement. replace.
  • the determining module includes a receiving submodule and a determining submodule.
  • the receiving submodule is configured to receive at least one health influence factor set by a user.
  • the determining submodule is configured to determine at least one health influence factor of the user setting received by the receiving submodule as a health influence factor included in the health assessment model of the memory to be evaluated; determining a corresponding number according to at least one health influence factor A submodel.
  • the receiving submodule is further configured to receive a weight and an algorithm corresponding to each health impact factor of the at least one health impact factor set by the user.
  • the determining submodule is further configured to determine the second submodel according to the weight and algorithm corresponding to each health impact factor received by the receiving submodule.
  • the receiving submodule is specifically configured to receive at least one health impact factor set by a user and an operating parameter and a failure rate parameter corresponding to each health impact factor.
  • the receiving sub-module is further configured to: before generating the health indication information of the memory to be evaluated according to the health of the memory to be evaluated, receiving a first preset value interval set by the user, and second The preset value interval and the third preset value interval.
  • the receiving submodule is further configured to: after the matching module matches the operating parameter values corresponding to each health influencing factor to the health assessment model, and obtain the health of the memory to be evaluated. , receiving an update of the template data that the user is evaluating the memory.
  • the template data includes at least one or more of the following: at least one health influencing factor, at least one health influencing factor, an operating parameter corresponding to each health influencing factor, a weight corresponding to each health influencing factor, and each An algorithm corresponding to the health influence factor, the first preset value interval, the second preset value interval, and the third preset value interval.
  • the determining submodule is further configured to update the health assessment model according to the template data of the updated memory to be evaluated obtained by the receiving submodule.
  • the present application provides an apparatus for memory evaluation, the apparatus comprising: a processor, a hard disk, at least one memory, a communication interface, an input device, a display, and a bus.
  • the hard disk and the at least one memory are used to store at least one instruction, and the processor, the hard disk, the at least one memory, the communication interface, the input device, and the display are connected by a bus.
  • the processor executes the hard disk and at least one instruction stored in the memory to cause the memory evaluation device to perform the memory evaluation method as shown in the first aspect above and various implementations thereof.
  • the present application provides a computer storage medium comprising: at least one instruction; when the at least one instruction is run on a computer, causing the computer to perform as shown in the first aspect above and various implementations thereof The method of memory evaluation.
  • the application provides a computer program product comprising: at least one instruction; when the at least one instruction is run on a computer, causing the computer to perform as shown in the first aspect above and various implementations thereof The method of memory evaluation.
  • FIG. 1 is a schematic structural diagram of a hardware of a server according to an embodiment of the present invention.
  • FIG. 2 is a schematic structural diagram of an apparatus for memory evaluation according to an embodiment of the present invention.
  • FIG. 2a is another schematic structural diagram of an apparatus for memory evaluation according to an embodiment of the present invention.
  • FIG. 3 is a schematic diagram of an MC interface according to an embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of a method for memory evaluation according to an embodiment of the present invention.
  • FIG. 5 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 8 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 9 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 10 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 11 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 12 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 13 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 14 is another schematic flowchart of a method for memory evaluation according to an embodiment of the present disclosure.
  • FIG. 15 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • 16 is another schematic flowchart of a method for memory evaluation according to an embodiment of the present invention.
  • FIG. 17 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 18 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 19 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 20 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 21 is another schematic flowchart of a method for memory evaluation according to an embodiment of the present disclosure.
  • FIG. 22 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 23 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 24 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 25 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • 26 is another schematic flowchart of a method for memory evaluation according to an embodiment of the present invention.
  • FIG. 27 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 28 is a schematic diagram of another MC interface according to an embodiment of the present invention.
  • FIG. 29 is another schematic flowchart of a method for memory evaluation according to an embodiment of the present disclosure.
  • FIG. 30 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • FIG. 31 is a schematic diagram of another MC interface according to an embodiment of the present disclosure.
  • 32 is another schematic flowchart of a method for memory evaluation according to an embodiment of the present invention.
  • FIG. 33 is another schematic structural diagram of an apparatus for memory evaluation according to an embodiment of the present invention.
  • FIG. 34 is another schematic structural diagram of an apparatus for memory evaluation according to an embodiment of the present invention.
  • the embodiment of the invention provides a method and a device for evaluating a memory, which is used for evaluating the health of the memory in the server, and prompting the user to replace the memory when the memory is not faulty and the health is low, so that the memory can be Support the server to run normally.
  • the method for memory evaluation provided by the embodiment of the present invention is applied to a server, where the server is a device for providing a computing service.
  • the server provided by the embodiment of the present invention may be an x86 server, and the x86 server is a server that adopts a Complex Instruction Set Computer (CISC) architecture.
  • CISC Complex Instruction Set Computer
  • the server provided by the embodiment of the present invention may also be a non-x86 server, and the solution provided by the application does not limit this.
  • the following describes the method for memory evaluation provided by the embodiment of the present invention by using an x86 server as an example.
  • servers such as x86 servers
  • the above hardware system may include components such as a processor, a communication interface, a system bus, a hard disk, and a memory.
  • the above software system may include an operating system and a management system, and the management system may be implemented by management software such as a management controller (MC).
  • MC management controller
  • the MC in the server can be used to monitor and manage the running data and inherent parameters of various components in the server, such as the running data of the memory in the server and the inherent parameters of the memory.
  • the running data of the memory may include data such as an operating temperature of the memory and a running time.
  • the “operational data of the memory” may be referred to as “the operating parameter value of the memory” or “the operating parameter of the memory”, and the different names are only for convenience of explanation, and the running data of the memory itself Not limited.
  • the inherent parameters of the memory may include the manufacturer, capacity, frequency, serial number, minimum voltage, RANK number, bit width, and the technology used in the memory.
  • the memory capacity can be 32,768 megabytes (Mbyte, MB); the primary frequency can be 2400 megahertz (MHz); the serial number is used to uniquely identify a memory, such as the serial number 0x27EACEEA; the minimum voltage can be 1200 millivolts ( Millivolt, mV); RANK number can be 1 column (rank) or 2rank, etc.; bit width can be 64 bits or 72 bits; the technique used can be "Synchronous
  • the health of the memory provided by the embodiment of the present invention may reflect the possibility of a memory failure. Among them, the higher the health of the memory, the less likely the memory is to be faulty (that is, the smaller the memory failure rate), the memory usually works normally and does not need to be replaced; the lower the health of the memory, the memory fails. The greater the likelihood (that is, the higher the memory failure rate), the memory usually does not work properly and needs to be replaced.
  • the method for memory evaluation provided by the embodiment of the present invention may determine whether to replace the memory before the memory fails according to the health of the memory.
  • FIG. 1 a schematic diagram of a hardware structure of a server provided by an embodiment of the present invention.
  • the server 11 shown in FIG. 1 may include a processor 111, a hard disk 112, at least one memory 113, and a communication interface 114 and a bus 115.
  • the processor 111 is a control center of the server, and may be a processor or a singularity of a plurality of processing elements.
  • the processor 111 may be a central processing unit (CPU), or may be an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more integrations of embodiments of the present invention.
  • a circuit such as one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs).
  • DSPs digital signal processors
  • FPGAs Field Programmable Gate Arrays
  • the processor 111 can monitor the operational data of the memory in the server 11 through the MC.
  • processor 111 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG.
  • the server can include multiple processors.
  • processors can be a single core processor (CPU) or a multi-core processor (multi-CPU).
  • a processor herein may refer to one or more devices, circuits, and/or processing cores for processing data, such as computer program instructions.
  • the hard disk 112 is an external memory of the server, also called external memory, for storing a large amount of permanent data. Even if the server loses power, the data will not be lost.
  • the hard disk 112 can store the system log during the operation data of the MC monitoring memory.
  • the hard disk may be implemented by a read only memory (ROM).
  • ROM read only memory
  • the hard disk may be a solid state drive (SSD), a hard disk drive (HDD), or the like.
  • the external storage of the above server may also be a Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, and a CD storage (including a compact disc, a laser disc, a compact disc, a digital versatile disc).
  • CD-ROM Compact Disc Read-Only Memory
  • CD storage including a compact disc, a laser disc, a compact disc, a digital versatile disc.
  • the Blu-ray disc, etc. is not described in detail in the embodiment of the present invention.
  • the memory is described by taking only one memory 113 in at least one memory 113 as an example.
  • the memory 113 is an internal memory that directly exchanges data with the processor, which is also called main memory; and is mainly implemented by a random access memory (RAM), also called a random access memory. Used to temporarily store operational data in the processor, as well as data exchanged with external memory such as a hard disk, and all programs in the server run in memory.
  • the processor 111 can perform various functions of the server by running or executing software or programs stored in the at least one memory 113, and calling data stored in the hard disk 112 and/or the at least one memory 113.
  • the memory 113 can store a program in which the processor 111 monitors the operational data of the memory in the server 11.
  • the memory 113 may be a RAM such as a static random access memory (SRAM) or a dynamic random access memory (DRAM).
  • the memory provided by the embodiment of the present invention may be a pluggable memory module in the server.
  • the memory 113 may be a dual inline memory module (DIMM) or a double data rate synchronous dynamic random access memory (Double Data Rate Synchronous Dynamic Random Access Memory, DDR SDRAM), also known as DDR implementation.
  • DIMM dual inline memory module
  • DDR SDRAM Double Data Rate Synchronous Dynamic Random Access Memory
  • the inherent parameters of the above memory may also include a memory type.
  • the memory type can include DDR, DDR2, DDR3, and DDR4.
  • each memory in the server can have a name, such as DIMM000, DIMM011, and so on.
  • Communication interface 114 can be used to interact with external devices.
  • the communication interface 114 may include two communication interfaces, a transmission interface for transmitting data to an external device and a receiving interface for receiving data from the external device, that is, the transmitting device may pass two different communication interfaces. Receive data and send data separately.
  • a communication interface of the server 11 can transmit data stored by the hard disk 112 and the at least one memory 113 to an external device.
  • the communication interface 114 can integrate the data receiving function and the data transmitting function on a communication interface having a data receiving function and a data transmitting function.
  • communication interface 114 can be an MC interface.
  • the processor 111, the hard disk 112, the at least one memory 113, and the communication interface 114 may be connected by a bus 115.
  • the bus 115 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the bus 115 described above can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is shown in Figure 1, but it does not mean that there is only one bus or one type of bus.
  • each CPU in the processor 111 in the server 11 can hang a memory 113.
  • the hardware structure of the server shown in FIG. 1 does not constitute a limitation to the server, and may include more or less components than those illustrated, or some components may be combined, or different component arrangements.
  • the server 11 further includes one or more temperature sensors and the like, and the one or more temperature sensors may be used to detect the temperature of some components in the server, such as the temperature of the CPU and the temperature of each memory.
  • the MC detects the running data of the at least one memory 113 in the server 11
  • the MC can be managed by human-computer interaction, so that the user can intuitively observe or manage the data obtained by the MC, such as at least one memory.
  • 113 operational data and intrinsic parameters can be realized by connecting the input device and the display to the server 11.
  • FIG. 2 it is a schematic structural diagram of an apparatus for memory evaluation according to an embodiment of the present invention.
  • the device 20 for memory evaluation shown in FIG. 2 includes a server 11, an inputter 12, and a display 13.
  • the connection relationship between the above-described server 11, the input device 12, and the display 13 is indicated by only a straight line in FIG.
  • the connection between the server 11, the input device 12 and the display 13 may be a wired connection or a wireless connection, which is not limited in the embodiment of the present invention.
  • the input device 12 and the display 13 described above may be served by the server 11, and the services in the server 11 may be implemented by the processor 11 in conjunction with the input device 12 and the display 13.
  • the device 10 for evaluating the memory may be implemented by a terminal device such as a desktop computer or a desktop computer or a desktop computer.
  • the server 11 is referred to as a host
  • the input device 12 may be a device such as a keyboard or a mouse.
  • the device 10 for memory evaluation composed of the server 11, the input device 12, and the display 13 may belong to the same desktop device and be referred to as the terminal device 1.
  • the input device 12 and the display 13 described above are not served by the server 11, but are served by other servers.
  • the server 11 described above provides services to the terminal device 1, and the above-described input device 12 and display 13 belong to the terminal device 2, and the terminal device 2 may be another desktop device.
  • the terminal device 2 may also be a terminal device provided with a touch screen.
  • the terminal device may be a mobile device, a tablet computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), and the like.
  • UMPC ultra-mobile personal computer
  • PDA personal digital assistant
  • the specific composition of the server 11, the input device 12 and the display 13 included in the device for memory evaluation provided by the implementation of the present invention is not limited. The following is a description of the method for memory evaluation provided by the embodiment of the present invention.
  • the server 11, the input device 12, and the display 13 are provided by the same terminal device as an example.
  • FIG. 2a is another structural diagram of the device for memory evaluation provided by the embodiment of the present invention.
  • the memory evaluation device 20 includes a processor 111, a hard disk 112, at least one memory 113, and a communication interface 114, a bus 115, an input device 12, and a display 13.
  • the method for memory evaluation provided by the embodiment of the present invention may display the human-computer interaction interface of the MC through the display 13, and the human-computer interaction interface of the MC may adopt a DOS interface or a browser interface.
  • a browser interface as an example of the human-computer interaction interface of the MC.
  • One MC can correspond to a login address, such as a Uniform Resource Locator (URL).
  • the input device 12 can receive the login address of the MC input by the user, and the display 13 can display the human-computer interaction interface (hereinafter referred to as the MC interface) of the MC by using a browser interface.
  • the memory evaluation method provided by the embodiment of the present invention is described as an example of the display of the MC interface after the user has input the login address of the MC through the input device.
  • the MC interface displayed on the display may be a Graphical User Interface (GUI); and the GUI includes graphic options in the form of text and icons, and the graphic options and icons in the form of GUI text.
  • GUI Graphical User Interface
  • Graphical options can be manipulated by the user via a mouse, keyboard, touch screen, or other input device.
  • the above GUI includes a window, a drop-down menu, a dialog box and its corresponding control mechanism (such as the CPU of the server).
  • the GUI is standardized in a variety of new applications or software, ie the same operation is always done in the same way; for example, any text form or icon form of the GUI (hereinafter referred to as the option) Clicking can be done by the user clicking the option with the mouse, or by tapping the option on the touch screen with the finger.
  • the processor can generate a corresponding click operation instruction and respond to the click operation.
  • FIG. 3 it is a schematic diagram of an MC interface provided by an embodiment of the present invention.
  • the MC interface in Figure 3 shows the intrinsic parameters of the six memories named DIMM000, DIMM001, DIMM002, DIMM010, DIMM011, and DIMM012, respectively.
  • the MC interface shown in FIG. 3 includes options such as "name ⁇ ”, “vendor ⁇ ", “capacity ⁇ ", “clock speed ⁇ ”, and "serial number ⁇ ".
  • the “ ⁇ ” included in each option corresponds to a drop-down menu.
  • the user can click the operation option 31 through the input device, that is, the " ⁇ " option in the "vendor ⁇ ” option, and the processor in the memory evaluation device instructs the display to display as shown in FIG. 3 after generating the corresponding click operation instruction.
  • the "manufacturer ⁇ " corresponds to the pull-down menu 311, and the pull-down menu 311 includes three options of "vendor A", “vendor B", and "vendor C". If the user clicks "vendor A" in the operation pull-down menu 311, the processor in the memory evaluation device can generate a corresponding click operation instruction, and instruct the display to display only the manufacturer as the manufacturer A in the MC interface shown in FIG. The intrinsic parameters of the memory.
  • the device for evaluating the memory determines a health assessment model of the memory to be evaluated.
  • the above step 401 can be performed by the processor 111 in the device 20 of the memory evaluation shown in FIG. 2a.
  • the memory to be evaluated is one memory in at least one memory in the server, that is, a memory in the device for memory evaluation.
  • the health assessment model of the memory to be evaluated is used to evaluate the health of the memory to be evaluated, and the health of the memory to be evaluated may reflect the possibility of failure of the memory to be evaluated, that is, the memory failure rate of the memory to be evaluated.
  • the health assessment model is a relationship between the health of the memory to be evaluated and the change of at least one health influence factor of the memory to be evaluated, and one health impact factor corresponds to one operating parameter and one failure rate parameter, and one health degree
  • the influencing factor corresponds to a weight, which is a constant. Wherein, for a health influencing factor, the value of the memory failure rate parameter (ie, the memory failure rate) varies with the value of the corresponding operating parameter (ie, the operating data).
  • the health impact factor of a memory may affect the normal operation of the memory, and may cause the memory to fail, that is, the memory fails.
  • the memory evaluation device stores data describing the relationship between the corresponding operating parameter and the failure rate parameter, such as describing the relationship of the failure rate parameter with respect to the operating parameter. Curve.
  • the data stored in the device for memory evaluation describing the relationship between the corresponding operating parameter and the failure rate parameter may be based on a large amount of data (such as a large amount of memory to be evaluated) by those skilled in the art.
  • the operation data of the related memory is obtained by training, or is obtained according to the literature related to the related art, and the embodiment of the present invention does not repeat this.
  • the weight corresponding to the health impact factor may indicate the degree of influence of the health influence factor on the health of the memory to be evaluated, and the health impact factors of different weights have different effects on the health of the memory. For example, the greater the weight corresponding to a health impact factor, the greater the impact of the health impact factor on the health of the memory being evaluated.
  • the weight of each health influencing factor in the health assessment model provided by the embodiment of the present invention may indicate the impact of each health influencing factor on the health of the memory to be evaluated, so that the health assessment model is to be evaluated.
  • the degree of influence of different health assessment factors of memory is more in line with the memory to be evaluated, which is helpful for accurately assessing the health of the memory to be evaluated.
  • the weight corresponding to each health influencing factor in the health assessment model of the memory to be evaluated may be preset by a related technical staff.
  • the weight corresponding to each health impact factor can also be set autonomously by the user based on experience or relevant statistical data of the memory to be evaluated.
  • the relevant technician can set different weights for each health influencing factor in the health assessment model of the memory to be evaluated.
  • the memory to be evaluated corresponds to two factors affecting health, one of the two health influencing factors has a weight corresponding to 60%, and the other health factor has a weight of 40%.
  • the sum of the weights corresponding to each of the health influencing factors of the at least one health influencing factor is equal to one.
  • the relevant technical personnel may set the same weight for each health influencing factor in the health assessment model of the memory to be evaluated, or the related technical personnel may not set the right to each of the above health impact factors. value. That is, each health impact factor has the same effect on assessing the health of the memory.
  • the memory evaluation device acquires at least one operating parameter value corresponding to each health impact factor of the at least one health impact factor.
  • step 402 can be performed by the processor 111 in the device 20 of the memory evaluation shown in FIG. 2a.
  • the operating parameter included in the health assessment model corresponds to at least one operating parameter value, for a health impact factor corresponding to the memory to be evaluated. Therefore, for a health influence factor corresponding to the memory to be evaluated, the device for memory evaluation may acquire the at least one operating parameter value according to the corresponding operating parameter. For example, for the memory to be evaluated, the device for memory evaluation can obtain the total running time of the memory to be evaluated corresponding to the health impact factor of the total memory running time.
  • the total running time of the memory to be evaluated may be saved in the hard disk of the device for memory evaluation, and may be evaluated by the memory.
  • the processor in the update may be performed before the processor in the memory evaluation device acquires the total running time of the memory to be evaluated.
  • the memory evaluation device respectively matches at least one operating parameter value corresponding to each health impact factor to the health assessment model to obtain the health of the memory to be evaluated.
  • the memory evaluation device may obtain the health assessment effect from the memory evaluation model. At least one operating parameter value of the factor is matched to the corresponding operating parameter in the health assessment model
  • the memory evaluation device can obtain the health of the memory to be evaluated by using the health assessment model of the memory to be evaluated.
  • the health of the memory to be evaluated may be represented by a value between 0 and 100, such as 80.
  • the device for evaluating the memory outputs the health indication information of the memory to be evaluated according to the health of the memory to be evaluated.
  • the above step 402 may generate the health indication information of the memory to be evaluated by the processor 111 in the memory evaluation device 20 shown in FIG. 2a, and instruct the display 13 in the memory evaluation device 20 to output the to-be-evaluated Memory health indication information.
  • the health indication information of the memory to be evaluated is used to indicate to the user whether the memory to be evaluated is replaced. For example, when the health of the memory to be evaluated is low, the health indication information of the memory to be evaluated output by the memory evaluation device may indicate that the memory to be evaluated needs to be replaced, and the memory to be evaluated is more likely to be faulty. When the health of the memory to be evaluated is high, the health indication information of the memory to be evaluated output by the memory evaluation device may indicate that the memory to be evaluated by the user does not need to be replaced, and the possibility that the memory to be evaluated is faulty is small at this time.
  • the memory evaluation device when the value of the health of the memory to be evaluated is within a preset numerical interval (for example, 70 to 100), the memory evaluation device outputs the health indication information of the memory to be evaluated to indicate to the user that the memory to be evaluated does not need to be replace. When the value of the health of the memory to be evaluated is within a preset numerical interval (for example, 0 to 45), the memory evaluation device outputs the health indication information of the memory to be evaluated to indicate to the user that the memory to be evaluated needs to be replaced.
  • a preset numerical interval for example, 70 to 100
  • the memory evaluation device outputs the health indication information of the memory to be evaluated to indicate to the user that the memory to be evaluated does not need to be replace.
  • a preset numerical interval for example, 0 to 45
  • the health assessment model of the memory to be evaluated may be pre-stored in the memory evaluation device by a person skilled in the art, such as the hard disk 112 in the memory evaluation device 20 shown in FIG. 2a.
  • a log may be generated. The above log may store data in the health assessment model of the memory to be evaluated (eg, at least one health impact factor of the memory to be evaluated) and the health of the memory to be evaluated.
  • the embodiment of the present invention may provide a health assessment model that describes the relationship between the health of the memory to be evaluated and the change of at least one health impact factor of the memory to be evaluated, so that the device for memory evaluation can be based on the memory to be evaluated.
  • the health assessment model obtains the health of the memory to be evaluated. Therefore, the device for memory evaluation can generate the health indication information of the memory to be evaluated according to the value of the health of the memory to be evaluated. In this way, the memory evaluation device can determine whether the memory to be evaluated is replaced before the memory to be evaluated fails due to the health of the memory to be evaluated.
  • the device for memory evaluation may output the health indication information of the memory to be evaluated if the memory does not fail and the health of the memory is low, so as to prompt the user to replace the memory, so that the memory can support the server. run.
  • At least one health impact factor included in the health assessment model provided by the embodiment of the present invention may include other health impact factors in addition to the total operation duration of the memory to be evaluated.
  • the at least one health influence factor provided by the embodiment of the present invention includes one or more of the following:
  • the health influence factors provided by the embodiments of the present invention are not limited to the health influence factors listed above (factors 1-7), and may also be other factors such as the vulcanization strength in the air.
  • the MC interface provided by the embodiment of the present invention can display the health assessment model of the memory in addition to the inherent parameters of each memory.
  • another MC interface provided by an embodiment of the present invention is an interface for setting a health assessment model for different memory to be evaluated.
  • the interface shown in FIG. 5 may be an interface provided by the desktop.
  • the display provided by the embodiment of the present invention may be a display of a desktop computer, and the input device may be a device such as a mouse and a keyboard of the desktop.
  • the MC interface 50 shown in FIG. 5 includes a "memory name” option 51, and the option 51 includes a " ⁇ " option.
  • the MC interface 50 includes a "memory operating temperature” option, a “memory traffic load” option, a “memory total runtime” option, a “memory plug” option, a "memory CE frequency” option, a “memory UCE frequency” option, and
  • the “Memory Performance Attenuation” option is an option for the 7 health impact factors, and each health impact factor corresponds to a “off” option. For example, factor 1 corresponds to the "memory operating temperature” option 52, and factor 1 corresponds to the "off” option 53.
  • the MC interface 50 shown in FIG. 5 also includes a "OK” option 54 and a "Cancel” option 55.
  • the MC interface 50 may provide a user with different memory name selections to implement a health impact factor included in the health assessment model for different memory settings.
  • the user clicks on the " ⁇ " option included in the option 51 of the MC interface 50, so that the processor in the memory evaluation device generates a corresponding click operation instruction, and then instructs the display to display on the MC interface as shown in FIG. Drop down menu 511.
  • the drop-down menu 511 includes six options: "DIMM000” option, "DIMM001” option, "DIMM002" option, "DIMM010” option, "DIMM011” option, and "DIMM012" option.
  • the user clicks on any option included in the operation pull-down menu 511 such as the "DIMM000” option
  • the processor in the memory evaluation device receives the corresponding operation instruction, and indicates the health influence factor displayed by the MC interface 50.
  • the option is the health impact factor for memory with a memory name of DIMM000.
  • the memory whose memory name is DIMM000 is the memory to be evaluated. It is conceivable that after the user clicks on the "DIMM000" option included in the pull-down menu 511 shown in FIG. 6, the processor in the memory evaluation device can generate a corresponding click operation instruction, and then can instruct the display to be displayed as shown in FIG. MC interface 50.
  • the above "user click operation on an option” may be a user operating a mouse click option, and an arrow as shown in FIG. 5 is used to indicate the position of the mouse cursor in the display interface.
  • the memory evaluation device can determine that the health assessment model does not include the health effect.
  • the factor which ignores the impact of the health impact factor on the health of the memory.
  • the user does not perform a click operation (or a continuous click operation twice) for the "off" option corresponding to the health influence factor, and the memory evaluation device can determine the health impact factor in the corresponding health assessment model to evaluate the health of the memory. Degree has an impact.
  • the method for memory evaluation provided by the embodiment of the present invention is described by clicking the operation of each option in the MC interface 50.
  • the "close" option 53 corresponding to factor 1 included in the MC interface 50 as shown in FIG. 7 can be clicked.
  • the health effect factor of the memory operating temperature does not affect the health of the memory whose memory name is "DIMM000". That is to say, the user can select the influence factors of the health of a certain memory by clicking the operation related option on the MC interface 50 described above.
  • the operation “determine” option 54 may be clicked to make the processor in the memory evaluation device determine.
  • the health assessment model of the memory to be evaluated above is presented.
  • the user may also click to operate the "cancel” option 55 above to cause the processor to re-determine the health assessment model of the memory to be evaluated.
  • the display for displaying the MC interface provided by the embodiment of the present invention may be implemented by a terminal device having a touch screen such as a mobile phone or a tablet computer.
  • FIG. 8 another MC interface provided by the embodiment of the invention is implemented by a touch screen of a mobile phone.
  • the MC interfaces 80 shown in Figures 8-1 and 8-2 of Figure 8 each include a memory name option 81, which includes a " ⁇ " option.
  • the MC interface 80 includes a "memory operating temperature” option, a "memory traffic load” option, a "memory total runtime” option, a "memory plug” option, a "memory CE frequency” option, a “memory UCE frequency” option, and
  • the “Memory Performance Attenuation” option is a 7 health impact factor option, and each health impact factor option corresponds to a “off” option.
  • the health impact factor option for factor 1 is the "memory operating temperature” option 82, and factor 1 corresponds to the "off” option 83.
  • MC interface 80 also includes an "OK” option 84 and a “Cancel” option 85.
  • the pull-down menu 811 shown in FIG. 8-2 includes six options of "DIMM000” option, "DIMM001” option, "DIMM002” option, "DIMM010” option, "DIMM011” option, and "DIMM012" option.
  • FIG. 9 another MC interface provided by the embodiment of the invention is implemented by a touch screen of a tablet computer.
  • the MC interface 90 shown in Figures 9-1 and 9-2 in Figure 9 includes a memory name option 91, which includes a " ⁇ " option.
  • the MC interface 90 includes a "memory operating temperature” option, a "memory traffic load” option, a "memory total runtime” option, a “memory plug” option, a "memory CE frequency” option, a “memory UCE frequency” option, and
  • the “Memory Performance Attenuation” option is a 7 health impact factor option, and each health impact factor option corresponds to a “off” option.
  • the health impact factor option for factor 1 is the "memory operating temperature” option 92, and factor 1 corresponds to the "off” option 93.
  • the MC interface 90 also includes a "OK” option 94 and a "Cancel” option 95.
  • the pull-down menu 911 shown in FIG. 9-2 includes six options of "DIMM000” option, "DIMM001” option, "DIMM002” option, "DIMM010” option, "DIMM011” option, and "DIMM012" option.
  • the display of the MC interface on the touch screen shown in FIG. 8 or FIG. 9 can be performed by the user using a finger, and then the processor in the mobile phone or the tablet can generate a corresponding click operation instruction.
  • the "hand icon" in FIGS. 8 and 9 is used to schematically represent a human hand. In the embodiment of the present invention, the position of the user's finger is represented only by the “hand icon”, and the “hand icon” is not displayed on the mobile phone or the tablet.
  • the MC interface provided by the terminal device with a touch screen such as the above-mentioned mobile phone or tablet computer
  • the embodiment of the present invention is described below by using the MC interface provided by the display of the desktop as an example to describe the method for memory evaluation provided by the embodiment of the present invention.
  • the health of memory in different batches and different models may be related to different health influence factors.
  • some memory health is sensitive to changes in memory operating temperature, and some memory health is sensitive to changes in memory runtime.
  • the health assessment model provided by the embodiment of the present invention presets a plurality of health influence factors, so that the user can select corresponding health influence factors for different memory to be evaluated, so that the health assessment model is targeted Evaluating the memory health assessment factor is more in line with the memory to be evaluated, which helps to accurately assess the health of the memory to be evaluated.
  • the relevant technical personnel may set the same weight for each health influencing factor in the health assessment model of the memory to be evaluated, or the related technical personnel may not set the weight for each health influencing factor. . That is, each health impact factor has the same effect on assessing the health of the memory.
  • the factor 1 corresponds to a weight of 20%
  • the factor 2 corresponds to a weight of 5%
  • the weight corresponding to factor 3 is 25%
  • the weight corresponding to factor 4 is 5%
  • the weight corresponding to factor 5 is 10%
  • the weight corresponding to factor 6 is 15%
  • the weight corresponding to factor 7 is 20%.
  • Each of the health impact factors described above corresponds to a weight, which can further indicate the impact of each health factor on the health of the memory to be evaluated.
  • FIG. 10 is a schematic diagram of another MC interface provided by an embodiment of the present invention.
  • Each health impact factor in the MC interface 50 shown in FIG. 10 corresponds to a weight option.
  • factor 1 shown in Figure 1 corresponds to the "20%" option (ie, option 56).
  • the processor the processor in the server
  • the memory evaluation device can generate a corresponding click operation instruction, and the receiving user receives the option through an input device (such as a keyboard). 56 to make changes. For example, change "20%” in option 56 to "25%”.
  • the weights corresponding to other factors may be modified accordingly.
  • the operating parameter corresponding to the memory operating temperature factor (factor 1) provided by the embodiment of the present invention is the operating temperature of the memory to be evaluated.
  • the operating parameter corresponding to the above memory service load factor (factor 2) is the number of times of charging and discharging of the memory to be evaluated.
  • the running parameter corresponding to the above total memory running time factor (factor 3) is the total running time of the memory to be evaluated.
  • the operating parameter corresponding to the above memory insertion factor (factor 4) is the number of times the memory to be evaluated is inserted and removed.
  • the operating parameter corresponding to the above-mentioned memory CE frequency factor (factor 5) is the number of CEs of the memory to be evaluated or the CE frequency of the memory to be evaluated.
  • the operating parameter corresponding to the above-mentioned memory UCE frequency factor is the number of UCEs of the memory to be evaluated or the UCE frequency of the memory to be evaluated.
  • the operating parameter corresponding to the above memory performance attenuation factor is the performance value attenuation of the memory to be evaluated.
  • the operating parameters corresponding to the health impact factors provided by the embodiments of the present invention may be obtained by a person skilled in the art according to a large amount of data training, such as training according to a plurality of running data of a memory similar to the memory to be evaluated, or may be according to the field.
  • the related documents are obtained, and the details of the embodiments of the present invention are not described herein.
  • the memory evaluation device stores data describing a relationship between the operating temperature of the memory to be evaluated and the failure rate parameter, such as memory of the memory to be evaluated. Failure rate curve for the change in operating temperature of the memory to be evaluated. In general, the higher the operating temperature of the memory to be evaluated, the greater the probability that the memory to be evaluated will fail, that is, the higher the failure rate.
  • the memory evaluation device stores data describing the relationship between the number of charge and discharge times of the memory to be evaluated and the failure rate parameter, such as the memory to be evaluated.
  • Memory Failure Rate A curve of the number of charge and discharge times of the memory to be evaluated.
  • the more the charge and discharge times of the memory the greater the pressure of the service load of the memory, the greater the possibility that the memory is faulty, and the higher the failure rate of the memory; the less the charge and discharge times of the memory represent the service of the memory.
  • the smaller the load pressure the less likely the memory is to fail, and the lower the memory failure rate.
  • the memory evaluation device stores data describing the relationship between the total running time of the memory to be evaluated and the failure rate parameter, such as the memory failure rate of the memory to be evaluated.
  • the failure rate parameter such as the memory failure rate of the memory to be evaluated.
  • the total running time of a memory (such as memory to be evaluated) is limited, that is, the lifetime of a memory is limited.
  • the larger the total running time of a memory the more likely the memory is to fail and the higher the failure rate.
  • the memory evaluation device stores data describing the relationship between the number of insertion and removal times of the memory to be evaluated and the failure rate parameter, such as the memory failure rate of the memory to be evaluated. A curve about the change in the number of insertions and removals of the memory to be evaluated.
  • the memory provided by the embodiment of the present invention (such as the memory to be evaluated) is mostly a memory strip with a gold plating layer. Since the thickness of the gold plating layer of the memory strip is constant, the gold plating layer of the memory strip is worn during the process of plugging and unplugging the memory strip, so the number of memory insertions may be a factor affecting the health of the memory.
  • the more times the memory is to be evaluated the more likely the memory to be evaluated is to be faulty, and the higher the failure rate is.
  • the less the number of memory insertions to be evaluated the more likely the memory to be evaluated is faulty. Small, the lower the failure rate.
  • the memory evaluation device stores data describing the relationship between the number of CEs of the memory to be evaluated or the CE frequency of the memory to be evaluated and the failure rate parameter.
  • the memory failure rate of the memory to be evaluated is a curve of the number of CEs of the memory to be evaluated or the CE frequency of the memory to be evaluated. The more the number of CEs to be evaluated in a period of time, the greater the probability that the memory to be evaluated is faulty, and the higher the failure rate. The less the number of CEs to be evaluated in a period of time, the less the memory to be evaluated occurs. The less likely the failure is, the lower the failure rate.
  • the memory evaluation device stores data describing the relationship between the UCE number of the memory to be evaluated or the UCE frequency of the memory to be evaluated and the failure rate parameter, such as
  • the memory failure rate of the memory to be evaluated is a curve of the number of UCEs of the memory to be evaluated or the UCE frequency of the memory to be evaluated. The more UCEs are generated in the memory to be evaluated for a period of time (or the UCE frequency of the memory to be evaluated is larger), the greater the probability of failure, the higher the failure rate; the memory to be evaluated is generated for a period of time.
  • the memory evaluation device stores data describing the relationship between the performance value attenuation amount of the memory to be evaluated and the failure rate parameter, such as the failure rate of the memory to be evaluated.
  • the performance value attenuation amount of the memory to be evaluated changes during the memory running process to be evaluated. Generally, the larger the performance value attenuation of a memory (such as the memory to be evaluated) and the smaller the performance value, the greater the probability of failure, and the higher the failure rate; the smaller the performance value attenuation of the memory and the performance value The larger the probability of failure, the lower the failure rate.
  • the MC interface may display data about the relationship between the operating parameter and the failure rate parameter corresponding to each health influencing factor, such as the value of the memory failure rate parameter regarding the corresponding operating parameter.
  • the curve of the value change.
  • the memory evaluation device stores a curve of the failure rate of each memory (such as the memory named "DIMM000" and the memory named "DIMM001") with respect to the corresponding operating parameter.
  • FIG. 11 another schematic diagram of an MC interface provided by an embodiment of the present invention is shown.
  • Each health impact factor in the MC interface 50 shown in Figure 11 corresponds to a "set” option.
  • the "memory running temperature” option 52 corresponds to the "settings” option 57.
  • the "Settings” option 57 is used to cause the MC interface 50 as shown in FIG. 12 to jump to the interface 50 displaying the "temperature-loss rate curve".
  • the processor in the memory evaluation device can generate a corresponding click operation instruction and instruct the display to display the window 511 including the window 511 as shown in FIG.
  • the MC interface 50 displays a "temperature-loss rate curve" in the window 511.
  • the "temperature-loss rate curve” shown in FIG. 12 is a curve describing the value of the failure parameter of the memory named "DIMM000" with respect to the value of the operating parameter of the memory operating temperature.
  • the "OK” option 512 is also included in the MC interface 50 shown in FIG. The “OK” option 512 described above is used by the user to determine the "temperature-loss rate curve” described above and to cause the display to display the MC interface 50 as shown in FIG.
  • the memory failure rate is 40%; the name is "DIMM000"
  • the memory failure rate is 95%.
  • the foregoing "long time” may be used by a related person to detect the lifetime of a memory, which is not described in detail in the embodiments of the present invention.
  • the above-mentioned "temperature-loss rate” curve is a curve for the memory named "DIMM000", which can be matched by a device for memory evaluation from multiple curves for different memories, and the above is for multiple memories.
  • the curve can be pre-stored in the device for memory evaluation.
  • the memory evaluation device can autonomously match the above-mentioned "temperature-loss rate” curve according to an inherent parameter such as a memory capacity of a memory named "DIMM000".
  • the processor in the memory evaluation device can generate a corresponding click operation instruction and instruct the display to display as shown in FIG.
  • the MC interface 50 of the window 511 is shown, and the "number of times of charge-loss" curve is displayed in the window 511.
  • the "charge times - failure rate” curve shown in FIG. 13 is a curve describing the value of the failure parameter of the memory named "DIMM000" with respect to the value of the operation parameter of the number of times of charge and discharge of the memory.
  • the "OK” option 512 is also included in the MC interface 50 shown in FIG.
  • the “OK” option 512 described above is also used by the user to determine the "charge-discharge number-loss rate” curve described above and cause the display to display the MC interface 50 as shown in FIG.
  • the "charge times - failure rate" curve shown in FIG. 13 above may be a curve for the memory evaluation device matching the memory named "DIMM000" from a plurality of curves for different memories, the above for different memory. Multiple curves are stored in the device for memory evaluation. Specifically, the device for memory evaluation can autonomously match the above-mentioned "charge-discharge number-loss rate” curve according to parameters such as memory capacity and other parameters of the memory named "DIMM000".
  • the device for memory evaluation may also store a “total running time-loss rate” curve for the factor 3, and a factor of “plug-and-drop-loss rate” for the factor 4, and the factor. 5 "CE number - failure rate” curve or “CE frequency - failure rate” curve, for the "UCE number - failure rate” curve of factor 6 or “CE frequency - failure rate” curve, for the performance of factor 7 Value attenuation - failure rate curve.
  • the embodiment of the present invention provides a detailed description of the corresponding curve in the MC interface after the "setting" option corresponding to the above factor 3 - factor 7 is clicked. Referring to the related description of the factor 1 and the factor 2 in the above embodiment, the present invention It will not be described in detail in the embodiment.
  • the device for evaluating the memory stores data describing the relationship between the operating parameter and the failure rate parameter corresponding to each health influencing factor, such as describing the failure rate parameter of the memory to be evaluated, and the corresponding operation.
  • the curve of the failure rate parameter of the above-mentioned memory to be evaluated with respect to the corresponding operation parameter change is pre-statisticd data. In this way, the memory evaluation device can evaluate the health of the memory to be evaluated that has not failed according to the data obtained from the existing statistics.
  • the health assessment model of the memory to be evaluated may include a first sub-model corresponding to each health impact factor, and a second sub-model, a health influence factor.
  • the first sub-model is the relationship between the health-related impairment value corresponding to the health-influencing factor and the operating parameter and the memory failure-factor parameter corresponding to the health-influencing factor; the second sub-model is the health of the memory to be evaluated.
  • step 403 may include step 403a and step 403b.
  • step 403a and step 403b the above step 403 in the method flowchart of the memory evaluation shown in FIG. 14 may include step 403a and step 403b:
  • the memory evaluation device respectively matches the operating parameter values corresponding to each health influencing factor to the first sub-model of the corresponding health influencing factors in the health assessment model, and obtains the health corresponding to each health influencing factor. Degree of damage.
  • step 403a may be performed by the processor 111 of the device 20 of the memory evaluation shown in FIG. 2a.
  • the operating parameter value corresponding to each health influencing factor of the memory to be evaluated may be obtained by the device for memory evaluation in real time.
  • Each of the health influencing factors corresponding to the health degree impairment value is used to indicate the effect of the health influencing factor on the health of the memory to be evaluated.
  • the first sub-model provided by the embodiment of the present invention may include a curve in the window 511 in the MC interface shown in FIG. 12 or FIG.
  • the memory evaluation device may refer to the existing “temperature-loss rate” curve.
  • the "temperature-loss rate” curve in the window 511 shown in FIG. 12 obtains the failure rate corresponding to each of the operating parameter values of the at least one operating parameter value, and superimposes the running time to obtain the health degree of the memory to be evaluated for the factor 1 Loss value (denoted as P 1 ).
  • at least one operating parameter value of the memory to be evaluated is an operating temperature value T 1 , an operating temperature value T 2 ... an operating temperature T n , etc., and n is a positive integer.
  • the running time of the memory to be evaluated under the condition that the operating temperature is T 1 is t 1_1
  • the running time under the condition that the operating temperature is T 2 is t 1_2
  • the running time under the condition that the running temperature is T n is t 1_n .
  • the operating temperature "Temperature failure rate” is a graph showing the value of T 1 when failure rate P 1_1, a value of the operating temperature T 2 at failure rate P 1_2, operating temperature
  • the failure rate when the value is T n is P 1 — n .
  • the fitness to be evaluated is the fitness loss value for factor 1 Above T 1, T 2, T n , t 1_1, t 1_2 and t 1_n are positive.
  • the device for memory evaluation can refer to the existing "charge and discharge times - failure rate".
  • the curve as shown in the "charge-discharge number-loss rate" curve in the window 511 shown in FIG. 13, obtains the failure rate corresponding to at least one operating parameter value, and superimposes the running time to obtain the fitness loss value of the memory to be evaluated for the factor 2 (Remarked as P 2 ).
  • at least one operating parameter value of the memory to be evaluated is a number of charging and discharging times N 1 , a number of charging and discharging times N 2 ...
  • N n a number of charging and discharging times N n
  • n a positive integer.
  • N 1 a length of charge and discharge in t the 2_1-th time
  • N 2_2 the length of charge and discharge during the time t 2_2
  • N n the long charge and discharge t within 2_n time
  • P 2_1 failure rate
  • N 2_2 the failure rate of the number of charge and discharge times
  • P 2 — n The fitness loss value of the memory to be evaluated for factor 2
  • the above N 1 , N 2 , N n , t 2_1 , t 2_2 and t 2_n are all positive numbers.
  • the device for memory evaluation can refer to the existing "total running time-loss rate".
  • the curve obtains a failure rate corresponding to at least one operating parameter value, and obtains a fitness loss value (denoted as P 3 ) for the factor 3 to be evaluated.
  • at least one operating parameter value of the memory to be evaluated is the total running time L 1 .
  • the total running time of the memory to be evaluated provided by the "total running time-loss rate" curve is L 1 and the failure rate is P 3_1 .
  • the device for memory evaluation can refer to the existing “plug-and-drop rate” system to obtain the curve.
  • the failure rate corresponding to the at least one operating parameter value, and the health loss value (denoted as P 4 ) of the memory to be evaluated for the factor 4 is obtained.
  • at least one operating parameter value of the memory to be evaluated is the number of insertions and withdrawals M 1 times.
  • the insertion/removal times of the memory to be evaluated provided by the "plug-and-drop-loss rate" curve have an invalidation rate of P 4_1 when M 1 is taken.
  • the device for memory evaluation can refer to the existing "number of CEs - failure rate".
  • the curve obtains the failure rate corresponding to the at least one operating parameter value, and superimposes the running time length; and combines the rate of change of each operating parameter value to obtain the health degree impairment value (denoted as P 5 ) of the memory to be evaluated for the factor 5.
  • at least one operating parameter value of the memory to be evaluated is a CE number F 1 , a CE number F 2 ... a CE number F n , and the like.
  • the number of CEs in the time period in which the first time duration is t 5_1 is F 1
  • the number of CEs in the time period in which the second time length is t 5_1 is F 2
  • the number of CEs in the time period of t 5_1 is F n
  • n is a positive integer.
  • the device for memory evaluation counts the number of CEs of the memory to be evaluated at regular intervals.
  • the failure rate of the number of CEs is F 5_n when F n is taken .
  • the at least one operating parameter value that is, the rate of change of the number of CEs F 1 , the number of CEs F 2 ... the number of CEs F n may be denoted as k 1 , and k 1 is a positive number greater than zero.
  • the memory to be evaluated is the fitness loss value for factor 5
  • the above F 1 , F 2 , F n and t 5_1 are all positive numbers.
  • the device for memory evaluation can refer to the existing "UCE number-loss rate".
  • the curve obtains a failure rate corresponding to at least one operating parameter value, and obtains a fitness loss value (denoted as P 6 ) for the factor 6 to be evaluated.
  • the UCE number of the memory to be evaluated provided by the "UCE number-loss rate" curve has a failure rate of P 6_1 when the value of the UCE is W 1 .
  • the device for memory evaluation can refer to the existing "performance value attenuation amount - failure rate"
  • the curve obtains the failure rate corresponding to the value of at least one operating parameter; and in combination with the rate of change of the values of the respective operating parameters, the health loss value (indicated as P 7 ) of the memory to be evaluated for the factor 7 is obtained.
  • at least one operating parameter value of the memory to be evaluated is a performance value attenuation amount Y 1 , a performance value attenuation amount Y 2 ...
  • n a performance value attenuation amount Y n , and the like, and n is a positive integer.
  • the attenuation value of the performance value in the time period of the first time period t 7_1 to be evaluated is Y 1
  • the attenuation value of the performance value in the time period of the second time length t 7_1 is Y 2
  • the attenuation value of the performance value in the period of the nth duration t 7_1 takes a value of Y n
  • n is a positive integer. That is to say, the memory evaluation device counts the performance value of the memory to be evaluated and the attenuation value of the performance value at regular intervals.
  • the "amount of attenuation performance value - Failure Rate" to be evaluated value memory performance curves provided by the attenuation value of Y 1 is the failure rate P 7_1
  • the at least one operating parameter that is, the performance value attenuation amount Y 1 , the performance value attenuation amount Y 2 ... the performance value attenuation amount Y n
  • the at least one operating parameter may be recorded as k 2
  • k 2 is a positive number greater than zero.
  • the memory to be evaluated is the fitness loss value for factor 7
  • the above Y 1 , Y 2 , Y n and t 7_1 are all positive numbers.
  • the S403b and the memory evaluation device obtain the health of the memory to be evaluated according to the fitness loss value corresponding to each health factor and the weight value corresponding to each health factor and the second sub-model.
  • step 403b may be performed by the processor 111 of the device 20 of the memory evaluation shown in FIG. 2a.
  • the device for evaluating the memory may obtain the health loss value of the memory to be evaluated corresponding to each health influencing factor according to the first sub-model corresponding to each health influencing factor in the health assessment model, Indicates the impact of each health impact factor on the health of the memory being evaluated. And matching the health impairment value corresponding to each health influencing factor and the weight corresponding to each health influencing factor to the second sub-model, respectively, and obtaining various health influencing factors with different weights (different weights) Under the influence of the evaluation of the health of the memory. In this way, different health assessment models can be generated for different memory to be evaluated, which is beneficial to improve the accuracy of the health of the memory to be evaluated obtained according to the health assessment model.
  • each of the at least one health impact factor included in the health assessment model corresponds to an algorithm, and the algorithm may be addition, multiplication, or the like.
  • the device for memory evaluation is obtained according to the fitness loss value corresponding to each health factor, the weight corresponding to each health factor, the second sub-model, and the algorithm corresponding to each health factor. The health of the memory to be evaluated.
  • each of the at least one health factor influencing factors included in the MC interface 50 shown in FIG. 15 corresponds to an “algorithm” option.
  • factor 1 shown in FIG. 15 corresponds to the "algorithm” option 58.
  • each health degree of at least one health loss value of the memory to be evaluated The impairment value is multiplied by the corresponding weight to obtain at least one health component of the memory to be evaluated; and at least one health component is accumulated to obtain the health of the memory to be evaluated.
  • the corresponding at least one health impact factor of the memory to be evaluated includes the above factors 1, factor 2, and factor 5, and the weights of factor 1, factor 2, and factor 5 are 20%, 5%, and 10%, respectively.
  • H the health of the memory to be evaluated
  • the device for evaluating the memory according to each fitness influencing factor corresponds to the fitness loss value, the weight corresponding to each health influencing factor, and
  • the second sub-model obtains the health of the memory to be evaluated, including: the device for memory evaluation according to the second model, the health loss value of the memory to be evaluated is taken as the health of the memory to be evaluated.
  • H 3 is a health component corresponding to the memory factor 3 to be evaluated
  • P 3 is a health loss value corresponding to the memory factor 3 to be evaluated.
  • the algorithm corresponding to a health influence factor in the health assessment model provided by the embodiment of the present invention may be other algorithms, such as an integration algorithm, in addition to the above addition and multiplication.
  • the algorithm corresponding to the health influencing factor provided by the embodiment of the present invention is a specific description of the integration algorithm.
  • the algorithm corresponding to a health impact factor in the foregoing embodiment is a related description of the addition, and details are not described herein again.
  • the memory evaluation device quantifies the health of the memory according to the weight corresponding to each health influence factor of the memory.
  • the degree of influence of each health influence factor on the health of the memory can be further quantified. In this way, it is beneficial to improve the accuracy of the health of the memory to be evaluated.
  • the health assessment model of the memory to be evaluated provided by the embodiment of the present invention includes a first sub-model corresponding to each health impact factor, and a second sub-model; therefore, the foregoing memory
  • the evaluated device determines a health assessment model of the memory to be evaluated, specifically determining a first sub-model corresponding to each health impact factor in the health assessment model and a second sub-model of the evaluation memory.
  • the foregoing step 401 includes steps 401a to 401e.
  • FIG. 16 it is a schematic flowchart of another method for memory evaluation provided by an embodiment of the present invention.
  • step 401 in FIG. 4 may include steps 401a-401e:
  • the device for memory evaluation receives at least one health influence factor set by a user.
  • step 401a may be performed by the communication interface 114 in the device 20 of the memory evaluation shown in FIG. 2a.
  • At least one health influence factor is preset, and the user may select a health influence factor for the memory to be evaluated from the preset at least one health influence factor.
  • the MC interface 50 includes the factor 1 - factor 7.
  • the user can click on the "off" option corresponding to each factor in the MC interface 50 through the input device, and select at least one corresponding to the memory to be evaluated from the factor 1 - factor 7. Health factors.
  • the device for memory evaluation determines at least one health influence factor set by the user as a health influence factor included in the health assessment model of the memory to be evaluated.
  • step 401b can be performed by the processor 111 of the device 20 of the memory evaluation shown in Fig. 2a.
  • the processor in the memory evaluation device can receive a click operation instruction from the input device and determine at least one health influence factor of the memory to be evaluated.
  • the user can click through the "off" option corresponding to the factor 5-factor 7 in the MC interface 50 shown in FIG. 5 through the input device.
  • the processor in the memory evaluation device can generate a corresponding click operation instruction and determine that at least one health influence factor of the memory to be evaluated is factor 1 - factor 4.
  • the device for memory evaluation determines a corresponding first sub-model according to at least one health influence factor.
  • step 401c may be performed by the processor 111 of the device 20 of the memory evaluation shown in FIG. 2a.
  • the first sub-model of each of the at least one health-influencing factors provided in the foregoing embodiment includes data of a relationship between the operating parameter and the failure rate parameter corresponding to the health-influencing factor, such as to be evaluated.
  • the failure rate parameter of the memory is a curve of the change of the operating parameter corresponding to each health influence factor.
  • the health assessment model provided by the embodiment of the present invention may be a health impact factor, and may include a value of a plurality of failure rate parameters (loss rate) regarding a change in the value of the operation parameter corresponding to the health influence factor. That is, a curve of a plurality of failure rates with respect to the value of the operating parameter corresponding to the health influencing factor is included in a first sub-model.
  • the device for memory evaluation can autonomously match the failure rate of the memory to be evaluated according to the inherent parameters of the memory to be evaluated (such as the memory capacity), and the curve of the operating parameter corresponding to each health impact factor, and The corresponding curve is selected by the user from a plurality of curves included in the first sub-model corresponding to a health influence factor.
  • FIG. 17 is a schematic diagram of another MC interface provided by an embodiment of the present invention.
  • the MC interface 50 shown in FIG. 17 further includes an option 513 for supporting the user to select "temperature-loss rate curve 1", which includes a " ⁇ " option.
  • the ⁇ option can correspond to a drop-down window.
  • the processor in the memory evaluation device can generate a corresponding click operation instruction and instruct the display to display as shown in FIG. 18.
  • the illustrated MC interface 50 includes a window 5131 that includes a "temperature-loss rate curve 1" option, a "temperature-loss rate curve 2" option, a “temperature-loss rate curve 3” option, and a “temperature-failure” option. 7 options for rate curve 4" option, “temperature-loss rate curve 5" option, “temperature-loss rate curve 6” option and “temperature-loss rate curve 7" option.
  • the device for memory evaluation receives a weight and an algorithm corresponding to each health influence factor of the at least one health impact factor set by the user.
  • step 401c may be performed by the communication interface 114 in the memory evaluation device 20 shown in FIG. 2a.
  • the above algorithm includes addition and/or multiplication.
  • the above algorithm may also be an integration algorithm or the like.
  • the method of memory evaluation in the embodiment of the present invention is described by taking the above algorithm as an addition and/or multiplication as an example.
  • FIG. 19 it is a schematic diagram of another MC interface provided by an embodiment of the present invention.
  • the weight corresponding to each health influence factor in the MC interface 50 shown in FIG. 19 can be set by the user through the input device.
  • the algorithm option corresponding to each health influence factor in the MC interface 50 shown in FIG. 19 further includes a “ ⁇ ” option, and the “ ⁇ ” option corresponds to a drop-down window.
  • a pull-down window 581 in the MC interface 50 shown at 20 is clicked by the user, and the processor in the memory evaluation apparatus can generate a corresponding click operation instruction. And instruct the display to display the MC interface 50 as shown in FIG.
  • the device for memory evaluation determines the second sub-model according to the weight and algorithm corresponding to each health influence factor.
  • step 401c may be performed by the processor 111 of the device 20 of the memory evaluation shown in FIG. 2a.
  • the second sub-model of the memory named "DIMM000" (memory to be evaluated) may be the "weight” option corresponding to each health influence factor shown by the MC interface 50.
  • the "Algorithm” option is determined. The user can click through the input device to operate the “weight” option and the “algorithm” option corresponding to each health impact factor in the MC interface 50 shown in FIG. 19, so that the processor in the memory evaluation device generates the corresponding Click operation instructions.
  • the devices for memory evaluation may determine a first sub-model corresponding to each health impact factor of different memory to be evaluated and a second sub-model of the memory to be evaluated, that is, determine Different health assessment models for the memory to be evaluated.
  • the health assessment model provided by the embodiment of the present invention can be made to conform to the memory to be evaluated, which is beneficial to improving the accuracy of the health of the memory to be evaluated obtained according to the health assessment model.
  • At least one health impact factor in the health assessment model provided by the embodiment of the present invention may be selected by the user for different memory to be evaluated; each health degree in the health assessment model
  • the plurality of curves included in the first sub-model corresponding to the influencing factors may also be selected by the user for different memory to be evaluated.
  • the method for memory evaluation provided in the embodiment of the present invention further supports the user adding a health influence factor to the health assessment model and adding a related curve to the first sub-model corresponding to a health influence factor.
  • step 401a may be replaced by step 401a'.
  • FIG. 21 it is a schematic flowchart of another method for memory evaluation provided by an embodiment of the present invention.
  • step 401a shown in FIG. 16 may be replaced with step 401a':
  • the 401a', the memory evaluation device receives at least one health influence factor set by the user and the operation parameter and the failure rate parameter corresponding to each health influence factor.
  • the operating parameter and the failure rate parameter corresponding to each health influencing factor set by the user refer to data of the value of the failure rate parameter regarding the value change of the operating parameter, such as the value of the failure rate parameter, regarding the operation.
  • the curve of the change in the value of the parameter refers to data of the value of the failure rate parameter regarding the value change of the operating parameter, such as the value of the failure rate parameter, regarding the operation.
  • the MC interface 50 as shown in FIG. 22 or FIG. 23 also includes an "Add" option 59 for adding a health impact factor to the health assessment model.
  • the processor in the memory evaluation device can generate a corresponding click operation instruction and instruct the display to display the MC as shown in FIG.
  • FIG. 24 it is another schematic diagram of an MC interface provided by an embodiment of the present invention.
  • the MC interface 50 shown in FIG. 24 further includes an "Add" option 514 for a health influence factor in the health assessment model. Add a failure rate curve for the operating parameters with respect to the corresponding operating parameter changes.
  • the processor in the memory evaluation device can generate a corresponding click operation instruction and instruct the display to display as shown in FIG. 25.
  • the MC interface 50 is shown.
  • the MC Curve 50 shown in Figure 25 includes the "Draw Curve” option and the "Import Curve” option.
  • the above “drawing curve” option is used to provide the user with a window for plotting the failure rate corresponding to a health impact factor of the memory to be evaluated with respect to the corresponding operating parameter variation curve.
  • the above-mentioned "Import Curve” option is used to provide the user with a window for calculating the failure rate corresponding to a health impact factor of the memory to be evaluated with respect to the corresponding operating parameter variation curve.
  • the user can select not only the health impact factor of the memory to be evaluated but also the failure rate corresponding to each health impact factor in the health assessment model.
  • the data (curve) of the parameter change may also be added in the health assessment model to the health impact factor of the memory to be evaluated and the data (curve) of the failure rate corresponding to each health impact factor with respect to the corresponding operational parameter change. Therefore, the health assessment model of the memory to be evaluated is more consistent with the memory to be evaluated, which is beneficial to improving the accuracy of the health of the memory to be evaluated obtained according to the health assessment model of the memory to be evaluated.
  • the device for evaluating the memory can match the health value of the memory to be evaluated to a preset value in the process of outputting the health indication information of the memory to be evaluated according to the health of the memory to be evaluated.
  • the value interval gives the health indication information of the memory to be evaluated.
  • step 404 in the above embodiment may include steps 404a-404c.
  • FIG. 27 it is a schematic flowchart of another method for memory evaluation provided by an embodiment of the present invention.
  • the method of memory evaluation shown in FIG. 27, step 404 shown in FIG. 4 above may include steps 404a-404c:
  • the device for memory evaluation outputs the first health degree indication information, where the first health degree indication information is used to prompt the user to evaluate the memory. replace.
  • the device for memory evaluation outputs the second health degree indication information, and the second health degree indication information is used to prompt the user that the memory to be evaluated can be replaced. .
  • the device for memory evaluation In a case where the value of the health of the memory to be evaluated is within a third preset value interval, the device for memory evaluation outputs a third health degree indication information, where the third health degree indication information is used to prompt the user that the memory to be evaluated needs to be replaced. .
  • the first preset value interval may be [75, 100]
  • the second preset value interval may be [45, 74]
  • the third preset value interval may be [0, 44].
  • the first preset value interval, the second preset value interval, and the third preset value interval may be other intervals, which are not limited in the embodiment of the present invention.
  • the health indication information of the memory to be evaluated may be displayed to the user by the MC interface displayed by the display.
  • FIG. 27 is a schematic diagram of another MC interface provided by an embodiment of the present invention.
  • each memory in the MC interface shown in FIG. 27 also corresponds to a "health" option 32.
  • the health indication information of the memory to be evaluated displayed on the MC interface is a healthy value of the memory to be evaluated.
  • the fitness indicator of the to-be-evaluated memory in the first preset value interval, the second preset value interval, and the third preset value interval is sequentially highlighted.
  • the memory with the name "DIMM000”, the memory with the name “DIMM002”, and the memory with the name “DIMM011” shown in the MC interface in Figure 27 are in normal fonts (denoted as font 1) to prompt The user does not need to replace the memory; the health indication information of the memory with the name "DIMM012" is displayed with a more prominent font (recorded as font 2) compared to the font 1, to prompt the user that the memory can be replaced, that is, no Replace it immediately; the memory with the name "DIMM001" and the memory with the name "DIMM010” indicate a more prominent font (marked as font 3) compared to font 2 to prompt the user that the memory needs to be immediately replace.
  • font 1, font 2, and font 3 are more prominently referred to as font 1, font 2, and font 3 are sequentially increased and bolded, or the colors of the above font 1, font 2, and font 3 are black in order. , orange and red, etc.
  • the health indication information of the memory to be evaluated displayed by the MC interface provided by the embodiment of the present invention may not only adopt the above-mentioned prominent font, but also may be other manners.
  • FIG. 28 it is another schematic diagram of an MC interface provided by an embodiment of the present invention.
  • the health indication information of the memory to be evaluated displayed on the MC interface is “healthy” in the case that the value of the health of the memory to be evaluated is within the first preset value interval, so as to prompt the user that the memory to be evaluated does not need to be replace.
  • the memory of the name "DIMM000" shown in FIG. 28 the memory of the name "DIMM002”
  • the memory of the name "DIMM011” are "healthy”.
  • the health indication information of the memory to be evaluated displayed on the MC interface is “general” to prompt the user that the memory to be evaluated can be replaced.
  • the health indication information of the memory named "DIMM012" displayed on the MC interface is "general”.
  • the health indication information of the memory to be evaluated displayed on the MC interface is “alarm” to prompt the user that the memory to be evaluated needs to be replaced.
  • the health indication information of the memory named "DIMM001" and the memory named "DIMM010" displayed on the MC interface is “alarm”.
  • the device for displaying the memory may display different values for the memory to be evaluated for different health values. Health indicator information.
  • the memory evaluation device can prompt the user to replace the memory to be evaluated, so that the memory to be evaluated can support The server is running normally.
  • the first preset value interval and the second preset value interval provided by the embodiment of the present invention may also be set by the user according to the autonomous setting.
  • the method for memory evaluation provided by the embodiment of the present invention may further include step 401 ′ before the foregoing step 401.
  • FIG. 29 it is a schematic flowchart of another method for memory evaluation provided by an embodiment of the present invention.
  • the method of memory evaluation shown in Fig. 29 may further include step 401' before step 401 shown in Fig. 26:
  • the device for memory evaluation receives a first preset value interval set by a user, a second preset value interval, and a third preset value interval.
  • step 401' may be performed by the communication interface 114 in the device 20 of the memory evaluation shown in Figure 2a.
  • the MC interface 50 shown in FIG. 30 and FIG. 31 further includes a “first preset value interval” option, a “second preset value interval” option, and a “third preset value interval”.
  • the option is for the user to set the first preset value interval, the second preset value interval, and the third preset value interval.
  • the value "45-74" in the "second preset value interval” option included in the MC interface shown in FIG. 30 can be set by the user through the input device, and the processor in the memory evaluation device can generate the corresponding The instruction and instruct the display to display the MC interface 50 as shown in FIG.
  • the user may set different preset value intervals for different memory to be evaluated, so that the memory evaluation device obtains the health of the memory to be evaluated according to the preset value interval.
  • the degree indication information is more in line with the memory to be evaluated, which is more favorable for prompting the user whether the memory to be evaluated needs to be replaced.
  • the device for memory evaluation can continuously evaluate the health of the memory to be evaluated.
  • the user can update the health assessment model of the memory to be evaluated to make the The health assessment model is more in line with the memory to be evaluated.
  • the method for memory evaluation provided by the embodiment of the present invention may further include step 405 and step 406 after step 404.
  • FIG. 32 it is a schematic flowchart of another method for memory evaluation provided by an embodiment of the present invention.
  • the method of memory evaluation shown in FIG. 32 may further include step 405 and step 406 after step 404 shown in FIG. 4:
  • the device for memory evaluation receives an update of template data of the user to evaluate the memory.
  • the above step 405 can be performed by the communication interface 114 in the device 20 of the memory evaluation shown in FIG. 2a.
  • the template data includes at least one or more of the following: at least one health influence factor, at least one health impact factor, an operation parameter corresponding to each health influence factor, a weight corresponding to each health influence factor, An algorithm corresponding to each health influence factor, a first preset value interval, a second preset value interval, and a third preset value interval
  • the memory evaluation device updates the health assessment model according to the template data of the updated memory to be evaluated.
  • step 406 can be performed by the processor 111 in the memory evaluation device 20 shown in FIG. 2a.
  • the device for evaluating the memory to be evaluated may refer to the description of the health assessment model for determining the memory to be evaluated in the foregoing embodiment. The description of the embodiments of the invention will not be repeated.
  • the memory evaluation device obtains the health of the memory to be evaluated according to the updated health assessment model.
  • the memory to be evaluated helps to more accurately prompt the user whether the memory to be evaluated needs to be replaced.
  • each network element such as a device for memory evaluation, includes hardware structures and/or software modules for performing respective functions in order to implement the above functions.
  • each network element such as a device for memory evaluation
  • the present invention can be implemented in a combination of hardware or hardware and computer software in combination with the elements and algorithm steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for each particular application to implement the described functionality, but such implementation should not be considered to be beyond the scope of the application.
  • the embodiment of the present invention may perform module division on the device for memory evaluation according to the foregoing method example.
  • each module may be divided according to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software modules. It should be noted that the division of the module in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.
  • FIG. 33 shows a possible composition diagram of the apparatus for memory evaluation provided in the above embodiment, as shown in FIG. 33, the memory evaluation apparatus 33 may include determining.
  • the above determining module 331, the means 33 for supporting the memory evaluation performs the steps 401, 401a-401e and 406 in the above embodiment, and/or other processes for the techniques described herein.
  • the above obtaining module 332, the means 33 for supporting the memory evaluation performs the step 402 in the above embodiment, and/or other processes for the techniques described herein.
  • the above matching module 333, the means 33 for supporting the memory evaluation performs step 403 and steps 403a-403b in the above embodiment, and/or other processes for the techniques described herein.
  • the output module 334, the means 33 for supporting memory evaluation, performs step 404 and steps 404a-403c in the above-described embodiments, and/or other processes for the techniques described herein.
  • the above determining module 331 may include a receiving submodule 3311 and a determining submodule 3312.
  • the receiving sub-module 3311, the means 33 for supporting the memory evaluation performs the steps 401a, 401d, 401' and 405 in the above embodiment, and/or other processes for the techniques described herein.
  • the determining sub-module 3312, the means 33 for supporting memory evaluation performs steps 401a, 401b, 401c, 401e, and 406 in the above-described embodiments, and/or other processes for the techniques described herein.
  • the above-described acquisition module 332, matching module 333, and determination sub-module 3312 may be integrated in one processing module.
  • the processing module may be a processor or a controller, such as a CPU, a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), and a field programmable gate array. (Field Programmable Gate Array, FPGA) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It is possible to implement or carry out the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processing unit described above may also be a combination of computing functions, such as one or more microprocessor combinations, a combination of a DSP and a microprocessor, and the like.
  • the output module 334 and the receiving submodule 3311 described above may be implemented by a processor and a communication interface.
  • the output module may specifically include a generating submodule and an output submodule.
  • the generating sub-module can be used to generate health indication information of the memory to be evaluated, and the output sub-module can be configured to output the health indication information of the memory to be evaluated through the display.
  • the storage module can be a memory.
  • the device 33 for memory evaluation described above may also include other functional modules.
  • the processing module may be the processor 111 shown in FIG. 2a.
  • the above storage module may be the hard disk 112 and at least one memory 113 shown in FIG. 2a.
  • the above communication module may be the communication interface 114 shown in FIG. 2a.
  • the communication bus 114 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the foregoing communication bus 114 can be divided into an address bus, a data bus, a control bus, and the like, which are not limited in this embodiment of the present invention.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used. Combinations can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes: a flash memory, a mobile hard disk, a read only memory, a random access memory, a magnetic disk, or an optical disk, and the like, which can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Quality & Reliability (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Debugging And Monitoring (AREA)
  • Techniques For Improving Reliability Of Storages (AREA)

Abstract

本申请提供一种内存评估的方法及装置，涉及计算机技术领域，可以在服务器的内存运行的过程中评估该内存的健康度，并在该内存未发生故障且健康度较低的情况下，提示用户更换该内存。具体方案包括：确定待评估内存的健康度评估模型，该健康度评估模型为待评估内存的健康度关于待评估内存的至少一个健康度影响因素变化的关系；获取至少一个健康度影响因素中每个健康度影响因素对应的至少一个运行参数值；将每个健康度影响因素对应的至少一个运行参数值，分别匹配至健康度评估模型，得到待评估内存的健康度；根据待评估内存的健康度，输出待评估内存的健康度指示信息，该评估内存的健康度指示信息用于向用户指示待评估内存是否需要更换。

Description

一种内存评估的方法及装置 技术领域
本发明实施例涉及计算机技术领域，尤其涉及一种内存评估的方法及装置。
背景技术
随着互联网技术(Internet Technology，IT)的发展，服务器的内存总容量越来越大，使得内存的正常工作对服务器的正常运行更加重要。因此，为了支持服务器正常运行，需要在内存发生故障之前判断内存是否正常工作。
现有技术中，对一些服务器，如X86服务器，一般基于内存是否可用，或者服务器是否能正常识别到内存，或者内存是否出现了不可纠正错误(Uncorrectable Error，UCE)等方面，判断内存是否能正常工作。即基于内存是否故障判断内存是否能正常工作。在判断得到服务器的内存故障后，提示更换已经发生故障的内存。
存在的问题是，现有技术在基于内存是否故障判断内存是否能正常工作的情况下，内存故障已经对服务器的正常运行造成了影响。例如，在判断得到内存不可用时，内存已经造成服务器宕机，业务受损，甚至数据丢失等严重影响。
发明内容
本申请提供一种内存评估的方法及装置，用于评估服务器中内存的健康度，并在该内存未发生故障且健康度较低的情况下，提示用户更换该内存，使得该内存可以支持该服务器正常运行。
为达到上述目的，本申请采用如下技术方案：
第一方面，提供一种内存评估的方法，该方法包括：确定待评估内存的健康度评估模型，该健康度评估模型为待评估内存的健康度关于待评估内存的至少一个健康度影响因素变化的关系，一个健康度影响因素对应一个运行参数和一个失效率参数，且一个健康度影响因素对应一个权值，该权值为常数；获取至少一个健康度影响因素中每个健康度影响因素对应的至少一个运行参数值，该至少一个运行参数值对应一个上述运行参数；将每个健康度影响因素对应的至少一个运行参数值，分别匹配至上述健康度评估模型，得到待评估内存的健康度；根据待评估内存的健康度，输出待评估内存的健康度指示信息，待评估内存的健康度指示信息用于向用户指示待评估内存是否需要更换。
需要说明的是，本申请提供一种描述待评估内存的健康度关于待评估内存的至少一个健康度影响因素变化的关系的健康度评估模型，使得内存评估的装置可以根据待评估内存的健康度评估模型得到待评估内存的健康度。从而，内存评估的装置可以根据待评估内存的健康度的数值大小，生成待评估内存的健康度指示信息。也就是说，内存评估的装置可以通过待评估内存的健康度，在待评估内存发生故障之前，判断待评估内存是否更换。并且，内存评估的装置可以在该内存未发生故障且该内存的健康度较低的情况下，输出待评估内存的健康度指示信息，以提示用户更换该内存，使得该内存可以支持该服务器正常运行。
并且，上述一个健康度影响因素对应的权值可以表示该健康度影响因素对待评估内存的健康度的影响程度，不同权值的健康度影响因素对待评估内存的健康度的影响不同。 例如，一个健康度影响因素对应的权值越大，该健康度影响因素对待评估内存的健康度影响越大。这样一来，本申请提供的健康度评估模型中每个健康度影响因素权值，可以指示每个健康度影响因素对待评估内存的健康度的影响，使得健康度评估模型中针对待评估内存的不同健康度评估因素的影响程度更符合该待评估内存，有利于准确评估待评内存的健康度。
在一种可能的实现方式中，上述将每个健康度影响因素对应的至少一个运行参数值，分别匹配至健康度评估模型，得到待评估内存的健康度可以包括：将每个健康度影响因素对应的至少一个运行参数值，分别匹配至健康度评估模型中相应的健康度影响因素的第一子模型中，得到每个健康度影响因素对应的健康度折损值；上述健康度评估模型包括第二子模型，以及每个健康度影响因素对应的第一子模型，一个健康度影响因素的第一子模型为该健康度影响因素对应的健康度折损值关于该健康度影响因素对应的运行参数和失效率参数之间的关系；该第二子模型为待评估内存的健康度关于每个健康度影响因素对应的健康度折损值和每个健康度影响因素对应的权值变化的关系；根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，得到待评估内存的健康度。
需要说明的是，本申请中提供的内存评估的装置可以根据健康度评估模型中每个健康度影响因素对应的第一子模型，得到每个健康度影响因素对应的待评估内存的健康度折损值，以指示出各个健康度影响因素对待评估内存的健康度的影响。并且，将上述各个健康度影响因素对应的健康度折损值以及各个健康度影响因素对应的权值分别匹配至上述第二子模型中，得到权重不同(权值不同)的各个健康度影响因素影响下评估内存的健康度。如此，可以针对不同的待评估内存生成不同的健康度评估模型，有利于提高根据健康度评估模型得到的待评估内存的健康度的准确性。
在一种可能的实现方式中，上述至少一个健康度影响因素包括以下一种或多种：内存运行温度因素、内存业务负载因素、内存总运行时长因素、内存插拔因素、内存可纠正错误CE频度因素、内存不可纠正错误UCE频度因素和内存性能衰减因素。
其中，本申请提供的健康度评估模型中预设了多个健康度影响因素，使用户可以针对不同的待评估内存选择相应的健康度影响因素，从而使得健康度评估模型中针对待评估内存的健康度评估因素更符合该待评估内存，有利于准确评估出待评估内存的健康度。
在一种可能的实现方式中，上述内存运行温度因素对应的运行参数为待评估内存的运行温度；上述内存业务负载因素对应的运行参数为待评估内存的充放电次数；上述内存总运行时长因素对应的运行参数为待评估内存的总运行时长；上述内存插拔因素对应的运行参数为待评估内存的插拔次数；上述内存CE频度因素对应的运行参数为待评估内存的CE个数和/或待评估内存的CE频度；上述内存UCE频度因素对应的运行参数为待评估内存的UCE个数和/或待评估内存的UCE频度；上述内存性能衰减因素对应的运行参数为待评估内存的性能值衰减量。
需要说明的是，本申请提供的内存评估的装置中可以存储有描述各个健康度影响因素对应的运行参数和失效率参数关系的数据，如描述待评估内存的失效率参数关于相应的运行参数变化的曲线。上述待评估内存的失效率参数关于相应的运行参数变化的曲线为预先统计得到的数据。这样一来，内存评估的装置可以根据已有统计得到的数据去评 估还没有发生故障的待评估内存的健康度。
在一种可能的实现方式中，上述健康度评估模型中包括的至少一个健康度影响因素中的每个健康度影响因素对应一个算法，该算法可以为加法和/或乘法。上述“根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，得到待评估内存的健康度”可以包括根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，以及每个健康度影响因素对应的算法，得到待评估内存的健康度。
其中，对内存评估的装置中的一个内存，即服务器中的一个内存来说，内存评估的装置根据该内存的各个健康度影响因素对应的权值量化各个健康度影响因素对该内存的健康度的影响的同时，可以根据各个健康度影响因素对应的算法进一步量化各个健康度影响因素对该内存的健康度的影响程度。这样一来，有利于提高待评估内存的健康度的准确性。
在一种可能的实现方式中，上述根据待评估内存的健康度，输出待评估内存的健康度指示信息可以包括：在待评估内存的健康度的数值在第一预设数值区间内的情况下，输出第一健康度指示信息，第一健康度指示信息用于提示用户待评估内存不需要更换；在待评估内存的健康度的数值在第二预设数值区间内的情况下，输出第二健康度指示信息，第二健康度指示信息用于提示用户待评估内存可以更换；在待评估内存的健康度的数值在第三预设数值区间内的情况下，输出第三健康度指示信息，第三健康度指示信息用于提示用户待评估内存需要更换。
需要说明的是，本申请提供的内存评估的方法中，内存评估的装置在向用户展示待评估内存的健康度指示信息的过程中，可以针对不同健康度的数值的待评估内存显示不同的健康度指示信息。这样一来，可以在待评估内存未发生故障且该内存的健康度较低(健康度的数值较小)的情况下，内存评估的装置提示用户更换待评估内存，使得待评估内存支持该服务器正常运行。
在一种可能的实现方式中，上述确定待评估内存的健康度评估模型包括：接收用户设置的至少一个健康度影响因素；将用户设置的至少一个健康度影响因素确定为待评估内存的健康度评估模型包含的健康度影响因素；根据至少一个健康度影响因素确定相应的第一子模型；接收用户设置的至少一个健康度影响因素中每个健康度影响因素对应的权值和算法；根据每个健康度影响因素对应的权值和算法确定第二子模型。
需要说明的是，由于不同待评估内存的健康度影响因素可能不同，并且不同待评估内存的各个健康度影响因素对应的失效率参数关于相应的运行参数变化的数据可能不同；因此不同的待评估内存对应的健康度评估模型可能不同。本发明实施例提供的内存评估的方法中，内存评估的装置可以确定出针对不同的待评估内存的各个健康度影响因素对应的第一子模型以及待评估内存的第二子模型，即确定出不同待评估内存的健康度评估模型。这样一来，可以使得本发明实施例提供的健康度评估模型符合待评估内存，有利于提高根据该健康度评估模型得到的待评估内存的健康度的准确性。
在一种可能的实现方式中，本申请提供的内存评估的方法，在根据待评估内存的健康度，生成待评估内存的健康度指示信息之前，还包括：接收用户设置的第一预设数值区间、第二预设数值区间和第三预设数值区间。
需要说明的是，本申请提供的内存评估的方法，用户可以针对不同的待评估内存设置不同的预设数值区间，使得内存评估的装置根据该预设数值区间得到的待评估内存的健康度指示信息更加符合该待评估内存，有利于更加准确地提示用户待评估内存是否需要更换。
在一种可能的实现方式中，本申请提供的内存评估的方法，在将每个健康度影响因素对应的运行参数值，分别输入至健康度评估模型，得到待评估内存的健康度之后，还包括：接收用户对待评估内存的模板数据的更新，该模板数据至少包括以下一种或多种：至少一个健康度影响因素、至少一个健康度影响因素中每个健康度影响因素对应的运行参数、每个健康度影响因素对应的权值、每个健康度影响因素对应的算法，第一预设数值区间、第二预设数值区间和第三预设数值区间；根据更新后的待评估内存的模板数据，更新健康度评估模型。
其中，由于用户可以更新待评估内存的健康度评估模型使该健康度评估模型更加符合该待评估内存，因此内存评估的装置根据更新后的健康度评估模型得到待评估内存的健康度更加符合该待评估内存，有利于更加准确地提示用户待评估内存是否需要更换。
第二方面，本申请提供一种内存评估的装置，该装置包括：确定模块、获取模块、匹配模块和输出模块。其中，上述确定模块，用于确定待评估内存的健康度评估模型，该健康度评估模型为待评估内存的健康度关于待评估内存的至少一个健康度影响因素变化的关系，一个健康度影响因素对应一个运行参数和一个失效率参数，且一个健康度影响因素对应一个权值，权值为常数。上述获取模块，用于获取上述确定模块确定出的至少一个健康度影响因素中每个健康度影响因素对应的至少一个运行参数值，至少一个运行参数值对应一个运行参数。上述匹配模块，用于将上述获取模块得到的每个健康度影响因素对应的至少一个运行参数值，分别匹配至健康度评估模型，得到待评估内存的健康度。上述输出模块，用于根据上述匹配模块得到的待评估内存的健康度，输出待评估内存的健康度指示信息，该待评估内存的健康度指示信息用于向用户指示待评估内存是否需要更换。
在一种可能的实现方式中，上述匹配模块，具体用于将每个健康度影响因素对应的至少一个运行参数值，分别匹配至健康度评估模型中相应的健康度影响因素的第一子模型中，得到每个健康度影响因素对应的健康度折损值；上述健康度评估模型包括第二子模型，以及每个健康度影响因素对应的第一子模型，一个健康度影响因素的第一子模型为该健康度影响因素对应的健康度折损值关于该健康度影响因素对应的运行参数和失效率参数之间的关系；第二子模型为待评估内存的健康度关于每个健康度影响因素对应的健康度折损值和每个健康度影响因素对应的权值变化的关系；根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，得到待评估内存的健康度。
在一种可能的实现方式中，上述至少一个健康度影响因素包括以下一种或多种：内存运行温度因素、内存业务负载因素、内存总运行时长因素、内存插拔因素、内存可纠正错误CE频度因素、内存不可纠正错误UCE频度因素和内存性能衰减因素。
在一种可能的实现方式中，上述内存运行温度因素对应的运行参数为待评估内存的运行温度；上述内存业务负载因素对应的运行参数为待评估内存的充放电次数；上述内 存总运行时长因素对应的运行参数为待评估内存的总运行时长；上述内存插拔因素对应的运行参数为待评估内存的插拔次数；上述内存CE频度因素对应的运行参数为待评估内存的CE个数和/或待评估内存的CE频度；上述内存UCE频度因素对应的运行参数为待评估内存的UCE个数和/或待评估内存的UCE频度；上述内存性能衰减因素对应的运行参数为待评估内存的性能值衰减量。
在一种可能的实现方式中，上述健康度评估模型中包括的至少一个健康度影响因素中的每个健康度影响因素对应一个算法，该算法可以为加法和/或乘法。上述匹配模块，还用于根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，以及每个健康度影响因素对应的算法，得到待评估内存的健康度。
在一种可能的实现方式中，上述输出模块，具体用于在待评估内存的健康度的数值处于第一预设数值区间内的情况下，输出第一健康度指示信息，第一健康度指示信息用于提示用户待评估内存不需要更换；在待评估内存的健康度的数值在第二预设数值区间内的情况下，输出第二健康度指示信息，第二健康度指示信息用于提示用户待评估内存可以更换；在待评估内存的健康度的数值在第三预设数值区间内的情况下，输出第三健康度指示信息，第三健康度指示信息用于提示用户待评估内存需要更换。
在一种可能的实现方式中，上述确定模块包括接收子模块和确定子模块。上述接收子模块，用于在接收用户设置的至少一个健康度影响因素。上述确定子模块，用于将接收子模块接收的用户设置的至少一个健康度影响因素确定为待评估内存的健康度评估模型包含的健康度影响因素；根据至少一个健康度影响因素确定相应的第一子模型。上述接收子模块，还用于接收用户设置的至少一个健康度影响因素中每个健康度影响因素对应的权值和算法。上述确定子模块，还用于根据接收子模块接收的每个健康度影响因素对应的权值和算法确定第二子模型。
在一种可能的实现方式中，上述接收子模块，具体用于接收用户设置的至少一个健康度影响因素以及每个健康度影响因素对应的运行参数和失效率参数。
在一种可能的实现方式中，上述接收子模块，还用于在根据待评估内存的健康度，生成待评估内存的健康度指示信息之前，接收用户设置的第一预设数值区间、第二预设数值区间和第三预设数值区间。
在一种可能的实现方式中，上述接收子模块还用于，在上述匹配模块将每个健康度影响因素对应的运行参数值，分别匹配至健康度评估模型，得到待评估内存的健康度之后，接收用户对待评估内存的模板数据的更新。上述该模板数据至少包括以下一种或多种：至少一个健康度影响因素、至少一个健康度影响因素中每个健康度影响因素对应的运行参数、每个健康度影响因素对应的权值、每个健康度影响因素对应的算法，第一预设数值区间、第二预设数值区间和第三预设数值区间。上述确定子模块，还用于根据上述接收子模块得到的更新后的待评估内存的模板数据，更新上述健康度评估模型。
第三方面，本申请提供一种内存评估的装置，该装置包括：处理器、硬盘、至少一个内存、通信接口、输入器、显示器和总线。上述硬盘以及至少一个内存用于存储至少一个指令，该处理器、该硬盘、该至少一个内存、该通信接口、该输入器和该显示器通过总线连接。当内存评估的装置运行时，处理器执行硬盘以及至少一个内存中存储的至少一个指令，以使内存评估的装置执行如上述第一方面及其各种实现方式中示出的内存 评估的方法。
第四方面，本申请提供一种计算机存储介质，该计算机存储介质包括：至少一个指令；当上述至少一个指令在计算机上运行时，使得计算机执行如上述第一方面及其各种实现方式中示出的内存评估的方法。
第五方面，本申请提供一种计算机程序产品，该计算机程序产品包括：至少一个指令；当至少一个指令在计算机上运行时，使得计算机执行如上述第一方面及其各种实现方式中示出的内存评估的方法。
附图说明
图1为本发明实施例提供的服务器的一种硬件结构示意图；
图2为本发明实施例提供的内存评估的装置的一种架构示意图；
图2a为本发明实施例提供的内存评估的装置的另一种结构示意图；
图3为本发明实施例提供的一种MC界面的示意图；
图4为本发明实施例提供的内存评估的方法的一种流程示意图；
图5为本发明实施例提供的另一种MC界面的示意图；
图6为本发明实施例提供的另一种MC界面的示意图；
图7为本发明实施例提供的另一种MC界面的示意图；
图8为本发明实施例提供的另一种MC界面的示意图；
图9为本发明实施例提供的另一种MC界面的示意图；
图10为本发明实施例提供的另一种MC界面的示意图；
图11为本发明实施例提供的另一种MC界面的示意图；
图12为本发明实施例提供的另一种MC界面的示意图；
图13为本发明实施例提供的另一种MC界面的示意图；
图14为本发明实施例提供的内存评估的方法的另一种流程示意图；
图15为本发明实施例提供的另一种MC界面的示意图；
图16为本发明实施例提供的内存评估的方法的另一种流程示意图；
图17为本发明实施例提供的另一种MC界面的示意图；
图18为本发明实施例提供的另一种MC界面的示意图；
图19为本发明实施例提供的另一种MC界面的示意图；
图20为本发明实施例提供的另一种MC界面的示意图；
图21为本发明实施例提供的内存评估的方法的另一种流程示意图；
图22为本发明实施例提供的另一种MC界面的示意图；
图23为本发明实施例提供的另一种MC界面的示意图；
图24为本发明实施例提供的另一种MC界面的示意图；
图25为本发明实施例提供的另一种MC界面的示意图；
图26为本发明实施例提供的内存评估的方法的另一种流程示意图；
图27为本发明实施例提供的另一种MC界面的示意图；
图28为本发明实施例提供的另一种MC界面的示意图；
图29为本发明实施例提供的内存评估的方法的另一种流程示意图；
图30为本发明实施例提供的另一种MC界面的示意图；
图31为本发明实施例提供的另一种MC界面的示意图；
图32为本发明实施例提供的内存评估的方法的另一种流程示意图；
图33为本发明实施例提供的内存评估的装置的另一种结构示意图；
图34为本发明实施例提供的内存评估的装置的另一种结构示意图。
具体实施方式
本发明实施例提供一种内存评估的方法及装置，用于评估服务器中内存的健康度，并在该内存未发生故障且健康度较低的情况下，提示用户更换该内存，使得该内存可以支持该服务器正常运行。
需要说明的是，本发明实施例提供的内存评估的方法应用于服务器，其中，服务器为一种用于提供计算服务的设备。示例性的，本发明实施例提供的服务器可以是x86服务器，x86服务器是采用复杂指令集计算机(Complex Instruction Set Computer，CISC)架构的服务器。当然，本发明实施例提供的服务器还可以是非x86服务器，本申请提供的方案对此不作限制。本发明实施例以下，仅以x86服务器为例说明本发明实施例提供的内存评估的方法。
其中，服务器，如x86服务器包括硬件系统和软件系统。上述硬件系统可以包括处理器、通信接口、系统总线、硬盘和内存等部件。上述软件系统可以包括操作系统和管理系统，该管理系统可以由管理软件，如管理控制器(Management Controller，MC)实现。需要说明的是，服务器中的MC可以用于监控、管理该服务器中各个部件的运行数据和固有参数，如该服务器中内存的运行数据和该内存的固有参数。其中，内存的运行数据可以包括内存的运行温度、运行时长等数据。需要说明的是，本发明实施例以下，可以将“内存的运行数据”称为“内存的运行参数值”或“内存的运行参数”，不同的名称仅仅为了方便说明，对内存的运行数据本身不造成限定。
另外，内存的固有参数可以包括内存的厂商、容量、主频、序列号、最小电压、RANK数、位宽以及该内存采用的技术等。例如，内存的容量可以为32768兆字节(Mbyte，MB)；主频可以为2400兆赫(MHz)；序列号用于唯一标识一个内存，如序列号为0x27EACEEA；最小电压可以为1200毫伏(millivolt，mV)；RANK数可以为1列(rank)或2rank等；位宽可以为64比特(bit)或72bit等；采用的技术可以为“Synchronous|Registered(Buffered)”。
本发明实施例提供的内存的健康度，可以反映出内存发生故障的可能性。其中，内存的健康度越高，该内存发生故障的可能性就越小(即内存失效率越小)，该内存通常可以正常运行且不需要更换；内存的健康度越低，该内存发生故障的可能性就越大(即内存的失效率越高)，该内存通常不能正常运行且需要更换。本发明实施例提供的内存评估的方法，可以根据内存的健康度，在内存发生故障之前，判断是否更换该内存。
下面将结合本发明实施例中的附图，详细描述本发明实施例中的技术方案。
示例性的，如图1所示，为本发明实施例提供的服务器的一种硬件结构示意图。图1示出的服务器11可以包括处理器111、硬盘112、至少一个内存113，以及通信接口114和总线115。
具体的，下面结合图1对服务器的各个构成部件进行具体的介绍：
处理器111为服务器的控制中心，可以是一个处理器，也可以是多个处理元件的统 称。例如，处理器111可以是一个中央处理器(central processing unit，CPU)，也可以是特定集成电路(Application Specific Integrated Circuit，ASIC)，或者可以被配置成实施本发明实施例的一个或多个集成电路，如：一个或多个微处理器(digital signal processor，DSP)，或，一个或者多个现场可编程门阵列(Field Programmable Gate Array，FPGA)。例如，处理器111可以通过MC监测服务器11中内存的运行数据。
在具体的实现中，作为一种实施例，处理器111可以包括一个或多个CPU，例如图1中所示的CPU0和CPU1。当然，在具体实现中，作为一种实施例，服务器可以包括多个处理器。这些处理器中的每一个可以是一个单核处理器(single-CPU)，也可以是一个多核处理器(multi-CPU)。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
硬盘112为服务器的一种外部存储器，也称为外存，用于保存大量的、永久性的数据。即使服务器掉电，这些数据也不会丢失。例如，硬盘112可以存储MC监测内存的运行数据过程中的系统日志。具体的，上述硬盘可以由只读存储器(Read Only Memory，ROM)实现。在具体实现中，作为一种实施例，硬盘可以为固态硬盘(Solid State Drive，SSD)、硬盘驱动器(Hard Disk Drive，HDD)等。
当然，上述服务器的外存除了硬盘之外，还可以是只读光盘(Compact Disc Read-Only Memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)，本发明实施例对此不作详细描述。
本发明实施例这里，仅以至少一个内存113中一个内存113为例对内存进行说明。
内存113为与处理器直接交换数据的内部存储器，也叫主存；主要由随机存取存储器(random access memory，RAM)又称随机存储器实现。用于暂时存储处理器中的运算数据，以及与硬盘等外部存储器交换的数据，并且服务器中所有程序均在内存中运行。具体的，处理器111可以通过运行或执行存储在至少一个内存113中的软件或程序，以及调用存储在硬盘112和/或至少一个内存113内的数据，执行服务器的各种功能。例如，内存113可以存储处理器111监测服务器11中内存的运行数据的程序。
在具体的实现中，作为一种实施例，上述内存113可以为静态随机存储器(Static RAM，SRAM)、动态随机存储器(Dynamic RAM，DRAM)等RAM。其中，本发明实施例提供的内存可以为服务器中可插拔的内存条。在具体的实现中，作为一种实施例，内存113可以由双列直插式存储模块(Dual Inline Memory Modules，DIMM)，或者双倍速率同步动态随机存储器(Double Data Rate Synchronous Dynamic Random Access Memory，DDR SDRAM)，也称DDR实现。
需要说明的是，上述内存的固有参数还可以包括内存类型。例如，内存类型可以包括DDR、DDR2、DDR3以及DDR4等类型。并且，在服务器中每个内存还可以有一个名称，如DIMM000、DIMM011等。
通信接口114可以用于与外部设备交互。示例性的，通信接口114可以包括两个通信接口，一个用于向外部设备发送数据的发送接口和一个用于接收来自外部设备的数据的接收接口，即发送设备可以通过两个不同的通信接口分别实现数据的接收和数据的发送。例如，服务器11的一个通信接口可以向外部设备发送硬盘112和至少一个内存113存储的数据。当然，该通信接口114可以将数据接收功能和数据发送功能集成在一个通 信接口上，该通信接口具备数据接收功能和数据发送功能。例如，通信接口114可以为MC接口。
上述处理器111、硬盘112、至少一个内存113以及通信接口114均可以通过总线115连接。其中，上述总线115可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。上述总线115可以分为地址总线、数据总线、控制总线等。为便于表示，图1中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
示例性的，结合图2所示的服务器11，服务器11中的处理器111中每个CPU可以下挂一个内存113。
图1中示出的服务器的硬件结构并不构成对服务器的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。例如，上述服务器11中还包括一个或多个温度传感器等部件，该一个或多个温度传感器可以用于检测服务器中一些部件的温度，如CPU的温度以及各个内存的温度。
需要说明的是，在服务器11中MC检测至少一个内存113的运行数据的同时，可以通过人机交互的方式管理该MC，使得用户能够直观地观测或管理该MC获得的数据，如至少一个内存113的运行数据和固有参数。具体的，可以通过为服务器11连接输入器和显示器，实现人机交互。
示例性的，如图2所示，为本发明实施例提供的一种内存评估的装置的架构示意图。图2所示的内存评估的装置20包括服务器11、输入器12和显示器13。其中，图2中仅使用直线表示上述服务器11、输入器12和显示器13之间的连接关系。上述服务器11、输入器12和显示器13的之间的连接可以为有线连接或者无线连接，本发明实施例对此不作限定。
可选的，上述输入器12和显示器13可以由服务器11提供服务，服务器11中的业务可以由处理器11结合输入器12和显示器13实现。其中，上述内存评估的装置10可以由台式电脑，又称台式机或桌面机(desktop computer)等终端设备实现。此时，上述服务器11称为主机，上述输入器12可以为键盘、鼠标等装置。例如，上述服务器11、输入器12、显示器13组成的内存评估的装置10可以属于同一个台式机，记为终端设备1。
可选的，上述输入器12和显示器13并不由服务器11提供服务，而是由其他的服务器提供服务。例如，上述服务器11为终端设备1提供服务，而上述输入器12和显示器13属于终端设备2，终端设备2可以是另一个台式机。
另外，在具体的实现中，作为一种实施例，上述终端设备2还可以为设置有触控屏的终端设备。其中，该终端设备可以为手机、平板电脑、笔记本电脑、超级移动个人计算机(Ultra-mobile Personal Computer，UMPC)、上网本、个人数字助理(Personal Digital Assistant，PDA)等终端设备。此时，上述输入器12和显示器13可以由终端设备2的触控屏实现。
其中，本发明实施提供的内存评估的装置包括的服务器11、输入器12和显示器13的具体组成方式不作限定。以下仅以本发明实施例提供的内存评估的装置包括的服务器 11、输入器12和显示器13由同一台终端设备提供为例，说明本发明实施例提供的内存评估的方法。
具体的，结合图2示出的内存评估的装置20以及图1示出的服务器11，如图2a所示，为本发明实施例提供的内存评估的装置的另一种结构示意图。图2a中，内存评估的装置20包括处理器111、硬盘112、至少一个内存113以及通信接口114、总线115、输入器12和显示器13。
需要说明的是，本发明实施例提供的内存评估的方法，可以通过显示器13显示MC的人机交互界面，该MC的人机交互界面可以采用DOS界面或浏览器界面。本发明实施例以下，仅以MC的人机交互界面采用浏览器界面为例，说明本发明实施例提供的内存评估的方法。其中，一个MC可以对应一个登录地址，如统一资源定位符(Uniform Resource Locator，URL)。此时，输入器12可以接收用户输入的MC的登录地址，显示器13可以采用浏览器界面显示该MC的人机交互界面(以下简称为MC界面)。本发明实施例以下，仅以用户已经通过输入器输入MC的登录地址之后，显示器显示MC界面为例，说明本发明实施例提供的内存评估的方法。
具体的，上述显示器上显示的MC界面可以是一种图形用户界面(Graphical User Interface，GUI)；并且该GUI中包括文字形式和图标形式的图形选项，该GUI文字形式的图形选项和图标形式的图形选项均可以由用户通过鼠标、键盘、触摸屏、或者用其他输入器进行操作。
上述GUI包括窗口、下拉菜单、对话框及其相应的控制机制(如该服务器的CPU)。同时，GUI在各种新式应用程序或软件中都是标准化的，即相同的操作总是以同样的方式来完成；如对该GUI中的任一文字形式或图标形式的图形选项(以下称为选项)进行点击操作，可以是用户通过鼠标点击该选项，或者用户通过手指点击触控屏上的该选项。用户在点击操作一个选项之后，处理器可以生成相应的点击操作指令，并响应该点击操作。
示例性的，如图3所示，为本发明实施例提供的一种MC界面的示意图。图3中的MC界面分别示出了名称为DIMM000、DIMM001、DIMM002、DIMM010、DIMM011和DIMM012的6个内存的固有参数。图3中示出的MC界面中包括“名称▼”、“厂商▼”、“容量▼”、“主频▼”、“序列号▼”等选项。每个选项中包括的“▼”对应一个下拉菜单。例如，用户可以通过输入器点击操作选项31，即“厂商▼”选项中的“▼”选项，内存评估的装置中的处理器在生成相应的点击操作指令之后，指示显示器显示如图3所示的“厂商▼”对应的下拉菜单311，下拉菜单311中包括“厂商A”、“厂商B”和“厂商C”三个选项。其中，若用户点击操作下拉菜单311中的“厂商A”，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器在图3所示的MC界面仅显示生产厂商为厂商A的内存的固有参数。
为使本发明实施例的目的、技术方案和优点更加清楚，下面结合图2a所示的内存评估的装置中的具体部件，通过图4所示的内存评估的方法的流程图对本发明实施例提供的内存评估的方法进行详细描述。此外，虽然在方法流程图中示出了本发明实施例提供的内存的评估的方法的逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤：
S401、内存评估的装置确定待评估内存的健康度评估模型。
示例性的，上述步骤401可以由图2a所示的内存评估的装置20中的处理器111执行。
其中，上述待评估内存为服务器中至少一个内存中的一个内存，即内存评估的装置中的一个内存。上述待评估内存的健康度评估模型用于评估该待评估内存的健康度，待评估内存的健康度可以反映该待评估内存发生故障的可能性，也即该待评估内存的内存失效率。
具体的，上述健康度评估模型为待评估内存的健康度关于该待评估内存的至少一个健康度影响因素变化的关系，一个健康度影响因素对应一个运行参数和一个失效率参数，且一个健康度影响因素对应一个权值，该权值为常数。其中，针对一个健康度影响因素，内存失效率参数的取值(即内存失效率)随着相应的运行参数的取值(即运行数据)而变化。
需要说明的是，一个内存对应的健康度影响因素可以影响该内存的正常运行，并可能导致该内存发生故障，即内存失效。针对一个内存(如待评估内存)对应的一个健康度影响因素，内存评估的装置中存储有描述相应的运行参数与失效率参数之间关系的数据，如描述失效率参数关于该运行参数的关系的曲线。
其中，针对待评估内存的一个健康度影响因素，内存评估的装置中存储的描述相应的运行参数与失效率参数的关系的数据可以由本领域相关技术人员根据大量数据(如大量的与待评估内存相关的内存的运行数据)训练得到的，或者根据与本领域相关的文献资料得到的，本发明实施例对此不再赘述。
另外，上述一个健康度影响因素对应的权值可以表示该健康度影响因素对待评估内存的健康度的影响程度，不同权值的健康度影响因素对待评估内存的健康度的影响不同。例如，一个健康度影响因素对应的权值越大，该健康度影响因素对待评估内存的健康度影响越大。这样一来，本发明实施例提供的健康度评估模型中每个健康度影响因素权值，可以指示每个健康度影响因素对待评估内存的健康度的影响，使得健康度评估模型中针对待评估内存的不同健康度评估因素的影响程度更符合该待评估内存，有利于准确评估待评内存的健康度。
其中，上述待评估内存的健康度评估模型中每个健康度影响因素对应的权值可以由相关技术人员预先设置。当然，每个健康度影响因素对应的权值也可以由用户根据经验或者待评估内存的相关统计数据自主设定。通常，相关技术人员可以对上述待评估内存的健康度评估模型中每个健康度影响因素设置不同的权值。例如，上述待评估内存对应两个健康度影响因素，这两个健康度影响因素中的一个健康度影响因素对应的权值为60％，另一个健康度影响因素对应的权值为40％。上述至少一个健康度影响因素中每个健康度影响因素对应的权值之和等于1。
可选的，相关技术人员可以对上述待评估内存的健康度评估模型中每个健康度影响因素设置相同的权值，或者，上述相关技术人员还可以对上述每个健康度影响因素不设置权值。即每个健康度影响因素对待评估内存的健康度的影响相同。
S402、内存评估的装置获取至少一个健康度影响因素中每个健康度影响因素对应的至少一个运行参数值。
示例性的，上述步骤402可以由图2a所示的内存评估的装置20中的处理器111执行。
其中，针对待评估内存对应的一个健康度影响因素，上述健康度评估模型中包括的运行参数对应至少一个运行参数值。从而，针对待评估内存对应的一个健康度影响因素，内存评估的装置可以根据相应的运行参数，获取上述至少一个运行参数值。例如，针对待评估内存，内存评估的装置可以获取内存总运行时长这一健康度影响因素对应的待评估内存的总运行时长。
可以想到的是，在内存评估的装置中的处理器获取待评估内存的总运行时长之前，上述待评估内存的总运行时长可以保存在内存评估的装置的硬盘中，并可以由内存评估的装置中的处理器进行更新。
S403、内存评估的装置将每个健康度影响因素对应的至少一个运行参数值，分别匹配至健康度评估模型，得到待评估内存的健康度。
需要说明的是，在上述健康度评估模型为待评估内存的健康度关于该待评估内存的至少一个健康度影响因素变化的关系情况下：内存评估的装置可以将内存评估模型得到该健康度影响因素的至少一个运行参数值与该健康度评估模型中相应的运行参数相匹
配。这样一来，内存评估的装置可以采用待评估内存的健康度评估模型得到待评估内存的健康度。
示例性的，上述待评估内存的健康度可以由0～100之间的一个数值表示，如80。其中，待评估内存的健康度的数值越大，该待评估内存的健康度越高；待评估内存的健康度的数值越小，该待评估内存的健康度越低。
S404、内存评估的装置根据待评估内存的健康度，输出待评估内存的健康度指示信息。
示例性的，上述步骤402可以由图2a所示的内存评估的装置20中的处理器111生成待评估内存的健康度指示信息，并指示该内存评估的装置20中的显示器13输出该待评估内存的健康度指示信息。
其中，上述待评估内存的健康度指示信息用于向用户指示该待评估内存是否更换。例如，在待评估内存的健康度较低时，内存评估的装置输出的待评估内存的健康度指示信息可以指示用户待评估内存需要更换，此时该待评估内存发生故障的可能性较大。在待评估内存的健康度较高时，内存评估的装置输出的待评估内存的健康度指示信息可以指示用户待评估内存不需要更换，此时该待评估内存发生故障的可能性较小。
示例性的，在待评估内存的健康度的数值在预设的数值区间内(如70～100)时，内存评估的装置输出待评估内存的健康度指示信息向用户指示该待评估内存不需要更换。在待评估内存的健康度的数值在预设的数值区间内(如0～45)时，内存评估的装置输出待评估内存的健康度指示信息向用户指示该待评估内存需要更换。
需要说明的是，上述待评估内存的健康度评估模型可以由本领域相关技术人员预先存储在内存评估的装置中，如图2a所示的内存评估的装置20中的硬盘112中。并且，在内存评估的装置执行本发明实施例提供的内存评估的方法的过程中，可以生成日志。上述日志可以存储待评估内存的健康度评估模型中的数据(如待评估内存的至少一个健康度影响因素)以及该待评估内存的健康度。
需要说明的是，本发明实施例可以提供一种描述待评估内存的健康度关于待评估内存的至少一个健康度影响因素变化的关系的健康度评估模型，使得内存评估的装置可以根据待评估内存的健康度评估模型得到待评估内存的健康度。从而，内存评估的装置可以根据待评估内存的健康度的数值大小，生成待评估内存的健康度指示信息。这样一来，内存评估的装置可以通过待评估内存的健康度，在待评估内存发生故障之前，判断待评估内存是否更换。并且，内存评估的装置可以在该内存未发生故障且该内存的健康度较低的情况下，输出待评估内存的健康度指示信息，以提示用户更换该内存，使得该内存可以支持该服务器正常运行。
在一种具体的实施例中，本发明实施例提供的健康度评估模型中包括的至少一个健康度影响因素除了上述待评估内存的运行总时长之外，还可以包括其他健康度影响因素。
具体的，本发明实施例提供的至少一个健康度影响因素包括以下一种或多种：
因素1、内存运行温度因素；
因素2、内存业务负载因素；
因素3、内存总运行时长因素；
因素4、内存插拔因素；
因素5、内存可纠正错误(Correctable Error，CE)频度因素；
因素6、内存UCE频度因素；
因素7、内存性能衰减因素。
需要说明的是，本发明实施例提供的各个健康度影响因素可以由本领域相关技术人员根据大量数据(如内存的运行数据)训练得到的，或者根据与本领域相关的文献资料得到的，本发明实施例对此不再赘述。
当然，本发明实施例提供的健康度影响因素不局限于上述列举的健康度影响因素(因素1-7)，还可以为其他因素，如空气中的硫化强度。
需要说明的是，本发明实施例提供的MC界面除了可以展示各个内存的固有参数之外，还可以展示上述内存的健康度评估模型。
示例性的，如图5所示，为本发明实施例提供的另一种MC界面，为针对不同的待评估内存设置健康度评估模型的界面。图5示出的MC界面可以为台式机提供的界面，此时，本发明实施例提供的显示器可以为台式机的显示器，输入器可以为该台式机的鼠标和键盘等设备。
其中，图5示出的MC界面50包括“内存名称”选项51，选项51包括一个“▼”选项。MC界面50包括“内存的运行温度”选项、“内存业务负载”选项、“内存总运行时长”选项、“内存插拔”选项、“内存CE频度”选项、“内存UCE频度”选项和“内存性能衰减”选项这7个健康度影响因素的选项，每个健康度影响因素对应一个“关闭”选项。例如，因素1对应“内存运行温度”选项52，因素1对应“关闭”选项53。另外，图5所示的MC界面50还包括一个“确定”选项54和一个“取消”选项55。
具体的，上述MC界面50可以向用户提供不同内存名称的选择，以实现用户针对不同内存设置健康度评估模型中包括的健康度影响因素。示例性的，用户点击操作MC界面50中选项51包括的“▼”选项，使得内存评估的装置中的处理器生成相应的点击操作指令后，指示显示器在上述MC界面上显示如图6所示的下拉菜单511。下拉菜单511中包 括“DIMM000”选项、“DIMM001”选项、“DIMM002”选项、“DIMM010”选项、“DIMM011”选项和“DIMM012”选项这6个选项。其中，用户点击操作下拉菜单511中包括的任一选项(如“DIMM000”选项)，使得内存评估的装置中的处理器接收到相应的操作指令后，指示上述MC界面50显示的健康度影响因素选项为内存名称为DIMM000的内存对应的健康度影响因素。此时，内存名称为DIMM000的内存为待评估内存。可以想到的是，用户点击操作图6所示的下拉菜单511包括的“DIMM000”选项后，内存评估的装置中的处理器可以生成相应的点击操作指令，随后可以指示显示器显示如图5所示的MC界面50。其中，图5中MC界面50显示的健康度影响因素选项为内存名称为DIMM000的内存对应的健康度影响因素。上述“用户对选项的点击操作”可以是用户操作鼠标点击选项，如图5所示的箭头用于表示鼠标的光标在该显示界面中的位置。
其中，用户对上述MC界面50中一个健康度影响因素选项对应的“关闭”选项点击操作(点击操作一次)之后，内存评估的装置便可以确定相应的健康度评估模型中不包括该健康度影响因素，即忽略该健康度影响因素对待评估内存的健康度的影响。用户对该健康度影响因素对应的“关闭”选项不执行点击操作(或者连续点击操作二次)，内存评估的装置便可以确定相应的健康度评估模型中该健康度影响因素对待评估内存的健康度有影响。本发明实施例以下，仅以MC界面50中的各个选项点击操作一次，说明本发明实施例提供的内存评估的方法。
示例性的，如图7所示的MC界面50中包括的因素1对应的“关闭”选项53可以被点击操作。此时，可以认为内存运行温度这一健康度影响因素不会对内存名称为“DIMM000”的内存的健康度造成影响。也就是说，用户可以在上述MC界面50上通过点击操作相关的选项，实现对某个内存的健康度影响因素的选择。
需要说明的是，用户在上述MC界面50中对内存名称为“DIMM000”的内存的健康度影响因素进行选择之后，可以点击操作“确定”选项54，以使得内存评估的装置中的处理器确定出上述待评估内存的健康度评估模型。或者，用户还可以点击操作上述“取消”选项55，以使得该处理器重新确定上述待评估内存的健康度评估模型。
除此之外，本发明实施例提供的展示MC界面的显示器可以由手机或平板电脑等具有触控屏的终端设备实现。
示例性的，如图8所示，为发明实施例提供的另一种MC界面，该MC界面由手机的触控屏实现。图8中的图8-1和图8-2示出的MC界面80均包括内存名称选项81，选项81包括一个“▼”选项。MC界面80包括“内存的运行温度”选项、“内存业务负载”选项、“内存总运行时长”选项、“内存插拔”选项、“内存CE频度”选项、“内存UCE频度”选项和“内存性能衰减”选项这7个健康度影响因素选项，每个健康度影响因素选项对应一个“关闭”选项。例如，因素1对应的健康度影响因素选项为“内存运行温度”选项82，因素1对应“关闭”选项83。另外，MC界面80还包括一个“确定”选项84和一个“取消”选项85。图8-2示出的下拉菜单811中包括“DIMM000”选项、“DIMM001”选项、“DIMM002”选项、“DIMM010”选项、“DIMM011”选项和“DIMM012”选项这6个选项。
示例性的，如图9所示，为发明实施例提供的另一种MC界面，该MC界面由平板电脑的触控屏实现。图9中的图9-1和图9-2示出的MC界面90包括内存名称选项91，选项91包括一个“▼”选项。MC界面90包括“内存的运行温度”选项、“内存业务负载” 选项、“内存总运行时长”选项、“内存插拔”选项、“内存CE频度”选项、“内存UCE频度”选项和“内存性能衰减”选项这7个健康度影响因素选项，每个健康度影响因素选项对应一个“关闭”选项。例如，因素1对应的健康度影响因素选项为“内存运行温度”选项92，因素1对应“关闭”选项93。另外，MC界面90还包括一个“确定”选项94和一个“取消”选项95。图9-2示出的下拉菜单911中包括“DIMM000”选项、“DIMM001”选项、“DIMM002”选项、“DIMM010”选项、“DIMM011”选项和“DIMM012”选项这6个选项。
其中，上述图8或图9中示出的触控屏上展示MC界面可以由用户使用手指进行点击操作，随后该手机或平板电脑中的处理器可以生成相应的点击操作指令。图8以及图9中的“人手图标”用于对人手进行示意性地表示。本发明实施例仅以该“人手图标”对用户的手指所处的位置进行表示，而实际中该手机或平板电脑上不显示该“人手图标”。
需要说明的是，对上述手机或平板电脑等具有触控屏的终端设备提供的MC界面的具体描述，可以参照本发明实施例对上述台式机的显示器提供的MC界面的描述，本发明实施例不再赘述。本发明实施例以下，仅以台式机的显示器提供的MC界面为例，说明本发明实施例提供的内存评估的方法。
可以想到的是，不同批次、不同型号(即固有参数不同)的内存的健康度可能与不同的健康度影响因素相关。例如，有的内存的健康度对内存运行温度的变化比较敏感，有的内存的健康度对内存运行时长的变化比较敏感。此时，本发明实施例提供的健康度评估模型中预设了多个健康度影响因素，使用户可以针对不同的待评估内存选择相应的健康度影响因素，从而使得健康度评估模型中针对待评估内存的健康度评估因素更符合该待评估内存，有利于准确评估出待评估内存的健康度。
可选的，相关技术人员可以对上述待评估内存的健康度评估模型中每个健康度影响因素设置相同的权值，或者，上述相关技术人员可以对上述每个健康度影响因素不设置权值。即每个健康度影响因素对待评估内存的健康度的影响相同。
示例性的，上述因素1对应的权值为20％，因素2对应的权值为5％。因素3对应的权值为25％，因素4对应的权值为5％，因素5对应的权值为10％，因素6对应的权值为15％，因素7对应的权值为20％。上述每个健康度影响因素对应一个权值，可以进一步指示每个健康度影响因素对待评估内存的健康度的影响。
如图10所示，为本发明实施例提供的另一种MC界面的示意图。图10示出的MC界面50中每个健康度影响因素对应一个权值选项。例如，图1示出的因素1对应“20％”选项(即选项56)。可以想到的是，用户可以对MC界面50中显示的任一权值进行更改。例如，如图10所示的选项56被点击操作后，内存评估的装置中的处理器(服务器中的处理器)可以生成相应的点击操作指令，接收用户通过输入器(如键盘)对该选项56进行更改。如将选项56中的“20％”修改为“25％”。此时，除上述选项56中的“20％”之外，其他因素对应的权值可以被相应的修改。
在一种具体的实施例中，本发明实施例提供的内存运行温度因素(因素1)对应的运行参数为待评估内存的运行温度。上述内存业务负载因素(因素2)对应的运行参数为待评估内存的充放电次数。上述内存总运行时长因素(因素3)对应的运行参数为待评估内存的总运行时长。上述内存插拔因素(因素4)对应的运行参数为待评估内存的插拔次数。 上述内存CE频度因素(因素5)对应的运行参数为待评估内存的CE个数或待评估内存的CE频度。上述内存UCE频度因素(因素6)对应的运行参数为待评估内存的UCE个数或待评估内存的UCE频度。上述内存性能衰减因素(因素7)对应的运行参数为待评估内存的性能值衰减量。
其中，本发明实施例提供的各个健康度影响因素对应的运行参数可以由本领域技术人员根据大量数据训练得到，如根据多个与待评估内存相似的内存的运行数据训练得到，或者可以根据本领域相关文献资料得到，本发明实施例对此不再赘述。
具体的，在待评估内存对应的健康度影响因素为因素1的情况下，内存评估的装置中存储有描述待评估内存的运行温度与失效率参数之间关系的数据，如待评估内存的内存失效率关于待评估内存的运行温度变化的曲线。一般而言，待评估内存的运行温度越高，该待评估内存发生故障的可能性越大，即失效率越高。
类似的，在待评估内存对应的健康度影响因素为因素2的情况下，内存评估的装置中存储有描述待评估内存的充放电次数与失效率参数之间关系的数据，如待评估内存的内存失效率关于待评估内存的充放电次数变化的曲线。其中，在一个内存(如待评估内存)正常工作的过程中，该内存上可以运行一个或多个业务，如数据存储或者数据修改等业务。上述业务在内存上运行的同时伴随着内存的业务负载压力。而内存的业务负载压力可以由内存的充放电次数表征。通常，内存的充放电次数越多代表该内存的业务负载压力越大，该内存发生故障的可能性越大，该内存的失效率越高；该内存的充放电次数越少代表该内存的业务负载压力越小，该内存发生故障的可能性越小，该内存的失效率越低。
在待评估内存对应的健康度影响因素为因素3的情况下，内存评估的装置中存储有描述待评估内存的总运行时长与失效率参数之间关系的数据，如待评估内存的内存失效率关于待评估内存的总运行时长变化的曲线。其中，一个内存(如待评估内存)的总运行时长是有限的，即一个内存的使用寿命是有限的。通常一个内存的总运行时长越大，该内存越容易发生故障，失效率越高。
在待评估内存对应的健康度影响因素为因素4的情况下，内存评估的装置中存储有描述待评估内存的插拔次数与失效率参数之间关系的数据，如待评估内存的内存失效率关于待评估内存的插拔次数变化的曲线。其中，本发明实施例提供的内存(如待评估内存)多为具有镀金层的内存条。由于内存条的镀金层的厚度是一定的，而在插拔内存条的过程中会造成内存条镀金层的磨损，因此内存插次数可以为一个内存的健康度影响因素。具体的，待评估内存插拔的次数越多，该待评估内存发生故障的可能性越大，失效率越高；待评估内存插拔的次数越少，该待评估内存发生故障的可能性越小，失效率越低。
在待评估内存对应的健康度影响因素为因素5的情况下，内存评估的装置中存储有描述待评估内存的CE个数或待评估内存的CE频度与失效率参数之间关系的数据，如待评估内存的内存失效率关于待评估内存的CE个数或待评估内存的CE频度变化的曲线。其中，待评估内存在一段时间产生CE个数越多，该待评估内存发生故障的可能性越大，失效率越高；待评估内存在一段时间产生CE个数越少，该待评估内存发生故障的可能性越小，失效率越低。或者，待评估内存的CE频度越大，该待评估内存发生故障的可能性 越大，失效率越高；待评估内存的CE频度越小，该待评估内存发生故障的可能性越小，失效率越低。
在待评估内存对应的健康度影响因素为因素6的情况下，内存评估的装置存储有描述待评估内存的UCE个数或待评估内存的UCE频度与失效率参数之间关系的数据，如待评估内存的内存失效率关于待评估内存的UCE个数或待评估内存的UCE频度变化的曲线。其中，待评估内存在一段时间产生UCE个数越多(或者，该待评估内存的UCE频度越大)，发生故障的可能性越大，失效率越高；该待评估内存在一段时间产生UCE个数越少(或者，待评估内存的CE频度越小)，发生故障的可能性越小，失效率越低。例如，待评估内存的UCE个数为1或2时，该待评估内存发生故障的可能性就比较大了。
在待评估内存对应的健康度影响因素为因素7的情况下，内存评估的装置存储有描述待评估内存的性能值衰减量与失效率参数之间关系的数据，如待评估内存的失效率关于待评估内存的性能值衰减量变化的曲线。其中，待评估内存运行过程中，该待评估内存的性能值衰减量会发生变化。通常，一个内存(如待评估内存)的性能值衰减量越大且该性能值越小，发生故障的可能性越大，失效率越高；该内存的性能值衰减量越小且该性能值越大，发生故障的可能性越小，失效率越低。
需要说明的是，本发明实施例提供的MC界面可以展示上述各个健康度影响因素对应的运行参数和失效率参数之间关系的数据，如内存的失效率参数的取值关于相应的运行参数的取值变化的曲线。其中，内存评估的装置中存储有各个内存(如名称为“DIMM000”的内存、名称为“DIMM001”的内存)的失效率关于相应的运行参数变化的曲线。
示例性的，如图11所示，为本发明实施例提供的另一种MC界面示意图。图11中示出的MC界面50中的每个健康度影响因素对应一个“设置”选项。如“内存运行温度”选项52对应“设置”选项57。具体的，“设置”选项57用于使如图12所示的MC界面50跳转至显示“温度-失效率曲线”的界面50。
如图11所示的因素1对应的“设置”选项57被点击操作后，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图12所示的包括窗口511的MC界面50，该窗口511中显示有“温度-失效率曲线”。其中，图12示出的“温度-失效率曲线”为描述名称为“DIMM000”的内存的失效率参数的取值关于内存运行温度这一运行参数的取值变化的曲线。图12所示的MC界面50中还包括“确定”选项512。上述“确定”选项512用于用户确定上述“温度-失效率曲线”，并使得显示器显示如图11所示的MC界面50。
示例性的，参照图12中的“温度-失效率曲线”，名称为“DIMM000”的内存的运行温度长时间处于45℃的情况下，该内存的失效率为40％；名称为“DIMM000”的内存的运行温度长时间处于80℃的情况下，该内存的失效率为95％。其中，上述“长时间”可以为相关技术人员检测一个内存的寿命所用的时间，本发明实施例这里不再详细描述。
需要说明的是，上述“温度-失效率”曲线为针对名称为“DIMM000”的内存的曲线，可以由内存评估的装置从针对不同内存的多个曲线中匹配得到，上述针对不同内存的多个曲线可以预先存储在内存评估的装置中。具体的，内存评估的装置可以自主地根据名称为“DIMM000”的内存的内存容量等固有参数匹配出上述“温度-失效率”曲线。
如图11所示的MC界面中包括的因素2对应的“设置”选项被点击操作后，内存评 估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图13所示的包括窗口511的MC界面50，该窗口511中显示有“充电次数-失效率”曲线。其中，图13示出的“充电次数-失效率”曲线为描述名称为“DIMM000”的内存的失效率参数的取值关于内存的充放电次数这一运行参数的取值变化的曲线。图13所示的MC界面50中还包括“确定”选项512。上述“确定”选项512还用于用户确定上述“充放电次数-失效率”曲线，并使得显示器显示如图11所示的MC界面50。
同样的，上述图13示出的“充电次数-失效率”曲线可以为内存评估的装置从针对不同内存的多个曲线中匹配出的针对名称为“DIMM000”的内存的曲线，上述针对不同内存的多个曲线存储在内存评估的装置中。具体的，内存评估的装置可以自主地根据名称为“DIMM000”的内存的固有参数，如内存容量等参数匹配出上述“充放电次数-失效率”曲线。
可以想到的是，本发明实施例提供的内存评估的装置中也可以存储有针对因素3的“总运行时长-失效率”曲线，针对因素4的“插拔次数-失效率”曲线，针对因素5的“CE个数-失效率”曲线或者“CE频率-失效率”曲线，针对因素6的“UCE个数-失效率”曲线或者“CE频率-失效率”曲线，针对因素7的“性能值衰减量-失效率”曲线。本发明实施例对上述因素3-因素7对应的“设置”选项被点击操作后MC界面中显示相应的曲线的详细描述，可以参照上述实施例中对因素1和因素2的相关描述，本发明实施例中不再赘述。
需要说明的是，本发明实施例中提供的内存评估的装置中存储有描述各个健康度影响因素对应的运行参数和失效率参数关系的数据，如描述待评估内存的失效率参数关于相应的运行参数变化的曲线。上述待评估内存的失效率参数关于相应的运行参数变化的曲线为预先统计得到的数据。这样一来，内存评估的装置可以根据已有统计得到的数据去评估还没有发生故障的待评估内存的健康度。
在一种具体的实施例中，本发明实施例提供的待评估内存的健康度评估模型可以包括每个健康度影响因素对应的第一子模型，以及一个第二子模型，一个健康度影响因素的第一子模型为该健康度影响因素对应的健康度折损值关于该健康度影响因素对应的运行参数和内存失效率参数之间的关系；第二子模型为待评估内存的健康度关于每个健康度影响因素对应的健康度折损值和每个健康度影响因素对应的权值变化的关系。
具体的，本发明实施例提供的内存评估的方法，上述步骤403可以包括步骤403a和步骤403b。示例性的，如图14所示的内存评估的方法流程图中的上述步骤403可以包括步骤403a和步骤403b：
S403a、内存评估的装置将每个健康度影响因素对应的运行参数值，分别匹配至健康度评估模型中相应的健康度影响因素的第一子模型中，得到每个健康度影响因素对应的健康度折损值。
示例性的，上述步骤403a可以由图2a示出的内存评估的装置20的处理器111执行。
其中，上述待评估内存的每个健康度影响因素对应的运行参数值可以由内存评估的装置实时获取。上述每个健康度影响因素对应健康度折损值用于表示该健康度影响因素对待评估内存的健康度的影响结果。
需要说明的是，本发明实施例提供的第一子模型可以包括图12或图13示出的MC界 面中的窗口511中的曲线。
示例性的，在待评估内存是名称为“DIMM000”的内存，待评估内存对应的健康度影响因素为因素1的情况下，内存评估的装置可参照已有的“温度-失效率”曲线，如图12所示的窗口511中的“温度-失效率”曲线，得到至少一个运行参数值中每个运行参数值对应的失效率，并叠加运行时长得到待评估内存针对因素1的健康度折损值(记为P 1)。示例性的，待评估内存的至少一个运行参数值分别为运行温度值T 1、运行温度值T 2…运行温度T n等，n为正整数。并且，待评估内存在运行温度为T 1的条件下的运行时长为t 1_1，在运行温度为T 2的条件下的运行时长为t 1_2，在运行温度为T n的条件下的运行时长为t 1_n。此时，结合图12中的“温度-失效率”曲线示出的运行温度取值为T 1时的失效率为P 1_1，运行温度取值为T 2时的失效率为P 1_2，运行温度取值为T n时的失效率为P 1_n。待评估内存针对因素1的健康度折损值为
Figure PCTCN2018087360-appb-000001
上述T 1、T 2、T n、t 1_1、t 1_2和t 1_n均为正数。
示例性的，在待评估内存是名称为“DIMM000”的内存，待评估内存对应的健康度影响因素为因素2的情况下，内存评估的装置可参照已有的“充放电次数-失效率”曲线，如图13所示的窗口511中的“充放电次数-失效率”曲线，得到至少一个运行参数值对应的失效率，并叠加运行时长得到待评估内存针对因素2的健康度折损值(记为P 2)。示例性的，待评估内存的至少一个运行参数值分别为充放电次数N 1、充放电次数N 2…充放电次数N n，n为正整数。并且，待评估内存在时长为t 2_1的时间内的充放电次数为N 1，在时长为t 2_2的时间内的充放电次数为N 2，在时长t 2_n的时间内的充放电次数为N n。此时，结合图13中的“温度-失效率”曲线示出的充放电次数取值为N 1时的失效率为P 2_1，充放电次数的取值为N 2时的失效率为P 2_2，充放电次数的取值为N n时的失效率为P 2_n。待评估内存针对因素2的健康度折损值为
Figure PCTCN2018087360-appb-000002
上述N 1、N 2、N n、t 2_1、t 2_2和t 2_n均为正数。
示例性的，在待评估内存是名称为“DIMM000”的内存，待评估内存对应的健康度影响因素为因素3的情况下，内存评估的装置可参照已有的“总运行时长-失效率”曲线，得到至少一个运行参数值对应的失效率，并得到待评估内存针对因素3的健康度折损值(记为P 3)。示例性的，待评估内存的至少一个运行参数值为总运行时长L 1。并且，“总运行时长-失效率”曲线提供的待评估内存的总运行时长的取值为L 1的时候失效率为P 3_1。此时，待评估内存针对因素3的健康度折损值为P 3＝P 3_1，上述L 1为正数。
示例性的，在待评估内存是名称为“DIMM000”的内存，对应的健康度影响因素为因素4的情况下，内存评估的装置可参照已有的“插拔次数-失效率”曲线，得到至少一个运行参数值对应的失效率，并得到待评估内存针对因素4的健康度折损值(记为P 4)。示例性的，待评估内存的至少一个运行参数值为插拔次数M 1次。并且，“插拔次数-失效率”曲线提供的待评估内存的插拔次数的取值为M 1时的失效率为P 4_1。此时，待评估内存针对因素4的健康度折损值为P 4＝P 4_1，上述M 1为正数。
示例性的，在待评估内存是名称为“DIMM000”的内存，待评估内存对应的健康度影响因素为因素5的情况下，内存评估的装置可参照已有的“CE个数-失效率”曲线，得到至少一个运行参数值对应的失效率，并叠加运行时长；再结合各个运行参数值的变化率，得到待评估内存针对因素5的健康度折损值(记为P 5)。示例性的，待评估内存的至少一个运行参数值为CE个数F 1、CE个数F 2…CE个数F n等。并且，待评估内存在第一个时长为t 5_1的时间段内的CE个数为F 1，在第二个时长为t 5_1的时间段内的CE个数为F 2，在第n个时长为t 5_1的时间段内的CE个数为F n，n为正整数。其中，内存评估的装置每隔一定的时间间隔统计一次待评估内存的CE个数。并且，“CE个数-失效率”曲线提供的待评估 内存的CE个数的取值为F 1时的失效率为P 5_1，CE个数的取值为F 2时的失效率为P 5_2，CE个数的取值为F n时的失效率为P 5_n。另外，上述至少一个运行参数值，即CE个数F 1、CE个数F 2…CE个数F n的变化率可以记为k 1，k 1为大于零的正数。此时，待评估内存针对因素5的健康度折损值为
Figure PCTCN2018087360-appb-000003
上述F 1、F 2、F n和t 5_1均为正数。
示例性的，在待评估内存是名称为“DIMM000”的内存，待评估内存对应的健康度影响因素为因素6的情况下，内存评估的装置可参照已有的“UCE个数-失效率”曲线，得到至少一个运行参数值对应的失效率，得到待评估内存针对因素6的健康度折损值(记为P 6)。并且，“UCE个数-失效率”曲线提供的待评估内存的UCE个数的取值为W 1时的失效率为P 6_1。此时，待评估内存针对因素6的健康度折损值为P 6＝P 6_1，上述W 1为正整数。
示例性的，在待评估内存是名称为“DIMM000”的内存，待评估内存对应的健康度影响因素为因素7的情况下，内存评估的装置可参照已有的“性能值衰减量-失效率”曲线，得到至少一个运行参数值对应的失效率；再结合各个运行参数值的变化率，得到待评估内存针对因素7的健康度折损值(记为P 7)。示例性的，待评估内存的至少一个运行参数值为性能值衰减量Y 1、性能值衰减量Y 2…性能值衰减量Y n等，n为正整数。并且，待评估内存在第一个时长为t 7_1的时间段内的性能值衰减量取值为Y 1，在第二个时长为t 7_1的时间段内的性能值衰减量取值为Y 2，在第n个时长为t 7_1的时间段内的性能值衰减量取值为Y n，n为正整数。也就是说，内存评估的装置每隔一定的时间间隔统计一次待评估内存的性能值以及性能值衰减量。此时，若“性能值衰减量-失效率”曲线提供的待评估内存的性能值衰减量的取值为Y 1时的失效率为P 7_1，性能值衰减量的取值为Y 2时的失效率为P 7_2，性能值衰减量的取值为Y n时的失效率为P 7_n。另外，上述至少一个运行参数，即性能值衰减量Y 1、性能值衰减量Y 2…性能值衰减量Y n的变化率可以记为k 2，k 2为大于零的正数。待评估内存针对因素7的健康度折损值为
Figure PCTCN2018087360-appb-000004
上述Y 1、Y 2、Y n和t 7_1均为正数。
S403b、内存评估的装置根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，得到待评估内存的健康度。
示例性的，上述步骤403b可以由图2a示出的内存评估的装置20的处理器111执行。
本发明实施例中，内存评估的装置可以根据健康度评估模型中每个健康度影响因素对应的第一子模型，得到每个健康度影响因素对应的待评估内存的健康度折损值，以指示出各个健康度影响因素对待评估内存的健康度的影响。并且，将上述各个健康度影响因素对应的健康度折损值以及各个健康度影响因素对应的权值分别匹配至上述第二子模型中，得到权重不同(权值不同)的各个健康度影响因素影响下评估内存的健康度。如此，可以针对不同的待评估内存生成不同的健康度评估模型，有利于提高根据健康度评估模型得到的待评估内存的健康度的准确性。
在一种具体的实施例中，上述健康度评估模型中包括的至少一个健康度影响因素中的每个健康度影响因素对应一个算法，该算法可以为加法、乘法等。此时，内存评估的装置根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，以及每个健康度影响因素对应的算法，得到待评估内存的健康度。
示例性的，如图15所示，为发明实施例提供的另一种MC界面。其中，图15所示的MC界面50中包括的至少一个健康度影响因素中每个健康度影响因素对应一个“算法”选项。例如，图15所示的因素1对应“算法”选项58。
具体的，在待评估内存的每个健康度影响因素对应的算法均为加法的情况下，内存 评估的装置根据第二模型，将待评估内存的至少一个健康度折损值中每个健康度折损值与相应的权值相乘，得到待评估内存的至少一个健康度分量；累加至少一个健康度分量，得到待评估内存的健康度。例如，待评估内存的对应的至少一个健康度影响因素包括上述因素1、因素2和因素5，并且因素1、因素2和因素5的权值分别为20％、5％和10％。上述至少一个健康度分量中因素1对应的健康度分量(记为H 1)H 1＝P 1×20％；因素2对应的健康度分量(记为H 2)H 2＝P 2×5％；因素5对应的健康度分量(记为H 5)H 5＝P 5×10％。此时，待评估内存的健康度(记为H)H＝P 1+P 2+P 5。
在待评估内存的一个健康度影响因素对应的算法为乘法的情况下，上述内存评估的装置根据每个健康度影响因素对应的健康度折损值、每个健康度影响因素对应的权值和第二子模型，得到待评估内存的健康度，包括：内存评估的装置根据第二模型，将待评估内存的健康度折损值作为待评估内存的健康度。示例性的，针对待评估内存，因素3对应的算法为乘法，则待评估内存的健康度H＝H 3＝P 3。其中，上述H 3为待评估内存因素3对应的健康度分量，P 3为待评估内存因素3对应的健康度折损值。
需要说明的是，本发明实施例提供的健康度评估模型中的一个健康度影响因素对应的算法除了上述加法和乘法之外还可以为其他算法，例如积分算法。其中，本发明实施例这里提供的一个健康度影响因素对应的算法为积分算法的具体描述，可以参照上述实施例中对一个健康度影响因素对应的算法为加法的相关描述，这里不再赘述。
其中，对内存评估的装置中的一个内存，即服务器中的一个内存来说，内存评估的装置根据该内存的各个健康度影响因素对应的权值量化各个健康度影响因素对该内存的健康度的影响的同时，可以根据各个健康度影响因素对应的算法进一步量化各个健康度影响因素对该内存的健康度的影响程度。这样一来，有利于提高待评估内存的健康度的准确性。
在一种具体的实施例中，由于本发明实施例提供的待评估内存的健康度评估模型中包括每个健康度影响因素对应的第一子模型，以及一个第二子模型；因此，上述内存评估的装置确定待评估内存的健康度评估模型，具体为确定健康度评估模型中每个健康度影响因素对应的第一子模型以及该评估内存的第二子模型。具体的，本发明实施例提供的内存评估的方法，上述步骤401包括步骤401a-步骤401e。示例性的，如图16所示，为本发明实施例提供的另一种内存评估的方法的流程示意图。图16示出的方法中，图4中的步骤401可以包括步骤401a-步骤401e：
S401a、内存评估的装置接收用户设置的至少一个健康度影响因素。
示例性的，上述步骤401a可以由图2a示出的内存评估的装置20中的通信接口114执行。
需要说明的是，本发明实施例提供的健康度评估模型中预先设置有至少一个健康度影响因素，用户可以从上述预先设置的至少一个健康度影响因素中选择针对待评估内存的健康度影响因素。
具体的，参照上述实施例中图15示出的MC界面，该MC界面50中包括因素1-因素7。针对待评估内存(名称为“DIMM000”的内存)，用户可以通过输入器点击操作该MC界面50中各个因素对应的“关闭”选项，从因素1-因素7中选择待评估内存对应的至少一个健康度影响因素。
S401b、内存评估的装置将用户设置的至少一个健康度影响因素确定为待评估内存的健康度评估模型包含的健康度影响因素。
示例性的，上述步骤401b可以由图2a示出的内存评估的装置20的处理器111执行。
其中，内存评估的装置中的处理器可以接收到来自输入器的点击操作指令，并确定出待评估内存的至少一个健康度影响因素。
例如，针对待评估内存(名称为“DIMM000”的内存)，用户可以通过输入器点击操作图5所示的MC界面50中因素5-因素7对应的“关闭”选项。内存评估的装置中的处理器可以生成相应的点击操作指令，并确定出待评估内存的至少一个健康度影响因素为因素1-因素4。
S401c、内存评估的装置根据至少一个健康度影响因素确定相应的第一子模型。
示例性的，上述步骤401c可以由图2a示出的内存评估的装置20的处理器111执行。
其中，上述实施例中提供的至少一个健康度影响因素中的每个健康度影响因素的第一子模型中包括该健康度影响因素对应的运行参数和失效率参数的关系的数据，如待评估内存的失效率参数关于各个健康度影响因素对应的运行参数变化的曲线。
本发明实施例提供的健康度评估模型针对一个健康度影响因素，可以包括多个失效率参数的取值(失效率)关于该健康度影响因素对应的运行参的取值变化的曲线。即一个第一子模型中包括多个失效率关于该健康度影响因素对应的运行参数的取值变化的曲线。
需要说明的是，内存评估的装置可以自主地根据待评估内存的固有参数(如内存容量等参数)匹配出待评估内存的失效率关于各个健康度影响因素对应的运行参数变化的曲线，还可以由用户从一个健康度影响因素对应的第一子模型包括的多个曲线中选择出相应的曲线。
示例性的，如17所示，为本发明实施例提供的另一种MC界面的示意图。参照上述图12所示的MC界面50，图17所示的MC界面50中还包括支持用户选择“温度-失效率曲线1”的选项513，该选项513中包括一个“▼”选项，该“▼”选项可以对应可以下拉窗口。其中，如图17所示的MC界面50中包括的选项513中的“▼”选项被点击操作后，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图18所示的包括窗口5131的MC界面50，该窗口5131中包括“温度-失效率曲线1”选项、“温度-失效率曲线2”选项、“温度-失效率曲线3”选项、“温度-失效率曲线4”选项、“温度-失效率曲线5”选项、“温度-失效率曲线6”选项和“温度-失效率曲线7”选项这7个选项。
可以想到的是，图18所示的MC界面50中示出的选项513对应的下拉窗口5131中的“温度-失效率曲线1”选项被用户点击操作之后，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图17所示的MC界面50。另外，上述图18和图19所示的MC界面50中还包括“取消”选项514。上述“取消”选项514用于用户取消上述对“温度-失效率曲线1”选项的选择。
S401d、内存评估的装置接收用户设置的至少一个健康度影响因素中每个健康度影响因素对应的权值和算法。
示例性的，上述步骤401c可以由图2a示出的内存评估的装置20中的通信接口114 执行。
其中，上述算法包括加法和/或乘法。当然，上述算法还可以是积分算法等。本发明实施例这里仅以上述算法为加法和/或乘法为例，说明本发明实施例的内存评估的方法。
示例性的，如图19所示，为本发明实施例提供的另一种MC界面的示意图。参照图10所示的MC界面50，图19所示的MC界面50中每个健康度影响因素对应的权值可以由用户通过输入器设置。参照上述图15所示的MC界面50，图19所示的MC界面50中每个健康度影响因素对应的算法选项还包括一个“▼”选项，该“▼”选项对应一个下拉窗口。例如，图19示出的MC界面50中因素1对应的选项58中的“▼”选项被用户点击操作，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图20所示的MC界面50中的下拉窗口581。具体的，图20所示的MC界面50中示出的选项58对应的下拉窗口581中的“加法”选项被用户点击操作之后，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图19所示的MC界面50。
S401e、内存评估的装置根据每个健康度影响因素对应的权值和算法确定第二子模型。
示例性的，上述步骤401c可以由图2a示出的内存评估的装置20的处理器111执行。
其中，参照图19所示的MC界面50，名称为“DIMM000”的内存(待评估内存)的第二子模型可以由该MC界面50示出的各个健康度影响因素对应的“权值”选项和“算法”选项确定。其中，用户可以通过输入器点击操作上述图19所示的MC界面50中的各个健康度影响因素对应的“权值”选项和“算法”选项，以使得内存评估的装置中的处理器生成相应的点击操作指令。
需要说明的是，由于不同待评估内存的健康度影响因素可能不同，并且不同待评估内存的各个健康度影响因素对应的失效率参数关于相应的运行参数变化的数据可能不同；因此不同的待评估内存对应的健康度评估模型可能不同。本发明实施例提供的内存评估的方法中，内存评估的装置可以确定出针对不同的待评估内存的各个健康度影响因素对应的第一子模型以及待评估内存的第二子模型，即确定出不同待评估内存的健康度评估模型。这样一来，可以使得本发明实施例提供的健康度评估模型符合待评估内存，有利于提高根据该健康度评估模型得到的待评估内存的健康度的准确性。
在一种具体的实施例中，本发明实施例提供的健康度评估模型中的至少一个健康度影响因素可以由用户针对不同的待评估内存进行选择；该健康度评估模型中的每个健康度影响因素对应的第一子模型中包括的多个曲线也可以由用户针对不同的待评估内存进行选择。除此之外，由于生产内存的工艺的提高，待评估内存的健康度影响因素以及该健康度影响因素对应的失效率关于相应运行参数变化的数据可能也会发生变化。因此，本发明实施例中提供的内存评估的方法还支持用户在健康度评估模型中添加健康度影响因素以及在一个健康度影响因素对应的第一子模型中添加相关的曲线。
具体的，本发明实施例提供的内存的评估方法，上述步骤401a可以替换为步骤401a＇。示例性的，如图21所示，为本发明实施例提供的另一种内存评估的方法的流程示意图。图21所示的方法中，图16示出的步骤401a可以替换为步骤401a＇：
401a＇、内存评估的装置接收用户设置的至少一个健康度影响因素以及每个健康度影响因素对应的运行参数和失效率参数。
其中，上述用户设置的每个健康度影响因素对应的运行参数和失效率参数指的是失效率参数的取值关于该运行参数的取值变化的数据，如失效率参数的取值关于该运行参数的取值变化的曲线。
示例性的，如图22或图23所示的MC界面50中还包括“添加”选项59，该“添加”选项59用于在健康度评估模型中添加一个健康度影响因素。其中，用户通过输入器点击操作图22所示MC界面50中的“添加”选项59之后，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图23所示MC界面50中包括的因素8，以及因素8对应的“设置”选项、“权值”选项、“算法”选项等。
进一步的，如图24所示，为本发明实施例提供的另一种MC界面示意图。参照图17和图18所示的MC界面50，图24所示的MC界面50中还包括“添加”选项514，该“添加”选项514用于在健康度评估模型中为一个健康度影响因素添加失效率关于运行参数关于相应的运行参数变化的曲线。示例性的，用户通过输入器点击操作图24所示MC界面50中的“添加”选项514之后，内存评估的装置中的处理器可以生成相应的点击操作指令，并指示显示器显示如图25所示MC界面50。图25所示的MC界面50中包括“绘制曲线”选项和“导入曲线”选项。其中，上述“绘制曲线”选项用于向用户提供绘制待评估内存的一个健康度影响因素对应的失效率关于相应运行参数变化曲线的窗口。上述“导入曲线”选项用于向用户提供导入待评估内存的一个健康度影响因素对应的失效率关于相应运行参数变化曲线的窗口。
需要说明的是，本发明实施例提供的健康度评估模型，用户不仅可以在该健康度评估模型中选择出待评估内存的健康度影响因素以及各个健康度影响因素对应的失效率关于相应的运行参数变化的数据(曲线)，还可以在该健康度评估模型中添加待评估内存的健康度影响因素以及各个健康度影响因素对应的失效率关于相应的运行参数变化的数据(曲线)。从而，使得待评估内存的健康度评估模型更加符合该待评估内存，有利于提高根据待评估内存的健康度评估模型得到的待评估内存的健康度的准确性。
在一种具体的实施例中，内存评估的装置在根据待评估内存的健康度，输出待评估内存的健康度指示信息的过程中，可以将待评估内存的健康度的数值匹配至预先设置的数值区间，得到待评估内存的健康度指示信息。具体的，上述实施例中的步骤404可以包括步骤404a-步骤404c。示例性的，如图27所示，为本发明实施例提供的另一种内存评估的方法的流程示意图。图27示出的内存评估的方法，上述图4示出的步骤404可以包括步骤404a-步骤404c：
S404a、在待评估内存的健康度的数值在第一预设数值区间内的情况下，内存评估的装置输出第一健康度指示信息，第一健康度指示信息用于提示用户待评估内存不需要更换。
S404b、在待评估内存的健康度的数值在第二预设数值区间内的情况下，内存评估的装置输出第二健康度指示信息，第二健康度指示信息用于提示用户待评估内存可以更换。
S404c、在待评估内存的健康度的数值在第三预设数值区间内的情况下，内存评估的装置输出第三健康度指示信息，第三健康度指示信息用于提示用户待评估内存需要更换。
示例性的，上述第一预设数值区间可以为[75，100]，第二预设数值区间可以为[45，74]，第三预设数值区间可以为[0，44]。当然，上述第一预设数值区间、第二预设数值 区间和第三预设数值区间还可以为其他区间，本发明实施例不作限制。
可以想到的是，本发明实施例提供的内存评估的方法，上述待评估内存的健康度指示信息可以由显示器显示的MC界面展示给用户。
如图27所示，为本发明实施例提供的另一种MC界面示意图。参照图3所示的MC界面，图27示出的MC界面中每个内存还对应一个“健康度”选项32。上述MC界面上显示的待评估内存的健康度指示信息为该待评估内存的健康的数值。其中，健康度的数值在第一预设数值区间、第二预设数值区间和第三预设数值区间的待评估内存的健康度指示信息依次突出显示。例如，图27中MC界面中显示的名称为“DIMM000”的内存、名称为“DIMM002”的内存以及名称为“DIMM011”的内存的健康度指示信息采用正常字体(记为字体1)，以提示用户该内存不需要更换；显示的名称为“DIMM012”的内存的健康度指示信息采用相较于字体1更加突出的字体(记为字体2)，以提示用户该内存可以被更换，即可以不立即更换；显示的名称为“DIMM001”的内存和名称为“DIMM010”的内存的健康度指示信息采用相较于字体2更加突出的字体(记为字体3)，以提示用户该内存需要立即被更换。
可选的，上述字体1、字体2、字体3依次更加突出指的是字体1、字体2、字体3依次增大并加粗，或者，上述字体1、字体2、字体3的颜色依次为黑色、橙色和红色等。
当然，本发明实施例提供的MC界面显示的待评估内存的健康度指示信息不仅可以采用上述突出的字体，还可以是其他方式。
示例性的，如图28所示，为本发明实施例提供的另一种MC界面示意图。
其中，待评估内存的健康度的数值在第一预设数值区间内的情况下，上述MC界面上显示的待评估内存的健康度指示信息为“健康”，以提示用户该待评估内存不需要更换。例如，图28中示出的名称为“DIMM000”的内存、名称为“DIMM002”的内存以及名称为“DIMM011”的内存的健康度指示信息为“健康”。
待评估内存的健康度的数值在第二预设数值区间内的情况下，上述MC界面上显示的待评估内存的健康度指示信息为“一般”，以提示用户该待评估内存可以被更换。此时，MC界面上显示的名称为“DIMM012”的内存的健康度指示信息为“一般”。
待评估内存的健康度的数值在第三预设数值区间内的情况下，上述MC界面上显示的待评估内存的健康度指示信息为“告警”，以提示用户该待评估内存需要被更换。此时，MC界面上显示的名称为“DIMM001”的内存和名称为“DIMM010”的内存的健康度指示信息为“告警”。
需要说明的是，本发明实施例提供的内存评估的方法，内存评估的装置在向用户展示待评估内存的健康度指示信息的过程中，可以针对不同健康度的数值的待评估内存显示不同的健康度指示信息。这样一来，可以在待评估内存未发生故障且该内存的健康度较低(健康度的数值较小)的情况下，内存评估的装置可以提示用户更换待评估内存，使得待评估内存可以支持该服务器正常运行。
可以想到的是，本发明实施例提供的第一预设数值区间、第二预设数值区间还可以由用户根据经自主设置。具体的，本发明实施例提供的内存评估的方法，在上述步骤401之前还可以包括步骤401＇。示例性的，如图29所示，为本发明实施例提供的另一种内存评估的方法的流程示意图。图29示出的内存评估的方法，上述图26示出的步骤401之 前还可以包括步骤401＇：
S401＇、内存评估的装置接收用户设置的第一预设数值区间、第二预设数值区间和第三预设数值区间。
示例性的，上述步骤401＇可以由图2a所示的内存评估的装置20中的通信接口114执行。
如图30或图31所示，为本发明实施例提供的另一种MC界面。参照上述实施例提供的MC界面，图30和图31示出的MC界面50中还包括“第一预设数值区间”选项、“第二预设数值区间”选项和“第三预设数值区间”选项，用于用户设置上述第一预设数值区间、第二预设数值区间和第三预设数值区间。示例性的，图30示出的MC界面中包括的“第二预设数值区间”选项中的数值“45-74”可以由用户通过输入器设置，内存评估的装置中的处理器可以生成相应的指令，并指示显示器显示如图31所示的MC界面50。其中，图31示出的MC界面50中包括的“第二预设数值区间”选项中的数值“45-64”。
需要说明的是，本发明实施例提供的内存评估的方法，用户可以针对不同的待评估内存设置不同的预设数值区间，使得内存评估的装置根据该预设数值区间得到的待评估内存的健康度指示信息更加符合该待评估内存，有利于更加准确地提示用户待评估内存是否需要更换。
在一种具体的实施例中，在待评估内存运行的过程中，内存评估的装置可以持续地评估该待评估内存的健康度，此时，用户可以更新待评估内存的健康度评估模型使该健康度评估模型更加符合该待评估内存。具体的，本发明实施例提供的内存评估的方法，在步骤404之后还可以包括步骤405和步骤406。示例性的，如图32所示，为本发明实施例提供的另一种内存评估的方法的流程示意图。图32示出的内存评估的方法，上述图4示出的步骤404之后还可以包括步骤405和步骤406：
S405、内存评估的装置接收用户对待评估内存的模板数据的更新。
示例性的，上述步骤405可以由图2a示出的内存评估的装置20中的通信接口114执行。
其中，上述模板数据至少包括以下一种或多种：至少一个健康度影响因素、至少一个健康度影响因素中每个健康度影响因素对应的运行参数、每个健康度影响因素对应的权值、每个健康度影响因素对应的算法，第一预设数值区间、第二预设数值区间和第三预设数值区间
S406、内存评估的装置根据更新后的待评估内存的模板数据，更新健康度评估模型。
示例性的，上述步骤406可以由图2a示出的内存评估的装置20中的处理器111执行。
需要说明的是，上述内存评估的装置更新待评估内存的模板数据以及待评估内存的健康度评估模型的过程，可以参考上述实施例中对确定待评估内存的健康度评估模型的相关描述，本发明实施例中不再赘述。
其中，由于用户可以更新待评估内存的健康度评估模型使该健康度评估模型更加符合该待评估内存，因此内存评估的装置根据更新后的健康度评估模型得到待评估内存的健康度更加符合该待评估内存，有利于更加准确地提示用户待评估内存是否需要更换。
上述主要从各个网元之间交互的角度对本发明实施例提供的方案进行了介绍。可以 理解的是，各个网元，例如内存评估的装置为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本发明实施例可以根据上述方法示例对内存评估的装置进行模块的划分，例如，可以对应各个功能划分各个模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件模块的形式实现。需要说明的是，本发明实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，图33示出了上述实施例中提供的内存评估的装置的一种可能的组成示意图，如图33所示，内存评估的装置33可以包括确定模块331、获取模块332、匹配模块333和输出模块334。
其中，上述确定模块331，用于支持内存评估的装置33执行上述实施例中的步骤401、步骤401a-步骤401e和步骤406，和/或用于本文所描述的技术的其它过程。上述获取模块332，用于支持内存评估的装置33执行上述实施例中的步骤402，和/或用于本文所描述的技术的其它过程。上述匹配模块333，用于支持内存评估的装置33执行上述实施例中的步骤403和步骤403a-步骤403b，和/或用于本文所描述的技术的其它过程。上述输出模块334，用于支持内存评估的装置33执行上述实施例中的步骤404和步骤404a-步骤403c，和/或用于本文所描述的技术的其它过程。
在一种可能的实现方式中，如图34所示，为上述实施例中提供的内存评估的装置的另一种可能的组成示意图。图34中示出的内存评估的装置33中，上述确定模块331可以包括接收子模块3311和确定子模块3312。其中，上述接收子模块3311，用于支持内存评估的装置33执行上述实施例中的步骤401a、步骤401d、步骤401＇和步骤405，和/或用于本文所描述的技术的其它过程。上述确定子模块3312，用于支持内存评估的装置33执行上述实施例中的步骤401a、步骤401b、步骤401c、步骤401e和步骤406，和/或用于本文所描述的技术的其它过程。
在采用集成的单元的情况下，上述获取模块332、匹配模块333和确定子模块3312可以集成在一个处理模块中。上述处理模块可以是处理器或控制器，例如可以是CPU，通用处理器，数字信号处理器(Digital Signal Processor，DSP)，专用集成电路(Application-Specific Integrated Circuit，ASIC)，现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。其可以实现或执行结合本发明公开内容所描述的各种举例说明逻辑方框，模块和电路。上述处理单元也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，DSP和微处理器的组合等等。上述输出模块334和上述接收子模块3311可以由处理器和通信接口中实现。上述输出模块具体可以包括生成子模块和输出子模块。该生成子模块可以用于生成待评估内存的健康度指示信息，该输出子模块可以用于通过显示器输出上述待评估内存的健康度指示信息。
存储模块可以是存储器。当然，上述内存评估的装置33还可以包括其他功能模块
结合上述实施例中图2a所示的内存评估的装置，上述处理模块可以为图2a所示的处理器111。上述存储模块可以为图2a所示的硬盘112和至少一个内存113。上述通信模块可以为图2a所示的通信接口114。其中，上述通信总线114具体可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。上述通信总线114可以分为地址总线、数据总线、控制总线等，本发明实施例对此不作限定。
需要说明的是，本发明实施例提供的内存评估的装置33中各个模块的详细描述以及各个模块执行上述实施例中的相关方法步骤后所带来的技术效果可以参考本发明方法实施例中的相关描述，此处不再赘述。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：快闪存储器、移动硬盘、只读存储器、随机存取存储器、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (21)

  1. 一种内存评估的方法，其特征在于，包括：
    确定待评估内存的健康度评估模型，所述健康度评估模型为所述待评估内存的健康度关于所述待评估内存的至少一个健康度影响因素变化的关系，一个所述健康度影响因素对应一个运行参数和一个失效率参数，且一个所述健康度影响因素对应一个权值，所述权值为常数；
    获取所述至少一个健康度影响因素中每个所述健康度影响因素对应的至少一个运行参数值，所述至少一个运行参数值对应一个所述运行参数；
    将每个所述健康度影响因素对应的至少一个运行参数值，分别匹配至所述健康度评估模型，得到所述待评估内存的健康度；
    根据所述待评估内存的健康度，输出所述待评估内存的健康度指示信息，所述待评估内存的健康度指示信息用于向用户指示所述待评估内存是否需要更换。
  2. 根据权利要求1所述的方法，其特征在于，所述将每个所述健康度影响因素对应的至少一个运行参数值，分别匹配至所述健康度评估模型，得到所述待评估内存的健康度，包括：
    将每个所述健康度影响因素对应的至少一个运行参数值，分别匹配至所述健康度评估模型中相应的所述健康度影响因素的第一子模型中，得到每个所述健康度影响因素对应的健康度折损值；所述健康度评估模型包括第二子模型，以及每个所述健康度影响因素对应的第一子模型，一个所述健康度影响因素的第一子模型为该健康度影响因素对应的健康度折损值关于该健康度影响因素对应的运行参数和所述失效率参数之间的关系；所述第二子模型为所述待评估内存的健康度关于每个所述健康度影响因素对应的健康度折损值和所述每个健康度影响因素对应的权值变化的关系；
    根据每个所述健康度影响因素对应的健康度折损值、每个所述健康度影响因素对应的权值和所述第二子模型，得到所述待评估内存的健康度。
  3. 根据权利要求2所述的方法，其特征在于，所述至少一个健康度影响因素包括以下一种或多种：
    内存运行温度因素、内存业务负载因素、内存总运行时长因素、内存插拔因素、内存可纠正错误CE频度因素、内存不可纠正错误UCE频度因素和内存性能衰减因素。
  4. 根据权利要求3所述的方法，其特征在于，所述内存运行温度因素对应的运行参数为所述待评估内存的运行温度；
    所述内存业务负载因素对应的运行参数为所述待评估内存的充放电次数；
    所述内存总运行时长因素对应的运行参数为所述待评估内存的总运行时长；
    所述内存插拔因素对应的运行参数为所述待评估内存的插拔次数；
    所述内存CE频度因素对应的运行参数为所述待评估内存的CE个数和/或所述待评估内存的CE频度；
    所述内存UCE频度因素对应的运行参数为所述待评估内存的UCE个数和/或所述待评估内存的UCE频度；
    所述内存性能衰减因素对应的运行参数为所述待评估内存的性能值衰减量。
  5. 根据权利要求1-4中任一项所述的方法，其特征在于，所述根据所述待评估内存的健康度，输出所述待评估内存的健康度指示信息，包括：
    在所述待评估内存的健康度的数值在第一预设数值区间内的情况下，输出第一健康度指示信息，所述第一健康度指示信息用于提示所述用户所述待评估内存不需要更换；
    在所述待评估内存的健康度的数值在第二预设数值区间内的情况下，输出第二健康度指示信息，所述第二健康度指示信息用于提示所述用户所述待评估内存可以更换；
    在所述待评估内存的健康度的数值在第三预设数值区间内的情况下，输出第三健康度指示信息，所述第三健康度指示信息用于提示所述用户所述待评估内存需要更换。
  6. 根据权利要求5所述的方法，其特征在于，所述确定待评估内存的健康度评估模型，包括：
    接收所述用户设置的至少一个所述健康度影响因素；
    将所述用户设置的至少一个所述健康度影响因素确定为所述待评估内存的所述健康度评估模型包含的健康度影响因素；
    根据所述至少一个健康度影响因素确定相应的第一子模型；
    接收用户设置的所述至少一个健康度影响因素中每个所述健康度影响因素对应的权值和算法，所述算法包括加法和/或乘法；
    根据每个所述健康度影响因素对应的权值和算法确定所述第二子模型。
  7. 根据权利要求6所述的方法，其特征在于，所述接收所述用户设置的至少一个所述健康度影响因素，包括：
    接收所述用户设置的至少一个所述健康度影响因素以及每个所述健康度影响因素对应的所述运行参数和所述失效率参数。
  8. 根据权利要求7所述的方法，其特征在于，在所述根据所述待评估内存的健康度，生成所述待评估内存的健康度指示信息之前，还包括：
    接收所述用户设置的所述第一预设数值区间、所述第二预设数值区间和所述第三预设数值区间。
  9. 根据权利要求8所述的方法，其特征在于，在所述将每个所述健康度影响因素对应的运行参数值，分别输入至所述健康度评估模型，得到所述待评估内存的健康度之后，还包括：
    接收所述用户对所述待评估内存的模板数据的更新，所述模板数据至少包括以下一种或多种：所述至少一个健康度影响因素、所述至少一个健康度影响因素中每个所述健康度影响因素对应的运行参数、每个所述健康度影响因素对应的权值、每个所述健康度影响因素对应的算法，所述第一预设数值区间、所述第二预设数值区间和所述第三预设数值区间；
    根据更新后的所述待评估内存的模板数据，更新所述健康度评估模型。
  10. 一种内存评估的装置，其特征在于，包括：
    确定模块，用于确定待评估内存的健康度评估模型，所述健康度评估模型为所述待评估内存的健康度关于所述待评估内存的至少一个健康度影响因素变化的关系，一个所述健康度影响因素对应一个运行参数和一个失效率参数，且一个所述健康度影响因素对应一个权值，所述权值为常数；
    获取模块，用于获取所述确定模块确定出的所述至少一个健康度影响因素中每个所述健康度影响因素对应的至少一个运行参数值，所述至少一个运行参数值对应一个所述运行参数；
    匹配模块，用于将所述获取模块得到的每个所述健康度影响因素对应的至少一个运行参数值，分别匹配至所述健康度评估模型，得到所述待评估内存的健康度；
    输出模块，用于根据所述匹配模块得到的所述待评估内存的健康度，输出所述待评估内存的健康度指示信息，所述待评估内存的健康度指示信息用于向用户指示所述待评估内存是否需要更换。
  11. 根据权利要求10所述的装置，其特征在于，所述匹配模块，具体用于将每个所述健康度影响因素对应的至少一个运行参数值，分别匹配至所述健康度评估模型中相应的所述健康度影响因素的第一子模型中，得到每个所述健康度影响因素对应的健康度折损值；所述健康度评估模型包括第二子模型，以及每个所述健康度影响因素对应的第一子模型，一个所述健康度影响因素的第一子模型为该健康度影响因素对应的健康度折损值关于该健康度影响因素对应的运行参数和所述失效率参数之间的关系；所述第二子模型为所述待评估内存的健康度关于每个所述健康度影响因素对应的健康度折损值和所述每个健康度影响因素对应的权值变化的关系；
    根据每个所述健康度影响因素对应的健康度折损值、每个所述健康度影响因素对应的权值和所述第二子模型，得到所述待评估内存的健康度。
  12. 根据权利要求11所述的装置，其特征在于，所述至少一个健康度影响因素包括以下一种或多种：
    内存运行温度因素、内存业务负载因素、内存总运行时长因素、内存插拔因素、内存可纠正错误CE频度因素、内存不可纠正错误UCE频度因素和内存性能衰减因素。
  13. 根据权利要求12所述的装置，其特征在于，所述内存运行温度因素对应的运行参数为所述待评估内存的运行温度；
    所述内存业务负载因素对应的运行参数为所述待评估内存的充放电次数；
    所述内存总运行时长因素对应的运行参数为所述待评估内存的总运行时长；
    所述内存插拔因素对应的运行参数为所述待评估内存的插拔次数；
    所述内存CE频度因素对应的运行参数为所述待评估内存的CE个数和/或所述待评估内存的CE频度；
    所述内存UCE频度因素对应的运行参数为所述待评估内存的UCE个数和/或所述待评估内存的UCE频度；
    所述内存性能衰减因素对应的运行参数为所述待评估内存的性能值衰减量。
  14. 根据权利要求10-13中任一项所述的装置，其特征在于，所述输出模块，具体用于在所述待评估内存的健康度的数值在第一预设数值区间内的情况下，输出第一健康度指示信息，所述第一健康度指示信息用于提示所述用户所述待评估内存不需要更换；
    在所述待评估内存的健康度的数值在第二预设数值区间内的情况下，输出第二健康度指示信息，所述第二健康度指示信息用于提示所述用户所述待评估内存可以更换；
    在所述待评估内存的健康度的数值在第三预设数值区间内的情况下，输出第三健康度指示信息，所述第三健康度指示信息用于提示所述用户所述待评估内存需要更换。
  15. 根据权利要求14所述的装置，其特征在于，所述确定模块包括：
    接收子模块，用于在接收所述用户设置的至少一个所述健康度影响因素；
    确定子模块，用于将所述接收子模块接收的所述用户设置的至少一个所述健康度影响因素确定为所述待评估内存的所述健康度评估模型包含的健康度影响因素；根据所述 至少一个健康度影响因素确定相应的第一子模型；
    所述接收子模块，还用于接收用户设置的所述至少一个健康度影响因素中每个所述健康度影响因素对应的权值和算法，所述算法包括加法和/或乘法；
    所述确定子模块，还用于根据所述接收子模块接收的每个所述健康度影响因素对应的权值和算法确定所述第二子模型。
  16. 根据权利要求15所述的装置，其特征在于，所述接收子模块，具体用于接收所述用户设置的至少一个所述健康度影响因素以及每个所述健康度影响因素对应的所述运行参数和所述失效率参数。
  17. 根据权利要求16所述的装置，其特征在于，所述接收子模块，还用于在所述根据所述待评估内存的健康度，生成所述待评估内存的健康度指示信息之前，接收所述用户设置的所述第一预设数值区间、所述第二预设数值区间和所述第三预设数值区间。
  18. 根据权利要求17所述的装置，其特征在于，所述接收子模块还用于，在所述匹配模块将每个所述健康度影响因素对应的运行参数值，分别匹配至所述健康度评估模型，得到所述待评估内存的健康度之后，接收所述用户对所述待评估内存的模板数据的更新，所述模板数据至少包括以下一种或多种：所述至少一个健康度影响因素、所述至少一个健康度影响因素中每个所述健康度影响因素对应的运行参数、每个所述健康度影响因素对应的权值、每个所述健康度影响因素对应的算法，所述第一预设数值区间、所述第二预设数值区间和所述第三预设数值区间；
    所述确定子模块，还用于根据所述接收子模块得到的更新后的所述待评估内存的模板数据，更新所述健康度评估模型。
  19. 一种内存评估的装置，其特征在于，包括：处理器、硬盘、至少一个内存、通信接口、输入器、显示器和总线；
    所述硬盘以及至少一个内存用于存储至少一个指令，所述处理器和所述硬盘、所述至少一个内存、所述通信接口、所述输入器和所述显示器通过所述总线连接，当所述内存评估的装置运行时，所述处理器执行所述硬盘以及至少一个内存中存储的所述至少一个指令，以使所述内存评估的装置执行如权利要求1-9中任一项所述的内存评估的方法。
  20. 一种计算机存储介质，其特征在于，包括：至少一个指令；
    当所述至少一个指令在计算机上运行时，使得所述计算机执行如权利要求1-9中任一项所述的内存评估的方法。
  21. 一种计算机程序产品，其特征在于，包括：至少一个指令；
    当所述至少一个指令在计算机上运行时，使得所述计算机执行如权利要求1-9中任一项所述的内存评估的方法。
PCT/CN2018/087360 2017-09-18 2018-05-17 一种内存评估的方法及装置 WO2019052208A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
EP18855251.7A EP3712773B1 (en) 2017-09-18 2018-05-17 Method and apparatus for memory evaluation
EP23158131.5A EP4220409A3 (en) 2017-09-18 2018-05-17 Memory evaluation method and apparatus
US16/816,597 US11354183B2 (en) 2017-09-18 2020-03-12 Memory evaluation method and apparatus
US17/741,765 US11868201B2 (en) 2017-09-18 2022-05-11 Memory evaluation method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710841912.5 2017-09-18
CN201710841912.5A CN109522175B (zh) 2017-09-18 2017-09-18 一种内存评估的方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/816,597 Continuation US11354183B2 (en) 2017-09-18 2020-03-12 Memory evaluation method and apparatus

Publications (1)

Publication Number Publication Date
WO2019052208A1 true WO2019052208A1 (zh) 2019-03-21

Family

ID=65722353

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/087360 WO2019052208A1 (zh) 2017-09-18 2018-05-17 一种内存评估的方法及装置

Country Status (4)

Country Link
US (2) US11354183B2 (zh)
EP (2) EP3712773B1 (zh)
CN (2) CN109522175B (zh)
WO (1) WO2019052208A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113656204A (zh) * 2020-05-12 2021-11-16 中国移动通信集团浙江有限公司 固态硬盘管理方法、装置及计算设备

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110082623A (zh) * 2019-05-21 2019-08-02 国网安徽省电力有限公司合肥供电公司 一种开关柜健康状态评价方法及系统
CN112486535B (zh) * 2020-11-27 2021-09-14 红石阳光（北京）科技股份有限公司 一种用于NB-IoT设备的远程升级方法及系统
CN112732185B (zh) * 2020-12-31 2024-04-26 广州市中崎商业机器股份有限公司 执行多种存储策略的记录设备、记录方法、装置和介质
CN113190405B (zh) * 2021-04-29 2022-08-19 山东英信计算机技术有限公司 一种节点健康检测方法、装置及电子设备和存储介质
CN114356238B (zh) * 2021-12-31 2024-06-25 深圳大普微电子科技有限公司 一种固态硬盘数据巡检方法及装置
CN115793990B (zh) * 2023-02-06 2023-06-23 天翼云科技有限公司 存储器健康状态确定方法、装置、电子设备及存储介质
CN116680112B (zh) * 2023-07-28 2023-11-03 苏州浪潮智能科技有限公司 内存状态检测方法、装置、通信设备及存储介质
CN116755978A (zh) * 2023-08-21 2023-09-15 深圳惠科存储科技有限公司 内存运行状态评估方法、电子设备及可读存储介质
CN118468355B (zh) * 2024-07-15 2024-09-24 安云印(天津)大数据科技有限公司 涉企服务电子印章生成方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050188269A1 (en) * 2003-12-10 2005-08-25 Microsoft Corporation System and method for providing a health model for software
CN103092739A (zh) * 2013-01-18 2013-05-08 浪潮电子信息产业股份有限公司 一种内存ecc报错报警机制
CN106227647A (zh) * 2016-07-20 2016-12-14 云南电网有限责任公司信息中心 一种针对服务器硬件状态评价的数据分析方法
CN106940678A (zh) * 2017-02-28 2017-07-11 深圳市华傲数据技术有限公司 一种系统实时健康度评估分析方法及装置

Family Cites Families (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5471479A (en) * 1992-08-06 1995-11-28 Motorola, Inc. Arrangement for column sparing of memory
US7168010B2 (en) * 2002-08-12 2007-01-23 Intel Corporation Various methods and apparatuses to track failing memory locations to enable implementations for invalidating repeatedly failing memory locations
US10389814B2 (en) * 2005-09-30 2019-08-20 Pure Storage, Inc. Prioritizing memory devices to replace based on namespace health
US10855769B2 (en) * 2005-09-30 2020-12-01 Pure Storage, Inc. Prioritizing memory devices to replace based on namespace health
US10257276B2 (en) * 2005-09-30 2019-04-09 International Business Machines Corporation Predictive rebalancing according to future usage expectations
US9774684B2 (en) * 2005-09-30 2017-09-26 International Business Machines Corporation Storing data in a dispersed storage network
CN102081622B (zh) * 2009-11-30 2013-01-02 中国移动通信集团贵州有限公司 评估系统健康度的方法及系统健康度评估装置
US9727266B2 (en) * 2009-12-29 2017-08-08 International Business Machines Corporation Selecting storage units in a dispersed storage network
US8838430B1 (en) * 2011-08-26 2014-09-16 Cadence Design Systems, Inc. Detection of memory access violation in simulations
US9152488B2 (en) * 2013-06-25 2015-10-06 Sandisk Technologies Inc. Storage module and low-complexity methods for assessing the health of a flash memory device
US9535774B2 (en) * 2013-09-09 2017-01-03 International Business Machines Corporation Methods, apparatus and system for notification of predictable memory failure
CN103646670B (zh) * 2013-12-05 2016-09-07 华为技术有限公司 一种评估存储系统性能的方法和设备
US9389941B2 (en) * 2014-02-18 2016-07-12 Netapp, Inc. Methods for diagnosing hardware component failure and devices thereof
US9450833B2 (en) * 2014-03-26 2016-09-20 International Business Machines Corporation Predicting hardware failures in a server
CN104951383A (zh) * 2014-03-31 2015-09-30 伊姆西公司 用于监测硬盘的健康状况的方法和装置
US20150309908A1 (en) * 2014-04-29 2015-10-29 Hewlett-Packard Development Company, L.P. Generating an interactive visualization of metrics collected for functional entities
US9436571B2 (en) * 2014-05-13 2016-09-06 Netapp, Inc. Estimating data storage device lifespan
CN105468484B (zh) * 2014-09-30 2020-07-28 伊姆西Ip控股有限责任公司 用于在存储系统中确定故障位置的方法和装置
US10275185B2 (en) * 2015-02-27 2019-04-30 International Business Machines Corporation Fail-in-place supported via decentralized or Distributed Agreement Protocol (DAP)
US10037171B2 (en) * 2015-04-30 2018-07-31 International Business Machines Corporation Accessing common data in a dispersed storage network
US20170046212A1 (en) * 2015-08-13 2017-02-16 Qualcomm Incorporated Reducing system downtime during memory subsystem maintenance in a computer processing system
US9684555B2 (en) * 2015-09-02 2017-06-20 International Business Machines Corporation Selective memory error reporting
CN105243007B (zh) * 2015-10-13 2018-09-11 广东欧珀移动通信有限公司 移动终端中内存的老化测试方法和装置
CN106980562A (zh) * 2016-01-18 2017-07-25 中兴通讯股份有限公司 一种硬盘监控方法及装置
US10514973B2 (en) * 2016-03-01 2019-12-24 Georgia Tech Research Corporation Memory and logic lifetime simulation systems and methods
CN105912454B (zh) * 2016-04-25 2018-09-11 网易（杭州）网络有限公司 一种系统健康评测方法及装置
CN105893231B (zh) * 2016-05-06 2019-02-05 思创数码科技股份有限公司 一种基于smart的预测硬盘亚健康指标的方法及装置
US10019195B1 (en) * 2016-06-27 2018-07-10 EMC IP Holdings Company LLC Storage array health score
US10387287B1 (en) * 2016-12-22 2019-08-20 EMC IP Holding Company LLC Techniques for rating system health
US10191799B2 (en) * 2016-12-29 2019-01-29 Sandisk Technologies Llc BER model evaluation
CN106951359A (zh) * 2017-02-28 2017-07-14 深圳市华傲数据技术有限公司 一种系统健康度检测分析方法及装置
CN106934242B (zh) * 2017-03-16 2018-07-20 杭州安脉盛智能技术有限公司 基于交叉熵法的多模式下设备的健康度评估方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050188269A1 (en) * 2003-12-10 2005-08-25 Microsoft Corporation System and method for providing a health model for software
CN103092739A (zh) * 2013-01-18 2013-05-08 浪潮电子信息产业股份有限公司 一种内存ecc报错报警机制
CN106227647A (zh) * 2016-07-20 2016-12-14 云南电网有限责任公司信息中心 一种针对服务器硬件状态评价的数据分析方法
CN106940678A (zh) * 2017-02-28 2017-07-11 深圳市华傲数据技术有限公司 一种系统实时健康度评估分析方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113656204A (zh) * 2020-05-12 2021-11-16 中国移动通信集团浙江有限公司 固态硬盘管理方法、装置及计算设备
CN113656204B (zh) * 2020-05-12 2023-11-21 中国移动通信集团浙江有限公司 固态硬盘管理方法、装置及计算设备

Also Published As

Publication number Publication date
US11354183B2 (en) 2022-06-07
CN109522175B (zh) 2020-09-04
EP4220409A3 (en) 2023-09-20
US11868201B2 (en) 2024-01-09
EP3712773A1 (en) 2020-09-23
EP3712773A4 (en) 2021-09-29
EP3712773B1 (en) 2023-04-12
CN112131071B (zh) 2024-05-17
US20220269553A1 (en) 2022-08-25
CN109522175A (zh) 2019-03-26
EP4220409A2 (en) 2023-08-02
CN112131071A (zh) 2020-12-25
US20200210270A1 (en) 2020-07-02

Similar Documents

Publication Publication Date Title
WO2019052208A1 (zh) 一种内存评估的方法及装置
US9026863B2 (en) Replacement of storage responsive to remaining life parameter
WO2016179571A1 (en) Predictive device failure analysis
US11294749B2 (en) Techniques to collect crash data for a computing system
JP2018205811A (ja) 影響範囲特定プログラム、影響範囲特定方法、および影響範囲特定装置
WO2020173136A1 (zh) 应用系统的监控方法、装置、设备及存储介质
US8725461B2 (en) Inferring effects of configuration on performance
US20100192029A1 (en) Systems and Methods for Logging Correctable Memory Errors
US11150886B2 (en) Automatic probabilistic upgrade of tenant devices
US9645873B2 (en) Integrated configuration management and monitoring for computer systems
US10007583B2 (en) Generating a data structure to maintain error and connection information on components and use the data structure to determine an error correction operation
CN113821369A (zh) 一种内存巡检的方法、装置及介质
EP2942714B1 (en) Monitoring method, monitoring apparatus, and electronic device
US9367373B2 (en) Automatic configuration consistency check
US20140019093A1 (en) Incrementally increasing system test workload
CN115114070A (zh) 一种故障诊断方法、装置、设备及介质
CN114936135A (zh) 一种异常检测方法、装置及可读存储介质
CN114238019A (zh) 一种硬盘显示方法、装置、设备及介质
US20200192761A1 (en) Load and Save Recovery Partition Using Mobile Device
US11928043B2 (en) Adaptive log level control system and method of using the same
JP2013525885A (ja) アプリケーションの無進行状態の検出
US20240362144A1 (en) System and method for monitoring data processing system performance using a digital twin
WO2021128084A1 (zh) 数据处理、获取、模型训练及功耗控制方法、系统及设备
CN115604091A (zh) 数据处理方法、装置、基板控制管理系统及电子设备
CN118034985A (zh) 数据处理方法、装置、电子设备以及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18855251

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018855251

Country of ref document: EP

Effective date: 20200420