CN105760267A - Comparative detection method for CPU consumption of storage device read-write - Google Patents
Comparative detection method for CPU consumption of storage device read-write Download PDFInfo
- Publication number
- CN105760267A CN105760267A CN201610102681.1A CN201610102681A CN105760267A CN 105760267 A CN105760267 A CN 105760267A CN 201610102681 A CN201610102681 A CN 201610102681A CN 105760267 A CN105760267 A CN 105760267A
- Authority
- CN
- China
- Prior art keywords
- detection method
- comparison
- machine
- statistical
- storage device
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2268—Logging of test results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2289—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing by configuration test
Abstract
The invention provides a comparative detection method for CPU consumption of storage device read-write in a same hardware environment, relates to the computer field, and particularly relates to a detection method for CPU consumption of storage device read-write.The detection method has the advantages that the operability is high, the realizability is achieved, data is clear, quantitative operation is achieved, and Linux scripts are simple and easy to write; no influence is generated while a server completes self running, the statistic functions are additionally achieved simultaneously, and convenience and effectiveness are achieved.
Description
Technical field
The present invention relates to computer realm, espespecially storage device read-write is to the CPU detection method consumed.
Background technology
Along with popularizing of computer, the office of people and life all be unable to do without computer, and storage device is as the topmost storage device of computer, often preserves a large amount of capsule information.Bigger workload is carry at ordinary times due to storage device, and be easier to be given a shock damage, so the ratio that storage device failure takies in computer glitch is also relatively larger, storage device is once break down, data will be caused cannot to read and loss of data, for many users, particularly enterprise customer, once common storage device failure is just enough to cause catastrophic effect.
Along with the density of server internal framework is more and more higher, on server, storage device number also gets more and more.Meanwhile, due to the development of CPU manufacturing process and new technique, the update promoting CPU is frequent all the more, and on server, operable calculating resource gets more and more, and concurrent test model is also ripe all the more.Being different from the hard disk of traditional magnetic head style, SSD hard disk is more quick, stable, reliably, in conjunction with actual read-write, checks the situation of calling of CPU and analyzes.
The disclosure of the invention of Chinese Patent Application No. CN201110455927 a kind of method for testing hard disk and device, wherein, the method includes: read the first predefined parameter information of hard disk；Tested hard disk carrying out system and installs plan test, whether testing hard disk can realize system installation function under various controller and multiple-working mode；According to predetermined policy, testing hard disk service behaviour under various controller and multiple-working mode；For various controller and several operation systems, hard disk is carried out hot plug test；Testing hard disk service behaviour under predetermined work load；Read the second predefined parameter information of hard disk, and the second predefined parameter information and the first predefined parameter information are compared, wherein, the first predefined parameter information and the second corresponding same kind of parameter of predefined parameter information.The stability of hard disk, reliability, the many aspects such as functional, compatible for polytype hard disk controller and mode of operation, can be carried out test comprehensively and assessment by the present invention.
Chinese Patent Application No. CN201510097757 provides the method for testing of a kind of software occupying system resources, belongs to system resource monitoring field.This method of testing is by the monitoring (including CPU, internal memory, hard disk, network interface card) to linux system resource, test system software is not installed before average resource take situation, re-test system is installed the average resource after software and is taken situation, and both contrasts drawing, system resource is taken situation by software product.The features such as compared with prior art, the method for the invention has many index and monitors simultaneously, and record information is directly perceived, and record data are reliable, quick obtaining statistical average, have good practicality and application value.
Above-mentioned prior art all asks that solving the CPU of storage device under the environment that server converges in current network consumes quick judgment method, the especially dependence test of this storage device of SSD.
Summary of the invention
The present invention is to solve that the CPU of storage device under the environment that above-mentioned technology server in current network converges consumes quick judgment method, the especially dependence test of this storage device of SSD.
In order to realize the above goal of the invention of the present invention, the present invention is achieved by the following technical solutions:
A kind of storage device read-write comparison and detection method to CPU consumption under same hardware environment,
S10: statistical machine and at least one test machine are linked together by network, is installed detection and uses described storage device, described storage device at least to include the SSD hard disk of PCIe interface or the head hard drive of SATA interface in described test machine；
S20: described statistical machine and the system environments of described test machine are set；
S30: allow described test machine testing results shell script；
S40: obtain cpu data when described test script program is run, generate statistics file；
S50: described statistics file is transmitted to described statistical machine；
S60: described statistics file is made chart by described statistical machine；
S70: contrast the described chart made by the described statistics file generated by different described test machines.
Above-mentioned measuring technology scheme, it is possible to the rapid build test environment to storage device, it is possible to the test result of quick obtaining storage device.
Further, described comparison and detection method, described S20 also includes being arranged to described statistical machine Windows operating system environment, linux operating system environment or Macintosh environment.
Further, described comparison and detection method, increase S25 before described S30: each described test machine normal operation, within described S30 every 2～5 seconds, run once described test script program.
Further, described comparison and detection method, described in described S25, the access time of test machine normal operation is at least more than 10 hours.
Further, described comparison and detection method, after described S30 has performed, perform a S25 and S30 step at least again.
Further, described comparison and detection method, shell script described in described S40 generated a statistics file every 24～48 hours.
Further, described comparison and detection method, statistical machine operational data collection shell script described in described S50, obtain described statistics file；Described statistics file is generated log file by described S60, more described log file is made described chart.
Further, described comparison and detection method, before described S60, perform S55: described statistical machine service data filters shell script first will filter out 0.1% noise in described log file.
Further, described comparison and detection method, described log file is made statistical table and cartogram by statistical machine described in described S70, then performs S80: contrasts described statistical table according to CPU Expenditure Levels, described cartogram is ranked up.
Further, described comparison and detection method, cartogram described in described S60 increases Trendline, the periodic quantity of described Trendline is arranged to every 10～50 cycles and takes a meansigma methods.
The present invention has the beneficial effects that, test environment is prone to build, and test result is easily obtained, simple and convenient, effectively quick, reliable and stable.
Accompanying drawing explanation
Below in conjunction with the drawings and specific embodiments, the present invention is described in further detail:
Fig. 1 is each equipment connecting relation first embodiment schematic diagram of the present invention；
Fig. 2 is the inventive method first embodiment flow chart；
Fig. 3 is the inventive method the second embodiment flow chart；
Fig. 4 is the present invention each equipment connecting relation the second embodiment schematic diagram；
Fig. 5 is the cartogram generated after certain testing service device testing results of second embodiment of the invention；
Fig. 6 is the schematic diagram that chart arranges in second embodiment of the invention Trendline；
Accompanying drawing illustrates:
100 statistical machines；110 statistical servers；200 test machines；210 the 1st test machines；
220 the 2nd test machines；300 networks
Detailed description of the invention
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, the accompanying drawing used required in embodiment or description of the prior art will be briefly described below, apparently, following description and accompanying drawing are illustrative of for the present invention, and are understood not to the restriction present invention.Following description describe numerous detail to facilitate, the present invention to be understood.But, in some instances, the requirement that know or routine details is also undeclared, succinct to meet description.
Statistical machine or test machine in the present invention include processor, containing single core processor or polycaryon processor.Processor is alternatively referred to as one or more microprocessor, CPU (CPU) etc..More specifically, the instruction set that processor can be complicated calculates (CISC) microprocessor, Jing Ke Cao Neng (RISC) microprocessor, very long instruction word (VLIW) microprocessor, realizes the processor of other instruction set, or realizes the processor of instruction set combination.Processor can be also one or more application specific processor, such as special IC (ASIC), field programmable gate array (FPGA), digital signal processor (DSP), network processing unit, graphic process unit, network processing unit, communication processor, cipher processor, coprocessor, flush bonding processor or can the logical block of any other type of processing instruction.Processor is for performing the instruction of the discussed operation of the present invention and step.
Storage device in the present invention includes memorizer, one or more volatile storage devices can be included, such as IDE head hard drive, SATA head hard drive, SCSI head hard drive, optical-fibre channel head hard drive or PCIe interface SSD hard disk, random access memory (RAM), dynamic ram (DRAM), synchronous dram (SDRAM), static RAM (SRAM) or other kinds of storage device.Memorizer can store and include by the information of processor or the job sequence of any other equipment execution.Such as, executable code and/or the data of several operation systems, device driver, firmware (such as, input and output fundamental system or BIOS) and/or application program can be loaded in memory and be performed by processor.
Operating system in the present invention can be any kind of operating system, Windows, WindowsPhone of such as Microsoft, Apple Macintosh or IOS, the Android of Google, and Linux, Unix operating system or other in real time or embedded OS such as VxWorks etc..
First embodiment
Fig. 1 is each equipment connecting relation first embodiment schematic diagram of the present invention.
Fig. 2 is the inventive method first embodiment flow chart:
It is a kind of that under same hardware environment, storage device read-write is to the CPU comparison and detection method consumed, particularly under same hardware environment, and the storage device to multiple stage test machine simultaneously:
S10: statistical machine and at least one test machine are linked together by network, is installed detection and uses described storage device, described storage device at least to include the SSD hard disk of PCIe interface or the head hard drive of SATA interface in described test machine；
S20: described statistical machine and the system environments of described test machine are set；
S30: allow described test machine testing results shell script；
S40: obtain cpu data when described test script program is run, generate statistics file；
S50: described statistics file is transmitted to described statistical machine；
S60: described statistics file is made chart by described statistical machine；
S70: contrast the described chart made by the described statistics file generated by different described test machines.
Above-mentioned measuring technology scheme, it is possible to the rapid build test environment to storage device, it is possible to obtain the test result of storage device.
Preferably, described comparison and detection method, described S20 also includes being arranged to described statistical machine Windows operating system environment, linux operating system environment or Macintosh environment.
Preferably, described comparison and detection method, shell script described in described S40 generated a statistics file every 24～48 hours.
Preferably, described comparison and detection method, statistical machine operational data collection shell script described in described S50, obtain described statistics file；Described statistics file is generated log file by described S60, more described log file is made chart.
Preferably, described comparison and detection method, described log file is made statistical table and cartogram by statistical machine described in described S60.
Preferably, described comparison and detection method, cartogram described in described S60 increases Trendline, the periodic quantity of described Trendline is arranged to every 10～50 cycles and takes a meansigma methods.
Second embodiment
Fig. 3 is the inventive method the second embodiment flow chart:
A kind of storage device read-write comparison and detection method to CPU consumption under same hardware environment, it is achieved step is as follows:
S10: statistical machine and at least one test machine are linked together by network, is installed detection and uses described storage device, described storage device at least to include the SSD hard disk of PCIe interface or the head hard drive of SATA interface in described test machine；
S20: described statistical machine and the system environments of described test machine are set；
S30: allow described test machine testing results shell script；
S40: obtain cpu data when described test script program is run, generate statistics file；
S50: described statistics file is transmitted to described statistical machine；
S60: described statistics file is made chart by described statistical machine；
S70: contrast the described chart made by the described statistics file generated by different described test machines.
Preferably, described comparison and detection method, the system environments arranging described statistical machine and/or described test machine in described S20 is Windows operating system environment, linux operating system environment or Macintosh environment.
Preferably, described comparison and detection method, increase S25 before described S30: each described test machine normal operation, within described S30 every 2～5 seconds, run once described test script program.
Preferably, described comparison and detection method, described in described S25, the access time of test machine normal operation is at least more than 10 hours.
Preferably, described comparison and detection method, after described S30 has performed, perform a S25 and S30 step at least again.
Preferably, described comparison and detection method, shell script described in described S40 generated a statistics file every 24～48 hours.
Preferably, described comparison and detection method, statistical machine operational data collection shell script described in described S50, obtain described statistics file；Described statistics file is generated log file by described S60, more described log file is made described chart.
Preferably, described comparison and detection method, before described S60, perform S55: described statistical machine service data filters shell script first will filter out 0.1% noise in described log file.
Preferably, described comparison and detection method, each described log file is made statistical table and cartogram by statistical machine described in described S70, then performs S80: contrasts described statistical table according to CPU Expenditure Levels, described cartogram is ranked up.
Preferably, described comparison and detection method, cartogram described in described S60 increases Trendline, the periodic quantity of described Trendline is arranged to every 10～50 cycles and takes a meansigma methods.
As shown in Figure 4, the present invention each equipment connecting relation the second embodiment schematic diagram, in figure, 100 statistical machines are preferably 110 statistical servers, and 200 test machines are preferably testing service device 1,2,3.
Usual each server is borne by 1. transmitting data, and 3. 2. resolution data preserves data, 4. the important task such as computing.
A large amount of computings of server, frequently result in the situation that CPU usage is too high, and therefore we need to collect relevant information and monitor in real time, it is ensured that data complete, transmission reliable.
And between server, also it is intercommunication.Under same hardware environment, 1,2,3 three same hardware environment of testing service device in such as Fig. 4, they and statistical server can interconnect on internet, access mutually, and they are by socketTCP link transmission data.
What testing service device 1,2,3 was installed is all linux operating system, and testing service device 1,2,3 is inner inserts SSD to be detected.
Statistical server is mounted with Windows operating system, can resolve according to the data that testing service device 1,2,3 sends, preserve, then draw form.According to form, draw.
The method that detection is compared: each server normal operation, such as data transmission, communication, etc..
Particularly after read-write (reading and writing 16 hours) for a long time, then detect one time, to judge its compressive resistance.
Meanwhile, while server zone normal operation, can't additionally increase its workload, only be to increase a scriptlet so that its CPU uses data be real-time transmitted to statistical server and present.
First, at normal operation in testing service device 1,2,3, run a linux test script simultaneously.This script had an order, it is possible to arrange schedule, just automatically generated a CPU statistics file every 24 hours, and this document can obtain the value of the CPU usage of the machine.And send the file to statistical server.
Concrete test process is as follows:
First, at normal operation in testing service device 1,2,3, run same data test script (socket_client.py).
The following is socket_client.py
This document can obtain the value of the CPU usage of the machine.And send the file to statistical server.Arrange this script to run once for 2 seconds.
Secondly, statistical server 110 operational data collection script (socket_server.py), obtain the CPU statistics file of testing service device 1,2,3, and it is generated .csv file (being called in embodiment one: log file).
The following is socket_server.py
This data collection script obtains the cpu data of testing service device 1,2,3, and it is generated .csv file.
The value of CPU string is taken out by the above-mentioned .csv file generated, in tables of data, is such as put in excel form, like this:
Sampling in every 2 seconds is set once, it is also possible to sampling in every 5 seconds is set in data test script once, can arrange.
In the data produced, filter out the noise of 0.1% with data collection script, such as 1000 data remove 1 data, in 10000 data, removes 10, then regenerate a valid data form.
By tables of data, such as excel form, it is generated as a picture, as it is shown in figure 5, this is a broken line graph.
In the figure, it can be clearly seen which value space CPU usage mainly drops on.
In order to increase benchmark, becoming apparent from, I adds Trendline, it can be seen that every 25 points take a value, the Trendline drawn.
Can also arranging every N number of point and take a value, this can be revised according to the dense degree of data.As shown in Figure 6.So, CPU usage just can embody intuitively very much.
The cpu performance of test SSD can pass through these data, and chart embodies.
And CPU recording data files can be sent to statistical server by multiple servers in real time, quickly in time, concurrently, intuitively.
While server completes the running of self, do not affect, increase above statistical function simultaneously, convenient, effectively.
In sum, this method of testing has, workable, it may be achieved property, clear data, quantization operation, and linux system shell script is simple and easy to write.While server completes the running of self, do not affect, increase above statistical function simultaneously, convenient, effectively.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when without departing substantially from the spirit of the present invention or basic feature, it is possible to realize the present invention in other specific forms.Therefore, no matter from which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the invention rather than described above limits, it is intended that all changes in the implication of the equivalency dropping on claim and scope be included in the present invention.Any accompanying drawing labelling in claim should be considered as the claim that restriction is involved.Furthermore, it is to be understood that " including " word is not excluded for other unit or step, odd number is not excluded for plural number.Multiple unit or the device stated in device claim can also be realized by software or hardware by a unit or device.The first, the second word such as grade is used for representing title, and is not offered as any specific order.
Claims (10)
1. a storage device read-write is to the CPU comparison and detection method consumed, it is characterised in that realize step as follows:
S10: statistical machine and at least one test machine are linked together by network, is installed detection and uses described storage device, described storage device at least to include the SSD hard disk of PCIe interface or the head hard drive of SATA interface in described test machine；
S20: described statistical machine and the system environments of described test machine are set；
S30: allow described test machine testing results shell script；
S40: obtain cpu data when described test script program is run, generate statistics file；
S50: described statistics file is transmitted to described statistical machine；
S60: described statistics file is made chart by described statistical machine；
S70: contrast the described chart made by the described statistics file generated by different described test machines.
2. comparison and detection method according to claim 1, it is characterized in that, the system environments arranging described statistical machine and/or described test machine in described step S20 is Windows operating system environment, linux operating system environment or Macintosh environment.
3. comparison and detection method according to claim 1, it is characterised in that increase step S25 before described step S30: each described test machine normal operation, runs once described test script program in described step S30 every 2～5 seconds.
4. comparison and detection method according to claim 3, it is characterised in that described in described step S25, the access time of test machine normal operation is at least more than 10 hours.
5. comparison and detection method according to claim 4, it is characterised in that after described step S30 has performed, performs a step S25 and step S30 at least again.
6. comparison and detection method according to claim 1, it is characterised in that shell script described in described step S40 generated a statistics file every 24～48 hours.
7. comparison and detection method according to claim 1, it is characterised in that statistical machine operational data collection shell script described in described step S50, obtains described statistics file；Described statistics file is generated log file by described step S60, more described log file is made described chart.
8. comparison and detection method according to claim 7, it is characterised in that before described step S60, performs step S55: described statistical machine service data filters shell script first will filter out 0.1% noise in described log file.
9. comparison and detection method according to claim 7, it is characterized in that, each described log file is made statistical table and cartogram by statistical machine described in described step S70, then performs step S80: contrast described statistical table according to CPU Expenditure Levels, described cartogram be ranked up.
10. comparison and detection method according to claim 9, it is characterised in that increasing Trendline in cartogram described in described step S60, the periodic quantity of described Trendline is arranged to every 10～50 cycles and takes a meansigma methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610102681.1A CN105760267A (en) | 2016-02-25 | 2016-02-25 | Comparative detection method for CPU consumption of storage device read-write |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610102681.1A CN105760267A (en) | 2016-02-25 | 2016-02-25 | Comparative detection method for CPU consumption of storage device read-write |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105760267A true CN105760267A (en) | 2016-07-13 |
Family
ID=56331210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610102681.1A Pending CN105760267A (en) | 2016-02-25 | 2016-02-25 | Comparative detection method for CPU consumption of storage device read-write |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105760267A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106789265A (en) * | 2016-12-27 | 2017-05-31 | 北京五八信息技术有限公司 | The clustering method and device of a kind of service cluster |
| CN107391333A (en) * | 2017-08-14 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of OSD disk failures method of testing and system |
| CN110544503A (en) * | 2019-08-28 | 2019-12-06 | 深圳忆联信息系统有限公司 | test method for evaluating total write-in quantity of SSD and computer equipment |
| CN110910945A (en) * | 2019-11-19 | 2020-03-24 | 深圳忆联信息系统有限公司 | Method and device for testing robustness of SSD (solid State disk) signal, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102075384A (en) * | 2010-12-20 | 2011-05-25 | 创新科存储技术有限公司 | Performance test system and method |
| CN102236601A (en) * | 2011-06-22 | 2011-11-09 | 福建新大陆通信科技股份有限公司 | Method for testing software stability of set top box |
| US8095636B2 (en) * | 2004-12-21 | 2012-01-10 | International Business Machines Corporation | Process, system and program product for executing test scripts against multiple systems |
| CN102662828A (en) * | 2012-03-14 | 2012-09-12 | 浪潮(北京)电子信息产业有限公司 | A method and device for achieving software automatic testing |
| CN104239193A (en) * | 2014-09-04 | 2014-12-24 | 浪潮电子信息产业股份有限公司 | Linux-based CPU (Central Processing Unit) and memory usage rate collection method |
-
2016
- 2016-02-25 CN CN201610102681.1A patent/CN105760267A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8095636B2 (en) * | 2004-12-21 | 2012-01-10 | International Business Machines Corporation | Process, system and program product for executing test scripts against multiple systems |
| CN102075384A (en) * | 2010-12-20 | 2011-05-25 | 创新科存储技术有限公司 | Performance test system and method |
| CN102236601A (en) * | 2011-06-22 | 2011-11-09 | 福建新大陆通信科技股份有限公司 | Method for testing software stability of set top box |
| CN102662828A (en) * | 2012-03-14 | 2012-09-12 | 浪潮(北京)电子信息产业有限公司 | A method and device for achieving software automatic testing |
| CN104239193A (en) * | 2014-09-04 | 2014-12-24 | 浪潮电子信息产业股份有限公司 | Linux-based CPU (Central Processing Unit) and memory usage rate collection method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106789265A (en) * | 2016-12-27 | 2017-05-31 | 北京五八信息技术有限公司 | The clustering method and device of a kind of service cluster |
| CN107391333A (en) * | 2017-08-14 | 2017-11-24 | 郑州云海信息技术有限公司 | A kind of OSD disk failures method of testing and system |
| CN107391333B (en) * | 2017-08-14 | 2020-10-16 | 苏州浪潮智能科技有限公司 | OSD disk fault testing method and system |
| CN110544503A (en) * | 2019-08-28 | 2019-12-06 | 深圳忆联信息系统有限公司 | test method for evaluating total write-in quantity of SSD and computer equipment |
| CN110910945A (en) * | 2019-11-19 | 2020-03-24 | 深圳忆联信息系统有限公司 | Method and device for testing robustness of SSD (solid State disk) signal, computer equipment and storage medium |
| CN110910945B (en) * | 2019-11-19 | 2021-08-17 | 深圳忆联信息系统有限公司 | Method and device for testing robustness of SSD (solid State disk) signal, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8359450B2 (en) | Memory utilization analysis | |
| US11263071B2 (en) | Enabling symptom verification | |
| US7428622B2 (en) | Managing disk storage media based on access patterns | |
| JP5705084B2 (en) | 2-pass automatic application measurement | |
| Chowdhury et al. | An exploratory study on assessing the energy impact of logging on android applications | |
| US11093349B2 (en) | System and method for reactive log spooling | |
| US8694834B2 (en) | Preventing log wrap with debug scripts | |
| Ates et al. | An automated, cross-layer instrumentation framework for diagnosing performance problems in distributed applications | |
| US20080276129A1 (en) | Software tracing | |
| US10936386B2 (en) | Method, device and computer program product for monitoring access request | |
| CN105760267A (en) | Comparative detection method for CPU consumption of storage device read-write | |
| US8219856B2 (en) | Memory growth detection | |
| US9442817B2 (en) | Diagnosis of application server performance problems via thread level pattern analysis | |
| CN102915269A (en) | Method for analyzing common logs of B/S (browser/server) software system | |
| KR20110052470A (en) | Symmetric multi-processor lock tracing | |
| Lai et al. | milliscope: A fine-grained monitoring framework for performance debugging of n-tier web services | |
| US20160140019A1 (en) | Event summary mode for tracing systems | |
| Sousa et al. | Evaluating eucalyptus virtual machine instance types: A study considering distinct workload demand | |
| US8850407B2 (en) | Test script generation | |
| Sârbu et al. | Profiling the operational behavior of OS device drivers | |
| WO2015198600A1 (en) | Analysis device, analysis method, and storage medium in which analysis program is recorded | |
| CN111435327B (en) | Log record processing method, device and system | |
| US8312433B2 (en) | Operating system aided code coverage | |
| Kavalanekar et al. | Measuring database performance in online services: a trace-based approach | |
| US20120159006A1 (en) | Monitoring input/output operations to specific storage locations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160713 |