CN101021809A - System power distribution testing method - Google Patents
System power distribution testing method Download PDFInfo
- Publication number
- CN101021809A CN101021809A CN 200710013382 CN200710013382A CN101021809A CN 101021809 A CN101021809 A CN 101021809A CN 200710013382 CN200710013382 CN 200710013382 CN 200710013382 A CN200710013382 A CN 200710013382A CN 101021809 A CN101021809 A CN 101021809A
- Authority
- CN
- China
- Prior art keywords
- measure
- voltage
- power supply
- supply output
- output line
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 8
- 238000010998 test method Methods 0.000 claims description 7
- 238000013213 extrapolation Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000000047 product Substances 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Abstract
The invention provides a method for testing power distribution of system. Firstly, it separately runs the compressed software for CPU, hard disk, memory and graphics, and separately records the actual consumption of peak current by using specialized test equipment, and then it calculates the actual maximum power consumption of each component. Secondly, it runs the software at the same time, and records their actual value in the current consumption, and calculates the overall actual maximum of power consumption. In the end, it combines the two records in power and a appropriate margin to reach a power supply option.
Description
Technical field
The present invention relates to the computer system field tests, the method for testing that specifically provides a kind of system power to distribute.
Background technology
At present, the selection foundation for performance number mainly contains two kinds when carrying out the power supply type selecting.
The one, fully the simple stack of the peak power of each parts in the system is selected.This value is on the basis with the power-handling capability addition of each parts, adds that certain allowance draws again.This yes insurance, but in actual applications, the situation that the power of each parts all reaches ratings simultaneously is absolutely not generation, also has certain allowance still more! So, can increase unnecessary production cost to product according to this superposition value fully, especially more can bring the waste of a large amount of production costs, and improve user's the cost that has for the bigger server power supply of power.
The 2nd, fully according to the recommended value among the System Power budget Roadmap of Intel.This suggestion numerical value is divided by radical sign 2 income values on the basis of first method.Because when system works, the state of each parts is different in the system, and some parts work is frequent (as processor) relatively, then fewer use (as the floppy drive) of some parts, therefore introduced a coefficient, rule of thumb normally add and the basis on divided by with numbers 2.This mode is the method that generally adopts at present, it greatly reduces cost than first kind of selection mode, but experiment showed, that this value is still excessive with respect to the actual consumption of system power, promptly with regard to present power is selected, still there is bigger cost waste.
Summary of the invention
The method of testing that a kind of system power of the present invention distributes is to propose at the inaccurate present situation that system power under the prior art is tested.It is based upon on the various concrete application foundations (as database, Web application, FTP, VOD video request program, recreation etc.), be used for the test macro power division, so that practicality power supply required according to reality and power supply manufacturer joint development high performance-price ratio, the actual power consumption that this method can precision measuring system simultaneously, and with this reliable basis as the power type selecting.
It is as follows that the method for testing that a kind of system power of the present invention distributes overcomes the above problems the technical scheme that is adopted:
The method of testing that a kind of system power distributes may further comprise the steps:
The pressurization software of A, difference central processor in service, hard disk, internal memory, network, video card;
B, write down the peak point current of each parts institute actual consumption respectively, and calculate the maximal value of the actual power consumption of each parts;
C, the pressurization software of above-mentioned parts is moved together, write down the maximal value of their overall actual consumption electric currents, calculate overall actual power consumption maximal value.
The step of the peak point current of each parts actual consumption of described measurement specifically comprises following;
For central processing unit:
A, all DC voltage of measuring mainboard CPU connecting line interface with current clamp be+voltage of the power supply output line of 12V, and write down greatest measure;
For the parts of extrapolation mainboard such as internal memory, video card:
A, measure the voltage on all on all connecting lines+12V power supply output line on the mainboard with current clamp, and the record greatest measure;
B, measure the voltage on all on all connecting lines+5V power supply output line on the mainboard with current clamp, and the record greatest measure;
C, measure the voltage on all on all connecting lines+3.3V power supply output line on the mainboard with current clamp, and the record greatest measure.
For hard disk:
A, with current clamp measure on the hard disk connecting line all+12V and+voltage on the 5V line, and record greatest measure.
The method of testing that a kind of system power of the present invention distributes, according to various application demands, move the pressurization software of CPU, hard disk, internal memory, network, video card at first respectively, and write down the peak point current of each parts institute actual consumption respectively with special testing apparatus, calculate the maximal value of the actual power consumption of each parts afterwards respectively; Pressurization software with above-mentioned parts moves together then, writes down the maximal value of their overall actual consumption electric currents, calculates overall actual power consumption maximal value.Two groups of performance numbers in conjunction with record add suitable allowance, are the foundation value of selecting the power specification.The system power that draws with this method serves as to select according to making power supply, can effectively reduce production costs and the user have cost, gone on intensive road, when improving product competitiveness, will inevitably bring more material benefit for users by the actual consumption customization.
Embodiment
Provide a specific embodiment below, and the invention will be further described in conjunction with specific embodiments, but not as a limitation of the invention.
Select for use testing hardware to comprise: current clamp, treat examining system (configuration maximization, Server joins Raid).
The pressurization software of selecting for use comprises: NocPscMaxpowerl.4.1 (Nocona Xeon or the pressurization of PrescottPentium4 processor); WinMAT (internal memory pressurization); IOMeter (hard disk pressurization); 3Dmark2001SE Pro330 (video card pressurization).
Concrete method of testing is as follows:
For central processing unit, move NocPscMaxpowerl.4.1 earlier, adjust the utilization factor to 100% of CPU.
All DC voltage of measuring mainboard CPU connecting line interface with current clamp be+voltage of the power supply output line of 12V, and write down greatest measure;
Parts such as internal memory for the extrapolation mainboard move WinMAT, video card operation 3Dmark2001 SE.
A, measure the voltage on all on all connecting lines+12V power supply output line on the mainboard with current clamp, and the record greatest measure;
B, measure the voltage on all on all connecting lines+5V power supply output line on the mainboard with current clamp, and the record greatest measure;
C, measure the voltage on all on all connecting lines+3.3V power supply output line on the mainboard with current clamp, and the record greatest measure.
Get final product according to default default value setting during isolated operation WinMAT, need add test parameter MemorySizeMB when moving together with other pressurization software, concrete operations are as follows, key in Keyword: MemorySizeMB; In Value, key in memory size or the number percent that needs test, be recommended as 50%.Click Add after finishing, can finish the interpolation of this parameter.
For hard disk, operation IOMeter.
With current clamp measure on the hard disk connecting line all+12V and+voltage on the 5V line, and record greatest measure.
At last, move all pressurization softwares.
With current clamp measure on all connecting lines all+voltage on the 12V power supply output line, and record greatest measure;
With current clamp measure on all connecting lines all+voltage on the 5V power supply output line, and record greatest measure;
With the voltage on owning on the current clamp measurement mainboard connecting line+3.3V power supply output line, and the record greatest measure.
After recording all magnitudes of voltage, calculate the performance number of consumption.
Above-described embodiment, the present invention embodiment a kind of more preferably just, the common variation that those skilled in the art carries out in the technical solution of the present invention scope and replacing all should be included in protection scope of the present invention.
Claims (3)
1, a kind of method of testing of system power distribution may further comprise the steps:
The pressurization software of A, difference central processor in service, hard disk, internal memory, network, video card;
B, write down the peak point current of each parts institute actual consumption respectively, and calculate the maximal value of the actual power consumption of each parts;
C, the pressurization software of above-mentioned parts is moved together, write down the maximal value of their overall actual consumption electric currents, calculate overall actual power consumption maximal value.
2, the method for testing of a kind of system power distribution according to claim 1 is characterized in that the step of the peak point current of each parts actual consumption of described measurement specifically comprises following;
For central processing unit:
A, all DC voltage of measuring mainboard CPU connecting line interface with current clamp be+voltage of the power supply output line of 12V, and write down greatest measure;
For the parts of extrapolation mainboard such as internal memory, video card:
A, measure the voltage on all on all connecting lines+12V power supply output line on the mainboard with current clamp, and the record greatest measure;
B, measure the voltage on all on all connecting lines+5V power supply output line on the mainboard with current clamp, and the record greatest measure;
C, measure the voltage on all on all connecting lines+3.3V power supply output line on the mainboard with current clamp, and the record greatest measure.
For hard disk:
A, with current clamp measure on the hard disk connecting line all+12V and+voltage on the 5V line, and record greatest measure;
3, a kind of system power according to claim 1 method of testing of distributing is characterized in that, the step of measuring the overall actual consumption current maxima of each parts specifically:
A, with current clamp measure on all connecting lines all+voltage on the 12V power supply output line, and record greatest measure;
B, with current clamp measure on all connecting lines all+voltage on the 5V power supply output line, and record greatest measure;
C, with current clamp measure on the mainboard connecting line all+voltage on the 3.3V power supply output line, and record greatest measure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200710013382 CN101021809A (en) | 2007-03-14 | 2007-03-14 | System power distribution testing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200710013382 CN101021809A (en) | 2007-03-14 | 2007-03-14 | System power distribution testing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101021809A true CN101021809A (en) | 2007-08-22 |
Family
ID=38709583
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 200710013382 Pending CN101021809A (en) | 2007-03-14 | 2007-03-14 | System power distribution testing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101021809A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101883019A (en) * | 2010-03-15 | 2010-11-10 | 浪潮电子信息产业股份有限公司 | Test method for verifying video application of storage server |
CN101414208B (en) * | 2007-10-16 | 2011-07-13 | 华硕电脑股份有限公司 | Electric energy sharing circuit |
CN102543144A (en) * | 2010-12-29 | 2012-07-04 | 鸿富锦精密工业(深圳)有限公司 | Electric parameter monitoring device of power supply of hard disk |
CN101799493B (en) * | 2009-12-30 | 2012-07-04 | 成都市华为赛门铁克科技有限公司 | Method and device for detecting system power |
CN103018545A (en) * | 2012-12-26 | 2013-04-03 | 北京百度网讯科技有限公司 | Whole cabinet power consumption test method |
CN107844186A (en) * | 2016-09-18 | 2018-03-27 | 鸿富锦精密工业(武汉)有限公司 | Electric supply system |
CN109583098A (en) * | 2018-12-04 | 2019-04-05 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of power supply direct current design automatic analysis method |
-
2007
- 2007-03-14 CN CN 200710013382 patent/CN101021809A/en active Pending
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101414208B (en) * | 2007-10-16 | 2011-07-13 | 华硕电脑股份有限公司 | Electric energy sharing circuit |
CN101799493B (en) * | 2009-12-30 | 2012-07-04 | 成都市华为赛门铁克科技有限公司 | Method and device for detecting system power |
CN101883019A (en) * | 2010-03-15 | 2010-11-10 | 浪潮电子信息产业股份有限公司 | Test method for verifying video application of storage server |
CN101883019B (en) * | 2010-03-15 | 2012-07-04 | 浪潮电子信息产业股份有限公司 | Test method for verifying video application of storage server |
CN102543144A (en) * | 2010-12-29 | 2012-07-04 | 鸿富锦精密工业(深圳)有限公司 | Electric parameter monitoring device of power supply of hard disk |
CN102543144B (en) * | 2010-12-29 | 2015-03-25 | 温州泓呈祥科技有限公司 | Electric parameter monitoring device of power supply of hard disk |
CN103018545A (en) * | 2012-12-26 | 2013-04-03 | 北京百度网讯科技有限公司 | Whole cabinet power consumption test method |
CN103018545B (en) * | 2012-12-26 | 2015-04-08 | 北京百度网讯科技有限公司 | Whole cabinet power consumption test method |
CN107844186A (en) * | 2016-09-18 | 2018-03-27 | 鸿富锦精密工业(武汉)有限公司 | Electric supply system |
CN107844186B (en) * | 2016-09-18 | 2019-12-06 | 鸿富锦精密工业(武汉)有限公司 | Power supply system |
CN109583098A (en) * | 2018-12-04 | 2019-04-05 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of power supply direct current design automatic analysis method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101021809A (en) | System power distribution testing method | |
DE112006000296B4 (en) | Modify the output of a power adapter | |
Abbott | The productivity and efficiency of the Australian electricity supply industry | |
DE102007053796B4 (en) | Operate integrated circuit logic blocks on independent voltages with a single power supply | |
Lee et al. | A new approach to the assessment of steady-state voltage stability margins using the P–Q–V curve | |
Wu et al. | Measuring E-government performance of provincial government website in China with slacks-based efficiency measurement | |
CN102857560B (en) | A kind of cloud towards multi-service application stores data distribution method | |
AU3755399A (en) | Index rebalancing for a capitalization weighted stock index | |
US20100031259A1 (en) | Estimating power consumption of a virtual server | |
DE112007001056T5 (en) | PRO Chip Voltage Programming for Energy Efficient Integrated Circuit (IC) Operation | |
CN100351787C (en) | Method for generating configuration monitoring page in monitoring system | |
US20060294408A1 (en) | Method for estimating power consumption of a cpu | |
Chen et al. | Adjusting productivity measures for CO2 emissions control: Evidence from the provincial thermal power sector in China | |
CN108364238A (en) | A kind of diversified powering mode selection method based on power supply area grade classification | |
Chang et al. | A new method for calculating loss coefficients [of power systems] | |
Zhan | Allocation of carbon emission quotas among provinces in China: efficiency, fairness and balanced allocation | |
Guo et al. | The effect of China’s carbon emission trading on eco-efficiency: an empirical study at the city level | |
CN1260898C (en) | Power source single-board universal tester | |
KR20140067581A (en) | Method of power management for graphic processing unit and system thereof | |
Tangena et al. | Finite element calculations on the influence of surface roughness on friction | |
CN113988373A (en) | Multi-task mass user load prediction method based on multi-channel convolutional neural network | |
Ghawghawe et al. | Application of power flow sensitivity analysis and PTDF for determination of ATC | |
Chiou et al. | Foreign direct investment in emerging markets: Bondholders' perspective | |
JP5802031B2 (en) | How to aggregate energy services from more than one participant | |
Nemoto et al. | Measurement of technical and allocative efficiencies using a CES cost frontier: a benchmarking study of Japanese transmission-distribution electricity |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |