CN102692988A - A power consumption method on a blade server - Google Patents
A power consumption method on a blade server Download PDFInfo
- Publication number
- CN102692988A CN102692988A CN2012101492269A CN201210149226A CN102692988A CN 102692988 A CN102692988 A CN 102692988A CN 2012101492269 A CN2012101492269 A CN 2012101492269A CN 201210149226 A CN201210149226 A CN 201210149226A CN 102692988 A CN102692988 A CN 102692988A
- Authority
- CN
- China
- Prior art keywords
- power
- blade
- module
- calculating
- idle
- 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
Images
Landscapes
- Power Sources (AREA)
Abstract
The invention provides a power consumption method on a blade server, comprising two sub-strategies: 1, idle power determination strategy; 2, system fan location determination strategy, wherein: 1, if an idle power is less than a blade rated power, then power-up on the blade is restricted; determining whether the maximum power of a single computing blade is less or equal to the present idle power or not is needed to determine whether a computing blade is allowed to power up or not, if the condition is not satisfied, then the computing blade is not allowed to power up; 2, if a corresponding fan disc array does not exist at the location of the blade requesting power up, then the blade is restricted to power up, i.e., the system fan location determination strategy specifically refers: the blade is allowed to power up if a corresponding fan exists at the location of the blade requesting power up, otherwise the blade is not allowed to power up.
Description
Technical field
The present invention relates to the server design field, use method for electrically on specifically a kind of blade server.
Background technology
Cloud computing is a kind of novel management of information resources and calculation services pattern, is the revolution of information industry after mainframe computer, PC, internet.Cloud computing can change conventional data centers operational management theory with the management and service of getting up of the calculating, storage, the Service Source organic combination that disperse, is the following developing direction of calculating.Cloud computing has the low-cost unique charm that solves magnanimity information processing with the design concept of its resource dynamic distribution, on-demand service.
The new round cloud computing transformation of carrying out gradually along with various places data center; The design concept of data center's infrastructure such as server, storage etc. is from traditional pursuit high-performance, high availability the time; Also more and more pay attention to characteristics such as high density, low-power consumption; Therefore, possesses the blade server of high density, low-power consumption, manageability, high performance-price ratio characteristics, the important component part when becoming the construction of cloud computing data center.
Based on the modular design concept of blade server, the power module of a plurality of blade systems, blower module etc. all adopt shares the formula design, supports hot plug, and can carry out the varying number modules configured according to user's needs.If but the rated power of power module on the throne can't satisfy the needs that calculate blade, or certain groove position has only the blade of calculating not have corresponding blower module, calculates blade and powers on if still give in this case, can cause system delay machine even device damage.Therefore, need to propose a kind of intelligentized blade server and power on strategy to solve this type of problem.
Summary of the invention
The blade server that the present invention proposes a kind of intelligence strategy that powers on comprises idle power decision plan, system fan location determination strategy.Wherein: 1) if idle power less than blade rated power, then limits blade and powers on; Middle blade server system is made up of power module, blower module, administration module, Switching Module, calculating blade, and the idle power computing formula is following:
Idle power=the biggest Shu of power module quantity * single supply module goes out Gong and Shuais – (the administration module quantity * single tube reason module peak power+single calculating of Switching Module quantity * single cross die change piece peak power+calculatings knife number * blade peak power)
Judge whether certain calculating blade can be allowed to power on, need judge that then whether single blade peak power of calculating is less than or equal to current idle power, if do not satisfy this condition, does not then allow this calculating blade to power on;
2) there is not corresponding fan disk battle array in blade position if request powers on, and then limits blade and powers on, and promptly system fan location determination strategy specifically refers to: the position of power blade has corresponding fan then can allow blade to power in the request, otherwise does not allow this blade to power on.
The invention has the beneficial effects as follows: based on the blade server system of this strategy design that powers on; Can be when system power supply and radiating condition possess; The restriction blade server powers on; Improve blade server system intellectual management degree, and then improved system reliability, thereby had vast potential for future development and high technological value.
Description of drawings
Fig. 1 is that calculating blade and position of fan concern synoptic diagram;
Fig. 2 is a blade server power up synoptic diagram.
Embodiment
Explanation at length below with reference to Figure of description method of the present invention being done.
With reference to the accompanying drawings, content of the present invention with instantiation the power on process of strategy of the blade server of describing in the invention that realizes is described.
As described in the summary of the invention, idle power decision plan (blade server system is made up of power module, blower module, administration module, Switching Module, calculating blade etc. in the example) specific as follows:
The idle power computing formula: idle power=the biggest Shu of power module quantity * single supply module goes out Gong and Shuais – (the administration module quantity * single tube reason module peak power+single calculating of Switching Module quantity * single cross die change piece peak power+calculatings knife number * blade peak power)
Calculate blade and whether can be allowed to power on if judge certain, need judge that then whether single blade peak power of calculating is less than or equal to current idle power, if do not satisfy this condition, does not then allow this calculating blade to power on.
As described in the summary of the invention, system fan location determination strategy specifically refers to: the request blade position that powers on has corresponding fan then can allow blade to power on, otherwise does not allow this blade to power on.
Calculating blade shown in the accompanying drawing 1 and position of fan relation, blade 1 is by fan 1 heat radiation.Blade 3 is by fan 1 and fan 2 heat radiations.So blade 1 corresponding fan 1, blade 3 corresponding fans 1 and fan 2.Therefore, if fan 1 is not on the throne, then calculates blade 1 and do not allow to power on; If fan 1 or fan 2 any one not on the throne, then calculate blade 3 and do not allow to power on.
As described in the summary of the invention, the blade server power up is specific as follows, shown in accompanying drawing 2:
1) user powers on through certain blade of blade server management system control;
2) management system judges according to the idle power decision plan whether this blade can normally power on, and then changes step 4 as allowing this blade to power on, otherwise changes step 3;
3) to user feedback because idle power is not enough, therefore do not allow current calculating blade to power on, flow process finishes;
4) management system judges according to system fan location determination strategy whether this blade can normally power on, and then changes step 6 as allowing this blade to power on, otherwise changes step 5;
5) do not have blower module to user feedback owing to correspondence position, therefore do not allow current calculating blade to power on, flow process finishes;
Management system powers on to this calculating blade, and flow process finishes.
Except that the described technical characterictic of instructions, be the known technology of those skilled in the art.
Claims (1)
1. use method for electrically on the blade server, it is characterized in that comprising two substrategys: 1) idle power decision plan; 2) system fan location determination strategy, wherein:
1) if idle power less than blade rated power, then limits blade and powers on; Middle blade server system is made up of power module, blower module, administration module, Switching Module, calculating blade, and the idle power computing formula is following:
Idle power=the biggest Shu of power module quantity * single supply module goes out Gong and Shuais – (the administration module quantity * single tube reason module peak power+single calculating of Switching Module quantity * single cross die change piece peak power+calculatings knife number * blade peak power)
Judge whether certain calculating blade can be allowed to power on, need judge that then whether single blade peak power of calculating is less than or equal to current idle power, if do not satisfy this condition, does not then allow this calculating blade to power on;
2) there is not corresponding fan disk battle array in blade position if request powers on, and then limits blade and powers on, and promptly system fan location determination strategy specifically refers to: the position of power blade has corresponding fan then can allow blade to power in the request, otherwise does not allow this blade to power on.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012101492269A CN102692988A (en) | 2012-05-15 | 2012-05-15 | A power consumption method on a blade server |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012101492269A CN102692988A (en) | 2012-05-15 | 2012-05-15 | A power consumption method on a blade server |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102692988A true CN102692988A (en) | 2012-09-26 |
Family
ID=46858517
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012101492269A Pending CN102692988A (en) | 2012-05-15 | 2012-05-15 | A power consumption method on a blade server |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102692988A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049050A (en) * | 2012-12-25 | 2013-04-17 | 华为技术有限公司 | Blade server capacity expansion configuration method and management system |
CN109739329A (en) * | 2018-12-27 | 2019-05-10 | 郑州云海信息技术有限公司 | A kind of method and device calculating number of power sources automatically in ERP system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030200473A1 (en) * | 1990-06-01 | 2003-10-23 | Amphus, Inc. | System and method for activity or event based dynamic energy conserving server reconfiguration |
CN101441506A (en) * | 2007-11-20 | 2009-05-27 | 中兴通讯股份有限公司 | Blade server system and power consumption management method thereof |
CN102043456A (en) * | 2010-12-10 | 2011-05-04 | 曙光信息产业(北京)有限公司 | Power supply allocation method of blade server |
CN102128175A (en) * | 2010-01-15 | 2011-07-20 | 全汉企业股份有限公司 | Method for starting fan |
-
2012
- 2012-05-15 CN CN2012101492269A patent/CN102692988A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030200473A1 (en) * | 1990-06-01 | 2003-10-23 | Amphus, Inc. | System and method for activity or event based dynamic energy conserving server reconfiguration |
CN101441506A (en) * | 2007-11-20 | 2009-05-27 | 中兴通讯股份有限公司 | Blade server system and power consumption management method thereof |
CN102128175A (en) * | 2010-01-15 | 2011-07-20 | 全汉企业股份有限公司 | Method for starting fan |
CN102043456A (en) * | 2010-12-10 | 2011-05-04 | 曙光信息产业(北京)有限公司 | Power supply allocation method of blade server |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103049050A (en) * | 2012-12-25 | 2013-04-17 | 华为技术有限公司 | Blade server capacity expansion configuration method and management system |
WO2014101406A1 (en) * | 2012-12-25 | 2014-07-03 | 华为技术有限公司 | Capacity expansion configuration method and management system for blade server |
CN103049050B (en) * | 2012-12-25 | 2015-10-21 | 华为技术有限公司 | A kind of capacity expansion configuration method administrating system of blade server |
CN109739329A (en) * | 2018-12-27 | 2019-05-10 | 郑州云海信息技术有限公司 | A kind of method and device calculating number of power sources automatically in ERP system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yadav et al. | MeReg: managing energy‐SLA tradeoff for green mobile cloud computing | |
Cao et al. | Optimal power allocation and load distribution for multiple heterogeneous multicore server processors across clouds and data centers | |
US20180262509A1 (en) | Differentiated containerization and execution of web content based on trust level and other attributes | |
EP3716107B1 (en) | Technologies for accelerated orchestration and attestation with edge device trust chains | |
Zhang et al. | A genetic algorithm‐based task scheduling for cloud resource crowd‐funding model | |
Borah et al. | Power saving strategies in green cloud computing systems | |
US20190171263A1 (en) | Processor computing power and power for thermal energy management solutions of a computing platform | |
Xie et al. | Schedule length minimization of parallel applications with energy consumption constraints using heuristics on heterogeneous distributed systems | |
CN102692988A (en) | A power consumption method on a blade server | |
Li | Optimal power and performance management for heterogeneous and arbitrary cloud servers | |
Sawada et al. | Eco Models of Storage-Based Severs | |
Xuan et al. | Energy Efficiency Opposition‐Based Learning and Brain Storm Optimization for VNF‐SC Deployment in IoT | |
Zhang‐Jian et al. | An energy‐saving algorithm for cloud resource management using a Kalman filter | |
Kansal et al. | Introduction to fog data analytics for IoT applications | |
CN105786757A (en) | On-board integrated distribution type high-performance operating system device | |
Chaudhrani et al. | Energy Aware Computing Resource Allocation Using PSO in Cloud | |
ZHANG et al. | Energy-efficient algorithm based on data classification for cloud storage system | |
Hu et al. | A Survey on Green Computing Based on Cloud Environment. | |
Jena et al. | Minimizing CO2 emissions on cloud data centers | |
CN104539731A (en) | Credible service diffusion method and device based on social network node optimization | |
CN204044726U (en) | A kind of low dimensional blade server backboard based on orthogonal connector | |
Zhao et al. | Hierarchical resource allocation and consolidation framework in a multi‐core server cluster using a Markov decision process model | |
Zhang et al. | Communication optimization for RDMA-based science data transmission tools | |
Cecowski et al. | The m2dc project: Modular microserver datacentre | |
AU2021106710A4 (en) | Controlling Power Consumptions as a service (CPCaaS) - System and Method for Controlling Power Consumptions in Cloud Environment through smart resource optimization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120926 |