US20120240123A1 - Energy And Performance Optimizing Job Scheduling - Google Patents

Energy And Performance Optimizing Job Scheduling Download PDF

Info

Publication number
US20120240123A1
US20120240123A1 US13/484,877 US201213484877A US2012240123A1 US 20120240123 A1 US20120240123 A1 US 20120240123A1 US 201213484877 A US201213484877 A US 201213484877A US 2012240123 A1 US2012240123 A1 US 2012240123A1
Authority
US
United States
Prior art keywords
job
cold
hot
schedule
jobs
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.)
Abandoned
Application number
US13/484,877
Inventor
Giridhar M. Prabhakar
Chiranjib Sur
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lenovo Enterprise Solutions Singapore Pte Ltd
Original Assignee
International Business Machines Corp
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
Priority to US12/961,633 priority Critical patent/US8776069B2/en
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Priority to US13/484,877 priority patent/US20120240123A1/en
Publication of US20120240123A1 publication Critical patent/US20120240123A1/en
Assigned to LENOVO ENTERPRISE SOLUTIONS (SINGAPORE) PTE. LTD. reassignment LENOVO ENTERPRISE SOLUTIONS (SINGAPORE) PTE. LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: INTERNATIONAL BUSINESS MACHINES CORPORATION
Application status is Abandoned legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806Task transfer initiation or dispatching
    • G06F9/4843Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G06F9/4893Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues taking into account power or heat criteria
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing
    • Y02D10/20Reducing energy consumption by means of multiprocessor or multiprocessing based techniques, other than acting upon the power supply
    • Y02D10/24Scheduling

Abstract

Energy and performance optimizing job scheduling that includes queuing jobs; characterizing jobs as hot or cold, specifying a hot and a cold job sub-queue; iteratively for a number of schedules, until estimated performance and power characteristics of executing jobs in accordance with a schedule meets predefined selection criteria: determining a schedule in dependence upon a user provided parameter, the characterization of each job as hot or cold, and an energy and performance optimizing heuristic; estimating performance and power characteristics of executing the jobs in accordance with the schedule; and determining whether the estimated performance and power characteristics meet the predefined selection criteria. If the estimated performance and power characteristics do not meet the predefined selection criteria, adjusting the user-provided parameter for a next iteration and executing the plurality of jobs in accordance with the determined schedule if the estimated performance and power characteristics meet the predefined selection criteria.

Description

    CROSS-REFERENCE TO RELATED APPLICATION
  • This application is a continuation application of and claims priority from U.S. patent application Ser. No. 12/961,633, filed on Dec. 7, 2010.
  • BACKGROUND OF THE INVENTION
  • 1. Field of the Invention
  • The field of the invention is data processing, or, more specifically, methods, apparatus, and products for energy and performance optimizing job scheduling.
  • 2. Description of Related Art
  • Electricity costs for powering and cooling the computing infrastructure in data centers is increasing. The environmental impact of such powering and cooling is also increasing. In today's computing environments, a set of jobs (also called tasks) are often scheduled in one of two ways: to increase computational efficiency of processing the set of jobs or to decrease power consumption in processing the set of tasks. To date, however, no job scheduling is carried out that takes into account both computational efficiency and power consumption of a set of jobs.
  • SUMMARY OF THE INVENTION
  • Methods, apparatus, and products for energy and performance optimizing job scheduling in a data processing system are disclosed. In accordance with embodiments of the present invention, energy and performance optimizing job scheduling includes queuing a plurality of jobs; characterizing each of the plurality of jobs as one of hot or cold, thereby specifying a hot job sub-queue and a cold job sub-queue; iteratively for a plurality of schedules of the plurality of jobs, until estimated performance and power characteristics of executing jobs in accordance with a schedule meets predefined selection criteria: determining a schedule for the plurality of jobs in dependence upon a user provided parameter, the characterization of each job as hot or cold, and an energy and performance optimizing heuristic; estimating performance and power characteristics of executing the jobs in accordance with the schedule; and determining whether the estimated performance and power characteristics meet the predefined selection criteria; if the estimated performance and power characteristics do not meet the predefined selection criteria, adjusting the user-provided parameter; and if the estimated performance and power characteristics meet the predefined selection criteria, executing the plurality of jobs in accordance with the schedule.
  • The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular descriptions of exemplary embodiments of the invention as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts of exemplary embodiments of the invention.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 sets forth a network diagram of a data processing system for energy and performance optimizing job scheduling according to embodiments of the present invention.
  • FIG. 2 sets forth a flow chart illustrating a further exemplary method for energy and performance optimizing job scheduling according to embodiments of the present invention.
  • DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS
  • Exemplary methods, apparatus, and products for energy and performance optimizing job scheduling in accordance with the present invention are described with reference to the accompanying drawings, beginning with FIG. 1. FIG. 1 sets forth a network diagram of a data processing system for energy and performance optimizing job scheduling according to embodiments of the present invention. A ‘job’ as the term is used here may refer to any process that is to be executed (carried out) in a data processing system, where the execution of the job may increase temperature of the data processing system or increase power consumption of the data processing system. A job, for example, may be a thread of execution to be scheduled by an operating system and executed by a computer processor, a query of database, an input/output request, data communications to be processed, a memory read or write, or other task carried out in a data processing system. A schedule as the term is used here is a specification of an order of execution of more than one job.
  • The data processing system of FIG. 1 is implemented with automated computing machinery—a computer (152)—that includes at least one computer processor (156) or ‘CPU’ as well as random access memory (168) (‘RAM’) which is connected through a high speed memory bus (166) and bus adapter (158) to processor (156) and to other components of the computer (152). Although the data processing system in the example of FIG. 1 is depicted as a single computer (152) with a single CPU, readers of skill in the art will recognize that energy and performance optimizing job scheduling may be carried out in other forms of data processing systems: massively parallel super-computers, data centers, a computer with a multi-processor or co-processor, and so on as will occur to readers of skill in the art.
  • Stored in RAM (168) is a job scheduling module (126), a module of computer program instructions for scheduling jobs in an energy and performance optimizing manner. The job scheduling module (126) of FIG. 1 may schedule jobs in an energy and performance optimizing manner in accordance with embodiments of the present invention by first receiving and queuing (112) a plurality of jobs (116). The job scheduling module (126) may then characterize each of the jobs (116) as one of hot or cold, thereby specifying a hot job sub-queue and a cold job sub-queue. The job scheduling module (126) may characterize each of the jobs (116) as hot or cold in ways known to those of skill in the art. For example, each job may have a type—a write to memory, a read to memory, and so on, and each type of job may, in a thermal job profile, be associated with a characterization. As another example, a job may have been previously executed in the data processing system and data describing the power consumption or ambient temperature of the data processing system during execution of the job may have been recorded, indicating whether the job is ‘hot’ or ‘cold’ relative to a predetermined threshold.
  • The example job scheduling module (126) of FIG. 1 may then, iteratively for a number of schedules (114) of the jobs, until estimated performance and power characteristics of executing jobs in accordance with a schedule (114) meets predefined selection criteria (106): determine a schedule (114) for the plurality of jobs in dependence upon a user provided parameter (104), the characterization of each job as hot or cold, and an energy and performance optimizing heuristic (102); estimate performance and power characteristics (108) of executing the jobs (116) in accordance with the schedule (114); and determine whether the estimated performance and power characteristics (108) meet the predefined selection criteria (106). If the estimated performance and power characteristics (108) do not meet the predefined selection criteria (106), the job scheduling module (126) may adjust the user-provided parameter (104) and proceed to the next iteration. If the estimated performance and power characteristics (108) meet the predefined selection criteria (106), the job scheduling module (126) may then execute the jobs (116) in accordance with the schedule (114).
  • Performance characteristics may be any description of execution performance of a particular schedule—time to complete the entre set of jobs when executed in accordance with the particular schedule, average time of execution per job when executed in accordance with the particular schedule, and so on as will occur to readers of skill in the art.
  • Power characteristics may be any representation of energy consumption related to executing a particular schedule of jobs—average temperature of one or more elements of data processing system (e.g. CPU temperature) during execution of each job, peak temperature of one or more elements of the data processing system during execution of the jobs in accordance with the particular schedule, average power consumed per task, total power consumed in executing the jobs in accordance with the schedule, and so on as will occur to readers of skill in the art.
  • The term ‘predefined selection criteria’ as used in this specification refers to a specification of acceptable power and performance characteristics of a schedule. Predefined selection criteria may be specified in various ways, including for example, as a range of acceptable power characteristics in association with a range of acceptable performance characteristics, as a predefined threshold of power and performance characteristics, as a computer function that, when executed provides a Boolean result (e.g. ‘True’ or ‘False’), and so on as will occur to readers of skill in the art.
  • A heuristic as the term is used here refers to a schedule selection algorithm that operates at least partially in dependence upon a user-provided value. The term ‘heuristic’ generally, outside of the scope of this specification, refers to experience-based techniques for problem solving, learning, and discovery. Heuristic methods are used to come to an optimal solution as rapidly as possible. Part of this method is using a “rule of thumb,” an educated guess, an intuitive judgment, or common sense. The ‘user-provided value’ of the present specification is type of ‘educated guess’ of sorts—a starting point from which the schedule selection algorithm may determine or identify an optimal (or semi-optimal) schedule.
  • Also stored in RAM (168) is an operating system (154). Operating systems useful energy and performance optimizing job scheduling according to embodiments of the present invention include UNIX™, Linux™, Microsoft XP™, AIX™, IBM's i5/OS™, and others as will occur to those of skill in the art. The operating system (154) and job scheduling module (126) in the example of FIG. 1 are shown in RAM (168), but many components of such software typically are stored in non-volatile memory also, such as, for example, on a disk drive (170).
  • The computer (152) of FIG. 1 includes disk drive adapter (172) coupled through expansion bus (160) and bus adapter (158) to processor (156) and other components of the computer (152). Disk drive adapter (172) connects non-volatile data storage to the computer (152) in the form of disk drive (170). Disk drive adapters useful in computers for energy and performance optimizing job scheduling according to embodiments of the present invention include Integrated Drive Electronics (‘IDE’) adapters, Small Computer System Interface (‘SCSI’) adapters, and others as will occur to those of skill in the art. Non-volatile computer memory also may be implemented for as an optical disk drive, electrically erasable programmable read-only memory (so-called ‘EEPROM’ or ‘Flash’ memory), RAM drives, and so on, as will occur to those of skill in the art.
  • The example computer (152) of FIG. 1 includes one or more input/output (‘I/O’) adapters (178). I/O adapters implement user-oriented input/output through, for example, software drivers and computer hardware for controlling output to display devices such as computer display screens, as well as user input from user input devices (181) such as keyboards and mice. The example computer (152) of FIG. 1 includes a video adapter (209), which is an example of an I/O adapter specially designed for graphic output to a display device (180) such as a display screen or computer monitor. Video adapter (209) is connected to processor (156) through a high speed video bus (164), bus adapter (158), and the front side bus (162), which is also a high speed bus.
  • The exemplary computer (152) of FIG. 1 includes a communications adapter (167) for data communications with other computers (182) and for data communications with a data communications network (100). Such data communications may be carried out serially through RS-232 connections, through external buses such as a Universal Serial Bus (‘USB’), through data communications networks such as IP data communications networks, and in other ways as will occur to those of skill in the art. Communications adapters implement the hardware level of data communications through which one computer sends data communications to another computer, directly or through a data communications network. Examples of communications adapters useful for energy and performance optimizing job scheduling according to embodiments of the present invention include modems for wired dial-up communications, Ethernet (IEEE 802.3) adapters for wired data communications network communications, and 802.11 adapters for wireless data communications network communications.
  • The arrangement of computers and other devices making up the exemplary system illustrated in FIG. 1 are for explanation, not for limitation. Data processing systems useful according to various embodiments of the present invention may include additional servers, routers, other devices, and peer-to-peer architectures, not shown in FIG. 1, as will occur to those of skill in the art. Networks in such data processing systems may support many data communications protocols, including for example TCP (Transmission Control Protocol), IP (Internet Protocol), HTTP (HyperText Transfer Protocol), WAP (Wireless Access Protocol), HDTP (Handheld Device Transport Protocol), and others as will occur to those of skill in the art. Various embodiments of the present invention may be implemented on a variety of hardware platforms in addition to those illustrated in FIG. 1.
  • For further explanation, FIG. 2 sets forth a flow chart illustrating a further exemplary method for energy and performance optimizing job scheduling according to embodiments of the present invention. The method of FIG. 2 includes queuing (202) a plurality of jobs (116) and characterizing (204) each of the plurality of jobs (116) as one of hot or cold, thereby specifying a hot job sub-queue (216) and a cold job sub-queue (218). Queuing (202) a plurality of jobs (116) may be carried out in various ways including, for example, by inserting a description of each job into a list of jobs. Characterizing (204) each of the plurality of jobs (116) as one of hot or cold, thereby specifying a hot job sub-queue (216) and a cold job sub-queue (218) may be carried out in various ways, including for example, by job type in accordance with a predefined thermal profile of job types.
  • The method of FIG. 2 also includes a portion carried out iteratively for a plurality of schedules (114) of the plurality of jobs (116), until estimated performance and power characteristics (108) of executing jobs in accordance with a schedule meets predefined selection criteria (106). The iterative portion includes determining (206) a schedule (114) for the plurality of jobs (116) in dependence upon a user provided parameter (104), the characterization (204) of each job as hot or cold, and an energy and performance optimizing heuristic (102); estimating (208) performance and power characteristics (108) of executing the jobs (116) in accordance with the schedule (114); and determining (210) whether the estimated performance and power characteristics (108) meet the predefined selection criteria (106). If the estimated performance and power characteristics (108) do not meet the predefined selection criteria (106), adjusting (214) the user-provided parameter (214) for a next iteration; and if the estimated performance and power characteristics (108) meet the predefined selection criteria (106), executing (212) the plurality of jobs (116) in accordance with the determined schedule (114).
  • In the method of FIG. 2, determining (206) a schedule (114) for the plurality of jobs (116) in dependence upon a user provided parameter (104), the characterization (204) of each job as hot or cold, and an energy and performance optimizing heuristic (102) may be carried out in various ways. In one possible way determining a schedule may include: for each possible schedule of the plurality of jobs, calculating:

  • ω=λ(σcold−σ*cold)+(1−λ)(σhot−σ*hot); and
  • selecting the schedule minimum calculated ω value. In the above equation σcold is the average stretch value for the cold job sub-queue of the possible schedule for which ω is calculated where the average stretch value represents the sum of times to complete execution of each job, in the possible schedule, preceding the final job in the cold job sub-queue including the time to complete execution of the final job in the cold job sub-queue, normalized by the time to complete execution of the final job in the cold job sub-queue. In similar manner, σhot is the average stretch value for the hot job sub-queue of the possible schedule for which ω is calculated, the stretch value representing the sum of times to complete execution of each job, in the possible schedule, preceding the final job in the hot job sub-queue including the time to complete execution of the final job in the hot job sub-queue, normalized by the time to complete execution of the final job in the hot job sub-queue. In the example equation listed above, σ*cold is the sum of the times to complete execution of each job in the cold job sub-queue, in the order of the schedule and ignoring hot jobs. Likewise, σ*hot is the sum of the times to complete execution of each job in the hot job sub-queue, in the order of the schedule and ignoring cold jobs. In the example equation above, λ is the user provided parameter (104).
  • The times to complete execution of jobs with regard to σcold, σhot, σ*cold, and σ*hot may be calculated from estimations, from previously recorded data, and in other ways as will occur to readers of skill in the art.
  • When λ is equal to
  • p cold 2 p cold 2 + p hot 2 ,
  • where pcold is the average power consumption of execution the cold job sub-queue and phot is the average power consumption of executing the hot job sub-queue, the schedule selected by the heuristic is a shortest hottest job first schedule. In another embodiment, when λ is equal to
  • p hot 2 p cold 2 + p hot 2 ,
  • the schedule is a shortest coolest job first schedule. In this way, a user may selectively weigh a schedule to run cooler jobs first or hotter jobs first by careful selection of λ.
  • Determining (206) a schedule (114) for the plurality of jobs may be carried out in accordance with another heuristic in which, for each possible schedule of the plurality of jobs, determining (206) a schedule (114) include calculating:
  • ω = σ - ( 1 + α ) [ σ cold * α + σ hot * ] ;
  • and
    selecting, as the schedule for executing the plurality jobs, the schedule having a minimum calculated ω value. In this example equation—this example heuristic—σ is the sum of times to complete execution of the plurality of jobs in accordance with the schedule, σ*cold is the sum of the times to execute each job in the cold job sub-queue in accordance with the schedule; σ* hot is the sum of the times to execute each job in the hot job sub-queue in accordance with the schedule; and α is the user-provided value.
  • As described above, the plurality of jobs may be characterized as one of hot or cold. In another embodiment, however, energy and performance optimizing job scheduling in a data processing system in accordance with embodiments of the present invention may include categorizing each of the plurality of jobs into one or more sub-queues in dependence upon the jobs' power characteristics and in accordance with predefined categorization rules. That is, more than two sub-queues (hot or cold) may be employed, where each sub-queue is associated with an average power consumption of a set jobs or an average temperature associated with a set of jobs. Categorization rules, as recited here, specify ranges of power consumption or temperature for each sub-queue. In this way, energy and performance optimizing job scheduling in accordance with embodiments of the present invention may be controlled in a fine-grain manner.
  • In view of the explanations set forth above, readers will recognize that the benefits of energy and performance optimizing job scheduling according to embodiments of the present invention include:
      • Selecting a job schedule that provides optimal energy and performance characteristics in an efficient, optimal manner;
      • Providing a user some control over job schedule selection with user selectable weighting parameters; and
      • Other benefits as will occur to readers of skill in the art.
  • Exemplary embodiments of the present invention are described largely in the context of a fully functional computer system for energy and performance optimizing job scheduling. Readers of skill in the art will recognize, however, that the present invention also may be embodied in a computer program product disposed upon computer readable storage media for use with any suitable data processing system. Such computer readable storage media may be any storage medium for machine-readable information, including magnetic media, optical media, or other suitable media. Examples of such media include magnetic disks in hard drives or diskettes, compact disks for optical drives, magnetic tape, and others as will occur to those of skill in the art. Persons skilled in the art will immediately recognize that any computer system having suitable programming means will be capable of executing the steps of the method of the invention as embodied in a computer program product. Persons skilled in the art will recognize also that, although some of the exemplary embodiments described in this specification are oriented to software installed and executing on computer hardware, nevertheless, alternative embodiments implemented as firmware or as hardware are well within the scope of the present invention.
  • As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.
  • Any combination of one or more computer readable medium(s) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
  • A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
  • Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
  • Aspects of the present invention are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
  • These computer program instructions may also be stored in a computer readable medium that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
  • The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
  • The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
  • It will be understood from the foregoing description that modifications and changes may be made in various embodiments of the present invention without departing from its true spirit. The descriptions in this specification are for purposes of illustration only and are not to be construed in a limiting sense. The scope of the present invention is limited only by the language of the following claims.

Claims (6)

1. A method of energy and performance optimizing job scheduling in a data processing system, the method comprising:
queuing a plurality of jobs;
characterizing each of the plurality of jobs as one of hot or cold, thereby specifying a hot job sub-queue and a cold job sub-queue;
iteratively for a plurality of schedules of the plurality of jobs, until estimated performance and power characteristics of executing jobs in accordance with a schedule meets predefined selection criteria:
determining a schedule for the plurality of jobs in dependence upon a user provided parameter, the characterization of each job as hot or cold, and an energy and performance optimizing heuristic;
estimating performance and power characteristics of executing the jobs in accordance with the schedule; and
determining whether the estimated performance and power characteristics meet the predefined selection criteria;
if the estimated performance and power characteristics do not meet the predefined selection criteria, adjusting the user-provided parameter for a next iteration; and
if the estimated performance and power characteristics meet the predefined selection criteria, executing the plurality of jobs in accordance with the determined schedule.
2. The method of claim 1 wherein determining a schedule for the plurality of jobs in dependence upon a user provided parameter, the characterization of each job as hot or cold, and an energy and performance optimizing heuristic further comprises:
for each possible schedule of the plurality of jobs, calculating:

ω=λ(σcold−σ*cold)+(1−λ)(σhot−σ*hot); and
selecting the schedule having a minimum calculated w value, wherein:
σcold comprises the average stretch value for the cold job sub-queue of the possible schedule for which w is calculated, the average stretch value representing the sum of times to complete execution of each job, in the possible schedule, preceding the final job in the cold job sub-queue including the time to complete execution of the final job in the cold job sub-queue, normalized by the time to complete execution of the final job in the cold job sub-queue;
σhot comprises the average stretch value for the hot job sub-queue of the possible schedule for which ω is calculated, the stretch value representing the sum of times to complete execution of each job, in the possible schedule, preceding the final job in the hot job sub-queue including the time to complete execution of the final job in the hot job sub-queue, normalized by the time to complete execution of the final job in the hot job sub-queue;
σ*cold comprises the sum of the times to complete execution of each job in the cold job sub-queue;
σ*hot comprises the sum of the times to complete execution of each job in the hot job sub-queue; and
λ comprises the user provided parameter.
3. The method of claim 2 wherein:
λ comprises
p cold 2 p cold 2 + p hot 2 ,
and the schedule comprises a shortest hottest job first schedule, wherein
pcold comprises the average power consumption of execution the cold job sub-queue; and
phot comprises the average power consumption of executing the hot job sub-queue.
4. The method of claim 2 wherein:
λ comprises
p hot 2 p cold 2 + p hot 2 ,
and the schedule comprises a shortest coolest job first schedule, wherein
pcold comprises the average power consumption of execution the cold job sub-queue; and
phot comprises the average power consumption of executing the hot job sub-queue.
5. The method of claim 1 wherein determining a schedule for the plurality of jobs in dependence upon a user provided parameter, the characterization of each job as hot or cold, and an energy and performance optimizing heuristic further comprises:
for each possible schedule of the plurality of jobs, calculating:
ω = σ - ( 1 + α ) [ σ cold * α + σ hot * ] ;
and
selecting, as the schedule for executing the plurality jobs, the schedule having a minimum calculated ω value, wherein:
σ comprises the sum of times to complete execution of the plurality of jobs in accordance with the schedule;
σ*cold comprises the sum of the times to execute each job in the cold job sub-queue in accordance with the schedule;
σ*hot comprises the sum of the times to execute each job in the hot job sub-queue in accordance with the schedule; and
α comprises the user-provided value.
6-18. (canceled)
US13/484,877 2010-12-07 2012-05-31 Energy And Performance Optimizing Job Scheduling Abandoned US20120240123A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US12/961,633 US8776069B2 (en) 2010-12-07 2010-12-07 Energy and performance optimizing job scheduling
US13/484,877 US20120240123A1 (en) 2010-12-07 2012-05-31 Energy And Performance Optimizing Job Scheduling

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US13/484,877 US20120240123A1 (en) 2010-12-07 2012-05-31 Energy And Performance Optimizing Job Scheduling

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US12/961,633 Continuation US8776069B2 (en) 2010-12-07 2010-12-07 Energy and performance optimizing job scheduling

Publications (1)

Publication Number Publication Date
US20120240123A1 true US20120240123A1 (en) 2012-09-20

Family

ID=46163507

Family Applications (2)

Application Number Title Priority Date Filing Date
US12/961,633 Active 2031-10-20 US8776069B2 (en) 2010-12-07 2010-12-07 Energy and performance optimizing job scheduling
US13/484,877 Abandoned US20120240123A1 (en) 2010-12-07 2012-05-31 Energy And Performance Optimizing Job Scheduling

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US12/961,633 Active 2031-10-20 US8776069B2 (en) 2010-12-07 2010-12-07 Energy and performance optimizing job scheduling

Country Status (1)

Country Link
US (2) US8776069B2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9588577B2 (en) 2013-10-31 2017-03-07 Samsung Electronics Co., Ltd. Electronic systems including heterogeneous multi-core processors and methods of operating same

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8631411B1 (en) 2009-07-21 2014-01-14 The Research Foundation For The State University Of New York Energy aware processing load distribution system and method
WO2014052843A1 (en) * 2012-09-28 2014-04-03 Cycle Computing, Inc. Real time optimization of compute infrastructure in a virtualized environment
CN104657666B (en) * 2013-11-21 2019-04-02 腾讯科技(深圳)有限公司 A kind of optimization method and device of terminal operating environment
GB2525917A (en) * 2014-05-09 2015-11-11 Arm Ip Ltd Energy-based scheduling of operations to be executed by a data processing apparatus
US9785481B2 (en) * 2014-07-24 2017-10-10 Qualcomm Innovation Center, Inc. Power aware task scheduling on multi-processor systems
US9361154B2 (en) 2014-09-30 2016-06-07 International Business Machines Corporation Tunable computerized job scheduling
US9983907B2 (en) 2015-10-27 2018-05-29 International Business Machines Corporation Resource-aware backfill job scheduling
CN106408126B (en) * 2016-09-23 2018-01-30 广东技术师范学院 Oriented three-stage energy optimization method collecting data concurrency

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050216222A1 (en) * 2004-03-29 2005-09-29 Sony Computer Entertainment Inc. Methods and apparatus for achieving thermal management using processing task scheduling
US20060010449A1 (en) * 2004-07-12 2006-01-12 Richard Flower Method and system for guiding scheduling decisions in clusters of computers using dynamic job profiling
US20080209243A1 (en) * 2005-05-03 2008-08-28 International Business Machines Corporation Scheduling processor voltages and frequencies based on performance prediction and power constraints
US20090064164A1 (en) * 2007-08-27 2009-03-05 Pradip Bose Method of virtualization and os-level thermal management and multithreaded processor with virtualization and os-level thermal management
US20100287396A1 (en) * 2007-12-28 2010-11-11 Freescale Semiconductor, Inc. Data processor performance prediction
US20110078479A1 (en) * 2009-09-25 2011-03-31 Vogman Viktor D Method and apparatus for reducing server power supply size and cost
US8555283B2 (en) * 2007-10-12 2013-10-08 Oracle America, Inc. Temperature-aware and energy-aware scheduling in a computer system

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7360102B2 (en) 2004-03-29 2008-04-15 Sony Computer Entertainment Inc. Methods and apparatus for achieving thermal management using processor manipulation
US7363519B2 (en) * 2004-12-24 2008-04-22 Gateway Inc. Method and apparatus for power management by user needs

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050216222A1 (en) * 2004-03-29 2005-09-29 Sony Computer Entertainment Inc. Methods and apparatus for achieving thermal management using processing task scheduling
US20060010449A1 (en) * 2004-07-12 2006-01-12 Richard Flower Method and system for guiding scheduling decisions in clusters of computers using dynamic job profiling
US20080209243A1 (en) * 2005-05-03 2008-08-28 International Business Machines Corporation Scheduling processor voltages and frequencies based on performance prediction and power constraints
US20090064164A1 (en) * 2007-08-27 2009-03-05 Pradip Bose Method of virtualization and os-level thermal management and multithreaded processor with virtualization and os-level thermal management
US8555283B2 (en) * 2007-10-12 2013-10-08 Oracle America, Inc. Temperature-aware and energy-aware scheduling in a computer system
US20100287396A1 (en) * 2007-12-28 2010-11-11 Freescale Semiconductor, Inc. Data processor performance prediction
US20110078479A1 (en) * 2009-09-25 2011-03-31 Vogman Viktor D Method and apparatus for reducing server power supply size and cost

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9588577B2 (en) 2013-10-31 2017-03-07 Samsung Electronics Co., Ltd. Electronic systems including heterogeneous multi-core processors and methods of operating same

Also Published As

Publication number Publication date
US20120144394A1 (en) 2012-06-07
US8776069B2 (en) 2014-07-08

Similar Documents

Publication Publication Date Title
US7302595B2 (en) Method and apparatus for dynamic power management in a processor system
EP1835426A1 (en) Estimating software power consumption
US7894191B2 (en) Fan rotation control method, fan rotation control system, and fan rotation control program
US8914515B2 (en) Cloud optimization using workload analysis
US20040216013A1 (en) Methods and apparatus to detect patterns in programs
US20070038987A1 (en) Preprocessor to improve the performance of message-passing-based parallel programs on virtualized multi-core processors
US9875135B2 (en) Utility-optimized scheduling of time-sensitive tasks in a resource-constrained environment
Ren et al. Hierarchical adaptive dynamic power management
CN102959510B (en) A method for computer modeling of resource consumption and power systems, and
US9063785B2 (en) Temperature-based thread scheduling
EP1734436A1 (en) Automatically controlling processor mode of multi-core processor
US8996890B2 (en) Method for power conservation in virtualized environments
US7069189B2 (en) Method and apparatus for controlling multiple resources using thermal related parameters
Tsai et al. A hyper-heuristic scheduling algorithm for cloud
US20070124094A1 (en) Histogram difference method and system for power/performance measurement and management
US20060178764A1 (en) Method and apparatus for autonomic policy-based thermal management in a data processing system
US8041521B2 (en) Estimating power consumption of computing components configured in a computing system
US9256428B2 (en) Load latency speculation in an out-of-order computer processor
US8527997B2 (en) Energy-aware job scheduling for cluster environments
US8689220B2 (en) Job scheduling to balance energy consumption and schedule performance
US8104030B2 (en) Mechanism to restrict parallelization of loops
US9015501B2 (en) Structure for asymmetrical performance multi-processors
KR20110069707A (en) Method and system for optimizing virtual storage size
US20110113270A1 (en) Dynamic Voltage and Frequency Scaling (DVFS) Control for Simultaneous Multi-Threading (SMT) Processors
US8589932B2 (en) Data processing workload control

Legal Events

Date Code Title Description
AS Assignment

Owner name: LENOVO ENTERPRISE SOLUTIONS (SINGAPORE) PTE. LTD.,

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:INTERNATIONAL BUSINESS MACHINES CORPORATION;REEL/FRAME:034194/0111

Effective date: 20140926

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION