System and method of providing a fixed time offset based dedicated co-allocation of a common resource set

PRIORITY DATA

0001This non-provisional patent application claims priority to U.S. Provisional Application No. 60/651,269, filed Feb. 9, 2005, the contents of which are incorporated herein by reference.

BACKGROUND OF THE INVENTION

00021. Field of the Invention

0003The present invention relates to a resource management system and more specifically to a system and method of providing a fixed time offset-based dedicated co-allocation of a common resource set in the context of managing resources within a compute environment such as a grid or a cluster.

00042. Introduction

0005Managers of clusters desire maximum return on investment often meaning high system utilization and the ability to deliver various qualities of service to various users and groups. A cluster is typically defined as a parallel computer that is constructed of commodity components and runs as its system software commodity software. A cluster contains nodes each containing one or more processors, memory that is shared by all of the processors in the respective node and additional peripheral devices such as storage disks that are connected by a network that allows data to move between nodes. A cluster is one example of a compute environment. Other examples include a grid, which is loosely defined as a group of clusters, and a computer farm which is another organization of computer for processing.

0006General background information on clusters and grids may be found in several publications. See, e.g., <i>Grid Resource Management, State of the Art and Future Trends, Jarek Nabrzyski, Jennifer M. Schopf, and Jan Weglarz, Kluwer Academic Publishers, </i>2004; and <i>Beowulf Cluster Computing with Linux, </i>edited by William Gropp, Ewing Lusk, and Thomas Sterling, Massachusetts Institute of Technology, 2003.

0007Often a job will include several requirements and may be dependent upon another job. An illustrative job may be that every night a television station needs to perform a weather study for its weather reports. The station may contract with an owner or operator of a cluster or a grid for computing time from 2:00 AM to 4:00 AM to utilize compute environment resources to run the analysis. The analysis may involve reserving the resources and include several jobs that require different kinds of resources within the compute environment. For example, a first job may require several hours of processing time, but also be dependent upon a second job to perform data staging or preparation of data prior to the beginning of the first job. Where these two jobs are inter-related and require the consumption of several different types of resources within a cluster or a grid, there is needed in the art for way to maximize the use of resources while being able to process jobs requiring disparate but interrelated resources.

SUMMARY OF THE INVENTION

0008Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The features and advantages of the invention may be realized and obtained by means of the instruments and combinations particularly pointed out in the appended claims. These and other features of the present invention will become more fully apparent from the following description and appended claims, or may be learned by the practice of the invention as set forth herein.

0009The invention herein relates to systems, methods and computer-readable media for optimizing the resources used in a compute environment such as a cluster or a grid. The invention enables an evaluation of all resources in an instance within a single node and then viewing the resources at a cluster level or as an aggregate of resources level (several clusters). The method involves considering a single node and stepping through all jobs or all requirements and/or resource requests on that given node and determining the resource availability for each resource requester within that node. Then the system arrives at a composite availability for that node before it analyses a subsequence node.

0010The method embodiment of the invention relates to at a method of managing resources within a computing environment comprising a group of computing devices. The method comprises, for each node in the compute environment: (1) traversing a list jobs having a fixed time relationship, wherein for each job in the list, the following steps occur: a. obtaining a range list of available timeframes for each job; b. converting each availability timeframe to a start range; c. shifting the resulting start range in time by a job offset; d. for a first job, copying the resulting start range into a node range; and e. for all subsequent jobs, logically AND'ing the start range with the node range. Next, the method comprises logically OR'ing the node range with a global range, generating a list of acceptable resources on which to start and the timeframe at which to start and creating reservations according to the list of acceptable resources for the resources in the group of computing devices and associated job offsets. The reservation will typically entail the co-allocation of resources according to the analysis done as disclosed herein.

0011In addition to the method embodiment, the invention includes embodiments such as a system (whether it is a single computing device or a group of compute devices in a compute environment) and a computer-readable medium storing instructions for controlling a computing and/or a compute environment as set forth in the method.

0012As can be seen from the above, the invention involves, for interrelated jobs that consume disparate resources, performing an analysis of the compute environment in order to maximize the establishment of reservation of compute resources to process the jobs.

BRIEF DESCRIPTION OF THE DRAWINGS

0013In order to describe the manner in which the above-recited and other advantages and features of the invention can be obtained, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments thereof which are illustrated in the appended documents and drawings. Understanding that these drawings depict only typical embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings.

0014<figref idref="DRAWINGS">FIG. 1A</figref> illustrates the basic concept of the present invention;

0015<figref idref="DRAWINGS">FIG. 1B</figref> illustrates further some of the concepts of the present invention;

0016<figref idref="DRAWINGS">FIG. 2</figref> illustrates the basic hardware components according to an embodiment of the invention; and

0017<figref idref="DRAWINGS">FIG. 3</figref> illustrates a method embodiment of the invention.

DETAILED DESCRIPTION OF THE INVENTION

0018Various embodiments of the invention are discussed in detail below. While specific implementations are discussed, it should be understood that this is done for illustration purposes only. A person skilled in the relevant art will recognize that other components and configurations may be used without parting from the spirit and scope of the invention. The present invention relates to resource reservations in the context of a cluster environment. The cluster may be operated by a hosting facility, hosting center, a virtual hosting center, data center, grid, cluster and/or utility-based computing environments.

0019Every reservation consists of three major components: a set of resources, a timeframe, and an access control list (ACL). Additionally, a reservation may also have a number of optional attributes controlling its behavior and interaction with other aspects of scheduling. A reservation's ACL specifies which jobs can use the reservation. Only jobs which meet one or more of a reservation's access criteria are allowed to use the reserved resources during the reservation timeframe. The reservation access criteria comprises, in one example, at least following: users, groups, accounts, classes, quality of service (QOS) and job duration. A job may be any venue or end of consumption of resource for any broad purpose, whether it be for a batch system, direct volume access or other service provisioning.

0020A workload manager, or scheduler, will govern access to the compute environment by receiving requests for reservations of resources and creating reservations for processing jobs. A workload manager functions by manipulating five primary, elementary objects. These are jobs, nodes, reservations, QOS structures, and policies. In addition to these, multiple minor elementary objects and composite objects are also utilized. These objects are also defined in a scheduling dictionary. A “job” as used herein is a general term in the sense that a job may include a number of subjobs which also may be referred to simply as jobs. Using the above example of a weather analysis job that runs on a cluster environment, consider that the weather analysis is a “job” but requires and will consume several different types of resources within the environment, such as data staging (disk space), processor time, bandwidth requirements and so forth. Each request for individual resources may be considered or termed a “job.” The present invention specifically relates to the scenario where there are at least two jobs that have an interrelationship in some fashion. For example, the data staging job needs to begin processing a certain amount of time prior to the start of the job that consumes processing time.

0021A workload manager may operate on a single computing device or multiple computing devices to manage the workload of a compute environment. The “system” embodiment of the invention may comprise a computing device that includes the necessary hardware and software components to enable a workload manager or a software module performing the steps of the invention. Such a computing device may include such known hardware elements as one or more central processors, random access memory (RAM), read-only memory (ROM), storage devices such as hard disks, communication means such as a modem or a card to enable networking with other computing devices, a bus that provides data transmission between various hardware components, a keyboard, a display, an operating system and so forth. There is no restriction that the particular system embodiment of the invention has any specific hardware components and any known or future developed hardware configurations are contemplated as within the scope of the invention when the computing device operates as is claimed.

0022We now turn to the details of the invention which relate to managing a compute environment in the context of maximizing usage of resources where two or more jobs require disparate but interrelated resources. <figref idref="DRAWINGS">FIG. 1A</figref> illustrates for 4 nodes within a cluster or a grid wherein a fixed time relationship between the jobs is created which allows specification and enforcement of a fixed time offset relationship <b>180</b> between each of the jobs resulting in at least one of a job overlap, juxtaposition or an offset-based relationship. An aspect of the invention involves establishing a forced relationship in space so that all jobs allocate the same resource objects while dedicating subsets of the resource's consumable resources to themselves. The resources mentioned herein relate to the various resources used within a cluster of computer nodes. For example, processing power, data storage, bandwidth in a network, licensing of software, RAM, and so forth. The example will relate to two resources of processor power and data storage but the invention may relate to any two different types of resource within the compute environment. Furthermore, the invention relates to at least two jobs but may involve two or more jobs requiring two or more disparate resources.

0023<figref idref="DRAWINGS">FIG. 1A</figref> shows a portion of a computing environment such as a cluster or a grid. The compute environment may have tens, hundreds, thousands (or more) processors or nodes within the environment. Illustrated therefore is a representative computing environment in which the concept of the invention may be applied. <figref idref="DRAWINGS">FIG. 1A</figref> shows four nodes <b>116</b>, <b>118</b>, <b>120</b>, <b>122</b> each having two types of resources: computer processor resources (P) and disk storage/data staging resources (D). There may be any number of nodes in which the invention may be operable and the two types of resources are only illustrative. For example, other types of resources could also be shown in a similar fashion. Assume that a job <b>1</b> requires a certain number of hours of computer processing time. Also assume that there is an associated job <b>2</b> that requires some amount of disk space time. The relationship between these is flexible. In other words, there may be a master job that has two or more sub-jobs (jobs <b>1</b> and <b>2</b>) or resource requests for processor time, disk space, etc. It is not a requirement in consuming resources on the compute environment that there be more than one job or resource request. However, it is the context of the present invention where disparate types of resources are interrelated. Jobs or resource requests that have a highest priority may be provided first access to all available resources.

0024<figref idref="DRAWINGS">FIG. 1A</figref> shows several features on node <b>1</b><b>116</b>. This figure shows an analysis and some of the steps of the invention. Feature <b>126</b> may represent used or unavailable resources at a particular time. The horizontal axis in <figref idref="DRAWINGS">FIGS. 1A and 1B</figref> relates to time with, typically, the “0 hr” time as current time. Features <b>130</b>, <b>132</b> and <b>102</b> represent available timeframes for job <b>1</b> to utilize the processor of node <b>1</b>. Features <b>138</b>, <b>140</b> and <b>136</b> represent available timeframes for utilizing disk space associated with job <b>2</b>. These bars shown as associated with node <b>1</b><b>116</b> are not reservations but represent available time frames on which a reservation could be made. Thus, for job <b>1</b>, available timeframes are shown at which the job could start include at 1 hr from the current time, two hours from the current time and three hours from the current time. Similarly, time frames in which the job <b>2</b> could start are shown in features <b>138</b>, <b>140</b> and <b>136</b>.

0025The graph of <figref idref="DRAWINGS">FIG. 1A</figref> is used to illustrate the resources (on the vertical axis) versus time (on the horizontal axis) for several nodes in the compute environment. It illustrates how the available timeframes for the jobs that utilize disparate types of resources will be processed to analyze the compute environment and maximize the resulting reservation of the compute environment to consume resources when the jobs process. Utilizing these features of the invention help to increase the efficiency of the compute environment.

0026Feature <b>150</b> represents a logical AND'ing of the available timeframes for processors and disk space and thus represents a listing of available timeframes for that node. Feature <b>152</b> represents a conversion of each availability timeframe into a start range. The system performs some analysis on the listing of available time ranges to determine given parameters such as when each job can start, and how long each job is, and other parameters, the actual available start ranges <b>152</b>A, <b>152</b>B for jobs may not be the same as the available timeframes <b>150</b>. For example, to generate the start range, the system utilizes a wall time which is applied to the availability timeframes to generate the start range. The wall time relates to the amount of time that a particular resource will be required to process a job. Thus, if an availability time (<b>130</b><figref idref="DRAWINGS">FIG. 1B</figref>) runs an hour, but the wall time for that resource will be required is ½ hour, then the start time associated with that particular availability timeframe must be for ½ hour as is represented by <b>130</b>A. Note the x's below several of the timeframes in <b>150</b> which illustrate that these are disqualified as time ranges for jobs to actually consume resources within the compute environment.

0027Node <b>2</b><b>118</b> is shown with unavailable resources <b>128</b> and available timeframes <b>154</b>, <b>156</b>, <b>158</b>, <b>160</b> for a resource type of a processor for a job, and available timeframes for disk space at <b>162</b>, <b>164</b> and <b>166</b> for another job. These timeframes may be for job <b>1</b> and job <b>2</b> respectively if these jobs will be utilizing more than one node. Feature <b>170</b> represents the available timeframes for node <b>2</b><b>118</b> which is an AND'ing of the available timeframes associated with the different resource types. Feature <b>172</b>A, <b>172</b>B and <b>172</b>C represent the start range for node <b>2</b> which is the result of an analysis of when jobs can actually start and complete given all other relative parameters. Node <b>3</b><b>120</b> is shown with blocks <b>174</b> and <b>176</b> showing unavailable resources. As can be appreciated, other resource types may be added to this concept, such as bandwidth, RAM, and so forth. The use of the processors and disk space is illustrative only.

0028Having introduced some of the features of <figref idref="DRAWINGS">FIG. 1A</figref>, we further discuss the overall concept of the invention. The process involves selecting a resource (which may be a node as in node <b>1</b><b>116</b> of <figref idref="DRAWINGS">FIG. 1A</figref>, or a particular resource such as a processor or disk space etc.) and then traversing all of the fixed time relationship jobs associated with that resource, starting with a first job, and then processing a second job in comparison to the first, and then a third job and so forth until all the jobs have been processed. Then the next resource and processes the jobs associated with that resource and then blends the processing of the various resources each having its associated jobs. Then a global analysis is done to blend the job-level and resource-level analysis in order to generate a listing of acceptable resource at which to start jobs and the time frame at which to start those jobs. These nested processing loops enable a user to receive the maximized listing of resources and available times to start. Thus, when the system walks through the analysis for a resource (like a node), the system identifies the bounds, time and quantity of the resource or resources on the node. Then the system walks through again and focuses on the particular range and identifies the details about how the system came up with the details of availability and start times, etc. in the first place. After the analysis, if the system creates a reservation to process the job, the system knows that the reservation will enable the compute environment to adequately process the at least two jobs with their offsets and disparate resource types.

0029A user interface may include the ability of a user to select from the list of acceptable resources and starting times or the system may automatically pick a particular time such as the first timeframe at which the jobs can process. The global analysis provides a global resource availability range which represents availability of all nodes in the compute environment, such as a cluster, which can co-allocate all the resources associated with the jobs.

0030In one aspect of the invention, the available timeframes shift. When this shift occurs, all of the available time frames <b>130</b>, <b>132</b>, <b>102</b> are equally shifted in time by the offset. In our example, all of these available timeframes are shifted back in time ½ hour. It does not matter which resource type is shifted and in which direction. In other words, the disk space available timeframes <b>138</b>, <b>140</b> and <b>136</b> may be shifted to the right by the offset of ½ hour. The only requirement is that the system track which availability timeframes associated with which resource type are shifted and which are not.

0031Returning to <figref idref="DRAWINGS">FIG. 1A</figref> and <figref idref="DRAWINGS">FIG. 1B</figref>, the start range <b>152</b>A, <b>152</b>B is shifted by a certain amount which is preferably the specified job offset <b>180</b>. This shifting is illustrated in <figref idref="DRAWINGS">FIG. 1B</figref>. The job offset represents a different in time between the start of a first job associated with a first resource type and the start of a second job consuming a different resource type but that is connected to the first job. For example, first job may be job <b>130</b> that starts at <b>1</b> hour and job <b>138</b> that starts ½ hour before job <b>130</b>. In this case, the job offset would be ½ hour. This job offset is an offset between any two job types. Therefore, it is not just between a job associated with disk space and a job associated with consuming processors. It may be an offset between any two associate jobs or resource requests of two resource types. <figref idref="DRAWINGS">FIG. 1B</figref> shows that all of the range list timeframes shift together. This is the preferable way to perform this shift. Each may separately be shifted as well or be shifted in different directions based on various parameters, such as, for example, the particular offset relationship between each range and an associated timeframe from a different resource. The shifted data whether it be from the start range or the available time frames for a particular job are then copied into a node range.

0032Next, a node range is generated which reflects available resources associated within a node. The copying of the shifted start range (or shifted availability timeframes or other data that may be shifted) into the node range is performed to a first job. For all subsequent jobs, the system logically AND's the respective job's start range with the node range. The start range in this case reflects, in one aspect of the invention, the start range for the respective subsequent job that is being processed. This may reflect the start range generated for each subsequent job which is AND'd together with the one node range or it may relate to different start ranges and different node ranges. Thus, in one aspect of the invention, the node range begins with being the start range copied from the first job. Then, each of the subsequence jobs, the start range for that particular job is AND'd with the node range and the node range thus becomes more constricted. Once all the jobs have been processed, the node range represents the range of available time all resources are available within a given node.

0033The system continues to process jobs within a node (or a resource) and then move to a next node (resource) in a compute environment. In this regard there are several nested loops of processing a node or a particular resource, and jobs or resource requests therein, and then move on to the next node or resource. Once all of the jobs associated with a resource or a node, such as all jobs on node <b>1</b><b>116</b>, and in one aspect of the invention after all nodes have been processed according to the steps above, the system logically OR's the node range with a global range. The global range reflects the timeframes and resource quantities available to the overall grouping of jobs where all jobs can simultaneously consume their requested resources at the specified offsets on the same set of allocated resources. Thus, the global range may be looking at timeframes and resources available on a cluster, grid or other grouping of compute resources. From this OR'ing of the node range with a global range, the system can generate a list of acceptable resources on which to start jobs and the timeframe at which to start. Once that list is generated, the workload manager or other management software generates a reservation for resources according to the list of acceptable resources and associated job offsets.

0034<figref idref="DRAWINGS">FIG. 1C</figref> illustrates in another way the process of an aspect of the invention. As with <figref idref="DRAWINGS">FIGS. 1A and 1B</figref>, this shows two resources (processor and disk space) of the many resources that may be associated with a node <b>116</b> in a compute environment. The first row shows the availability timeframes for two jobs for resources on node <b>1</b>. The features shown correspond to those of <figref idref="DRAWINGS">FIG. 1A</figref>. The next row shows start ranges for each availability time frame. For example, start ranges <b>130</b>A, <b>132</b>A and <b>102</b>A correspond respectively to the availability time frames <b>130</b>, <b>132</b> and <b>102</b> and represent the start range for each of the time frames. As mentioned above, the start range represents, in one aspect, a possible time frame at which the job could start. Thus, the start range is more restrictive than the availability range. The start ranges for the disk resource are shown as <b>138</b>A, <b>140</b>A and <b>136</b>A.

0035The next row illustrates the shifting of the start ranges in time by, for example, the offset <b>180</b>. Thus, start ranges <b>120</b>A, <b>132</b>A and <b>102</b>A are all shifted to the left in time by the offset <b>180</b>. Any time period may be chosen, and the other resource start ranges <b>138</b>A, <b>140</b>A and <b>136</b>A could also be shifted by a time, such as time <b>180</b>, to the right to match up. Whichever group of start ranges is shifted may be shifted together as a unit as shown.

0036The next row illustrates a node range <b>182</b>A, <b>182</b>B, <b>182</b>C. This represents the range of available time all resources contained within a given node are available. This may be generated in several different ways such as through logical AND or OR operations associated with the various start ranges. For example, shown in the Node Range row of <figref idref="DRAWINGS">FIG. 1C</figref> is the logical AND'ing of the shifted start ranges for the resource of processor and the start ranges for the disk storage. There may be other ways to generate the node range. As can be appreciated, the node range represents a more constraining listing of times than the start ranges.

0037The next row <b>190</b> of <figref idref="DRAWINGS">FIG. 1C</figref> represents a global range <b>184</b>A, <b>184</b>B, <b>184</b>C and <b>184</b>D shows show the timeframes and resource quantities available to the overall grouping of jobs. Row <b>192</b> shows a global list <b>186</b>A, <b>186</b>B and <b>186</b>C which show a list of acceptable resources on which to start jobs and the timeframe at which to start. This may be generated in several different ways. Shown in <figref idref="DRAWINGS">FIG. 1C</figref> is a logical OR'ing of a node range and the global range. Finally, row <b>194</b> shows a reservation <b>188</b> of resources. As mentioned herein, a user may select this reservation or it may be automatically generated according to a set of parameters. The reservation <b>188</b> reflects the generation of a reservation associated with the global listing <b>186</b>B of available resources. With the reservation <b>188</b>, the job that needs to be submitted to consume resources will be established with its necessary offset between disparate resources and be processed in an efficient manner.

0038We now turn to a general description of a computing device according to an embodiment of the invention. With reference to <figref idref="DRAWINGS">FIG. 2</figref>, an exemplary system for implementing the invention includes a general purpose computing device <b>200</b>, including a processing unit (CPU) <b>220</b>, a system memory <b>230</b>, and a system bus <b>210</b> that couples various system components including the system memory <b>230</b> to the processing unit <b>220</b>. The system bus <b>210</b> may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The system may also include other memory such as read only memory (ROM) <b>240</b> and random access memory (RAM) <b>250</b>. A basic input/output (BIOS), containing the basic routine that helps to transfer information between elements within the computing device <b>200</b>, such as during start-up, is typically stored in ROM <b>240</b>. The computing device <b>200</b> further includes storage means such as a hard disk drive <b>260</b>, a magnetic disk drive, an optical disk drive, tape drive or the like. The storage device <b>260</b> is connected to the system bus <b>210</b> by a drive interface. The drives and the associated computer-readable media provide nonvolatile storage of computer readable instructions, data structures, program modules and other data for the computing device <b>200</b>. The basic components are known to those of skill in the art and appropriate variations are contemplated depending on the type of device, such as whether the device is a small, handheld computing device, a desktop computer, or a computer server.

0039Although the exemplary environment described herein employs the hard disk, it should be appreciated by those skilled in the art that other types of computer readable media which can store data that is accessible by a computer, such as magnetic cassettes, flash memory cards, digital video disks, Bernoulli® cartridges, random access memories (RAMs) read only memory (ROM), and the like, may also be used in the exemplary operating environment. The system above provides an example server or computing device that may be utilized and networked with a cluster, clusters or a grid to manage the resources according to the principles set forth herein. In this case, the system aspect of the invention becomes the computing environment having multiple processors and nodes as is the case in a cluster or a grid. It is also recognized that other hardware configurations may be developed in the future upon which the method may be operable.

0040<figref idref="DRAWINGS">FIG. 3</figref> illustrates the method embodiment of the invention. The method relates to scheduling multiple jobs with a fixed relationship in both time and space. A method consisting of two or more jobs where each job has its own duration, resource requirements, allocated resources and actions. Other parameters may also be associated with each job. The method establishes a fixed time relationship between the jobs which allows specification and enforcement of a fixed time offset relationship between each of the jobs resulting in a job overlap, juxtaposition or an offset-based relationship. Further, the method comprises the forced relationship in space so that all jobs allocate the same resource objects while dedicating subsets of the resource's consumable resources to themselves.

0041As shown in <figref idref="DRAWINGS">FIG. 3</figref>, the method comprises determining whether a job has a highest priority, and if yes, providing first access to all currently available resources (<b>302</b>), traversing a list of available resources (<b>304</b>), for each resource, traversing a list of fixed time relationship jobs (<b>306</b>). In this case, each resource may refer to a particular resource such as processor or disk space or may refer to a node such as node <b>1</b>, <b>2</b> or <b>3</b> in <figref idref="DRAWINGS">FIG. 1A</figref>. The method further comprises obtaining a range list of available timeframes for each job(<b>308</b>), converting each availability range to a start range (<b>310</b>), shifting the resulting start range (or other data) in time by the specified amount of time such as by the job offset (<b>312</b>), for a first job, copying the resulting start range into a node range (<b>314</b>), for all subsequent jobs, logically AND'ing the start range with the node range (<b>316</b>), once all jobs have been processed, logically OR'ing the node range with a global range (<b>318</b>), and once all nodes have been processed, the resulting global range reflects the timeframes and resource quantities available to the overall grouping of jobs where all jobs can simultaneously consume their requested resources at the specified offsets on the same set of allocated resources (<b>320</b>). Based on the information, the method comprises generating a list of acceptable resources on which to start and the timeframe at which to start (<b>322</b>) and resource reservations can then be created (<b>324</b>).

0042In one aspect of the invention, the nested loops in the flowchart of <figref idref="DRAWINGS">FIG. 3</figref> are that steps <b>306</b>-<b>318</b> are processed on the resource or node level, and steps <b>308</b>-<b>316</b> are nested within the node and relate to processing each job within the resource or node. Then starting at step <b>320</b> the method turns to a global view to further analyze the overall grouping of jobs and other resources available from which the method involves generating the list of available resources on which to start jobs and the timeframes at which to start.

0043A user interface is also involved in which an administrator or a user who submits jobs or some other user can graphically view the analysis. Therefore, there are various steps involved in the interaction with a user, such as presenting the generated list of acceptable resources on which to start jobs and available timeframes at which to start. There may be options such as an opportunity to pay an additional amount of money for an earlier time frame that is available but perhaps is outside of the scope of a particular usage package that the user or group has. For example, if a particular group has paid for a service that guarantees processing time within 3 hours of a request, and an available time based on the analysis above includes a time frame in 1 hour, that the user may opt to pay an additional amount (or be given the opportunity for free) to go ahead and select that start time of 1 hour. As another example of the user interaction, the user may be presented with available time frames from starting in 1 hour, 3.5 hours and 10 hours. The user then may be able to select and submit a request (say 10 hours) and the system will then establish the reservation for the resources according to the request. The system may alternately have an automatic approach where the user has a profile in which the earliest time is always selected, or the cheapest time, or the time that insures the job to be processed before 9:00 AM the next day, and so forth.

0044Embodiments within the scope of the present invention may also include computer-readable media for carrying or having computer-executable instructions or data structures stored thereon. Such computer-readable media can be any available media that can be accessed by a general purpose or special purpose computer. By way of example, and not limitation, such computer-readable media can comprise RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code means in the form of computer-executable instructions or data structures. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or combination thereof) to a computer, the computer properly views the connection as a computer-readable medium. Thus, any such connection is properly termed a computer-readable medium. Combinations of the above should also be included within the scope of the computer-readable media.

0045Computer-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing device to perform a certain function or group of functions. Computer-executable instructions also include program modules that are executed by computers in stand-alone or network environments. Generally, program modules include routines, programs, objects, components, and data structures, etc. that perform particular tasks or implement particular abstract data types. Computer-executable instructions, associated data structures, and program modules represent examples of the program code means for executing steps of the methods disclosed herein. The particular sequence of such executable instructions or associated data structures represents examples of corresponding acts for implementing the functions described in such steps.

0046Those of skill in the art will appreciate that other embodiments of the invention may be practiced in network computing environments with many types of computer system configurations, including personal computers, hand-held devices, multi-processor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. Embodiments may also be practiced in distributed computing environments where tasks are performed by local and remote processing devices that are linked (either by hardwired links, wireless links, or by a combination thereof through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

0047Although the above description may contain specific details, they should not be construed as limiting the claims in any way. Other configurations of the described embodiments of the invention are part of the scope of this invention. For example, each of the processing steps above may involve various logical operations, such as AND'ing or OR'ing timeframes or other data together, or performing some other operation to move to the next step. Accordingly, the appended claims and their legal equivalents should only define the invention, rather than any specific examples given.