On-demand compute environment

Description

RELATED APPLICATION

The present application is related to U.S. application Ser. No. 11/276,852 incorporated herein by reference.

A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure as it appears in the United States Patent & Trademark Office patent file or records, but otherwise reserves all copyright rights whatsoever.

BACKGROUND OF THE INVENTION
1. Field of the Invention

The present invention relates to a resource management system and more specifically to a system and method of providing access to on-demand compute resources.

2. Introduction

Managers 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.

Often a set of resources organized in a cluster or a grid may have jobs to be submitted to the resources that require more capability than the set of resource has available. In this regard, there is a need in the art for being able to easily, efficiently and on-demand be able to utilize new resources or different resources to handle a job. The concept of “on-demand” compute resources has been developing in the high performance computing community recently. An on-demand computing environment enables companies to procure compute power for average demand and then contract remote processing power to help in peak loads or to offload all their compute needs to a remote facility. Several reference books having background material related to on-demand computing or utility computing include Mike Ault, Madhu Tumma, Oracle 10 g Grid & Real Application Clusters, Rampant TechPress, 2004 and Guy Bunker, Darren Thomson, Delivering Utility Computing Business-driven IT Optimization, John Wiley & Sons Ltd, 2006.

In Bunker and Thompson, section 3.3 on page 32 is entitled “Connectivity: The Great Enabler” wherein they discuss how the interconnecting of computers will dramatically increase their usefulness. This disclosure addresses that issue. There exists in the art a need for improved solutions to enable communication and connectivity with an on-demand high performance computing center.

SUMMARY OF THE INVENTION

Additional 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.

Various embodiments of the invention include, but are not limited to, methods, systems, computing devices, clusters, grids and computer-readable media that perform the processes and steps described herein.

An on-demand compute environment comprises a plurality of nodes within an on-demand compute environment available for provisioning and a slave management module operating on a dedicated node within the on-demand compute environment, wherein upon instructions from a master management module at a local compute environment, the slave management module modifies at least one node of the plurality of nodes. Methods and computer readable media are also disclosed for managing an on-demand compute environment.

A benefit of the approaches disclosed herein is a reduction in unnecessary costs of building infrastructure to accommodate peak demand. Thus, customers only pay for the extra processing power they need only during those times when they need it.

BRIEF DESCRIPTION OF THE DRAWINGS

In 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.

FIG. 1 illustrates the basic arrangement of the present disclosure;

FIG. 2 illustrates basic hardware components;

FIG. 3 illustrates a method aspect of the disclosure;

FIG. 4 illustrates a method aspect of the disclosure;

FIG. 5 illustrates another method aspect of the disclosure; and

FIG. 6 illustrates another method aspect of the disclosure.

DETAILED DESCRIPTION OF THE INVENTION

Various embodiments 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.

This disclosure relates to the access and management of on-demand or utility computing resources at a hosting center. FIG. 1 illustrates the basic arrangement and interaction between a local compute environment 104 and an on-demand hosting center 102. The local compute environment may comprise a cluster, a grid, or any other variation on these types of multiple node and commonly managed environments. The on-demand hosting center or on-demand computing environment 102 comprises a plurality of nodes that are available for provisioning and preferably has a dedicated node containing a hosting master 128 which may comprise a slave management module 106 and/or at least one other module such as the entity manager 128 and node provisioner 118.

Products such as Moab provide an essential service for optimization of a local compute environment. It provides an analysis into how & when local resources, such as software and hardware devices, are being used for the purposes of charge-back, planning,

auditing, troubleshooting and reporting internally or externally. Such optimization enables the local environment to be tuned to get the most out of the resources in the local compute environment. However, there are times where more resources are needed.

Typically a hosting center 102 will have the following attributes. It allows an organization to provide resources or services to customers where the resources or services are custom-tailored to the needs of the customer. Supporting true utility computing usually requires creating a hosting center 102 with one or more capabilities as follows: secure remote access, guaranteed resource availability at a fixed time or series of times, integrated auditing/accounting/billing services, tiered service level (QoS/SLA) based resource access, dynamic compute node provisioning, full environment management over compute, network, storage, and application/service based resources, intelligent workload optimization, high availability, failure recovery, and automated re-allocation.

A management module 108 such as, by way of example, Moab™ (which may also refer to any Moab product such as the Moab Workload Manager®, Moab Grid Monitor®, etc. from Cluster Resources, Inc.) enables utility computing by allowing compute resources to be reserved, allocated, and dynamically provisioned to meet the needs of internal or external workload. Thus, at peak workload times, the local compute environment does not need to be built out with peak usage in mind. As periodic peak resources are required, triggers can cause overflow to the on-demand environment and thus save money for the customer. The module 108 is able to respond to either manual or automatically generated requests and can guarantee resource availability subject to existing service level agreement (SLA) or quality of service (QOS) based arrangements. As an example, FIG. 1 shows a user submitting a job or a query 110 to the cluster or local environment 104. The local environment will typically be a cluster or a grid with local workload. Jobs may be submitted which have explicit resource requirements. The local environment 104 will have various attributes such as operating systems, architecture, network types, applications, software, bandwidth capabilities, etc, which are expected by the job implicitly. In other words, jobs will typically expect that the local environment will have certain attributes that will enable it to consume resources in an expected way.

Other software is shown by way of example in a distributed resource manager such as Torque 128 and various nodes 130, 132 and 134. The management modules (both master and/or slave) may interact and operate with any resource manager, such as Torque, LSF, SGE, PBS and LoadLeveler and are agnostic in this regard. Those of skill in the art will recognize these different distributed resource manager software packages.

A hosting master or hosting management module 106 may also be an instance of a Moab software product with hosting center capabilities to enable an organization to dynamically control network, compute, application, and storage resources and to dynamically provision operating systems, security, credentials, and other aspects of a complete end-to-end compute environments. Module 106 is responsible for knowing all the policies, guarantees, promises and also for managing the provisioning of resources within the utility computing space 102. In one sense, module 106 may be referred to as the “master” module in that it couples and needs to know all of the information associated with both the utility environment and the local environment. However, in another sense it may be referred to as the slave module or provisioning broker wherein it takes instructions from the customer management module 108 for provisioning resources and builds whatever environment is requested in the on-demand center 102. A slave module would have none of its own local policies but rather follows all requests from another management module. For example, when module 106 is the slave module, then a master module 108 would submit automated or manual (via an administrator) requests that the slave module 106 simply follows to manage the build out of the requested environment. Thus, for both IT and end users, a single easily usable interface can increase efficiency, reduce costs including management costs and improve investments in the local customer environment. The interface to the local environment which also has the access to the on-demand environment may be a web-interface or access portal as well. Restrictions of feasibility only may exist. The customer module 108 would have rights and ownership of all resources. The allocated resources would not be shared but be dedicated to the requestor. As the slave module 106 follows all directions from the master module 108, any policy restrictions will preferably occur on the master module 108 in the local environment.

The modules also provide data management services that simplify adding resources from across a local environment. For example, if the local environment comprises a wide area network, the management module 108 provides a security model that ensures, when the environment dictates, that administrators can rely on the system even when untrusted resources at the certain level have been added to the local environment or the on-demand environment. In addition, the management modules comply with n-tier web services based architectures and therefore scalability and reporting are inherent parts of the system. A system operating according to the principles set forth herein also has the ability to track, record and archive information about jobs or other processes that have been run on the system.

A hosting center 102 provides scheduled dedicated resources to customers for various purposes and typically has a number of key attributes: secure remote access, guaranteed resource availability at a fixed time or series of times, tightly integrated auditing/accounting services, varying quality of service levels providing privileged access to a set of users, node image management allowing the hosting center to restore an exact customer-specific image before enabling access. Resources available to a module 106, which may also be referred to as a provider resource broker, will have both rigid (architecture, RAM, local disk space, etc.) and flexible (OS, queues, installed applications etc.) attributes. The provider or on-demand resource broker 106 can typically provision (dynamically modify) flexible attributes but not rigid attributes. The provider broker 106 may possess multiple resources each with different types with rigid attributes (i.e., single processor and dual processor nodes, Intel nodes, AMD nodes, nodes with 512 MB RAM, nodes with 1 GB RAM, etc).

This combination of attributes presents unique constraints on a management system. We describe herein how the management modules 108 and 106 are able to effectively manage, modify and provision resources in this environment and provide full array of services on top of these resources.

Utility-based computing technology allows a hosting center 102 to quickly harness existing compute resources, dynamically co-allocate the resources, and automatically provision them into a seamless virtual cluster. The management modules' advanced reservation and policy management tools provide support for the establishment of extensive service level agreements, automated billing, and instant chart and report creation.

Also shown in FIG. 1 are several other components such as an identity manager 112 and a node provisioner 118 as part of the hosting center 102. The hosting master' 128 may include an identity manager interface 112 that may coordinate global and local information regarding users, groups, accounts, and classes associated with compute resources. The identity manager interface 112 may also allow the management module 106 to automatically and dynamically create and modify user accounts and credential attributes according to current workload needs. The hosting master 128 allows sites extensive flexibility when it comes to defining credential access, attributes, and relationships. In most cases, use of the USERCFG, GROUPCFG, ACCOUNTCFG, CLASSCFG, and QOSCFG parameters is adequate to specify the needed configuration. However, in certain cases, such as the following, this approach may not be ideal or even adequate: environments with very large user sets; environments with very dynamic credential configurations in terms of fairshare targets, priorities, service access constraints, and credential relationships; grid environments with external credential mapping information services; enterprise environments with fairness policies based on multi-cluster usage.

The modules address these and similar issues through the use of the identity manager 112. The identity manager 112 allows the module to exchange information with an external identity management service. As with the module's resource manager interfaces, this service can be a full commercial package designed for this purpose, or something far simpler by which the module obtains the needed information for a web service, text file, or database.

Next attention is turned to the node provisioner 118 and as an example of its operation, the node provisioner 118 can enable the allocation of resources in the hosting center 102 for workload from a local compute environment 104. The customer management module 108 will communicate with the hosting management module 106 to begin the provisioning process. In one aspect, the provisioning module 118 may generate another instance of necessary management software 120 and 122 which will be created in the hosting center environment as well as compute nodes 124 and 126 to be consumed by a submitted job. The new management module 120 is created on the fly, may be associated with a specific request and will preferably be operative on a dedicated node. If the new management module 120 is associated with a specific request or job, as the job consumes the resources associated with the provisioned compute nodes 124, 126, and the job becomes complete, then the system would remove the management module 120 since it was only created for the specific request. The new management module 120 may connect to other modules such as module 108. The module 120 does not necessarily have to be created but may be generated on the fly as necessary to assist in communication and provisioning and use of the resources in the utility environment 102. For example, the module 106 may go ahead and allocate nodes within the utility computing environment 102 and connect these nodes directly to module 108 but in that case you may lose some batch ability as a tradeoff. The hosting master 128 having the management module 106, identity manager 112 and node provisioner 118 preferably is co-located with the utility computing environment but may be distributed. The management module on the local environment 108 may then communicate directly with the created management module 120 in the hosting center to manage the transfer of workload and consumption of on-demand center resources.

FIG. 6 provides an illustration of a method aspect of utilizing the new management module. As shown, this method comprises receiving an instruction at a slave management module associated with an on-demand computing environment from a master management module associated with a local computing environment (602) and based on the instruction, creating a new management module on a node in the on-demand computing environment and provisioning at least one compute node in the on-demand computing environment, wherein the new management module manages the at least one compute node and communicates with the master management module (604).

There are two supported primary usage models, a manual and an automatic model. In manual mode, utilizing the hosted resources can be as easy as going to a web site, specifying what is needed, selecting one of the available options, and logging in when the virtual cluster is activated. In automatic mode, it is even simpler. To utilize hosted resources, the user simply submits jobs to the local cluster. When the local cluster can no longer provide an adequate level of service, it automatically contacts the utility hosting center, allocates additional nodes, and runs the jobs. The end user is never aware that the hosting center even exists. He merely notices that the cluster is now bigger and that his jobs are being run more quickly.

When a request for additional resources is made from the local environment, either automatically or manually, a client module or client resource broker (which may be, for example, an instance of a management module 108 or 120) will contact the provider resource broker 106 to request resources. It will send information regarding rigid attributes of needed resources as well as quantity or resources needed, request duration, and request timeframe (i.e., start time, feasible times of day, etc.) It will also send flexible attributes which must be provisioned on the nodes 124, 126. Both flexible and rigid resource attributes can come from explicit workload-specified requirement or from implicit requirements associated with the local or default compute resources. The provider resource broker 106 must indicate if it is possible to locate requested resources within the specified timeframe for sufficient duration and of the sufficient quantity. This task includes matching rigid resource attributes and identifying one or more provisioning steps required to put in place all flexible attributes.

When provider resources are identified and selected, the client resource broker 108 or 120 is responsible for seamlessly integrating these resources in with other local resources. This includes reporting resource quantity, state, configuration and load. This further includes automatically enabling a trusted connection to the allocated resources which can perform last mile customization, data staging, and job staging. Commands are provided to create this connection to the provider resource broker 106, query available resources, allocate new resources, expand existing allocations, reduce existing allocations, and release all allocated resources.

In most cases, the end goal of a hosting center 102 is to make available to a customer, a complete, secure, packaged environment which allows them to accomplish one or more specific tasks. This packaged environment may be called a virtual cluster and may consist of the compute, network, data, software, and other resources required by the customer. For successful operation, these resources must be brought together and provisioned or configured so as to provide a seamless environment which allows the customers to quickly and easily accomplish their desired tasks.

Another aspect of the invention is the cluster interface. The desired operational model for many environments is providing the customer with a fully automated self-service web interface. Once a customer has registered with the host company, access to a hosting center portal is enabled. Through this interface, customers describe their workload requirements, time constraints, and other key pieces of information. The interface communicates with the backend services to determine when, where, and how the needed virtual cluster can be created and reports back a number of options to the user. The user selects the desired option and can monitor the status of that virtual cluster via web and email updates. When the virtual cluster is ready, web and email notification is provided including access information. The customer logs in and begins working.

The hosting center 102 will have related policies and service level agreements. Enabling access in a first come-first served model provides real benefits but in many cases, customers require reliable resource access with guaranteed responsiveness. These requirements may be any performance, resource or time based rule such as in the following examples: I need my virtual cluster within 24 hours of asking; I want a virtual cluster available from 2 to 4 PM every Monday, Wednesday, and Friday; I want to always have a virtual cluster available and automatically grow/shrink it based on current load, etc.

Quality of service or service level agreement policies allow customers to convert the virtual cluster resources to a strategic part of their business operations greatly increasing the value of these resources. Behind the scenes, a hosting center 102 consists of resource managers, reservations, triggers, and policies. Once configured, administration of such a system involves addressing reported resource failures (i.e., disk failures, network outages, etc) and monitoring delivered performance to determine if customer satisfaction requires tuning policies or adding resources.

The modules associated with the local environment 104 and the hosting center environment 102 may be referred to as a master module 108 and a slave module 106. This terminology relates to the functionality wherein the hosting center 102 receives requests for workload and provisioning of resources from the module 108 and essentially follows those requests. In this regard, the module 108 may be referred to as a client resource broker 108 which will contact a provider resource broker 106 (such as an On-Demand version of Moab).

The management module 108 may also be, by way of example, a Moab Workload Manager® operating in a master mode. The management module 108 communicates with the compute environment to identify resources, reserve resources for consumption by jobs, provision resources and in general manage the utilization of all compute resources within a compute environment. As can be appreciated by one of skill in the art, these modules may be programmed in any programming language, such as C or C++ and which language is immaterial to the invention.

In a typical operation, a user or a group submits a job to a local compute environment 104 via an interface to the management module 108. An example of a job is a submission of a computer program that will perform a weather analysis for a television station that requires the consumption of a large amount of compute resources. The module 108 and/or an optional scheduler 128 such as TORQUE, as those of skill in the art understand, manages the reservation of resources and the consumption of resources within the environment 104 in an efficient manner that complies with policies and restrictions. The use of a resource manager like TORQUE 128 is optional and not specifically required as part of the disclosure.

A user or a group of users will typically enter into a service level agreement (SLA) which will define the policies and guarantees for resources on the local environment 104. For example, the SLA may provide that the user is guaranteed 10 processors and 50 GB of hard drive space within 5 hours of a submission of a job request. Associated with any user may be many parameters related to permissions, guarantees, priority level, time frames, expansion factors, and so forth. The expansion factor is a measure of how long the job is taking to run on a local environment while sharing the environment with other jobs versus how long it would take if the cluster was dedicated to the job only. It therefore relates to the impact of other jobs on the performance of the particular job. Once a job is submitted and will sit in a job queue waiting to be inserted into the cluster 104 to consume those resources. The management software will continuously analyze the environment 104 and make reservations of resources to seek to optimize the consumption of resources within the environment 104. The optimization process must take into account all the SLA's of users, other policies of the environment 104 and other factors.

As introduced above, this disclosure provides improvements in the connectivity between a local environment 104 and an on-demand center 102. The challenges that exist in accomplishing such a connection include managing all of the capabilities of the various environments, their various policies, current workload, workload queued up in the job queues and so forth.

As a general statement, disclosed herein is a method and system for customizing an on-demand compute environment based on both implicit and explicit job or request requirements. For example, explicit requirements may be requirements specified with a job such as a specific number of nodes or processor and a specific amount of memory. Many other attributes or requirements may be explicitly set forth with a job submission such as requirements set forth in an SLA for that user. Implicit requirements may relate to attributes of the compute environment that the job is expecting because of where it is submitted. For example, the local compute environment 104 may have particular attributes, such as, for example, a certain bandwidth for transmission, memory, software licenses, processors and processor speeds, hard drive memory space, and so forth. Any parameter that may be an attribute of the local environment in which the job is submitted may relate to an implicit requirement. As a local environment 104 communicates with an on-demand environment 102 for the transfer of workload, the implicit and explicit requirements are seamlessly imported into the on-demand environment 102 such that the user's job can efficiently consume resources in the on-demand environment 102 because of the customization of that environment for the job. This seamless communication occurs between a master module 108 and a slave module 106 in the respective environments. As shown in FIG. 1, a new management module 120 may also be created for a specific process or job and also communicate with a master module 108 to manage the provisioning, consumption and clean up of compute nodes 124, 126 in the on-demand environment 102.

Part of the seamless communication process includes the analysis and provisioning of resources taking into account the need to identify resources such as hard drive space and bandwidth capabilities to actually perform the transfer of the workload. For example, if it is determined that a job in the queue has a SLA that guarantees resources within 5 hours of the request, and based on the analysis by the management module of the local environment the resources cannot be available for 8 hours, and if such a scenario is at triggering event, then the automatic and seamless connectivity with the on-demand center 102 will include an analysis of how long it will take to provision an environment in the on-demand center that matches or is appropriate for the job to run. That process, of provisioning the environment in the on-demand center 102, and transferring workload from the local environment 104 to the on-demand center 102, may take, for example, 1 hour. In that case, the on-demand center will begin the provisioning process one hour before the 5 hour required time such that the provisioning of the environment and transfer of data can occur to meet the SLA for that user. This provisioning process may involve reserving resources within the on-demand center 102 from the master module 108 as will be discussed more below.

FIG. 3 illustrates an embodiment in this regard, wherein a method comprises detecting an event in a local compute environment (302). The event may be a resource need event such as a current resource need or a predicted resource need. Based on the detected event, a module automatically establishes communication with an on-demand compute environment (304). This may also involve dynamically negotiating and establishing a grid/peer relationship based on the resource need event. A module provisions resources within the on-demand compute environment (306) and workload is transferred from the local-environment transparently to the on-demand compute environment (308). Preferably, local information is imported to the on-demand environment and on-demand information is communicated to the local compute environment, although only local environment information may be needed to be transmitted to the on-demand environment. Typically, at least local environment information is communicated and also job information may be communicated to the on-demand environment. Examples of local environment information may be at least one of class information, configuration policy information and other information. Information from the on-demand center may relate to at least one of resources, availability of resources, time frames associated with resources and any other kind of data that informs the local environment of the opportunity and availability of the on-demand resources. The communication and management of the data between the master module or client module in the local environment and the slave module is preferably transparent and unknown to the user who submitted the workload to the local environment. However, one aspect may provide for notice to the user of the tapping into the on-demand resources and the progress and availability of those resources.

Example triggering events may be related to at least one of a resource threshold, a service threshold, workload and a policy threshold or other factors. Furthermore, the event may be based one of all workload associated with the local compute environment or a subset of workload associated with the compute environment or any other subset of a given parameter or may be external to the compute environment such as a natural disaster or power outage or predicted event.

The disclosure below provides for various aspects of this connectivity process between a local environment 104 and an on-demand center 102. The CD submitted with the priority Provisional Patent Application includes source code that carries out this functionality. The various aspects will include an automatic triggering approach to transfer workload from the local environment 104 to the on-demand center 102, a manual “one-click” method of integrating the on-demand compute environment 102 with the local environment 104 and a concept related to reserving resources in the on-demand compute environment 102 from the local compute environment 104.

The first aspect relates to enabling the automatic detection of a triggering event such as passing a resource threshold or service threshold within the compute environment 104. This process may be dynamic and involve identifying resources in a hosting center, allocating resources and releasing them after consumption. These processes may be automated based on a number of factors, such as: workload and credential performance thresholds; a job's current time waiting in the queue for execution, (queuetime) (i.e., allocate if a job has waited more than 20 minutes to receive resources); a job's current expansion factor which relates to a comparison of the affect of other jobs consuming local resources has on the particular job in comparison to a value if the job was the only job consuming resources in the local environment; a job's current execution load (i.e., allocate if load on job's allocated resources exceeds 0.9); quantity of backlog workload (i.e., allocate if more than 50,000 proc-hours of workload exist); a job's average response time in handling transactions (i.e., allocate if job reports it is taking more than 0.5 seconds to process transaction); a number of failures workload has experienced (i.e., allocate if a job cannot start after 10 attempts); overall system utilization (i.e., allocate if more than 80% of machine is utilized) and so forth. This is an example list and those of skill in the art will recognize other factors that may be identified as triggering events.

Other triggering events or thresholds may comprise a predicted workload performance threshold. This would relate to the same listing of events above but be applied in the context of predictions made by a management module or customer resource broker.

Another listing of example events that may trigger communication with the hosting center include, but are not limited to events such as resource failures including compute nodes, network, storage, license (i.e., including expired licenses); service failures including DNS, information services, web services, database services, security services; external event detected (i.e., power outage or national emergency reported) and so forth. These triggering events or thresholds may be applied to allocate initial resources, expand allocated resources, reduce allocated resources and release all allocated resources. Thus, while the primary discussion herein relates to an initial allocation of resources, these triggering events may cause any number of resource-related actions. Events and thresholds may also be associated with any subset of jobs or nodes (i.e., allocate only if threshold backlog is exceeded on high priority jobs only or jobs from a certain user or project or allocate resources only if certain service nodes fail or certain licenses become unavailable.)

For example, if a threshold of 95% of processor consumption is met by 951 processors out of the 1000 processors in the environment are being utilized, then the system (which may or may not include the management module 108) automatically establishes a connection with the on-demand environment 102. Another type of threshold may also trigger the automatic connection such as a service level received threshold, a service level predicted threshold, a policy-based threshold, a threshold or event associated with environment changes such as a resource failure (compute node, network storage device, or service failures).

In a service level threshold, one example is where a SLA specifies a certain service level requirement for a customer, such as resources available within 5 hours. If an actual threshold is not met, i.e., a job has waited now for 5 hours without being able to consume resource, or where a threshold is predicted to not be met, these can be triggering events for communication with the on-demand center. The module 108 then communicates with the slave manager 106 to provision or customize the on-demand resources 102. The two environments exchange the necessary information to create reservations of resources, provision, handle licensing, and so forth, necessary to enable the automatic transfer of jobs or other workload from the local environment 104 to the on-demand environment 102. For a particular task or job, all or part of the workload may be transferred to the on-demand center. Nothing about a user job 110 submitted to a management module 108 changes. The on-demand environment 102 then instantly begins running the job without any change in the job or perhaps even any knowledge of the submitter.

There are several aspects of the disclosure that are shown in the source code on the CD. One is the ability to exchange information. For example, for the automatic transfer of workload to the on-demand center, the system will import remote classes, configuration policy information and other information from the local scheduler 108 to the slave scheduler 106 for use by the on-demand environment 102. Information regarding the on-demand compute environment, resources, policies and so forth are also communicated from the slave module 106 to the local module 108.

The triggering event for the automatic establishment of communication with the on-demand center and a transfer of workload to the on-demand center may be a threshold that has been passed or an event that occurred. Threshold values may comprise an achieved service level, predicted service level and so forth. For example, a job sitting in a queue for a certain amount of time may trigger a process to contact the on-demand center and transfer that job to the on-demand center to run. If a queue has a certain number of jobs that have not been submitted to the compute environment for processing, if a job has an expansion factor that has a certain value, if a job has failed to start on a local cluster one or more times for whatever reason, then these types of events may trigger communication with the on-demand center. These have been examples of threshold values that when passed will trigger communication with the on-demand environment.

Example events that also may trigger the communication with the on-demand environment include, but are not limited to, events such as the failure of nodes within the environment, storage failure, service failure, license expiration, management software failure, resource manager fails, etc. In other words, any event that may be related to any resource or the management of any resource in the compute environment may be a qualifying event that may trigger workload transfer to an on-demand center. In the license expiration context, if the license in a local environment of a certain software package is going to expire such that a job cannot properly consume resources and utilize the software package, the master module 108 can communicate with the slave module 106 to determine if the on-demand center has the requisite license for that software. If so, then the provisioning of the resources in the on-demand center can be negotiated and the workload transferred wherein it can consume resources under an appropriate legal and licensed framework.

The basis for the threshold or the event that triggers the communication, provisioning and transfer of workload to the on-demand center may be all jobs/workload associated with the local compute environment or a subset of jobs/workload associated with the local compute environment. In other words, the analysis of when an event and/or threshold should trigger the transfer of workload may be based on a subset of jobs. For example, the analysis may be based on all jobs submitted from a particular person or group or may be based on a certain type of job, such as the subset of jobs that will require more than 5 hours of processing time to run. Any parameter may be defined for the subset of jobs used to base the triggering event.

The interaction and communication between the local compute environment and the on-demand compute environment enables an improved process for dynamically growing and shirking provisioned resource space based on load. This load balancing between the on-demand center and the local environment may be based on thresholds, events, all workload associated with the local environment or a subset of the local environment workload.

Another aspect of the disclosure is the ability to automate data management between two sites. This involves the transparent handling of data management between the on-demand environment 102 and the local environment 104 that is transparent to the user. Typically environmental information will always be communicated between the local environment 104 and the on-demand environment 102. In some cases, job information may not need to be communicated because a job may be gathering its own information, say from the Internet, or for other reasons. Therefore, in preparing to provision resources in the on-demand environment all information or a subset of information is communicated to enable the process. Yet another aspect of the invention relates to a simple and easy mechanism to enable on-demand center integration. This aspect of the invention involves the ability of the user or an administrator to, in a single action like the click of a button or a one-click action, be able to command the integration of an on-demand center information and capability into the local resource manager 108.

This feature is illustrated in FIG. 4. A module, preferably associated with the local compute environment, receives a request from an administrator to integrate an on-demand compute environment into the local compute environment (402). The creation of a reservation or of a provisioning of resources in the on-demand environment may be from a request from an administrator or local or remote automated broker. In this regard, the various modules will automatically integrate local compute environment information with on-demand compute environment information to make available resources from the on-demand compute environment to requestors of resources in the local compute environment (404). Integration of the on-demand compute environment may provide for integrating: resource configuration, state information, resource utilization reporting, job submission information, job management information resource management, policy controls including priority, resource ownership, queue configuration, job accounting and tracking and resource accounting and tracking. Thus, the detailed analysis and tracking of jobs and resources may be communicated back from the on-demand center to the local compute environment interface. Furthermore, this integration process may also include a step of automatically creating at least one of a data migration interface and a job migration interface.

Another aspect provides for a method of integrating an on-demand compute environment into a local compute environment. The method comprises receiving a request from an administrator or via an automated command from an event trigger or administrator action to integrate an on-demand compute environment into a local compute environment. In response to the request, local workload information and/or resource configuration information is routed to an on-demand center and an environment is created and customized in the on-demand center that is compatible with workload requirements submitted to the local compute environment. Billing and costing are also automatically integrated and handled.

The exchange and integration of all the necessary information and resource knowledge may be performed in a single action or click to broaden the set of resources that may be available to users who have access initially only to the local compute environment 104. The system may receive the request to integrate an on-demand compute environment into a local compute environment in other manners as well, such as any type of multi-modal request, voice request, graffiti on a touch-sensitive screen request, motion detection, and so forth. Thus the one-click action may be a single tap on a touch sensitive display or a single voice command such as “integrate” or another command or multi-modal input that is simple and singular in nature. In response to the request, the system automatically integrates the local compute environment information with the on-demand compute environment information to enable resources from the on-demand compute environment available to requestors of resources in the local compute environment.

The one-click approach relates to the automated approach expect a human is in the middle of the process. For example, if a threshold or a triggering event is passed, an email or a notice may be sent to an administrator with options to allocate resources from the on-demand center. The administrator may be presented with one or more options related to different types of allocations that are available in the on-demand center—and via one-click or one action the administrator may select the appropriate action. For example, three options may include 500 processors in 1 hour; 700 processors in 2 hours; and 1000 processors in 10 hours. The options may be intelligent in that they may take into account the particular triggering event, costs of utilizing the on-demand environment, SLAs, policies, and any other parameters to present options that comply with policies and available resources. The administrator may be given a recommended selection based on SLAs, cost, or any other parameters discussed herein but may then choose the particular allocation package for the on-demand center. The administrator also may have an option, without an alert, to view possible allocation packages in the on-demand center if the administrator knows of an upcoming event that is not capable of being detected by the modules, such as a meeting with a group wherein they decide to submit a large job the next day which will clearly require on-demand resources. The one-click approach encapsulates the command line instruction to proceed with the allocation of on-demand resources.

One of the aspects of the disclosure is the integration of an on-demand environment 102 and a local compute environment 104 is that the overall data appears locally. In other words, the local scheduler 108 will have access to the resources and knowledge of the on-demand environment 102 but those resources, with the appropriate adherence to local policy requirements, is handled locally and appears locally to users and administrators of the local environment 104.

Another aspect of the invention that is enabled with the attached source code is the ability to specify configuration information and feeding it down the line. For example, the interaction between the compute environments supports static reservations. A static reservation is a reservation that a user or an administrator cannot change, remove or destroy. It is a reservation that is associated with the resource manager 108 itself. A static reservation blocks out time frames when resources are not available for other uses. For example, if to enable a compute environment to have workload run on (or consume) resources, a job takes an hour to provision a resources, then the module 108 may make a static reservation of resources for the provisioning process. The module 108 will locally create a static reservation for the provisioning component of running the job. The module 108 will report on these constraints associated with the created static reservation within the on-demand compute environment.

Then, the module 108 will communicate with the slave module 106 if on-demand resources are needed to run a job. The module 108 communicates with the slave module 106 and identifies what resources are needed (20 processors and 512 MB of memory, for example) and inquires when can those resources be available. Assume that module 106 responds that the processors and memory will be available in one hour and that the module 108 can have those resources for 36 hours. Once all the appropriate information has been communicated between the modules 106 and 108, then module 108 creates a static reservation to block the first part of the resources which requires the one hour of provisioning. The module 108 may also block out the resources with a static reservation from hour 36 to infinity until the resources go away. Therefore, from zero to one hour is blocked out by a static reservation and from the end of the 36 hours to infinity is blocked out. In this way, the scheduler 108 can optimize the on-demand resources and insure that they are available for local workloads. The communication between the modules 106 and 108 is performed preferably via tunneling.

Another aspect relates to receiving requests or information associated with resources in an on-demand center. An example will illustrate. Assume that a company has a reservation of resources within an on-demand center but then finds out that their budget is cut for the year. There is a mechanism for an administrator to enter information such as a request for a cancellation of a reservation so that they do not have to pay for the consumption of those resources. Any type of modification of the on-demand resources may be contemplated here. This process involves translating a current or future state of the environment for a requirement of the modification of usable resources. Another example includes where a group determines that they will run a large job over the weekend that will knowingly need more than the local environment. An administrator can submit in the local resource broker 108 a submission of information associated with a parameter—such as a request for resources and the local broker 108 will communicate with the hosting center 106 and the necessary resources can be reserved in the on-demand center even before the job is submitted to the local environment.

The modification of resources within the on-demand center may be an increase, decrease, or cancellation of resources or reservations for resources. The parameters may be a direct request for resources or a modification of resources or may be a change in an SLA which then may trigger other modifications. For example, if an SLA prevented a user from obtaining more than 500 nodes in an on-demand center and a current reservation has maximized this request, a change in the SLA agreement that extended this parameter may automatically cause the module 106 to increase the reservation of nodes according to the modified SLA. Changing policies in this manner may or may not affect the resources in the on-demand center.

FIG. 5 illustrates a method embodiment related to modifying resources in the on-demand compute environment. The method comprises receiving information at a local resource broker that is associated with resources within an on-demand compute environment (502). Based on the information, the method comprises communicating instructions from the local resource broker to the on-demand compute environment (504) and modifying resources associated with the on-demand compute environment based on the instructions (506). As mentioned above, examples of the type of information that may be received include information associated with a request for a new reservation, a cancellation of an existing reservation, or a modification of a reservation such as expanding or contracting the reserved resources in the on-demand compute environment. Other examples include a revised policy or revision to an SLA that alters (increases or perhaps decreases) allowed resources that may be reserved in the on-demand center. The master module 108 will then provide instructions to the slave module 106 to create or modify reservations in the on-demand computing environment or to make some other alteration to the resources as instructed.

Receiving resource requirement information may be based on user specification, current or predicted workload. The specification of resources may be fully explicit, or may be partially or fully implicit based on workload or based on virtual private cluster (VPC) package concept where VPC package can include aspects of allocated or provisioning support environment and adjustments to resource request timeframes including pre-allocation, allocation duration, and post-allocation timeframe adjustments. The Application incorporated above provides information associated with the VPC that may be utilized in many respects in this invention. The reserved resources may be associated with provisioning or customizing the delivered compute environment. A reservation may involve the co-allocation of resources including any combination of compute, network, storage, license, or service resources (i.e., parallel database services, security services, provisioning services) as part of a reservation across multiple different resource types. Also, the co-allocation of resources over disjoint timeframes to improve availability and utilization of resources may be part of a reservation or a modification of resources. Resources may also be reserved with automated failure handling and resource recovery.

Another feature associated with reservations of resources within the on-demand environment is the use of provisioning padding. This is an alternate approach to the static reservation discussed above. For example, if a reservation of resources would require 2 hours of processing time for 5 nodes, then that reservation may be created in the on-demand center as directed by the client resource broker 108. As part of that same reservation or as part of a separate process, the reservation may be modified or adjusted to increase its duration to accommodate for provisioning overhead and clean up processes. Therefore, there may need to be ½ hour of time in advance of the beginning of the two hour block wherein data transmission, operating system set up, or any other provisioning step needs to occur. Similarly, at the end of the two hours, there may need to be 15 minutes to clean up the nodes and transmit processed data to storage or back to the local compute environment. Thus, an adjustment of the reservation may occur to account for this provisioning in the on-demand environment. This may or may not occur automatically, for example, the user may request resources for 2 hours and the system may automatically analyze the job submitted or utilize other information to automatically adjust the reservation for the provisioning needs. The administrator may also understand the provisioning needs and specifically request a reservation with provisioning pads on one or both ends of the reservation.

A job may also be broken into component parts and only one aspect of the job transferred to an on-demand center for processing. In that case, the modules will work together to enable co-allocation of resources across local resources and on-demand resources. For example, memory and processors may be allocated in the local environment while disk space is allocated in the on-demand center. In this regard, the local management module could request the particular resources needed for the co-allocation from the on-demand center and when the job is submitted for processing that portion of the job would consume on-demand center resources while the remaining portion of the job consumes local resources. This also may be a manual or automated process to handle the co-allocation of resources.

Another aspect relates to interaction between the master management module 106 and the slave management module 106. Assume a scenario where the local compute environment requests immediate resources from the on-demand center. Via the communication between the local and the on-demand environments, the on-demand environment notifies the local environment that resources are not available for eight hours but provides the information about those resources in the eight hours. At the local environment, the management module 108 may instruct the on-demand management module 106 to establish a reservation for those resources as soon as possible (in eight hours) including, perhaps, provisioning padding for overhead. Thus, although the local environment requested immediate resources from the on-demand center, the best that could be done in this case is a reservation of resources in eight hours given the provisioning needs and other workload and jobs running on the on-demand center. Thus, jobs running or in the queue at the local environment will have an opportunity to tap into the reservation and given a variety of parameters, say job number 12 has priority or an opportunity to get a first choice of those reserved resources.

With reference to FIG. 2, an exemplary system for implementing the invention includes a general purpose computing device 200, including a processing unit (CPU) 220, a system memory 230, and a system bus 210 that couples various system components including the system memory 230 to the processing unit 220. The system bus 210 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) 240 and random access memory (RAM) 250. A basic input/output (BIOS), containing the basic routine that helps to transfer information between elements within the computing device 200, such as during start-up, is typically stored in ROM 240. The computing device 200 further includes storage means such as a hard disk drive 260, a magnetic disk drive, an optical disk drive, tape drive or the like. The storage device 260 is connected to the system bus 210 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 200. In this regard, the various functions associated with the invention that are primarily set forth as the method embodiment of the invention may be practiced by using any programming language and programming modules to perform the associated operation within the system or the compute environment. Here the compute environment may be a cluster, grid, or any other type of coordinated commodity resources and may also refer to two separate compute environments that are coordinating workload, workflow and so forth such as a local compute environment and an on-demand compute environment. Any such programming module will preferably be associated with a resource management or workload manager or other compute environment management software such as Moab but may also be separately programmed. 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.

Although 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, memory 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. It is also recognized that other hardware configurations may be developed in the future upon which the method may be operable.

Embodiments 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.

Computer-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.

Those 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. As can also be appreciated, the compute environment itself, being managed according to the principles of the invention, may be an embodiment of the invention. Thus, separate embodiments may include an on-demand compute environment, a local compute environment, both of these environments together as a more general compute environment, and so forth. In a distributed computing environment, program modules may be located in both local and remote memory storage devices. Accordingly, the scope of the claims should be governed by the claims and their equivalents below rather than by any particular example in the specification.

Claims

1. A compute environment comprising: a processor; anda non-transitory computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform operations comprising: receiving, at a first management module operating on a first compute node in the compute environment, from a second management module associated with an external compute environment separate from the compute environment, a specification of resources to process a workload, wherein the specification of resources comprises both an explicit specification of resources provided to the external compute environment and an implicit specification of resources based on an attribute of the external compute environment;creating a new management module on a second compute node in the compute environment;provisioning at least one other compute node in the compute environment to process the workload, wherein the new management module is configured to manage the at least one other compute node and communicate with the second management module; andautomatically removing the new management module after the workload has been processed.
2. The compute environment of claim 1, wherein the specification of resources specifies an allocation of time, and wherein the instructions, when executed by the processor, further cause the processor to automatically adjust a duration of the allocation of time.
3. The compute environment of claim 2, wherein the automatic increase of the duration is to accommodate for one or more clean-up processes.
4. The compute environment of claim 2, wherein the automatic adjustment of the duration is based on at least one provisioning operation for the at least one other compute node before processing of the workload thereon.
5. A method of managing a compute environment, the method comprising: receiving, at a first management module operating on a first compute node in the compute environment, from a second management module associated with an external compute environment separate from the compute environment, a specification of resources to process a workload, wherein the specification of resources comprises both an explicit specification of resources provided to the external compute environment and an implicit specification of resources based on an attribute of the external compute environment;creating a new management module on a second compute node in the compute environment;provisioning at least one other compute node in the compute environment to process the workload, wherein the new management module manages the at least one other compute node and communicate with the second management module; andautomatically removing the new management module after the workload has been processed.
6. The method of claim 5, wherein the at least one other compute node is provisioned based at least on an analysis of at least part of the workload.
7. The method of claim 6, wherein the provisioning of the at least one other compute node comprises dynamic modification of the at least one other compute node based at least on one or more flexible attributes associated with the specification of resources, the one or more flexible attributes selected from the group consisting of: (i) one or more operating system attributes, (ii) one or more application software attributes, and (iii) one or more queue attributes.
8. The method of claim 5, wherein the external compute environment comprises a local compute environment, and the compute environment comprises an on-demand compute environment that is separately managed from the local compute environment.
9. The method of claim 5, further comprising creating at least one virtual cluster within the compute environment, the creation of the at least one virtual cluster comprising dynamic selection of a plurality of compute resources, and provisioning of the selected compute resources for use by at least part of the workload.
10. The method of claim 9, wherein the creating the at least one virtual cluster is responsive to the receiving of the specification of resources.
11. The method of claim 5, further comprising, responsive to the receiving the specification of resources, causing (i) dynamic co-allocation of a plurality of compute resources, and (ii) provisioning of the co-allocated compute resources for use by at least part of the workload.
12. The method of claim 5, wherein the creating a new management module on the second compute node in the compute environment comprises creating one or more new software instances on one or more respective ones of a plurality of compute nodes within the first compute environment.
13. The method of claim 5, wherein: the creating the specification of resources to process workload is in preparation for an assumption of at least a portion of the workload by the compute environment from the external compute environment; andthe at least one implicit resource requirement based at least on one or more attributes of the external compute environment comprises at least one rigid requirement relating to at least one of a memory requirement or data storage requirement.
14. The method of claim 5, wherein: the creating the specification of resources to process workload is in preparation for an assumption of at least a portion of the workload by the compute environment from the external compute environment; andthe at least one implicit resource requirement based at least on one or more attributes of the external compute environment comprises at least one rigid requirement relating to at least one of a network storage device.
15. The method of claim 5, wherein: the creating the specification of resources to process workload is in preparation for an assumption of at least a portion of the workload by the compute environment from the external compute environment; andthe at least one implicit resource requirement based at least on one or more attributes of the external compute environment comprises at least one flexible requirement relating to at least one of a operating system (OS) or installed software application.
16. The method of claim 5, wherein the at least one implicit resource requirement comprises at least one resource requirement relating to at least one of an operating system (OS) or a network type.
17. The method of claim 5, further comprising (i) identifying one or more resource constraints associated with processing the workload within the first compute environment, and (ii) causing dynamic modification of at least a portion of the first compute environment based at least on the identified one or more resource constraints.
18. The method of claim 17, wherein: the identifying the one or more resource constraints comprises identifying one or more resource provisioning requirements necessary for processing of the workload by the at least one other compute node; andthe method further comprises causing provisioning of the at least one other compute node based at least on the one or more provisioning requirements.
19. The method of claim 5, wherein the receiving the specification of resources to process the workload comprises receiving as specification of resources that is configured based at least on: (i) notification of a user submitting the workload for processing that additional compute resources are required to process the job, and (ii) affirmative action by the notified user acknowledging or requesting the additional compute resources.
20. The method of claim 5, wherein the receiving the specification of resources to process the workload comprises receiving as specification of resources that (i) is created automatically such that it requires no user intervention, and (ii) is configured based at least on determination that compute resources in addition to those of the external compute environment are required to process the workload.
21. The method of claim 5, wherein: the compute environment comprises one or more untrusted resources; andthe method further comprises data from the external compute environment relating to one or more security models, the one or more security models configured to maintain a level of security even with the presence of the one or more untrusted resources within the compute environment.
22. A non-transitory computer-readable storage medium having stored therein instructions which, when executed by a processor, cause the processor to perform operations comprising: receiving, at a first management module operating on a first compute node in the compute environment, from a second management module associated with an external compute environment separate from the compute environment, a specification of resources to process a workload, wherein the specification of resources comprises both an explicit specification of one or more resources provided to the external compute environment and an implicit specification of one or more resources based at least on an attribute of the external compute environment;creating a new management module on a second compute node in the compute environment;provisioning at least one other compute node in the compute environment to process the workload, wherein the new management module is configured to manage the at least one other compute node and communicate with the second management module; andautomatically removing the new management module after the workload has been processed.
23. The non-transitory computer-readable storage medium of claim 22, wherein the at least one other compute node is provisioned according at least to an analysis of at least part of the workload.
24. A method of managing a first compute environment, the method comprising: receiving, at a first management module operating on a first node in the first compute environment, from a second management module associated with an external compute environment separate from the first compute environment, a specification of resources to process a workload, wherein the specification of resources comprises both (i) first data explicitly specifying resources, the specified resources which must be provided by the first compute environment when servicing the workload, and (ii) second data specifying one or more flexible resources, the flexible resources which can be dynamically modified by the first compute environment;creating a new management module on a second node in the first compute environment;provisioning at least one compute node in the compute environment to process the workload, wherein the new management module is configured to manage the at least one compute node and communicate with the second management module; andautomatically removing the new management module after the workload has been processed.
25. The method of claim 24, wherein the second data specifying the one or more flexible resources is based at least in part on one or more attributes of the external compute environment.
26. A computerized apparatus configured for communication with a first compute environment, the computerized apparatus associated with an external compute environment separate from the first compute environment, the computerized apparatus comprising: a processor; anda non-transitory computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the computerized apparatus to perform operations comprising: receive data relating to at least one explicit resource requirement for processing workload;cause creation of a specification of resources to process the workload, the specification of resources comprising both (i) the data relating to the at least one explicit resource requirement, and (ii) data relating to at least one implicit resource requirement, the at least one implicit resource requirement based at least on one or more attributes of the external compute environment;cause transmission of the specification of resources from a first management module of the computerized apparatus to a second management module operating on a first node in the first compute environment, the specification of resources requiring creation of a new management module on a second node in the first compute environment, the new management module configured to manage at least one compute node in the first compute environment to process the workload; andreceive data communications at the first management module from the first compute environment indicating that the new management module has been automatically removed from the first compute environment after the workload has been processed.
27. The computerized apparatus of claim 26, wherein the external compute environment comprises a compute environment having a plurality of commonly managed compute resources, and the first compute environment comprises an on-demand compute environment that is separately managed from the local compute environment.
28. The computerized apparatus of claim 26, wherein the specification of resources is configured to cause creation of at least one virtual cluster within the first compute environment, the creation of the at least one virtual cluster comprising dynamic selection of a plurality of compute resources, and provisioning of the selected compute resources for use by at least part of the workload.
29. The computerized apparatus of claim 26, wherein the specification of resources is configured to cause dynamic co-allocation of a plurality of compute resources, and provisioning of the co-allocated compute resources for use by at least part of the workload.
30. The computerized apparatus of claim 26, wherein the creation of a new management module on a second node in the first compute environment comprises creation of one or more new software instances on one or more respective ones of nodes within the first compute environment.
31. The computerized apparatus of claim 26, wherein: the creation of the specification of resources to process workload is in preparation for an assumption of at least a portion of the workload by the first compute environment; andthe at least one implicit resource requirement based at least on one or more attributes of the external compute environment comprises at least one rigid resource requirement relating to one or more compute processors.
32. The computerized apparatus of claim 26, wherein the at least one implicit resource requirement comprises at least one resource requirement relating to at least one of an operating system (OS) or a network type.
33. The computerized apparatus of claim 26, wherein the instructions are further configured to, when executed by the processor, cause the computerized apparatus to (i) identify one or more resource constraints associated with processing the workload within the first compute environment, and (ii) cause dynamic modification of at least a portion of the first compute environment based at least on the identified one or more resource constraints.
34. The computerized apparatus of claim 33, wherein the identification of the one or more resource constraints comprises identification of one or more resource provisioning requirements necessary for processing of the workload by the at least one compute node.
35. The computerized apparatus of claim 26, wherein the receipt of data relating to at least one explicit resource requirement comprises receipt of user-specified data submitted via a computerized job request to the external compute environment, the user-specified data comprising data rigidly requiring at least one of computer processor or memory requirements.
36. The computerized apparatus of claim 26, wherein the causation of creation of a specification of resources to process the workload is pursuant to (i) notification of a user submitting the workload for processing that additional compute resources are required to process the job, and (ii) affirmative action by the notified user acknowledging or requesting the additional compute resources.
37. The computerized apparatus of claim 26, wherein the causation of creation of a specification of resources to process the workload is (i) automated such that it requires no user intervention, and (ii) is based at least on determination by the computerized apparatus that compute resources in addition to those of the external environment are required to process the workload.
38. The computerized apparatus of claim 26, wherein the first management module of the computerized apparatus comprises a security model configured to account for addition of one or more untrusted resources to at least one of the external compute environment or the first compute environment.
39. A non-transitory computer-readable storage medium having stored therein instructions which, when executed by a processor apparatus of a computerized device within a first compute environment, cause the computerized apparatus to perform operations comprising: receive data relating to at least one explicit resource requirement;cause creation of a specification of resources to process workload, the specification of resources comprising both (i) at least a portion of the data relating to the at least one explicit resource requirement, and (ii) data relating to at least one second resource requirement, the at least one second resource requirement based at least on one or more attributes of the first compute environment;cause transmission of the specification of resources from a first management module of the computerized apparatus to a second management module operating on a first node in a second compute environment, the specification of resources configured to cause creation of a new software instance on a second node in the second compute environment, the new software instance configured to communicate with at least one compute node in the second compute environment to process the workload; andreceive data communications at the first management module from the second compute environment indicating that the new software instance has been automatically removed from the second compute environment after the workload has been processed.
40. A method of operating a first compute environment to cause utilization of compute resources within a second, separately managed compute environment, the method comprising: receiving at least one first data structure at the first compute environment, the at least one data structure comprising a request to process workload, the request comprising at least one explicit resource requirement;creating at least one second data structure, the at least one second data structure comprising both (i) data relating to the at least one explicit resource requirement, and (ii) data relating to at least one additional resource requirement, the at least one additional resource requirement based at least on at least one of a network attribute or operating system attribute of the first compute environment;causing transmission, from a first software module of the first compute environment to a second software module operating on a node in the second compute environment, the specification of resources configured to cause creation of a new software instance on a second node in the second compute environment, the new software instance configured to communicate with at least one compute node in the second compute environment to effect processing of at least a portion of the workload; andreceiving at least one data communication at the first compute environment from the second compute environment, the at least one data communication indicating that the new software instance has been automatically removed from the second compute environment pursuant to completion of processing of the at least portion of the workload.

PRIORITY CLAIM

The present application is a continuation of U.S. patent application Ser. No. 13/758,164, filed Feb. 4, 2013, which is a continuation of U.S. patent application Ser. No. 12/752,622, filed Apr. 1, 2010, now U.S. Pat. No. 8,370,495, issued Feb. 5, 2013, which is a continuation of U.S. patent application Ser. No. 11/276,856, filed Mar. 16, 2006, now U.S. Pat. No. 7,698,430, issued Apr. 13, 2010, which claims priority to U.S. Provisional Application No. 60/662,240 filed Mar. 16, 2005, the contents of which are incorporated herein by reference.

US Referenced Citations (591)

Number	Name	Date	Kind
4215406	Gomola et al.	Jul 1980	A
4412288	Herman	Oct 1983	A
4525780	Bratt et al.	Jun 1985	A
4532893	Day et al.	Aug 1985	A
4553202	Trufyn	Nov 1985	A
4677614	Circo	Jun 1987	A
4850891	Walkup et al.	Jul 1989	A
4852001	Tsushima et al.	Jul 1989	A
4943932	Lark et al.	Jul 1990	A
5146561	Carey et al.	Sep 1992	A
5257374	Hammer et al.	Oct 1993	A
5299115	Fields et al.	Mar 1994	A
5325526	Cameron et al.	Jun 1994	A
5349682	Rosenberry	Sep 1994	A
5377332	Entwistle et al.	Dec 1994	A
5495533	Linehan et al.	Feb 1996	A
5542000	Semba	Jul 1996	A
5598536	Slaughter et al.	Jan 1997	A
5600844	Shaw et al.	Feb 1997	A
5651006	Fujino et al.	Jul 1997	A
5675739	Eilert et al.	Oct 1997	A
5701451	Rogers et al.	Dec 1997	A
5732077	Whitehead	Mar 1998	A
5737009	Payton	Apr 1998	A
5761433	Billings	Jun 1998	A
5761484	Agarwal et al.	Jun 1998	A
5774660	Brendel et al.	Jun 1998	A
5774668	Choquier et al.	Jun 1998	A
5781624	Mitra et al.	Jul 1998	A
5799174	Muntz et al.	Aug 1998	A
5801985	Roohparvar et al.	Sep 1998	A
5826239	Du et al.	Oct 1998	A
5828888	Kozaki et al.	Oct 1998	A
5854887	Kindell et al.	Dec 1998	A
5874789	Su	Feb 1999	A
5911143	Deinhart et al.	Jun 1999	A
5920545	Räsänen et al.	Jul 1999	A
5930167	Lee et al.	Jul 1999	A
5935293	Detering et al.	Aug 1999	A
5961599	Kalavade et al.	Oct 1999	A
5978356	Elwalid et al.	Nov 1999	A
5987611	Freund	Nov 1999	A
6006192	Cheng et al.	Dec 1999	A
6012052	Altschuler et al.	Jan 2000	A
6052707	D'Souza	Apr 2000	A
6078953	Vaid et al.	Jun 2000	A
6085238	Yuasa et al.	Jul 2000	A
6097882	Mogul	Aug 2000	A
6108662	Hoskins et al.	Aug 2000	A
6151598	Shaw et al.	Nov 2000	A
6161170	Burger et al.	Dec 2000	A
6175869	Ahuja et al.	Jan 2001	B1
6182142	Win et al.	Jan 2001	B1
6185575	Orcutt	Feb 2001	B1
6185601	Wolff	Feb 2001	B1
6195678	Komuro	Feb 2001	B1
6201611	Carter et al.	Mar 2001	B1
6202080	Lu et al.	Mar 2001	B1
6223202	Bayeh	Apr 2001	B1
6226677	Slemmer	May 2001	B1
6247056	Chou et al.	Jun 2001	B1
6253230	Couland et al.	Jun 2001	B1
6259675	Honda	Jul 2001	B1
6289382	Bowman-Amuah	Sep 2001	B1
6314114	Coyle et al.	Nov 2001	B1
6317787	Boyd et al.	Nov 2001	B1
6327364	Shaffer et al.	Dec 2001	B1
6330562	Boden et al.	Dec 2001	B1
6330605	Christensen et al.	Dec 2001	B1
6338085	Ramaswamy	Jan 2002	B1
6338112	Wipfel et al.	Jan 2002	B1
6339717	Baumgartl et al.	Jan 2002	B1
6343311	Nishida et al.	Jan 2002	B1
6343488	Hackfort	Feb 2002	B1
6345287	Fong et al.	Feb 2002	B1
6351775	Yu	Feb 2002	B1
6353844	Bitar et al.	Mar 2002	B1
6363434	Eytchison	Mar 2002	B1
6363488	Ginter et al.	Mar 2002	B1
6366945	Fong et al.	Apr 2002	B1
6370584	Bestavros et al.	Apr 2002	B1
6374254	Cochran et al.	Apr 2002	B1
6385302	Antonucci et al.	May 2002	B1
6392989	Jardetzky et al.	May 2002	B1
6393569	Orenshteyn	May 2002	B1
6393581	Friedman et al.	May 2002	B1
6404768	Basak et al.	Jun 2002	B1
6418459	Gulick	Jul 2002	B1
6434568	Bowman-Amuah	Aug 2002	B1
6438125	Brothers	Aug 2002	B1
6438134	Chow et al.	Aug 2002	B1
6438594	Bowman-Amuah	Aug 2002	B1
6452924	Golden et al.	Sep 2002	B1
6453383	Stoddard et al.	Sep 2002	B1
6463454	Lumelsky et al.	Oct 2002	B1
6464261	Dybevik et al.	Oct 2002	B1
6466980	Lumelsky et al.	Oct 2002	B1
6477580	Bowman-Amuah	Nov 2002	B1
6487390	Virine et al.	Nov 2002	B1
6490432	Wegener et al.	Dec 2002	B1
6502135	Munger et al.	Dec 2002	B1
6520591	Jun et al.	Feb 2003	B1
6529499	Doshi et al.	Mar 2003	B1
6564261	Gudjonsson et al.	May 2003	B1
6571215	Mahapatro	May 2003	B1
6571391	Acharya et al.	May 2003	B1
6578068	Bowman-Amuah	Jun 2003	B1
6587469	Bragg	Jul 2003	B1
6600898	De Bonet et al.	Jul 2003	B1
6601234	Bowman-Amuah	Jul 2003	B1
6606660	Bowman-Amuah	Aug 2003	B1
6622168	Datta	Sep 2003	B1
6626077	Gilbert	Sep 2003	B1
6628649	Raj et al.	Sep 2003	B1
6629081	Cornelius et al.	Sep 2003	B1
6633544	Rexford et al.	Oct 2003	B1
6640238	Bowman-Amuah	Oct 2003	B1
6651098	Carroll et al.	Nov 2003	B1
6661787	O'Connell et al.	Dec 2003	B1
6724733	Schuba et al.	Apr 2004	B1
6735188	Becker et al.	May 2004	B1
6738736	Bond	May 2004	B1
6772211	Lu et al.	Aug 2004	B2
6775701	Pan	Aug 2004	B1
6779016	Aziz et al.	Aug 2004	B1
6781990	Puri et al.	Aug 2004	B1
6785724	Drainville	Aug 2004	B1
6816903	Rakoshitz et al.	Nov 2004	B1
6816905	Sheets et al.	Nov 2004	B1
6857020	Chaar et al.	Feb 2005	B1
6862606	Major et al.	Mar 2005	B1
6868097	Soda et al.	Mar 2005	B1
6874031	Corbeil	Mar 2005	B2
6928471	Pabari et al.	Aug 2005	B2
6934702	Faybishenko et al.	Aug 2005	B2
6947982	McGann et al.	Sep 2005	B1
6950833	Costello et al.	Sep 2005	B2
6971098	Khare et al.	Nov 2005	B2
6978310	Rodriguez et al.	Dec 2005	B1
7013322	Lahr	Mar 2006	B2
7020719	Grove et al.	Mar 2006	B1
7035854	Hsaio et al.	Apr 2006	B2
7058070	Tran et al.	Jun 2006	B2
7076717	Grossman et al.	Jul 2006	B2
7080378	Noland et al.	Jul 2006	B1
7082606	Wood et al.	Jul 2006	B2
7085825	Pishevar et al.	Aug 2006	B1
7085837	Kimbrel et al.	Aug 2006	B2
7085893	Krissell et al.	Aug 2006	B2
7089294	Baskey et al.	Aug 2006	B1
7099933	Wallace et al.	Aug 2006	B1
7100192	Igawa et al.	Aug 2006	B1
7102996	Amdahl et al.	Sep 2006	B1
7103625	Hipp et al.	Sep 2006	B1
7124289	Suorsa	Oct 2006	B1
7126913	Patel et al.	Oct 2006	B1
7127613	Pabla et al.	Oct 2006	B2
7127633	Olson et al.	Oct 2006	B1
7140020	McCarthy et al.	Nov 2006	B2
7143088	Green et al.	Nov 2006	B2
7146233	Aziz et al.	Dec 2006	B2
7146416	Yoo et al.	Dec 2006	B1
7155478	Ims et al.	Dec 2006	B2
7155502	Galloway et al.	Dec 2006	B1
7171415	Kan et al.	Jan 2007	B2
7299294	Bruck et al.	Jan 2007	B1
7177823	Lam et al.	Feb 2007	B2
7185046	Ferstl et al.	Feb 2007	B2
7197549	Salama et al.	Mar 2007	B1
7197559	Goldstein et al.	Mar 2007	B2
7206819	Schmidt	Apr 2007	B2
7213065	Watt	May 2007	B2
7216173	Clayton et al.	May 2007	B2
7225249	Barry et al.	May 2007	B1
7228350	Hong et al.	Jun 2007	B2
7231445	Aweya et al.	Jun 2007	B1
7242501	Ishimoto	Jul 2007	B2
7243351	Kundu	Jul 2007	B2
7249179	Romero et al.	Jul 2007	B1
7251688	Leighton et al.	Jul 2007	B2
7275249	Miller et al.	Sep 2007	B1
7278008	Case et al.	Oct 2007	B1
7278142	Bandhole et al.	Oct 2007	B2
7281045	Aggarwal et al.	Oct 2007	B2
7284109	Paxie et al.	Oct 2007	B1
7293092	Sukegawa	Nov 2007	B2
7305464	Phillipi et al.	Dec 2007	B2
7313793	Traut et al.	Dec 2007	B2
7320025	Steinberg et al.	Jan 2008	B1
7324555	Chen et al.	Jan 2008	B1
7328406	Kalinoski et al.	Feb 2008	B2
7334108	Case et al.	Feb 2008	B1
7334230	Chung et al.	Feb 2008	B2
7340578	Khanzode	Mar 2008	B1
7343467	Brown et al.	Mar 2008	B2
7350186	Coleman et al.	Mar 2008	B2
7353276	Bain et al.	Apr 2008	B2
7356655	Allen et al.	Apr 2008	B2
7356770	Jackson	Apr 2008	B1
7366101	Varier et al.	Apr 2008	B1
7373391	Iinuma	May 2008	B2
7373524	Motsinger et al.	May 2008	B2
7380039	Miloushev et al.	May 2008	B2
7386586	Headley et al.	Jun 2008	B1
7386611	Dias et al.	Jun 2008	B2
7389310	Bhagwan et al.	Jun 2008	B1
7392325	Grove et al.	Jun 2008	B2
7398216	Barnett et al.	Jul 2008	B2
7398471	Rambacher	Jul 2008	B1
7401355	Supnik et al.	Jul 2008	B2
7415709	Hipp et al.	Aug 2008	B2
7418518	Grove et al.	Aug 2008	B2
7421402	Chang et al.	Sep 2008	B2
7421500	Talwar et al.	Sep 2008	B2
7426489	Van Soestbergen et al.	Sep 2008	B2
7426546	Breiter et al.	Sep 2008	B2
7428540	Coates et al.	Sep 2008	B1
7433304	Galloway et al.	Oct 2008	B1
7437460	Chidambaran et al.	Oct 2008	B2
7437730	Goyal	Oct 2008	B2
7441261	Slater et al.	Oct 2008	B2
7451199	Kandefer et al.	Nov 2008	B2
7451201	Alex et al.	Nov 2008	B2
7454467	Girouard et al.	Nov 2008	B2
7461134	Ambrose	Dec 2008	B2
7463587	Rajsic et al.	Dec 2008	B2
7464159	DiLuoffo et al.	Dec 2008	B2
7467225	Anerousis et al.	Dec 2008	B2
7475419	Basu et al.	Jan 2009	B1
7483945	Blumofe	Jan 2009	B2
7487254	Walsh et al.	Feb 2009	B2
7492720	Pruthi et al.	Feb 2009	B2
7502884	Shah	Mar 2009	B1
7503045	Aziz et al.	Mar 2009	B1
7516221	Souder et al.	Apr 2009	B2
7529835	Agronow et al.	May 2009	B1
7533385	Barnes	May 2009	B1
7543052	Cesa Klein	Jun 2009	B1
7546553	Bozak et al.	Jun 2009	B2
7551614	Teisberg et al.	Jun 2009	B2
7554930	Gaddis et al.	Jun 2009	B2
7568199	Bozak et al.	Jul 2009	B2
7577722	Khandekar et al.	Aug 2009	B1
7577834	Traversat et al.	Aug 2009	B1
7577959	Nguyen et al.	Aug 2009	B2
7583607	Steele et al.	Sep 2009	B2
7584274	Bond	Sep 2009	B2
7590746	Slater et al.	Sep 2009	B2
7590747	Coates et al.	Sep 2009	B2
7594011	Chandra	Sep 2009	B2
7594015	Bozak	Sep 2009	B2
7596784	Abrams et al.	Sep 2009	B2
7610289	Muret et al.	Oct 2009	B2
7627691	Buchsbaum et al.	Dec 2009	B1
7631066	Schatz et al.	Dec 2009	B1
7640547	Neiman et al.	Dec 2009	B2
7657535	Moyaux et al.	Feb 2010	B2
7668809	Kelly et al.	Feb 2010	B1
7680933	Fatula, Jr.	Mar 2010	B2
7685281	Saraiya et al.	Mar 2010	B1
7685602	Tran et al.	Mar 2010	B1
7693976	Perry et al.	Apr 2010	B2
7693993	Sheets et al.	Apr 2010	B2
7694305	Karlsson et al.	Apr 2010	B2
7698386	Amidon et al.	Apr 2010	B2
7698398	Lai	Apr 2010	B1
7698430	Jackson	Apr 2010	B2
7701948	Rabie et al.	Apr 2010	B2
7716334	Rao et al.	May 2010	B2
7725583	Jackson	May 2010	B2
7739541	Rao et al.	Jun 2010	B1
7743147	Suorsa et al.	Jun 2010	B2
7747451	Keohane et al.	Jun 2010	B2
RE41440	Briscoe et al.	Jul 2010	E
7752258	Lewin et al.	Jul 2010	B2
7752624	Crawford, Jr. et al.	Jul 2010	B2
7756658	Kulkarni et al.	Jul 2010	B2
7757236	Singh	Jul 2010	B1
7761557	Fellenstein et al.	Jul 2010	B2
7765288	Bainbridge et al.	Jul 2010	B2
7765299	Romero	Jul 2010	B2
7769620	Fernandez et al.	Aug 2010	B1
7769803	Birdwell et al.	Aug 2010	B2
7770120	Baudisch	Aug 2010	B2
7774331	Barth et al.	Aug 2010	B2
7778234	Cooke et al.	Aug 2010	B2
7788403	Darugar et al.	Aug 2010	B2
7793288	Sameske	Sep 2010	B2
7796619	Feldmann et al.	Sep 2010	B1
7813822	Hoffberg	Oct 2010	B1
7827361	Karlsson et al.	Nov 2010	B1
7844787	Ranganathan et al.	Nov 2010	B2
7900206	Joshi et al.	Mar 2011	B1
7930397	Midgley	Apr 2011	B2
8078708	Wang	Dec 2011	B1
8185776	Gentes et al.	May 2012	B1
8196133	Kakumani et al.	Jun 2012	B2
8260893	Bandhole et al.	Sep 2012	B1
8261349	Peng	Sep 2012	B2
8321048	Coss et al.	Nov 2012	B1
8464250	Ansel	Jun 2013	B1
8726278	Shawver et al.	May 2014	B1
8863143	Jackson	Oct 2014	B2
8954584	Subbarayan et al.	Feb 2015	B1
9116755	Jackson	Aug 2015	B2
20010015733	Sklar	Aug 2001	A1
20010051929	Suzuki	Dec 2001	A1
20010052016	Skene et al.	Dec 2001	A1
20020002578	Yamashita	Jan 2002	A1
20020002636	Vange et al.	Jan 2002	A1
20020010783	Primak et al.	Jan 2002	A1
20020032716	Nagato	Mar 2002	A1
20020049608	Hartsell et al.	Apr 2002	A1
20020059094	Hosea et al.	May 2002	A1
20020059274	Hartsell et al.	May 2002	A1
20020062377	Hillman et al.	May 2002	A1
20020062451	Scheidt et al.	May 2002	A1
20020083299	Van Huben et al.	Jun 2002	A1
20020091786	Yamaguchi et al.	Jul 2002	A1
20020093915	Larson	Jul 2002	A1
20020103886	Rawson, III	Aug 2002	A1
20020107962	Richter et al.	Aug 2002	A1
20020116234	Nagasawa	Aug 2002	A1
20020116721	Dobes et al.	Aug 2002	A1
20020120741	Webb et al.	Aug 2002	A1
20020133537	Lau	Sep 2002	A1
20020133821	Shteyn	Sep 2002	A1
20020138635	Redlich	Sep 2002	A1
20020152305	Jackson et al.	Oct 2002	A1
20020156891	Ulrich et al.	Oct 2002	A1
20020156984	Padovano	Oct 2002	A1
20020161869	Griffin et al.	Oct 2002	A1
20020166117	Abrams et al.	Nov 2002	A1
20020173984	Robertson et al.	Nov 2002	A1
20020174165	Kawaguchi	Nov 2002	A1
20020174227	Hartsell et al.	Nov 2002	A1
20020198734	Greene et al.	Dec 2002	A1
20030004772	Dutta et al.	Jan 2003	A1
20030014503	Legout et al.	Jan 2003	A1
20030014524	Tormasov	Jan 2003	A1
20030014539	Reznick	Jan 2003	A1
20030028656	Babka	Feb 2003	A1
20030036820	Yellepeddy et al.	Feb 2003	A1
20030039246	Guo et al.	Feb 2003	A1
20030041308	Ganesan et al.	Feb 2003	A1
20030050989	Marinescu et al.	Mar 2003	A1
20030058277	Bowman-Amuah	Mar 2003	A1
20030065703	Aborn	Apr 2003	A1
20030069949	Chan et al.	Apr 2003	A1
20030097429	Wu et al.	May 2003	A1
20030097439	Strayer et al.	May 2003	A1
20030101084	Otero Perez	May 2003	A1
20030105721	Ginter et al.	Jun 2003	A1
20030112792	Cranor et al.	Jun 2003	A1
20030120472	Lind	Jun 2003	A1
20030120701	Pulsipher et al.	Jun 2003	A1
20030120710	Pulsipher et al.	Jun 2003	A1
20030126013	Shand	Jul 2003	A1
20030126202	Watt	Jul 2003	A1
20030126283	Prakash et al.	Jul 2003	A1
20030144894	Robertson et al.	Jul 2003	A1
20030154112	Neiman et al.	Aug 2003	A1
20030158940	Leigh	Aug 2003	A1
20030177121	Moona et al.	Sep 2003	A1
20030177334	King et al.	Sep 2003	A1
20030182429	Jagels	Sep 2003	A1
20030191857	Terrell et al.	Oct 2003	A1
20030195931	Dauger	Oct 2003	A1
20030202709	Simard et al.	Oct 2003	A1
20030204773	Petersen et al.	Oct 2003	A1
20030210694	Jayaraman et al.	Nov 2003	A1
20030212738	Wookey et al.	Nov 2003	A1
20030231647	Petrovykh	Dec 2003	A1
20040003077	Bantz et al.	Jan 2004	A1
20040003086	Parham et al.	Jan 2004	A1
20040010544	Slater et al.	Jan 2004	A1
20040010550	Gopinath	Jan 2004	A1
20040015579	Cooper et al.	Jan 2004	A1
20040015973	Skovira	Jan 2004	A1
20040034873	Zenoni	Feb 2004	A1
20040039815	Evans et al.	Feb 2004	A1
20040044718	Ferstl	Mar 2004	A1
20040054630	Ginter et al.	Mar 2004	A1
20040054777	Ackaouy et al.	Mar 2004	A1
20040054780	Romero	Mar 2004	A1
20040066782	Nassar	Apr 2004	A1
20040068730	Miller et al.	Apr 2004	A1
20040071147	Roadknight et al.	Apr 2004	A1
20040073908	Benejam	Apr 2004	A1
20040103078	Smedberg et al.	May 2004	A1
20040103305	Ginter et al.	May 2004	A1
20040107273	Biran et al.	Jun 2004	A1
20040111307	Demsky	Jun 2004	A1
20040117610	Hensley	Jun 2004	A1
20040121777	Schwarz et al.	Jun 2004	A1
20040128495	Hensley	Jul 2004	A1
20040128670	Robinson et al.	Jul 2004	A1
20040133665	Deboer et al.	Jul 2004	A1
20040139202	Talwar et al.	Jul 2004	A1
20040143664	Usa et al.	Jul 2004	A1
20040150664	Baudisch	Aug 2004	A1
20040179528	Powers et al.	Sep 2004	A1
20040181370	Froehlich et al.	Sep 2004	A1
20040181476	Smith et al.	Sep 2004	A1
20040189677	Amann et al.	Sep 2004	A1
20040194098	Chung et al.	Sep 2004	A1
20040199621	Lau	Oct 2004	A1
20040199646	Susai et al.	Oct 2004	A1
20040203670	King et al.	Oct 2004	A1
20040213395	Ishii et al.	Oct 2004	A1
20040218615	Griffin et al.	Nov 2004	A1
20040221038	Clarke et al.	Nov 2004	A1
20040236852	Birkestrand et al.	Nov 2004	A1
20040260746	Brown et al.	Dec 2004	A1
20040267897	Hill et al.	Dec 2004	A1
20050010465	Drew et al.	Jan 2005	A1
20050021759	Gupta et al.	Jan 2005	A1
20050021862	Schroeder et al.	Jan 2005	A1
20050022188	Tameshige et al.	Jan 2005	A1
20050027863	Talwar et al.	Feb 2005	A1
20050027864	Bozak et al.	Feb 2005	A1
20050027865	Bozak et al.	Feb 2005	A1
20050034070	Meir et al.	Feb 2005	A1
20050038835	Chidambaran et al.	Feb 2005	A1
20050044226	McDermott et al.	Feb 2005	A1
20050044228	Birkestrand et al.	Feb 2005	A1
20050049884	Hunt et al.	Mar 2005	A1
20050050057	Mital et al.	Mar 2005	A1
20050050200	Mizoguchi	Mar 2005	A1
20050054354	Roman et al.	Mar 2005	A1
20050055322	Masters et al.	Mar 2005	A1
20050055694	Lee	Mar 2005	A1
20050055698	Sasaki et al.	Mar 2005	A1
20050060360	Doyle et al.	Mar 2005	A1
20050060608	Marchand	Mar 2005	A1
20050066358	Anderson et al.	Mar 2005	A1
20050076145	Ben-Zvi et al.	Apr 2005	A1
20050080845	Gopinath	Apr 2005	A1
20050080891	Cauthron	Apr 2005	A1
20050080930	Joseph	Apr 2005	A1
20050102396	Hipp	May 2005	A1
20050102683	Branson	May 2005	A1
20050108407	Johnson et al.	May 2005	A1
20050114862	Bisdikian et al.	May 2005	A1
20050120160	Plouffe et al.	Jun 2005	A1
20050125213	Chen et al.	Jun 2005	A1
20050125537	Martins et al.	Jun 2005	A1
20050125538	Tawil	Jun 2005	A1
20050131898	Fatula	Jun 2005	A1
20050132378	Horvitz et al.	Jun 2005	A1
20050138618	Gebhart	Jun 2005	A1
20050144315	George et al.	Jun 2005	A1
20050149940	Calinescu	Jul 2005	A1
20050160137	Ishikawa et al.	Jul 2005	A1
20050165925	Dan et al.	Jul 2005	A1
20050177600	Eilam et al.	Aug 2005	A1
20050187866	Lee	Aug 2005	A1
20050188088	Fellenstein et al.	Aug 2005	A1
20050190236	Ishimoto	Sep 2005	A1
20050192771	Fischer et al.	Sep 2005	A1
20050193103	Drabik	Sep 2005	A1
20050193231	Scheuren	Sep 2005	A1
20050198200	Subramanian et al.	Sep 2005	A1
20050204040	Ferri et al.	Sep 2005	A1
20050209892	Miller	Sep 2005	A1
20050210470	Chung et al.	Sep 2005	A1
20050213507	Banerjee et al.	Sep 2005	A1
20050213560	Duvvury	Sep 2005	A1
20050234846	Davidson et al.	Oct 2005	A1
20050235150	Kaler et al.	Oct 2005	A1
20050243867	Petite	Nov 2005	A1
20050246705	Etelson et al.	Nov 2005	A1
20050267948	McKinley et al.	Dec 2005	A1
20050268063	Diao et al.	Dec 2005	A1
20050278392	Hansen et al.	Dec 2005	A1
20050278760	Dewar et al.	Dec 2005	A1
20050283822	Appleby et al.	Dec 2005	A1
20050288961	Tabrizi	Dec 2005	A1
20050289540	Nguyen et al.	Dec 2005	A1
20060008256	Khedouri et al.	Jan 2006	A1
20060015555	Douglass et al.	Jan 2006	A1
20060015637	Chung	Jan 2006	A1
20060015773	Singh et al.	Jan 2006	A1
20060028991	Tan et al.	Feb 2006	A1
20060031379	Kasriel et al.	Feb 2006	A1
20060031547	Tsui et al.	Feb 2006	A1
20060031813	Bishop et al.	Feb 2006	A1
20060039246	King et al.	Feb 2006	A1
20060041444	Flores	Feb 2006	A1
20060047920	Moore et al.	Mar 2006	A1
20060048157	Dawson et al.	Mar 2006	A1
20060053215	Sharma	Mar 2006	A1
20060059253	Goodman et al.	Mar 2006	A1
20060069671	Conley et al.	Mar 2006	A1
20060069774	Chen	Mar 2006	A1
20060069926	Ginter et al.	Mar 2006	A1
20060089894	Balk et al.	Apr 2006	A1
20060090136	Miller et al.	Apr 2006	A1
20060095917	Black-Ziegelbein et al.	May 2006	A1
20060112184	Kuo	May 2006	A1
20060117208	Davidson	Jun 2006	A1
20060117317	Crawford et al.	Jun 2006	A1
20060126619	Teisberg et al.	Jun 2006	A1
20060126667	Smith et al.	Jun 2006	A1
20060129687	Goldszmidt et al.	Jun 2006	A1
20060136235	Keohane et al.	Jun 2006	A1
20060136928	Crawford et al.	Jun 2006	A1
20060136929	Miller et al.	Jun 2006	A1
20060143350	Miloushev et al.	Jun 2006	A1
20060149695	Bossman et al.	Jul 2006	A1
20060153191	Rajsic et al.	Jul 2006	A1
20060155740	Chen et al.	Jul 2006	A1
20060155912	Singh et al.	Jul 2006	A1
20060159088	Aghvami et al.	Jul 2006	A1
20060161466	Trinon et al.	Jul 2006	A1
20060161585	Clarke et al.	Jul 2006	A1
20060168107	Balan et al.	Jul 2006	A1
20060168224	Midgley	Jul 2006	A1
20060173730	Birkestrand	Aug 2006	A1
20060189349	Montulli et al.	Aug 2006	A1
20060190775	Aggarwal et al.	Aug 2006	A1
20060190975	Gonzalez	Aug 2006	A1
20060212332	Jackson	Sep 2006	A1
20060212333	Jackson	Sep 2006	A1
20060212740	Jackson	Sep 2006	A1
20060224725	Bali et al.	Oct 2006	A1
20060224741	Jackson	Oct 2006	A1
20060227810	Childress et al.	Oct 2006	A1
20060251419	Zadikian et al.	Nov 2006	A1
20060294238	Naik et al.	Dec 2006	A1
20070003051	Kiss et al.	Jan 2007	A1
20070050777	Hutchinson et al.	Mar 2007	A1
20070061441	Landis et al.	Mar 2007	A1
20070067366	Landis	Mar 2007	A1
20070067435	Landis et al.	Mar 2007	A1
20070083899	Compton et al.	Apr 2007	A1
20070088822	Coile et al.	Apr 2007	A1
20070094691	Gazdzinski	Apr 2007	A1
20070124344	Rajakannimariyan et al.	May 2007	A1
20070143824	Shahbazi	Jun 2007	A1
20070155406	Dowling et al.	Jul 2007	A1
20070180380	Khavari et al.	Aug 2007	A1
20070264986	Warrillow et al.	Nov 2007	A1
20070266136	Esfahany et al.	Nov 2007	A1
20070271375	Hwang	Nov 2007	A1
20070297350	Eilam	Dec 2007	A1
20080104231	Dey et al.	May 2008	A1
20080215730	Sundaram et al.	Sep 2008	A1
20080255953	Chang et al.	Oct 2008	A1
20080263558	Lin et al.	Oct 2008	A1
20080279167	Cardei et al.	Nov 2008	A1
20090043809	Fakhouri et al.	Feb 2009	A1
20090070771	Yuyitung et al.	Mar 2009	A1
20090100133	Giulio et al.	Apr 2009	A1
20090103501	Farrag et al.	Apr 2009	A1
20090105059	Dorry et al.	Apr 2009	A1
20090113056	Tameshige et al.	Apr 2009	A1
20090138594	Fellenstein et al.	May 2009	A1
20090178132	Hudis et al.	Jul 2009	A1
20090210356	Abrams et al.	Aug 2009	A1
20090210495	Wolfson et al.	Aug 2009	A1
20090216910	Duchesneau	Aug 2009	A1
20090217329	Riedl et al.	Aug 2009	A1
20090225360	Shirai	Sep 2009	A1
20090234962	Strong et al.	Sep 2009	A1
20090234974	Arndt et al.	Sep 2009	A1
20090235104	Fung	Sep 2009	A1
20090238349	Pezzutti	Sep 2009	A1
20090240547	Fellenstein et al.	Sep 2009	A1
20090292824	Marashi et al.	Nov 2009	A1
20090327489	Swildens et al.	Dec 2009	A1
20100036945	Allibhoy et al.	Feb 2010	A1
20100049931	Jacobson et al.	Feb 2010	A1
20100088205	Robertson	Apr 2010	A1
20100091676	Moran et al.	Apr 2010	A1
20100103837	Jungck et al.	Apr 2010	A1
20100114531	Korn et al.	May 2010	A1
20100131624	Ferris	May 2010	A1
20100153546	Clubb et al.	Jun 2010	A1
20100217801	Leighton et al.	Aug 2010	A1
20100235234	Shuster	Sep 2010	A1
20100281166	Buyya et al.	Nov 2010	A1
20100318665	Demmer et al.	Dec 2010	A1
20100332262	Horvitz et al.	Dec 2010	A1
20110179134	Mayo et al.	Jul 2011	A1
20120137004	Smith	May 2012	A1
20120159116	Lim et al.	Jun 2012	A1
20120185334	Sarkar et al.	Jul 2012	A1
20120218901	Jungck et al.	Aug 2012	A1
20120226788	Jackson	Sep 2012	A1
20140317292	Odom	Oct 2014	A1

Foreign Referenced Citations (24)

Number	Date	Country
2496783	Mar 2004	CA
0268435	May 1988	EP
0 859 314	Aug 1998	EP
1331564	Jul 2003	EP
1365545	Nov 2003	EP
1492309	Dec 2004	EP
1865684	Dec 2007	EP
2391744	Feb 2004	GB
20040107934	Dec 2004	KR
WO 1998011702	Mar 1998	WO
WO 1999015999	Apr 1999	WO
WO 1999057660	Nov 1999	WO
WO 2000014938	Mar 2000	WO
WO 2000060825	Oct 2000	WO
WO 2001009791	Feb 2001	WO
WO 0114987	Mar 2001	WO
WO 0115397	Mar 2001	WO
WO 2001039470	May 2001	WO
WO 2003046751	Jun 2003	WO
WO 2004070547	Aug 2004	WO
WO 2004092884	Oct 2004	WO
WO 2005017783	Feb 2005	WO
WO 2006036277	Apr 2006	WO
WO 2006112981	Oct 2006	WO

Non-Patent Literature Citations (173)

Entry
US 7,774,482 B1, 08/2010, Szeto et al. (withdrawn)
Kuan-Wei Cheng, Chao-Tung Yang, Chuan-Lin Lai and Shun-Chyi Chang, “A parallel loop self-scheduling on grid computing environments,” 7th International Symposium on Parallel Architectures, Algorithms and Networks, 2004. Proceedings., 2004, pp. 409-414 (Year: 2004).
Banicescu et al., “Efficient Resource Management for Scientific Applications in Distributed Computing Environment”, 1998, Mississippi State Univ, Dept of Comp. Science, p. 45-54. (Year: 1998).
Banicescu et al., “Competitive Resource Management in Distributed Computing Environments with Hectiling”, 1999, High Performance Computing Symposium, p. 1-7 (Year: 1999).
Liu, Simon. “Securing the Clouds: Methodologies and Practices.” Encyclopedia of Cloud Computing (2016): 220. (Year: 2016).
Final Office Action on U.S. Appl. No. 14/154,912 dated Dec. 7, 2017.
Notice of Allowance on U.S. Appl. No. 14/331,772 dated Jan. 10, 2018.
Non-Final Office Action on U.S. Appl. No. 14/590,102 dated Aug. 15, 2017.
Non-Final Office Action issued on U.S. Appl. No. 14/833,673, dated Sep. 24, 2015.
Non-Final Office Action on U.S. Appl. No. 14/154,912 dated Jul. 20, 2017.
Non-Final Office Action on U.S. Appl. No. 14/331,772 dated Aug. 11, 2017.
U.S. Appl. No. 60/662,240, filed Nov. 1985, Trufyn.
U.S. Appl. No. 11/279,007, filed Jul. 2000, Smith et al.
Chandra, Abhishek et al., “Quantifying the Benefits of Resource Multiplexing in On-Demand Data Centers”, Department of Computer Science, University of Massachusetts Amherst, 2003.
Rolia, Jerome et al., “Adaptive Internet Data Centers”, Hewlett Packard Labs, Palo Alto, CA, USA , 2000.
Chase, Jeffrey et al., “Dynamic Virtual Clusters in a Grid Site Manager”, Department of Computer Science, Duke University, Box 30129, Durham, NC 27708, USA. 2003.
Doyle, Ronald et al., “Model-Based Resource Provisioning in a Web Service Utility”, IBM, Research Triangle Park, Department of Computer Science, Duke University, 2003.
Bradford, Lindsay et al., “Experience Using a Coordination-based Architecture for Adaptive Web Content Provision”, Centre for Information Technology Innovation, Queensland University of Technology, Australia, 2005.
Ranjan, S. et al., “QoS-Driven Server Migration for Internet Data Centers”, In Proceedings of IWQoS, 2002.
Russell, Clark, et al., “Providing Scalable Web Service Using Multicast Delivery”, College of Computing, Georgia Institute of Technology, Atlanta, GA 30332-0280, 1995.
Reed, Daniel et al., “The Next Frontier: Interactive and Closed Loop Performance Steering”, Department of Computer Science, University of Illinois, Urbana, Illinois 61801, International Conference on Parallel Processing Workshop, 1996.
Bian, Qiyong, et al., “Dynamic Flow Switching, A New Communication Service for ATM Networks”, 1997.
Feldmann, Anja, et al., “Reducing Overhead in Flow-Switched Networks: An Empirical Study of Web Traffic”, AT&T Labs—Research, Florham Park, NJ, 1998.
Feldmann, Anja, et al., “Efficient Policies for Carrying Web Traffic Over Flow-Switched Networks”, IEEE/ACM Transactions on Networking, vol. 6, No. 6, Dec. 1998.
Feng, Chen, et al., “Replicated Servers Allocation for Multiple Information Sources in a Distributed Environment”, Department of Computer Science, Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong, Sep. 2000.
Wang, Z., et al., “Resource Allocation for Elastic Traffic: Architecture and Mechanisms”, Bell Laboratories, Lucent Technologies, Network Operations and Management Symposium, 2000. 2000 IEEE/IFIP, pp. 157-170. Apr. 2000.
Fan, Li, et al., “Summary Cache: A Scalable Wide-Area Web Cache Sharing Protocol”, IEEE/ACM Transactions on networking, vol. 8, No. 3, Jun. 2000.
Yang, Chu-Sing, et al., “Building an Adaptable, Fault Tolerant, and Highly Manageable Web Server on Clusters of Non-dedicated Workstations”, Department of Computer Science and Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan, R.O.C.. 2000.
Appleby, K., et al., “Oceano-SLA Based Management of a Computing Utility”, IBM T.J. Watson Research Center, P.O.Box 704, Yorktown Heights, New York 10598, USA. Proc. 7th IFIP/IEEE Int'l Symp. Integrated Network Management, IEEE Press 2001.
Abdelzaher, Tarek, et al., “Performance Guarantees for Web Server End-Systems: A Control-Theoretical Approach”, IEEE Transactions on Parallel and Distributed Systems, vol. 13, No. 1, Jan. 2002.
Garg, Rahul, et al., “A SLA Framework for QoS Provisioning and Dynamic Capacity Allocation”, 2002.
Xu, Jun, et al., “Sustaining Availability of Web Services under Distributed Denial of Service Attacks”, IEEE Transactions on Computers, vol. 52, No. 2, pp. 195-208, Feb. 2003.
McCann, Julie, et al., “Patia: Adaptive Distributed Webserver (A Position Paper)”, Department of Computing, Imperial College London, SW1 2BZ, UK. 2003.
Urgaonkar, Bhuvan, et al., “Sharc: Managing CPU and Network Bandwidth in Shared Clusters”, IEEE Transactions on Parallel and Distributed Systems, vol. 15, No. 1, pp. 2-17, Jan. 2004.
Liao, Raymond, et al., “Dynamic Core Provisioning for Quantitative Differentiated Services”, IEEE/ACM Transactions on Networking, vol. 12, No. 3, pp. 429-442, Jun. 2004.
Amini, Lisa, et al., “Effective Peering for Multi-provider Content Delivery Services”, IBM Research, Hawthorne, New York, Columbia University, New York, New York. 2004.
Soldatos, John, et al., “On the Building Blocks of Quality of Service in Heterogeneous IP Networks”, IEEE Communications Surveys, The Electronic Magazine of Original Peer-Reviewed Survey Articles, vol. 7, No. 1. First Quarter 2005.
Devarakonda, Murthy, et al., “Policy-Based Multi-Datacenter Resource Management”, IBM Research, P.O.Box 704, Yorktown Hts, NY. Sixth IEEE International Workshop on Policies for Distributed Systems and Networks, pp. 247-250, Jun. 2005.
Rashid, Mohammad, et al., “An Analytical Approach to Providing Controllable Differentiated Quality of Service in Web Servers”, IEEE Transactions on Parallel and Distributed Systems, vol. 16, No. 11, pp. 1022-1033, Nov. 2005.
Braumandl, R. et al., “ObjectGlobe: Ubiquitous query processing on the Internet”, Universit{umlaut over ( )}at Passau, Lehrstuhl f{umlaut over ( )}ur Informatik, 94030 Passau, Germany. Technische Universit{umlaut over ( )}at M{umlaut over ( )}unchen, Institut f{umlaut over ( )}ur Informatik, 81667 M{umlaut over ( )}unchen, Germany. Edited by F. Casati, M.-C. Shan, D. Georgakopoulos. Accepted: Mar. 14, 2001.Published online: Jun. 7, 2001—_c Springer-Verlag 2001.
Kai, Shen, et al., “Supporting Cluster-based Network Services on Functionally Symmetric Software Architecture”, Proceedings of the 2004 ACM/IEEE conference on Supercomputing, 2004.
Benkner, Siegfried, et al., “VGE—A Service-Oriented Grid Environment for On-Demand Supercomputing”, Institute for Software Science, University of Vienna, Nordbergstrasse 15/C/3, A-1090 Vienna, Austria. Proceedings of the 5th IEEE/ACM International Workshop on Grid Computing. pp. 11-18. 2004.
Amir, Yari et al., “WALRUS—a Low Latency, High Throughput Web Service Using Internet-wide Replication”, Department of Computer Science, The Johns Hopkins University, 1998.
Azuma, K. et al., “Design, Implementation and Evaluation of Resource Management System for Internet Servers”, Journal of High Speed Networking, IOS Press, vol. 14, No. 4/2005, Oct. 2005.
Baentsch, Michael et al., “World Wide Web Caching: The Application-Level View of the Internet”, Communications Magazine, IEEE, vol. 35, Issue 6, pp. 170-178, Jun. 1997.
Banga, Gaurav et al., “Resource Containers: A New Facility for Resource Management in Server Systems”, Rice University, originally published in the Proceedings of the 3rd Symposium on Operating Systems Design and Implementation, New Orleans, Louisiana, Feb. 1999.
Belloum, A. et al., “A Scalable Web Server Architecture”, World Wide Web: Internet and Web Information Systems, 5, 5-23, 2002 Kluwer Academic Publishers. Manufactured in The Netherlands. 2000.
Cardellini, Valeria et al., “Geographic Load Balancing for Scalable Distributed Web Systems”, Proceedings of the 8th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, pp. 20-27. 2000.
Casalicchio, Emiliano, et al., “Static and Dynamic Scheduling Algorithms for Scalable Web Server Farm”, University of Roma Tor Vergata, Roma, Italy, 00133. 2001.
Chase, Jeffrey et al., “Dynamic Virtual Clusters in a Grid Site Manager”, Department of Computer Science, Duke University, Box 90129, Durham, NC 27708, U.S.A. Proceedings of the 12th IEEE International Symposium on High Performance Distributed Computing, 2003.
Chawla, Hamesh et al., “HydraNet: Network Support for Scaling of Large-Scale Services”, Proceedings of 7th International Conference on Computer Communications and Networks, 1998. Oct. 1998.
Chen, Xiangping et al., “Performance Evaluation of Service Differentiating Internet Servers”, IEEE Transactions on Computers, vol. 51, No. 11, pp. 1368-1375, Nov. 2002.
Chu, Wesley et al., “Taks Allocation and Precedence Relations for Distributed Real-Time Systems”, IEEE Transactions on Computers, vol. C-36, No. 6, pp. 667-679. Jun. 1987.
Clarke, Michael et al., “An Architecture for Dynamically Extensible Operating Systems”, Distributed Multimedia Research Group, Department of Computing, Lancaster University, Bailrigg, Lancaster, LA1 4YR, U.K. Proceedings on Fourth International Conference on Configurable Distributed Systems. May 1998.
Colajanni, Michele et al., “Dynamic Load Balancing in Geographically Distributed Heterogeneous Web Servers”, Dip. di Informatica, Sistemi e Produzione, Universita di Roma, Tor Vergata, Roma, Italy 00133, 18th International Conference on Distributed Computing Systems, pp. 295-302, May 1998.
Colajanni, Michele et al., “Analysis of Task Assignment Policies in Scalable Distributed Web-server Systems”, IEEE Transactions on Parallel and Distributed Systes, vol. 9, No. 6, Jun. 1998.
Conti, Marco, et al., “Client-side content delivery policies in replicated web services: parallel access versus single server approach”, Istituto di Informatica e Telematica (IIT), Italian National Research Council (CNR), Via G. Moruzzi, I. 56124 Pisa, Italy, Performance Evaluation 59 (2005) 137-157, Available online Sep. 11, 2004.
Dilley, John, et al., “Globally Distributed Content Delivery”, IEEE Internet Computing, 1089-7801/02/$17.00 © 2002 IEEE, pp. 50-58, Sep.-Oct. 2002.
Ercetin, Ozgur et al., “Market-Based Resource Allocation for Content Delivery in the Internet”, IEEE Transactions on Computers, vol. 52, No. 12, pp. 1573-1585, Dec. 2003.
Fong, L.L. et al., “Dynamic Resource Management in an eUtility”, IBM T. J. Watson Research Center, 0-7803-7382-0/02/$17.00 © 2002 IEEE.
Foster, Ian et al., “The Anatomy of the Grid—Enabling Scalable Virtual Organizations”, To appear: Intl J. Supercomputer Applications, 2001.
Gayek, P., et al., “A Web Content Serving Utility”, IBM Systems Journal, vol. 43, No. 1, pp. 43-63. 2004.
Genova, Zornitza et al., “Challenges in URL Switching for Implementing Globally Distributed Web Sites”, Department of Computer Science and Engineering, University of South Florida, Tampa, Florida 33620. 0-7695-077 I-9/00 $10.00-IEEE. 2000.
Guo, Jiani et al., “QoS Aware Job Scheduling in a Cluster-based Web Server for Multimedia Applications”, Computer Science and Engineering, University of California, Riverside, CA 92521, 0-7695-2312-9/05/$20.00 (c) 2005 IEEE.
Hu, E.C. et al., “Adaptive Fast Path Architecture”, Copyright 2001 by International Business Machines Corporation, pp. 191-206, IBM J. Res. & Dev. vol. 45 No. 2 Mar. 2001.
Huang, Chengdu, et al., “An Architecture for Real-Time Active Content Distribution”, Proceedings of the 12th 16th Euromicro Conference on Real-Time Systems (ECRTS'04), 1068-3070/04 $20.00 © 2004 IEEE.
Jann, Joefon et al., “Web Applications and Dynamic Reconfiguration in UNIX Servers”, IBM, Thomos J. Watson Research Center, Yorktown Heights, New York 10598, 0-7803-7756-7/03/$17.00. 2003 IEEE. pp. 186-194.
Jiang, Xuxian et al., “SODA: a Service-On-Demand Architecture for Application Service Hosting Utility Platforms”, Proceedings of the 12th IEEE International Symposium on High Performance Distributed Computing (HPDC'03) 1082-8907/03 $17.00 © 2003 IEEE.
Kant, Krishna et al., “Server Capacity Planning for Web Traffic Workload”, IEEE Transactions on Knowledge and Data Engineering, vol. 11, No. 5, Sep./Oct. 1999, pp. 731-474.
Kapitza, Rudiger et al., “Decentralized, Adaptive Services: The AspectIX Approach for a Flexible and Secure Grid Environment”, M. Jeckle, R. Kowalczyk, and P. Braun (Eds.): GSEM 2004, LNCS 3270, pp. 107-118, 2004. © Springer-Verlag Berlin Heidelberg 2004.
Koulopoulos, D. et al., “PLEIADES: An Internet-based parallel/distributed system”, Software-Practice and Experience 2002; 32:1035-1049 (DOI: 10.1002/spe.468).
Kuz, Ihor et al., Delft University of Technology Vrije Universiteit Vrije Universiteit Delft, The Netherlands, 0-7695-0819-7/00 $10.00 0 2000 IEEE.
Lu, Chenyang et al., “A Feedback Control Approach for Guaranteeing Relative Delays in Web Servers”, Department of Computer Science, University of Virginia, Charlottesville, VA 22903, 0-7695-1134-1/01 $10.00. 2001 IEEE.
Mahon, Rob et al., “Cooperative Design in Grid Services”, The 8th International Conference on Computer Supported Cooperative Work in Design Proceedings. pp. 406-412. IEEE 2003.
Montez, Carlos et al., “Implementing Quality of Service in Web Servers”, LCMI—Depto de Automacao e Sistemas—Univ. Fed. de Santa Catarina, Caixa Postal 476-88040-900—Florianopolis—SC—Brasil, 1060-9857/02 $17.00. 2002 IEEE.
Haddad, Ibrahim et al., “MOSIX: A Cluster Load-Balancing Solution for Linux”, Linux Journal, vol. 2001, Issue 85es, Article No. 6, May 2001.
Naik, Vijay et al., “Adaptive Resource Sharing in a Web Services Environment”, Middleware Conference, vol. 78, Proceedings of the 5th ACM/IFIP/USENIX international conference on Middleware, pp. 311-330. 2004.
Nakrani, Sunil et al., “On Honey Bees and Dynamic Server Allocation in Internet Hosting Centers”, Computing Laboratory, University of Oxford, Oxford OX1 3QD, England, UK Copyright © 2004 International Society for Adaptive Behavior, vol. 12(3-4): pp. 223-240. 2004.
Abdelwahed, Sherif et al., “A Control-Based Framework for Self-Managing Distributed Computing Systems”, WOSS'04 Oct. 31-Nov. 1, 2004 Newport Beach, CA, USA. Copyright 2004 ACM 1-58113-989-6/04/0010.
Aweya, James et al., “An adaptive load balancing scheme for web servers”, International Journal of Network Management 2002; 12: 3-39 (DOI: 10.1002/nem.421), Copyright 2002 John Wiley & Sons, Ltd.
Chen, Liang et al., “Resource Allocation in a Middleware for Streaming Data”, 2nd Workshop on Middleware for Grid Computing Toronto, Canada, pp. 5-10, Copyright 2004 ACM.
Workshop on Performance and Architecture of Web Servers (PAWS-2000) Jun. 17-18, 2000, Santa Clara, CA (Held in conjunction with SIGMETRICS-2000).
Hadjiefthymiades, Stathes et al., “Using Proxy Cache Relocation to Accelerate Web Browsing in Wireless/Mobile Communications”, University of Athens, Dept. of Informatics and Telecommunications, Panepistimioupolis, Ilisia, Athens, 15784, Greece. WWW10, May 1-5, 2001, Hong Kong.
Fox, Armando et al., “Cluster-Based Scalable Network Services”, University of California at Berkeley, SOSP-16 10/97 Saint-Malo, France, ACM 1997.
Chen, Thomas, “Increasing the Observability of Internet Behavior”, Communications of the ACM, vol. 44, No. 1, pp. 93-98, Jan. 2001.
Shaikh, Anees et al., “Implementation of a Service Platform for Online Games”, Network Software and Services, IBM T.J. Watson Research Center, Hawthorne, NY 10532, SIGCOMM'04 Workshops, Aug. 30 & Sep. 3, 2004, Portland, Oregon, USA. Copyright 2004 ACM.
Chellappa, Ramnath et al., “Managing Computing Resources in Active Intranets”, International Journal of Network Management, 2002, 12:117-128 (DOI:10.1002/nem.427).
Lowell, David et al., “Devirtualizable Virtual Machines Enabling General, Single-Node, Online Maintenance”, ASPLOS'04, Oct. 9-13, 2004, Boston, Massachusetts, USA. pp. 211-223, Copyright 2004 ACM.
Shen, Kai et al., “Integrated Resource Management for Cluster-based Internet Services”, USENIX Association, 5th Symposium on Operating Systems Design and Implementation. vol. 36, Issue SI (Winter 2002), pp. 225-238. 2002.
Cardellini, Valeria et al., “The State of the Art in Locally Distributed Web-Server Systems”, ACM Computing Surveys, vol. 34, No. 2, Jun. 2002, pp. 263-311.
Grajcar, Martin, “Genetic List Scheduling Algorithm for Scheduling and Allocation on a Loosely Coupled Heterogeneous Multiprocessor System”, Proceedings of the 36th annual ACM/IEEE Design Automation Conference, New Orleans, Louisiana, pp. 280-285. 1999.
Chandra, Abhishek et al., “Dynamic Resource Allocation for Shared Data Centers Using Online Measurements” Proceedings of the 11th international conference on Quality of service, Berkeley, CA, USA pp. 381-398. 2003.
Grimm, Robert et al., “System Support for Pervasive Applications”, ACM Transactions on Computer Systems, vol. 22, No. 4, Nov. 2004, pp. 421-486.
Bent, Leeann et al., “Characterization of a Large Web Site Population with Implications for Content Delivery”, WWW2004, May 17-22, 2004, New York, New York, USA ACM 1-58113-844-X/04/0005, pp. 522-533.
Pacifici, Giovanni et al., “Performance Management for Cluster Based Web Services”, IBM TJ Watson Research Center, May 13, 2003.
Conti, Marco et al., “Quality of Service Issues in Internet Web Services”, IEEE Transactions on Computers, vol. 51, No. 6, pp. 593-594, Jun. 2002.
Raunak, Mohammad et al., “Implications of Proxy Caching for Provisioning Networks and Servers”, IEEE Journal on Selected Areas in Communications, vol. 20, No. 7, pp. 1276-1289, Sep. 2002.
Reumann, John et al., “Virtual Services: A New Abstraction for Server Consolidation”, Proceedings of 2000 USENIX Annual Technical Conference, San Diego, California, Jun. 18-23, 2000.
Rolia, J. et al., “Resource Access Management for a Utility Hosting Enterprise Applications”, IFIP/IEEE Eighth International Symposium on Integrated Network Management, pp. 549-562, Mar. 2003.
Ryu, Kyung Dong et al., “Resource Policing to Support Fine-Grain Cycle Stealing in Networks of Workstations”, IEEE Transactions on Parallel and Distributed Systems, vol. 15, No. 10, pp. 878-892, Oct. 2004.
Sacks, Lionel et al., “Active Robust Resource Management in Cluster Computing Using Policies”, Journal of Network and Systems Management, vol. 11, No. 3, pp. 329-350, Sep. 2003.
Sit, Yiu-Fai et al., “Cyclone: A High-Performance Cluster-Based Web Server with Socket Cloning”, Department of Computer Science and Information Systems, The University of Hong Kong, Cluster Computing 7, 21-37, 2004. Kluwer Academic Publishers.
Sit, Yiu-Fai et al., “Socket Cloning for Cluster-BasedWeb Servers”, Department of Computer Science and Information Systems, The University of Hong Kong, Proceedings of the IEEE International Conference on Cluster Computing, IEEE 2002.
Snell, Quinn et al., “An Enterprise-Based Grid Resource Management System”, Brigham Young University, Provo, Utah 84602, Proceedings of the 11th IEEE International Symposium on High Performance Distributed Computing, 2002.
Tang, Wenting et al., “Load Distribution via Static Scheduling and Client Redirection for Replicated Web Servers”, Department of Computer Science and Engineering, 3115 Engineering Building, Michigan State University, East Lansing, MI 48824-1226, Proceedings of the 2000 International Workshop on Parallel Processing, pp. 127-133, IEEE 2000.
Taylor, Steve et al., “Grid Resources for Industrial Applications”, Proceedings of the IEEE International Conference on Web Services. 2004.
Vidyarthi, Deo Prakash et al., “Cluster-Based Multiple Task Allocation in Distributed Computing System”, Proceedings of the 18th International Parallel and Distributed Processing Symposium, IEEE 2004.
Villela, Daniel et al., “Provisioning Servers in the Application Tier for E-commerce Systems”, pp. 57-66, IEEE 2004.
Xu, Zhiwei et al., “Cluster and Grid Superservers: The Dawning Experiences in China”, Institute of Computing Technology, Chinese Academy of Sciences, P.O. Box 2704, Beijing 100080, China. Proceedings of the 2001 IEEE International Conference on Cluster Computing. IEEE 2002.
Zeng, Daniel et al., “Efficient Web Content Delivery Using Proxy Caching Techniques”, IEEE Transactions on Systems, Man, and Cybernetics—Part C: Applications and Reviews, vol. 34, No. 3, pp. 270-280, Aug. 2004.
Zhang, Qian et al., “Resource Allocation for Multimedia Streaming Over the Internet”, IEEE Transactions on Multimedia, vol. 3, No. 3, pp. 339-355, Sep. 2001.
Gupta et al., “Provisioning a virtual private network: a network design problem for multicommodity flow”, Proceedings of the thirty-third annual ACM symposium on Theroy of computing [online], Jul. 2001, pp. 389-398, abstract [retrieved on Jun. 14, 2007], Retrieved from the Internet: URL:http://portal.acm.org/citation.crm?id=380830&dl=ACM&coll-GUIDE.
Foster et al., “A Distributed Resource Management Architecture that Supports Advance Reservations and Co-Allocation,” Seventh International Workshop on Quality of Service (IWQoS '99), 1999, pp. 27-36.
Final Office Action on U.S. Appl. No. 14/691,120 dated Sep. 13, 2017.
Chen et al., “A flexible service model for advance reservation,” Computer Networks 37 (2001), pp. 251-262.
Final Office Action issued on U.S. Appl. No. 11/276,855, dated Jan. 26, 2012.
Final Office Action issued on U.S. Appl. No. 11/276,852, dated Mar. 5, 2013.
Final Office Action issued on U.S. Appl. No. 11/276,854, dated Apr. 18, 2011.
Final Office Action issued on U.S. Appl. No. 11/276,854, dated Jun. 8, 2010.
Final Office Action on U.S. Appl. No. 11/276,853, dated Oct. 16, 2009.
Final Office Action on U.S. Appl. No. 11/276,855, dated Aug. 13, 2009.
Non-Final Office Action for U.S. Appl. No. 11/276,855, dated Dec. 31, 2009.
Non-Final Office Action issued on U.S. Appl. No. 11/276,852, dated Feb. 10, 2009.
Non-Final Office Action issued on U.S. Appl. No. 11/276,852, dated Mar. 17, 2011.
Non-Final Office Action issued on U.S. Appl. No. 11/276,852, dated Mar. 4, 2010.
Non-Final Office Action issued on U.S. Appl. No. 11/276,852, dated Jan. 16, 2014.
Non-Final Office Action issued on U.S. Appl. No. 11/276,854, dated Oct. 27, 2010.
Non-Final Office Action issued on U.S. Appl. No. 11/276,854, dated Nov. 26, 2008.
Non-Final Office Action issued on U.S. Appl. No. 11/276,854, dated Aug. 1, 2012.
Non-Final Office Action issued on U.S. Appl. No. 11/276,855, dated Dec. 30, 2008.
Non-Final Office Action on U.S. Appl. No. 11/276,854, dated Jun. 5, 2013.
Non-Final Office Action on U.S. Appl. No. 11/276,855, dated Dec. 7, 2010.
Non-Final Office Action on U.S. Appl. No. 14/691,120 dated Mar. 2, 2017.
Notice of Allowance issued on U.S. Appl. No. 11/276,852, dated Nov. 26, 2014.
Notice of Allowance issued on U.S. Appl. No. 11/276,854, dated Mar. 6, 2014.
Notice of Allowance issued on U.S. Appl. No. 13/758,164, dated Apr. 15, 2015.
Notice of Allowance issued on U.S. Appl. No. 14/704,231, dated Sep. 2, 2015.
Notice of Allowance on U.S. Appl. No. 11/276,855, dated Sep. 13, 2013.
Notice of Allowance on U.S. Appl. No. 14/833,673, dated Dec. 2, 2016.
Non-Final Office Action on U.S. Appl. No. 14/691,120 dated Feb. 12, 2018.
Notice of Allowance on U.S. Appl. No. 14/590,102 dated Jan. 22, 2018.
Non-Final Office Action on U.S. Appl. No. 14/154,912 dated May 8, 2018.
U.S. Non-Final Office Action on U.S. Appl. No. 14/987,8059, dated May 11, 2018.
Final Office Action on U.S. Appl. No. 14/154,912 dated Oct. 11, 2018, 17 pps.
Final Office Action on U.S. Appl. No. 14/691,120 dated Aug. 27, 2018, 16 pps.
Final Office Action on U.S. Appl. No. 14/987,059 dated Oct. 11, 2018, 15 pps.
Non-Final Office Action on U.S. Appl. No. 15/478,467 dated Jul. 13, 2018, 21 pps.
Final Office Action on U.S. Appl. No. 15/478,467 dated Jan. 11, 2019.
Non-Final Office Action on U.S. Appl. No. 14/691,120 dated Mar. 22, 2019.
Non-Final Office Action on U.S. Appl. No. 14/987,059 dated Jan. 31, 2019.
Notice of Allowance on U.S. Appl. No. 14/154,912 dated Feb. 7, 2019.
Notice of Allowance on U.S. Appl. No. 14/154,912 dated Apr. 3, 2019.
Non-Final Office Action issued on U.S. Appl. No. 11/276,854, dated Jun. 10, 2009, 16 pages.
Final Office Action issued on U.S. Appl. No. 11/276,852, dated Oct. 16, 2009, 15 pages.
Final Office Action issued on U.S. Appl. No. 11/276,855, dated Jul. 22, 2010, 16 pages.
Final Office Action issued on U.S. Appl. No. 11/276,852, dated Oct. 4, 2010, 19 pages.
Non-Final Office Action on U.S. Appl. No. 11/276,855, dated Jun. 27, 2011, 16 pages.
Final Office Action issued on U.S. Appl. No. 11/276,852, dated Oct. 5, 2011, 20 pages.
Non-Final Office Action issued on U.S. Appl. No. 11/276,852, dated Jun. 26, 2012, 21 pages.
Final Office Action issued on U.S. Appl. No. 14/833,673, dated Feb. 11, 2016, 14 pages.
Non-Final Office Action issued on U.S. Appl. No. 14/833,673, dated Jun. 10, 2016, 11 pages.
Notice of Allowance issued on U.S. Appl. No. 15/478,467 dated May 30, 2019, 14 pages.
Notice of Allowance issued on U.S. Appl. No. 14/987,059 dated Jul. 8, 2019, 7 pages.
Final Office Action issued on U.S. Appl. No. 14/691,120, dated Oct. 3, 2019, 15 pages.
Notice of Allowance issued on U.S. Appl. No. 14/987,059 dated Nov. 7, 2019, 7 pages.
Notice of Allowance issued on U.S. Appl. No. 14/987,059 dated Feb. 14, 2020, 7 pages.
Caesar et al., “Design and Implementation of a Routing Control Platform,” Usenix, NSDI '05 Paper, Technical Program, obtained from the Internet, on Apr. 13, 2021, at URL <https://www.usenix.org/legacy/event/nsdi05/tech/full_papers/caesar/caesar_html/>, 23 pages.
Bader et al.; “Applications”; The International Journal of High Performance Computing Applications, vol. 15, No.; pp. 181-185; Summer 2001.
Coomer et al.; “Introduction to the Cluster Grid—Part 1”; Sun Microsystems White Paper; 19 pages; Aug. 2002.
Joseph et al.; “Evolution of grid computing architecture and grid adoption models”; IBM Systems Journal, vol. 43, No. 4; 22 pages; 2004.
Smith et al.; “Grid computing”; MIT Sloan Management Review, vol. 46, Iss. 1.; 5 pages; Fall 2004.
“Microsoft Computer Dictionary, 5th Ed.”; Microsoft Press; 3 pages; 2002.
“Random House Concise Dictionary of Science & Computers”; 3 pages; Helicon Publishing; 2004.

Related Publications (1)

	Number	Date	Country
	20150381521 A1	Dec 2015	US

Provisional Applications (1)

	Number	Date	Country
	60662240	Mar 2005	US

Continuations (3)

	Number	Date	Country
Parent	13758164	Feb 2013	US
Child	14827927		US
Parent	12752622	Apr 2010	US
Child	13758164		US
Parent	11276856	Mar 2006	US
Child	12752622		US

On-demand compute environment

Information

Patent Number

Date Filed

Date Issued

Inventors

Original Assignees

Examiners

Agents

CPC

Field of Search

US

CPC

International Classifications

Disclaimer

Term Extension

Abstract