JP2006524379A - Apparatus, method, and program for providing temporary resource on demand - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide temporary resource on demand by a capacity manager so as to guarantee that a temporary resource can be recovered when a specified resource time expires.
Access to a minimum resource specification corresponding to a logical partition is controlled to prevent the sum of all minimum resource specifications from exceeding basic resources on the system. By ensuring that the sum of the minimum resource specifications for all logical partitions is satisfied by the basic resources on the system, temporary resources can always be recovered when needed.

Description

  The present invention relates generally to data processing, and more specifically to the field of resource management within a logically partitioned computer system.

  Since the dawn of the computer age, computer systems have evolved into extremely sophisticated devices that can be offered in a wide variety of settings. Computer systems generally include a combination of hardware (eg, semiconductors, circuit boards, etc.) and software (eg, computer programs). As advances in semiconductor processing and computer architecture have boosted computer hardware performance, more sophisticated computer software has emerged to take advantage of hardware performance improvements, resulting in only a few years ago It has become a much more powerful computer system.

  A combination of hardware and software on a particular computer system defines a computing environment. Thus, different computing environments are provided by different hardware platforms and different operating systems. In recent years, engineers have recognized that it is possible to provide different computing environments on the same physical computer system by logically partitioning computer system resources for different computing environments. is doing. The eServer iSeries computer system developed by IBM is an example of a computer system that supports logical partitioning. If logical partitioning on the iSeries computer system is desired, partition manager code (called “hypervisor” in iSeries terminology) is installed that allows the definition of various computing environments on the same platform. . Once the partition manager is installed, logical partitions can be created that define various computing environments. The partition manager manages the logical partition to ensure that the logical partition can share the necessary resources in the computer system while maintaining a separate computing environment defined by the logical partition.

  Computer systems that include multiple logical partitions generally share resources between the logical partitions. For example, a computer system with two logical partitions and a single CPU will allocate 50% of the CPU to each partition, 33% of memory to the first partition, and 67% of memory to the second partition. Could be defined as allocating two different I / O slots to two logical partitions, one per partition. When logical partitions are defined and shared resources are allocated to logical partitions, each logical partition operates as a separate computer system. Thus, in the above example having a single computer system with two logical partitions, the two logical partitions will appear to be two separate and distinct computer systems for all practical purposes.

  Recent developments in the computer industry allow customers to purchase additional resources on demand. In this scenario, a customer purchases a computer system that may include one or more resources that are initially disabled. In that case, there are several ways by which manufacturers can make these additional resources available to customers. If the customer desires to permanently upgrade his system to include additional resources, the customer can purchase a software key from the system manufacturer. When this software key is entered, the resource (s) specified in the software key are permanently available, as if the system was purchased with these resources available. This is known in the art as “permanent capacity upgrade on demand”. If the customer does not require permanent use of additional resources, the customer requests an enablement code from the manufacturer to make these resources available for a specified resource-time. be able to. This is known in the art as “temporary capacity on demand”. In related application No. 10/406652, entitled “METHOD TO PROVIDE ON-DEMAND RESOURCE ACCESS”, filed on March 4, 2003, a system and method for providing temporary capacity on demand is disclosed. One way to provide temporary capacity on demand is to make a resource available for a specified resource time and disable that resource when the specified resource time expires.

  Another method for enabling temporary access to resources is known as “metered capacity on demand” and was filed on July 10, 2003, “APPARATUS AND”. METHOD FOR PROVIDING METERED CAPACITY OF COMPUTER RESOURCES "is the subject of related application No. 10/616676. When using metered capacity on demand, a temporary resource becomes available and only the actual usage of that resource is charged to the customer.

  When using either temporary capacity-on-demand or weighing capacity-on-demand, the customer typically enters into a contractual agreement with the manufacturer, and the manufacturer monitors the system to ensure that the customer has a temporary or weighing capacity on-demand Ensure that demand is properly charged. Another way to allow temporary access to computer system resources is known as “activate immediate”, in which case the customer can enable the specified resource time. The code is purchased (or given on a “trial” basis), but the customer does not sign the contract and the manufacturer does not monitor the system. Since the manufacturer does not monitor the system, the system is vulnerable to potential tampering by the customer. In an immediate activation scenario, the customer purchases an enabling code for a specified resource time. The resource is then available for a specified resource time. When the specified resource time expires, the resource must recover (ie, become unavailable).

However, due to system integrity and legal considerations, there are limitations on what the system can do to recover temporary resources. In other words, it would be unacceptable to force recovery of temporary resources, since doing so may prevent the computer system from executing customer workloads. This means that when a specified resource time expires, certain actions by the customer may prevent resource recovery. For example, if a customer changes the minimum resource specification to a level that includes one or more of the temporary resources, the system may fail to recover all temporary resources. In this case, the customer will be able to enjoy the permanent availability of temporary resources without paying the manufacturer for these resources.
Patent Application No. 10/406652 Patent application No. 10/616676

  The present invention seeks to address these problems.

  The capacity manager provides temporary resource on demand to ensure that the temporary resource can be recovered when the specified resource time expires. Access to the minimum resource specification corresponding to the logical partition is controlled to prevent the sum of all minimum resource specifications from exceeding the base resource on the system. By ensuring that the sum of the minimum resource specifications for all logical partitions is satisfied by the base resources on the system, temporary resources can be used when needed without affecting the minimum service level defined by the customer. Always be able to recover.

  These and other features and advantages of the present invention will become apparent from the following more detailed description of the preferred embodiments of the present invention as illustrated in the accompanying drawings.

  Preferred embodiments of the invention are described below in conjunction with the accompanying drawings, in which like names indicate like elements.

  Preferred embodiments have traditionally ensured that temporary resources can be recovered when the period for making them available has expired without affecting the minimum service level defined by the customer. It is a significant advancement over technology. Access to the minimum resource specification in each logical partition is controlled such that the sum of the minimum resource specification for all logical partitions cannot exceed the basic resources in the system. Since the sum of the minimum resource specifications cannot exceed the available base resources, recovery of all temporary resources is guaranteed.

  Referring to FIG. 1, computer system 100 is an enhanced IBM eServer iSeries computer system and represents one suitable type of computer system that supports logical partitioning according to preferred embodiments. One skilled in the art will appreciate that the mechanism and apparatus of the present invention applies equally to any computer system that supports logical partitions. As shown in FIG. 1, the computer system 100 includes one or more processors 110 connected to a main memory 120, a mass storage interface 130, a display interface 140, a network interface 150, And a plurality of input / output slots 180. These system components are interconnected through the use of system bus 160. Mass storage interface 130 is used to connect a mass storage device (such as direct access storage device 155) to computer system 100. One particular type of direct access storage device is a CD RW drive, which can read data from a CD RW 195. Note that mass storage interface 130, display interface 140, and network interface 150 may actually be implemented as adapters coupled to I / O slot 180.

  The main memory 120 accommodates the partition manager 121 and the N logical partitions 125 shown in FIG. 1 as the logical partitions 125A to 125N. Partition manager 121 preferably creates these N logical partitions 125. Each logical partition preferably includes a corresponding operating system 126, shown in FIG. 1 as operating systems 126A-126N.

  The operating system 126 is a multitasking operating system such as OS / 400, AIX, or Linux, but those skilled in the art will not limit the spirit and scope of the present invention to any one operating system. You will understand. Any suitable operating system can be used. Operating system 126 is a sophisticated program that includes low-level code for managing the resources of computer system 100. Some of these resources are processor 110, main memory 120, mass storage interface 130, display interface 140, network interface 150, system bus 160, and I / O slot 180. The operating system 126 in each partition may be the same as the operating system in the other partition, or it may be a completely different operating system. Thus, one partition can run the OS / 400 operating system and different partitions can run other instances of OS / 400, perhaps different releases, or run in different preferences (eg, time zones). . The operating system in the logical partition could be different from OS / 400 (such as AIX or Linux) provided that it is compatible with the hardware. In this way, logical partitions can provide a completely different computing environment on the same physical computer system.

  The partition manager 121 preferably includes a capacity manager 122 that manages temporary resources. “Temporary resources” as described herein can be provided using “Temporary Capacity On Demand”, “Metric Capacity On Demand” or “Immediate Activation” as described in the Background section above. Please note that. In addition, the preferred embodiments extend to any and all methods for providing temporary resources within a computer system, whether currently known or developed in the future. The capacity manager 122 includes a minimum resource enforcement mechanism 123 that ensures that the sum of all minimum resource designations on the device 100 does not exceed the level satisfied by the basic resources of the device 100. As used herein, the term “basic resource” refers to a resource that becomes permanently available on the device 100 and includes all resources that become available when the computer system is acquired; Contains all additional resources that are permanently available. By ensuring that the minimum resource specification for the computer system 100 does not exceed the level of the basic resource, the capacity manager 122 can always recover the temporary resource when the corresponding resource time expires.

  Partitions 125A-125N are shown in FIG. 1 as residing in main memory 120. However, one skilled in the art will recognize that a partition is a logical construct that includes resources other than memory. A logical partition generally specifies a portion of memory, along with processor capacity and allocation of other system resources such as memory 120 or I / O slot 180. Thus, a partition can provide one or more input / output functions that can provide an interface function to the mass storage interface 130, display interface 140, network interface 150, or input / output device plugged into the input / output slot 180. It could be defined to include two processors and a portion of memory 120 along with processors and / or slots. The other partition could then be defined to include three other processors, another portion of memory 120, and one or more input / output processors. A partition is shown in FIG. 1 as a symbolic representation of a logical partition, which would include system resources outside of memory 120 within computer system 100. It should also be noted that the partition manager 121 preferably includes functions and mechanisms that reside in memory and hardware separate from the partition and are not directly usable by the partition.

  Computer system 100 is similar to the case where computer system 100 programs can only access a large single storage entity instead of accessing multiple small storage entities such as main memory 120 and DASD device 155. It uses a well-known virtual addressing mechanism that allows it to behave. Thus, although the partition manager 121 and the partitions 125A-125N are shown as resident in the main memory 120, those skilled in the art will have all of these items fully contained in the main memory 120 at the same time. You will recognize that it is not. It should also be noted that the term “memory” is used herein to refer generically to the entire virtual memory of computer system 100.

  Each processor 110 can be constructed from one or more microprocessors and / or integrated circuits. The processor 110 executes program instructions stored in the main memory 120. Main memory 120 stores programs and data accessible to processor 110. When computer system 100 is started, processor 110 first executes the program instructions that make up partition manager 121, which initializes the operating system in the logical partition.

  Although computer system 100 is shown as including only a single system bus, those skilled in the art will recognize that the present invention may be implemented using a computer system having multiple buses. I will. In addition, each of the input / output interfaces used in the preferred embodiment includes a separate fully programmed microprocessor that is used to offload computationally intensive processing from the processor 110, such as within the iSeries I / O processor. In some cases, it may be a simple industry standard input / output adapter (IOA).

  Display interface 140 is used to connect one or more displays 165 directly to computer system 100. These displays 165 may be non-intelligent (ie, dumb) terminals or fully programmable workstations and are used to allow system administrators and users to communicate with computer system 100. However, although the display interface 140 is provided to support communication with one or more displays 165, all necessary interaction with the user and other processes can occur through the network interface 150. It should be noted that the computer system 100 does not necessarily require the display 165 as it can.

  The network interface 150 is used to connect other computer systems and / or workstations (eg, 175 in FIG. 1) to the computer system 100 via the network 170. The present invention describes how the computer system 100 can be used regardless of whether the network connection 170 is made using modern analog and / or digital techniques, or through some future networking mechanism. It applies equally whether connected to other computer systems and / or workstations. In addition, a wide variety of network protocols can be used to implement the network. These protocols are special computer programs that allow computers to communicate over the network 170. TCP / IP (Transmission Control Protocol / Internet Protocol) is an example of a suitable network protocol.

  At this point, the present invention has been described and will continue to be described in the context of a fully functional computer system, although those skilled in the art will recognize the present invention as various forms of programs. It is important to note that it will be understood that the present invention is equally applicable regardless of the particular type of computer readable signal transmission medium used to actually perform the distribution. It is a thing. Examples of suitable signal transmission media include recordable type media such as flexible disks and CD RW (eg, 195 in FIG. 1) and transmission type media such as digital and analog communication links.

  A more detailed view of the partition manager 121 of FIG. 1 is shown in FIG. The partition manager 121 includes a minimum resource specification 210, a current resource specification 220, and a maximum resource specification 230 for each logical partition. The minimum resource specification 210 specifies the minimum resource defined by the customer that must be available for the logical partition to function properly. The current resource specification 220 specifies a resource that is currently allocated to the logical partition. The maximum resource specification 230 specifies the maximum resource that can be allocated to the logical partition. The partition manager manages and controls access to the minimum resource specification 210, the current resource specification 220, and the maximum resource specification 230.

  Whether capacity manager 122 is requested by temporary capacity on demand, requested by capacity capacity on demand, requested by immediate activation, or in some other manner Regardless of whether you manage temporary resources. Capacity manager 122 determines whether enablement code 242 is valid and is used to enable one or more resources when it is determined that enablement code is valid Enabled enablement code mechanism 240. Capacity manager 122 also includes a resource allocator 250, which is a mechanism for allocating resources for use. Thus, if the enabling code mechanism 240 determines that the enabling code 242 is valid, the resource allocator 250 makes the corresponding resource (s) available.

  The minimum resource enforcement mechanism 123 within the capacity manager 122 ensures that the sum of all minimum resource designations 210 for all logical partitions does not exceed the basic resources in the system. Controls access to the minimum resource specification 210. If the sum of the minimum resource specifications 210 is always maintained at a level that can be satisfied by the basic resources of the computer system, the temporary resources can always be recovered without affecting the service level defined by the customer.

  FIG. 1 illustrates a sample computer system that includes some of the salient features of both hardware and software according to preferred embodiments, but a more detailed logical diagram for some of the components of FIG. 3 is shown as system 300. In system 300, N logical partitions 125A-125N are shown as running respective operating systems 126A-126N. The logical partition is managed by the partition manager 121. The partition manager 121 manages the resources 350 shown in FIG. 3 as resources 350A to 350X. The associated “resource” can be any hardware or software that can be controlled by the partition manager 340. Examples of hardware resources include processors, memory, and hard disk drives. Examples of software resources include databases, internal communications (such as logical LANs), or applications (such as word processors, emails). The partition manager 121 controls which resources 350 can be used by the logical partition. When a resource becomes available to the partition manager 121, it is categorized as an available resource 360 if it is not already assigned to a logical partition, and a shared resource 370 when multiple logical partitions can access the resource. And is categorized as a dedicated resource 380 when it is exclusively assigned to a logical partition. FIG. 3 shows dedicated resources 380A... 380N corresponding to the respective logical partitions 125A.

  Referring to FIG. 4, a flow diagram of one suitable method 400 for providing temporary resource on demand begins with a customer requesting an enabling code from a manufacturer (step 410). The customer receives an enabling code that includes a resource time designation (step 420). The term “resource time” is a general term that allows any resource or combination of resources to be specified for any suitable time period. An example of resource time is processor-day. The customer enters the enablement code, which makes the resources on the computer system available (step 430). A timer is then started (step 440). The user can then use the resource (step 450) as long as the resource time does not expire (step 460 = NO). When the resource time expires (step 460 = YES), the resource becomes unavailable (step 470).

  A simple example will demonstrate the usefulness of the method 400. Assume that a company that sells products through catalog sales experiences peak demand in November and December every year for holiday shopping. The company could purchase a computer system with one or more additional processors that are installed but initially disabled. In that case, the company may contract with a computer system provider to enable additional processor (s) for a set period. Assume that the computer system has two additional processors, and that the peak purchase period lasts for 30 days from November 15 to December 14. Customers will be able to purchase 60 processor days of additional capacity from November 15th. In that case, the two additional processors will be available for 30 days (providing 60 processor days of additional capacity). After 60 processor days have passed, the two additional processors are disabled.

  If the usage of the temporary resource is monitored by the manufacturer, the manufacturer can ensure that the customer is properly billed for the temporary resource. However, in an immediate activation scenario, the system is not monitored by the manufacturer. This could result in lost revenue due to abuse by customers using temporary capacity for periods longer than the specified resource time. For example, this could happen if the minimum resource specification total for a logical partition increases to a level that can only be satisfied by using temporary resources (ie, not satisfied with only basic resources). When the resource time expires (step 460 = YES), the method 400 will attempt to disable the temporary resource (step 470). However, if the minimum specified resource total requires the use of temporary resources, the capacity manager may not be able to disable (or recover) all of the temporary resources. For this reason, some mechanism is required to ensure that temporary resources can be recovered. This is the subject of the preferred embodiments.

  The method 500 according to the preferred embodiments includes all the steps of the method 400 described above in connection with FIG. However, it should be noted that the method 500 further includes a step 510 of controlling access to the minimum resource designation corresponding to the logical partition to ensure that temporary resources can be recovered. By controlling access to the minimum resource specification for the logical partition, the method 500 can ensure that the minimum resource specification can be satisfied by only the base resource, thereby creating a state where the temporary resource can always be recovered. Some examples are given below to illustrate these concepts.

  For this example, assume that the computer system has three logical partitions, called 1, 2, and 3. As shown in the current processor specification column in FIG. 6, it is assumed that the basic system includes eight processors, all of which are allocated to logical partitions, but partition 1 has two processors. Thus, partition 2 has 5 processors and partition 3 has 1 processor. In this case, assume that the customer pays for the temporary use of the eight additional processors using the immediate activation scenario described above. As shown in FIG. 7, these additional processors can be made available to the partition manager by designating these eight temporary processors as available resources 360 shown in FIG. Once these eight temporary processors are designated as available resources 360, they can be allocated to the logical partition as shared resources 370 or as dedicated processors 380. For this example, assume that these eight temporary processors are allocated as dedicated processors 380, as shown in FIG. 8, which shows that logical partition 1 with six processors and nine A partition 2 having a processor and a partition 3 having one processor are shown. The problem with the prior art implementation is illustrated in FIG. 8, where the minimum processor capacity for the logical partition has been increased to a level whose sum exceeds the base system processor. The total number of processors within the minimum processor designation for the three partitions is 9. However, it should be noted that of the 16 processors currently in use, only 8 are basic processors. Thus, when the designated processor time purchased by the customer expires, the system will attempt to recover eight temporary processors. However, the problem is that at this point, the minimum processor designation total, which is 9 in FIG. 8, exceeds 8 basic processors. For this reason, the prior art will succeed in recovering only 7 of the 8 temporary processors. The 8th processor will still be available for customer use, as required by the minimum processor specified sum. This would allow the customer to use the temporary resource on a perpetual basis without paying the manufacturer for continued use of the temporary resource.

  Preferred embodiments eliminate this problem in the prior art by controlling access to the minimum resource specification so that the sum of the minimum resource specification does not exceed the level of basic resources on the system. Thus, for the examples of FIGS. 6 and 7, the minimum processor designation can be changed as shown in FIG. 9, but the sum of these minimum processor designations cannot exceed eight basic system processors. . Thus, in FIG. 9, the minimum processor designation for partition 1 has increased from 1 to 3, but the total processors in the minimum processor designation (3 for partition 1, 4 for partition 2, 1 for partition 3) Is still shown to be less than or equal to 8 basic processors.

  Here, it is assumed that the customer decides to make three of the temporary processors permanent by paying the manufacturer for the permanent usage of the three processors. The customer receives a key that permanently enters three of the eight temporary processors when entered into the system. In this example, the number of basic processors has increased from 8 to 11. Thus, the minimum processor designation total can increase to 11 at this point. Thus, in FIG. 10, for a total of 11 processors, partition 1 has a minimum processor designation of 6, partition 2 has a minimum processor designation of 4, and partition 3 has a minimum processor designation of 1. This is still equal to the number of basic processors in the system. In preferred embodiments, the partition manager is prohibited from changing the minimum resource specification to a value such that the sum of the minimum resource specifications for all partitions will exceed the basic resources in the system.

  By controlling access to the minimum resource specification so that the sum does not exceed the basic resources of the system, the preferred embodiments achieve a system that can always recover temporary resources after the specified resource time expires. This eliminates potential revenue losses and thus enhances revenue generation by providing computer systems with the ability to provide temporary resources on demand.

  Those skilled in the art will appreciate that many variations are possible within the scope of the present invention. Thus, while the invention has been particularly shown and described in connection with preferred embodiments thereof, those skilled in the art will recognize that other changes may be made in form and detail.

  The scope of this disclosure includes any novel feature and combination of features disclosed herein. This informs the Applicant that new claims can be clearly expressed in accordance with such features or combinations of features during the pursuit of proceedings of this application or any additional application derived therefrom. . In particular, in connection with the claims herein, the features of the dependent claims can be combined with the features of the independent claims, and the features of each independent claim are listed in the claims. Not only a specific combination but also any suitable method can be used.

  For the avoidance of doubt, the term “comprising” as used herein throughout the description and claims shall be construed to mean “consisting only of”. Must not.

FIG. 2 is a block diagram of a computer device according to preferred embodiments. FIG. 2 is a block diagram of the partition manager of FIG. 1. FIG. 2 is a block diagram illustrating logical components within a logical partition computer system. 3 is a flow diagram of a method for providing temporary resource on demand. FIG. 5 is a flow diagram of a method according to preferred embodiments for providing temporary resource on demand to ensure that temporary resources can be recovered. FIG. 3 is a diagram representing the allocation of processors between three logical partitions to illustrate the principles of the preferred embodiments. FIG. 3 is a diagram representing the allocation of processors between three logical partitions to illustrate the principles of the preferred embodiments. FIG. 3 is a diagram representing the allocation of processors between three logical partitions to illustrate the principles of the preferred embodiments. FIG. 3 is a diagram representing the allocation of processors between three logical partitions to illustrate the principles of the preferred embodiments. FIG. 3 is a diagram representing the allocation of processors between three logical partitions to illustrate the principles of the preferred embodiments.

Claims (24)

At least one processor;
A memory coupled to the at least one processor;
Multiple logical partitions defined on the device;
A capacity manager resident in the memory and executed by the at least one processor, wherein the at least one temporary resource time during a specified resource time for at least one of the plurality of logical partitions; Capacity to manage on-demand and control access to a minimum resource specification for each of the plurality of logical partitions to ensure that the at least one temporary resource can be recovered when the specified resource time expires A manager,
Having a device.   The apparatus of claim 1, wherein the capacity manager resides in a partition manager that manages the plurality of logical partitions.   By ensuring that the sum of all the minimum resource designations for all of the plurality of logical partitions does not exceed the sum of the basic resources in the device, the capacity manager allows the capacity for each of the plurality of logical partitions The apparatus of claim 1, wherein the apparatus controls access to a minimum resource specification. At least one processor;
A memory coupled to the at least one processor;
Multiple logical partitions defined on the device;
A partition manager residing in the memory and executed by the at least one processor, the partition manager comprising:
A capacity manager for managing at least one temporary resource on demand for a specified resource time for at least one of the plurality of logical partitions, the capacity manager comprising:
An apparatus having a minimum resource enforcement mechanism that controls access to a minimum resource specification for each of the plurality of logical partitions to ensure that the at least one temporary resource can be recovered when the specified resource time expires. The partition manager
An enabling code mechanism that evaluates an enabling code to determine whether the code is valid, wherein the enabling code mechanism includes the specified resource time. The apparatus of claim 4 further comprising:   The apparatus of claim 4, wherein the partition manager further comprises a resource allocator that enables the at least one temporary resource.   The apparatus of claim 6, wherein the resource allocator recovers the at least one temporary resource when the specified resource time expires. A computer-implemented method for providing at least one temporary resource on demand for a specified resource time in a computer system comprising a plurality of logical partitions, comprising:
Enabling the at least one temporary resource for the specified resource time;
Controlling access to a minimum resource specification for each of the plurality of logical partitions to ensure that the at least one temporary resource can be recovered when the specified resource time expires;
Having a method.   The step of controlling access to the minimum resource specification for each of the plurality of logical partitions comprises: sum of all the minimum resource specifications for all of the plurality of logical partitions is a base resource in the computer system. 9. The method of claim 8, comprising the step of not exceeding the sum. A computer-implemented method for providing at least one temporary resource on demand for a specified resource time in a computer system comprising a plurality of logical partitions, comprising:
Requesting an enabling code corresponding to the at least one temporary resource for the specified resource time;
Receiving the enabling code;
Enabling the at least one temporary resource for the specified resource time;
Using the at least one temporary resource for the specified resource time;
Controlling access to a minimum resource specification for each of the plurality of logical partitions to ensure that the at least one temporary resource can be recovered when the specified resource time expires;
Having a method.   11. The method of claim 10, further comprising evaluating an enabling code to determine if the code is valid, the enabling code further including the specified resource time. .   The method of claim 10, further comprising enabling the at least one temporary resource.   The method of claim 10, further comprising recovering the at least one temporary resource when the specified resource time expires. Manage at least one temporary resource on demand for a specified resource time within a computer system that includes multiple logical partitions and recover the at least one temporary resource when the specified resource time expires A capacity manager that controls access to a minimum resource designation for each of the plurality of logical partitions to ensure
A computer readable signal transmission medium carrying the capacity manager;
A program with   The program according to claim 14, wherein the signal transmission medium includes a recordable medium.   The program according to claim 14, wherein the signal transmission medium includes a transmission medium.   The program according to claim 14, wherein the capacity manager resides in a partition manager that manages the plurality of logical partitions.   By ensuring that the sum of all minimum resource specifications for all of the plurality of logical partitions does not exceed the sum of the basic resources in the computer system, the capacity manager allows each of the plurality of logical partitions to 15. The program according to claim 14, which controls access to the minimum resource designation for. (A) a partition manager,
(A1) a capacity manager for managing at least one temporary resource on demand for a specified resource time in a computer system including a plurality of logical partitions, the capacity manager comprising:
(A1a) A minimum resource enforcement mechanism for controlling access to a minimum resource specification for each of the plurality of logical partitions to ensure that the at least one temporary resource can be recovered when the specified resource time expires A partition manager having the capacity manager;
(B) a computer-readable signal transmission medium carrying the partition manager;
A program with   The program according to claim 19, wherein the signal transmission medium includes a recordable medium.   The program according to claim 19, wherein the signal transmission medium includes a transmission medium. The partition manager
An enabling code mechanism that evaluates an enabling code to determine whether the code is valid, wherein the enabling code mechanism includes the specified resource time. The program according to claim 19, further comprising:   The program of claim 19, wherein the partition manager further comprises a resource allocator that enables the at least one temporary resource.   24. The program product of claim 23, wherein the resource allocator recovers the at least one temporary resource when the specified resource time expires.

Images