摘要:
We describe a method for solving the joint problem of optimal routing and optimal bandwidth allocation in a network that supports plural subnetworks and plural communication services. Our method involves, for each source-destination pair communicating via a given subnetwork and a given class of service, determining a traffic rate to be offered to each of a set of permissible routes between that source and that destination, in the given subnetwork and service class. Our method further involves allocating a respective bandwidth to each link of each subnetwork. Significantly, the determinations of traffic rate to be offered, and the allocations of bandwidth to respective links of subnetworks, are performed in a mutually responsive manner.
摘要:
A method is described for network optimization based on a multirate, circuit-switched analysis. Network loss probabilities are determined as a solution of a set of fixed point equations and the sensitivity of network performance, as a function of offered load and loss probabilities, is determined as a solution to a set of linear equations. Because the numerical complexity of solving both the fixed point equations and the sensitivity equations is of an order which renders an exact solution computationally intractable, an asymptotic approximation is applied which yields a solution to the network loss probabilities and network sensitivities. A global optimization procedure is then applied using an iterative, steepest ascent optimization procedure to yield a set of virtual path routings and capacity allocations.
摘要:
A method and apparatus use a set of parameters characterizing an interference signal at a base unit for determining power levels for signals transmitted from a communications device to the base unit. The set of parameters comprises second or higher order statistics characterizing the interference signal, and the parameters are used to determine a desired power level for signals received at the base unit. The desired power level is communicated to a communications device via a pilot signal transmitted by the base unit at a predetermined level. The predetermined level and the power of the received pilot signal are used to compute a path gain between the base unit and communications device. The path gain and desired power level are then used to determine the power level of signals transmitted from the communications device to the base unit.
摘要:
Transmission power of a wireless terminal for transmitting a signal representing information of a particular information class to a base station capable of receiving signals for a plurality of information classes is determined based on a probability measure indicating received signal outage durations that would likely occur over a time interval. Moreover, the transmission power is determined to achieve probable signal outage durations according to the measure that are tolerable for the particular information class to be transmitted. The probability measure is further based on an enhanced characterization of a variation and mean of the detected signal interference magnitude over a time interval. Respective differences in the tolerable signal outage intervals for different information classes, such as voice, audio or video or data, and the corresponding enhanced interference characterization enable transmission of signals representing the information classes at desirably respective low power levels while still providing an acceptable quality of service relative to conventional power control techniques. Such low transmission powers tend to contribute less interference to the communication system and enable greater communication capacity.
摘要:
A method and system for migrating at least one critical resource during a migration of an operative portion of a computer system are disclosed. In at least some embodiments, the method includes (a) sending first information constituting a substantial copy of a first of the at least one critical resource via at least one intermediary between a source component and a destination component. The method further includes (b) transitioning a status of the destination component from being incapable of receiving requests to being capable of receiving requests, and (c) re-programming an abstraction block to include modified addresses so that at least one incoming request signal is forwarded to the destination component rather than to the source component.
摘要:
A method and system for handling interrupts within a computer system during hardware resource migration are disclosed. In at least some embodiments, the method includes (a) programming an address conversion component so that incoming interrupt signals are directed to a control component rather than to a source processing resource, and (b) accumulating the incoming interrupt signals at the control component. Additionally the method also includes, subsequent to the migration of the partition from the source processing resource to a destination processing resource, (c) sending the accumulated incoming interrupt signals to the destination processing resource, and (d) reprogramming the address conversion component so that further incoming interrupt signals are directed to the destination processing resource.
摘要:
A method of allocating a resource in a computer system having a plurality of operating systems, and related system, are disclosed. In at least one embodiment, the method includes providing an advanced configuration and power interface (ACPI) operating to facilitate interactions between at least one of the plurality of the operating systems and one or more of the resource, a hardware device, and firmware, and determining whether the resource is allocated to a first of the plurality of operating systems. The method further includes ejecting the resource from the first operating system, and allocating the resource to a second of the plurality of operating systems.
摘要:
Embodiments of the present invention are directed to enhancing VPAR monitors to allow an active VPAR to be moved from one machine to another, as well as to enhancing virtual-machine monitors to move active VPARs from one machine to another. Because traditional VPAR monitors lack access to many computational resources and to executing-operating-system state, VPAR movement is carried out primarily by specialized routines executing within active VPARs, unlike the movement of guest operating systems between machines carried out by virtual-machine-monitor routines.
摘要:
Techniques are provided for allocating a plurality of resources on a chip to a plurality of partitions in a partitionable computer system. In one embodiment, a resource allocated to a first partition generates a physical address in an address space allocated to the first partition. A partition identification value identifies the first partition. The first partition identification value is stored in the first physical address to produce a partition-identifying address, which may be transmitted to a system fabric. In another embodiment, a transaction is received which includes a source terminus identifier identifying a source device which transmitted the transaction. It is determined, based on the source terminus identifier, whether the source device is allocated to the same partition as any of the plurality of resources. If the source device is so allocated, the transaction is transmitted to a resource that is allocated to the same partition as the source device.
摘要:
Implementations of speedy boot for computer systems are disclosed. In an exemplary embodiment, a method of speedy boot for a computer system may include invoking a platform management interrupt (PMI) to soft reset a processor without resetting hardware for the processor. The method may also include bypassing at least some initialization procedures and tests to speed recovery of the computer system to a usable state. The method may also include resetting operating system interfaces and loading the operating system.