Bandwidth Guarantee and Work Conservation in Cloud Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud networks lack accurate bandwidth guarantees, preventing tenants from determining lower bounds on application performance, which hinders the transfer of enterprise applications to public clouds due to unpredictable performance.
Innovation Solution
A bandwidth guarantee and work conservation apparatus that provides multiplexing of networking resources in a work-conserving manner, ensuring each virtual machine receives a minimum absolute bandwidth and dynamically allocates spare capacity using a hose model and rate-limiters, allowing for efficient job completion and independent operation of hypervisors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cloud networks share bandwidth in a best efforts manner, then network resource utilization is improved, but bandwidth guarantee accuracy deteriorates
Solution Approach 1:
The patent segments bandwidth management into two distinct layers: a guarantee layer that ensures minimum bandwidth allocation and a best-effort layer that optimizes resource utilization. This segmentation allows the system to provide accurate bandwidth guarantees while simultaneously achieving high network resource utilization through dynamic sharing of spare capacity.
Solution Approach 2:
The patent introduces rate-limiters as intermediary components that enforce bandwidth guarantees and manage traffic flow. These rate-limiters act as mediators between the guarantee layer and best-effort layer, ensuring that minimum bandwidth commitments are honored while allowing dynamic allocation of additional capacity when available.
2Reliability
If static bandwidth reservation is provided to tenants, then bandwidth guarantee is improved, but network resource utilization deteriorates
Solution Approach 1:
The patent transforms static bandwidth reservation into a dynamic system where bandwidth allocation adapts to actual network conditions and tenant needs. The rate-limiters dynamically adjust traffic rates based on available capacity, ensuring guarantees are met while maximizing utilization of unused bandwidth through work-conserving multiplexing.
Solution Approach 2:
The patent changes the parameter of bandwidth allocation from fixed static values to dynamic values that adjust based on network conditions. The system monitors actual usage and available capacity, modifying allocation parameters in real-time to balance guarantee reliability with resource utilization efficiency.
3Adaptability or versatility
If bandwidth guarantees are not provided, then network flexibility is improved, but application performance predictability deteriorates
Solution Approach 1:
The patent segments bandwidth management into guarantee and best-effort layers, where the guarantee layer provides predictable performance bounds for applications while the best-effort layer maintains network flexibility for dynamic resource allocation. This segmentation enables both performance predictability and network adaptability simultaneously.
Data Source
AI summary
According to an example, a method for bandwidth guarantee and work conservation includes determining virtual machine (VM) bandwidth guarantees assigned to VMs in a network including a source VM that communicates with destination VMs. The method further includes assigning minimum bandwidth guarantees to communications between the source VM with the destination VMs by dividing a VM bandwidth guarantee assigned to the source VM between the destination VMs based on active VM-to-VM communications between the source VM and the destination VMs. The method also includes allocating, by a processor, spare bandwidth capacity in the network to a communication between the source VM and a destination VM based on the assigned minimum bandwidth guarantees.