Cloud Bandwidth Scheduling for Fair Workload Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing environments do not manage network bandwidth as a resource, leading to excessive consumption by workloads, which can starve others and degrade performance for high-throughput or low-latency applications.
Innovation Solution
Treat network bandwidth as a managed resource, scheduling workloads on nodes with sufficient capacity and implementing mechanisms to prevent overconsumption, using real-time metrics for dynamic adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If network bandwidth is not explicitly allocated or reserved for containers, then workloads can consume excessive bandwidth, but this causes other workloads to be starved for network resources and degrades performance for high-throughput or low-latency applications
Solution Approach 1:
The patent segments network bandwidth into allocatable units similar to CPU and memory resources. Network bandwidth is divided into requestable amounts that can be assigned to individual containers through resource configuration, enabling fine-grained control and prevention of any single workload from monopolizing network resources.
Solution Approach 2:
The patent implements preliminary allocation of network bandwidth by requiring containers to specify network resource requests in their configuration. The cloud system pre-allocates and reserves the requested network bandwidth before container execution, ensuring that network resources are available when needed and preventing resource starvation for other workloads.
2Ease of operation
If cloud systems allocate resources like CPU and memory based on container requests, then resource scheduling is efficient and reliable, but network bandwidth lacks similar allocation mechanisms leading to unmanaged consumption
Solution Approach 1:
The patent extends the existing resource management framework to include network bandwidth alongside CPU and memory. The same scheduling and allocation mechanisms that manage compute and memory resources are now applied universally to network bandwidth, allowing consistent resource management across all container resources through a unified approach.
Solution Approach 2:
The patent enables containers to self-serve network bandwidth resources by specifying their own network resource requests in their configuration. The cloud system automatically processes these requests and allocates appropriate network bandwidth without requiring manual intervention, making the system easier to operate while managing complexity through automation.
Data Source
AI summary
A system for managing network bandwidth as a resource in cloud computing environments. The system obtains the network bandwidth capacity of each node within a cloud environment based on metadata provided by a cloud service provider. The system assigns a network bandwidth requirement to each workload scheduled on the nodes. The system tracks the available network bandwidth of each node dynamically by deducting the bandwidth requirements of scheduled workloads from the node's total bandwidth capacity. Dynamically tracking the available network bandwidth of each node includes in responds to scheduling a first workload on a node based on the node's bandwidth capacity and the workload's bandwidth requirement, updating the node's available bandwidth, and a second workload is scheduled based on the updated availability.