Networking SLA System for Cloud Datacenter Resource Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In multi-tenancy cloud architectures, provisioning resources in large-scale datacenters is challenging, particularly in isolating resources among tenants while ensuring interconnectedness of instances within the same computing device, and existing cloud computing service level agreements (SLAs) do not effectively constrain or guarantee networking resources like bandwidth.
Innovation Solution
A device and method that includes a non-transitory memory storage with instructions executed by processors to receive a networking SLA specifying bandwidth requirements, determine available network resources across nodes, and deploy instances based on these resources, using a modular SLA system that integrates with cloud management systems to schedule resources and enforce quality of service rules across different levels of computing infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If resources are allocated to each tenant with isolation in multi-tenancy cloud architectures, then tenant resource isolation is improved, but resource allocation complexity increases
Solution Approach 1:
The patent segments network resources into discrete units (network slices, virtual networks) that can be independently allocated to different tenants. Each tenant receives a dedicated network slice with guaranteed bandwidth and isolation, while the overall system maintains a unified resource management framework that handles multiple tenants efficiently.
Solution Approach 2:
The patent introduces a network slice manager as an intermediary component between the cloud management system and network resources. This manager abstracts the complexity of resource allocation and isolation by automatically creating, managing, and enforcing network slices, thereby simplifying the overall system architecture while maintaining tenant isolation.
2Ease of operation
If multiple instances are provisioned for the same tenant in the same subnet, then instance interconnectedness is improved, but network resource allocation difficulty increases
Solution Approach 1:
The patent applies preliminary action by pre-configuring network slices and reserving network resources before instances are deployed. When multiple instances need to be provisioned for the same tenant, the pre-established network slices ensure immediate interconnectedness without requiring real-time complex network reconfiguration, as the network path is already predetermined.
Solution Approach 2:
The patent implements dynamic network resource allocation where the system can automatically adjust network slice configurations based on real-time instance deployment requirements. The network slice manager dynamically creates virtual networks and assigns bandwidth resources, allowing flexible instance interconnectedness while managing allocation complexity through automated decision-making algorithms.
3Device complexity
If traditional SLAs are used without networking constraints, then computing resource management is simplified, but networking resource guarantees are lost
Solution Approach 1:
The patent merges computing SLAs and networking SLAs into a unified service level agreement framework. The network slice manager integrates network resource guarantees with computing resource allocation, ensuring that both types of SLAs are enforced consistently. This combination maintains management simplicity while achieving reliable networking resource guarantees through integrated policy enforcement.
Solution Approach 2:
The patent implements feedback mechanisms where the network slice manager continuously monitors network resource usage and adjusts allocations to ensure SLA compliance. The system receives feedback on bandwidth consumption, latency, and other network parameters, and automatically modifies network slice configurations to maintain guaranteed performance levels, thereby achieving reliable guarantees without complex manual management.
Data Source
AI summary
A service level agreement (SLA) system is provided for multi-tenant cloud computing to enable provisioning of computing instances for tenants with a networking SLA. A networking SLA may specify a bandwidth requirement, for example, between instances to be scheduled for a tenant in a datacenter. The SLA system evaluates nodes in the datacenter based on a remaining capacity of links associated with nodes implementing the networking SLA. A modular system is provided to enable integration of the SLA system into existing cloud computing infrastructures. The cloud management system may query the SLA system to determine nodes in the datacenter capable of meeting a networking SLA. The list may be ordered to indicate nodes having better capacity to fulfill the networking SLA. The cloud management system can utilize the ordered list of nodes in scheduling instance deployments for tenant requests.