Container Scheduler Overlay Network Complexity Weighting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Container schedulers and orchestrators in multi-host networking environments face challenges with frequent overlay network rule updates, leading to CPU resource overload due to the complexity of overlay networks, as they do not typically know the number of overlay networks or rules on each host, resulting in inefficient resource utilization and increased latency.

Innovation Solution

Assigning an overlay network complexity weight to each host based on the number of network service ports exposed by containers, filtering hosts by resource availability and complexity weight, and dispatching new containers to hosts with lower complexity to reduce the need for additional overlay networks and rule updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If container schedulers orchestrate overlay networks in multi-host networking environments, then network security and abstraction layers are improved, but CPU resource overhead and latency increase due to frequent rule updates

Engineering Contradiction:

Improvenetwork securityVSAvoidCPU resource overhead

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by pre-calculating and pre-distributing overlay network rules to hosts before containers are actually deployed. The controller computes the set of overlay networks and their associated rules in advance, then distributes them to relevant hosts. This preliminary preparation reduces the need for frequent rule updates during container deployment, thereby lowering CPU overhead while maintaining security.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of overlay network rules and distributes them to multiple hosts simultaneously. Instead of having each host independently process and update rules, the controller generates rule copies and pushes them to the appropriate hosts in advance. This copying mechanism eliminates redundant rule processing on each host, reducing overall CPU resource consumption while preserving network security through consistent rule distribution.

Inventive Principle:

Principle #26Copying

2Adaptability or versatility

If container schedulers update overlay network rules frequently to accommodate container deployments, then network adaptability is improved, but processing latency and resource utilization worsen

Engineering Contradiction:

Improvenetwork adaptabilityVSAvoidprocessing latency

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary calculations of overlay network rules based on anticipated container deployments and service port exposures. By pre-computing the necessary rules before containers are actually deployed, the system maintains network adaptability while avoiding the latency of real-time rule generation and distribution during container startup.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The controller implements a feedback mechanism where it monitors container deployments and service port exposures, then adjusts overlay network rules accordingly. This feedback loop allows the system to maintain adaptability by responding to actual deployment needs while optimizing rule distribution timing to minimize processing latency and avoid unnecessary frequent updates.

Inventive Principle:

Principle #23Feedback

3Device complexity

If container schedulers do not track overlay network complexity per host, then system complexity is reduced, but resource utilization efficiency and latency performance worsen

Engineering Contradiction:

Improvesystem complexityVSAvoidresource utilization efficiency

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The system introduces an intermediary controller that acts as a mediator between container deployments and overlay network rule management. This controller tracks overlay network complexity and rule distributions across hosts, maintaining resource utilization efficiency without requiring each individual host to implement complex tracking mechanisms. The intermediary handles the complexity centrally while keeping host-level systems simple.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11775354B2Reducing overlay network overhead across container hosts

Publication Date: 2023.10.03 RED HAT LLC

AI summary

A system for reducing overlay network overhead includes a memory, a processor in communication with the memory, a first container and a second container running on a first host, and a container scheduler executing on the processor. Each of the first container and second container expose a network service port(s). The container scheduler executes on the processor to assign a network complexity weight to the first host. The network complexity weight is based on a quantity of network service ports that the first container and the second container expose. The container scheduler also filters hosts based on resource availability corresponding to each host and ranks the hosts based on a respective network complexity weight corresponding to each host. Additionally, the container scheduler dispatches a third container to a second host based on the resource availability and network complexity weight corresponding to the second host.