Cloud QoS Scheduling via Immutable Log Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Cloud computing providers face challenges in ensuring guaranteed Quality of Service (QoS) due to the vast amount of data flowing through their environments, making it difficult to meet specified service level agreements (SLAs) for computing resources and data transfer.

Innovation Solution

A system that determines the optimal compute node for processing workloads based on immutable logs, considering resource utilization levels and network link saturation to ensure compliance with QoS parameters, using a non-blocking matrix switch for predictable data transfer and caching hierarchies for performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If cloud computing providers process vast amounts of data through their environments, then the quantity of data processed increases, but the ability to guarantee Quality of Service (QoS) deteriorates

Engineering Contradiction:

Improvequantity of dataVSAvoidQuality of Service guarantee

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system segments the cloud computing environment into multiple compute nodes, each with assigned workloads. The workload manager divides and distributes data processing tasks across these nodes, allowing the system to handle vast quantities of data while maintaining QoS guarantees through distributed processing and localized resource management.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-assigning workloads to compute nodes and pre-establishing resource allocation plans. The workload manager proactively monitors resource utilization and adjusts workload distribution before QoS violations occur, ensuring service level agreements are maintained even as data volume increases.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If more workloads are assigned to compute nodes, then productivity increases, but resource utilization levels exceed thresholds causing QoS violations

Engineering Contradiction:

Improveworkload processing capacityVSAvoidQoS parameter compliance

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements dynamic workload management where the workload manager continuously monitors resource utilization levels and dynamically adjusts workload assignments. When compute nodes approach utilization thresholds, the system automatically redistributes workloads to maintain QoS compliance while maximizing overall productivity through flexible resource allocation.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system employs feedback mechanisms where the workload manager receives continuous information about resource utilization levels from compute nodes and adjusts workload assignments accordingly. This closed-loop control ensures that productivity is maximized while QoS parameters are maintained by responding to real-time resource status changes.

Inventive Principle:

Principle #23Feedback

3Quantity of substance

If data transfer through the network fabric increases, then the quantity of data processed improves, but network link utilization saturates causing performance degradation

Engineering Contradiction:

Improvedata transfer volumeVSAvoidnetwork transfer speed

Core Design Contradiction:

Quantity of substanceVSSpeed

Solution Approach 1:

The system applies local quality by keeping data processing local to compute nodes wherever possible. The workload manager assigns processing tasks to nodes that already have or can quickly access the required data, minimizing network fabric utilization. This localized processing approach allows high data transfer volumes to be handled without saturating network links.

Inventive Principle:

Principle #3Local quality

4Productivity

If compute nodes are allocated to handle peak workloads, then productivity during peak times improves, but resource utilization becomes uneven across the system

Engineering Contradiction:

Improvepeak workload handling capacityVSAvoidresource utilization distribution

Core Design Contradiction:

ProductivityVSStability of the object's composition

Solution Approach 1:

The system uses dynamic resource allocation where the workload manager continuously balances workload assignments across compute nodes based on current utilization levels. During peak times, additional workloads are distributed to available nodes, and the system dynamically rebalances resources afterward, maintaining both peak productivity and long-term resource utilization stability.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11599393B2Guaranteed quality of service in cloud computing environments

Publication Date: 2023.03.07 STATE STREET CORPORATION

AI summary

Systems, methods, apparatuses, and computer-readable media for guaranteed quality of service (QoS) in cloud computing environments. A workload related to an immutable log describing a transaction may be received. A determination is made based on the immutable log that a first compute node stores at least one data element to process the transaction. Utilization levels of computing resources of the first compute node may be determined. Utilization levels of links connecting the first compute node to the fabric may be determined. A determination may be made, based on the utilization levels, that processing the workload on the first compute node satisfies one or more QoS parameters specified in a service level agreement (SLA). The workload may be scheduled for processing on the first compute node based on the determination that processing the workload on the first compute node satisfies the one or more QoS parameters specified in the SLA.