Cloud Workload Volatility Management via VM Swapping

Solution Overview

Problem

Existing cloud resource management approaches are ineffective in managing workload volatility, leading to constant VM migration and inefficient distribution when workloads are unstable, as they primarily focus on balancing workload rather than managing noise or volatility across hosts.

Innovation Solution

A volatility balancing engine identifies and swaps volatile VMs with stable VMs based on workload metrics, distributing volatility across hosts without affecting workload distribution, allowing for simultaneous operation with existing load balancing mechanisms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional load balancing is used to distribute workloads across hosts, then workload distribution is improved, but constant VM migration occurs when workloads are unstable

Engineering Contradiction:

Improveworkload distributionVSAvoidhost utilization stability

Core Design Contradiction:

ProductivityVSStability of the object's composition

Solution Approach 1:

The system performs preliminary identification of noisy hosts and noisy VMs before migration decisions are made. By pre-characterizing hosts and VMs based on their volatility patterns, the system can make informed migration decisions that prevent constant back-and-forth migrations, thereby stabilizing host utilization while maintaining workload distribution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring workload patterns and volatility metrics. This feedback allows the system to adapt migration decisions based on observed behavior, preventing unnecessary migrations and stabilizing host utilization while maintaining effective workload distribution across the cluster.

Inventive Principle:

Principle #23Feedback

2Productivity

If load balancer moves VMs to balance workload on noisy hosts, then workload distribution is improved, but volatility management deteriorates

Engineering Contradiction:

Improveworkload distributionVSAvoidvolatility management

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs preliminary identification and characterization of noisy hosts and noisy VMs before migration decisions are made. By pre-characterizing entities based on their volatility patterns, the system can make informed migration decisions that prevent constant back-and-forth migrations, thereby stabilizing host utilization while maintaining workload distribution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring workload patterns and volatility metrics. This feedback allows the system to adapt migration decisions based on observed behavior, preventing unnecessary migrations and stabilizing host utilization while maintaining effective workload distribution across the cluster.

Inventive Principle:

Principle #23Feedback

3Productivity

If VMs are frequently migrated to maintain even utilization, then workload distribution is improved, but resource management efficiency deteriorates

Engineering Contradiction:

Improveworkload distributionVSAvoidmigration overhead

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary identification of noisy hosts and noisy VMs before migration decisions are made. By pre-characterizing hosts and VMs based on their volatility patterns, the system can make informed migration decisions that prevent constant back-and-forth migrations, thereby stabilizing host utilization while maintaining workload distribution.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring workload patterns and volatility metrics. This feedback allows the system to adapt migration decisions based on observed behavior, preventing unnecessary migrations and stabilizing host utilization while maintaining effective workload distribution across the cluster.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11403130B2Method and apparatus for workload volatility management in cloud computing

Publication Date: 2022.08.02 VMWARE INC

AI summary

System and computer-implemented method for managing workload volatility in a cloud architecture including a plurality of computing instances in a group of hosts use volatiltiy factors to identify first and second hosts and then a first virtual computing instance in the first host. A workload metric associated with the group of hosts is used to identify a second virtual computing instance in the second host to be swapped with the first virtual computing instance in the first host. The first and second virtual computing instances are swapped so that the first virtual computing instance is migrated from the first host to the second host and the second virtual computing instance is migrated from the second host to the first host.