When companies use Elastigroup, Spot by NetApp’s cloud compute platform, they’re able to operate the most efficient, reliable infrastructure at the lowest possible cost. Elastigroup’s core features automate infrastructure management and optimize cloud resources, delivering up to 90% savings on cloud costs.
Today, Spot by NetApp released intelligent traffic flow, powerful new functionality to Elastigroup, that will further enhance our customers’ ability to optimize their clusters. Instead of randomly distributing traffic across cloud resources with a load balancer, Elastigroup will intelligently manage and control incoming traffic for optimal instance utilization and high performance.
Spot instance availability vs. performance
When running workloads on spot VMs, availability, reliability and performance are top of mind. Spot instances can be stopped or terminated with little warning, so using them means managing this risk. One best practice is to leverage a heterogeneous cluster and give your workloads a larger pool of spot instances to choose from.
There are typically two approaches when using spot instances with auto scaling groups and load balancers.
Option 1: Create a cluster of homogenous instances (all the same type or size) so when traffic is distributed, it will be done equally, helping to achieve balanced utilization and performance. This can result in low availability in spot markets and pools.
Option 2: Use different sized instances which deliver high availability by diversifying the workload across multiple pools of spot instance types and sizes. This flexibility, however, can lead to significant inefficiencies and performance issues as the load balancers will distribute traffic equally, regardless of instance size–or users can operate the load balancer manually.
Each of these options has significant drawbacks. A homogenous spot instance cluster will not have the same level of high availability that a heterogeneous cluster has. While a heterogeneous cluster will suffer from performance and cloud efficiency issues as the load balancer’s distribution method ignores instance size. This potentially results in underutilization of larger, high-capacity instances (that are still paid for) while the smaller, low-capacity instances, can get overwhelmed, simultaneously creating cloud waste AND critical performance issues.
Trying to manually maintain a balanced spot instance group is time-consuming and difficult. It requires constant performance monitoring to track and fix any gaps caused by traffic balancing, changing running instance types and modifying the traffic weight.
Introducing Intelligent Traffic Flow
To address these challenges, Spot by NetApp is excited to announce Elastigroup’s latest feature– Intelligent Traffic Flow.
Unlimited Spot VM selection
Intelligent Traffic Flow (ITF) is a software layer connected to Elastigroup that appropriately manages and controls the distribution of incoming traffic for optimal instance utilization. Users can select as many instance types and sizes as they want while ITF ensures that traffic is evenly spread across instances, according to their size.
How does ITF work?
ITF uses the application load balancers’ weighting capability to distribute incoming traffic based on instance capacity. In this first release, ITF will group instances according to their vCPU count and will automatically calculate the weight of each group relative to the overall number of vCPU within the entire Elastigroup. Each instance in the cluster will end up with the same, optimal level of vCPU utilization. In the next release, ITF will also be able to calculate and balance traffic based on other metrics such as memory and network consumption.
Together with core capabilities for compute provisioning, cost optimization, and predictive scaling, ITF rounds out Elastigroup’s functionality to deliver the most advanced, automated cloud infrastructure management platform available.
For every scaling event that takes place in the Elastigroup platform, ITF seamlessly recalculates the target group’s weight and automatically rebalances traffic without any manual intervention. Users can leverage as many spot instance markets as they wish to achieve even higher availability while resource utilization is efficient and optimized across instances.
Intelligent Traffic Flow is available now. Additional information on how it works is available in the Spot Elastigroup documentation. Guidance on how to configure it is also available in the documentation.