Francisco Ciol Rodrigues Aveiro is studying for a Bachelor of Computer Engineering at INSPER, Sao Paulo, Brazil.
Francisco's course covers both software and hardware development, including artificial intelligence, project design and onboard development. Francisco is working with Alysson Oliveira (Software Engineer, LexisNexis Risk Solutions Group) and is completing a 6 month long internship in the Brazil office. His project reflects the contribution he will make to the HPCC Systems Platform.
During this current era of information, the use of cloud computing became a necessity due to the amount of computational power needed. The access to storage and processing power at low cost allied with ease of access are some of the advantages of using such service, which is available as platform as a service (PaaS), software as a service (SaaS), infrastructure as a service (IaaS), and hardware as a service (HaaS). In the IaaS model payment is normally under the Pay-as-you-go politics, where you pay for what you’re using. Though pricing may be cheap, the misusage of resources and unnecessary uptime can bring up the cost. In order to minimize those costs, autoscaling features and containerized applications can be used to control the misusage of resource.
An example of containerized systems with autoscaling capability is Kubernetes, as it can be configured to scale the cluster to what is needed and them return to a minimal state when demand goes down, all in a relatively simple manner. This prevents unnecessary resource usage while scaling to properly attend to any task needed. Another cost associated with a cloud cluster is the amount of external IPs needed. Since you need to pay for each external IP exposed to the web, a full cluster with unique IPs for every service can be expensive. To reduce the number of externals IPs used, a single entry-point can be configured, to then redirect to each service based on a subdomain or path.
Such implementation also centralizes access management to the cluster, improving security and governance over the cluster. The objective of this study is to achieve a single entry point to access an AWS Kubernetes cluster, configuring Ingress and AWS ALB to manage and redirect user access to the correct service in a cluster. Then create a helm chart to replicate this structure in others HPCC Systems clusters. With this implementation, an HPCC Systems cluster would only use one external IP for its multiple services thus reducing cost and improving security.
In this Video Recording, Francisco provides a tour and explanation of his poster content.
HPCC Systems Ingress Configuration with AWS ALB
Click on the poster for a larger image.