Infinitely Scalable Clusters: Grid Computing 101

We are currently seeing a major change in the IT industry, and the cloud environment has turned into a safe haven. With a variety of major businesses switching to the public cloud, we have also seen a huge drive towards scaling, and automation. Generally, both the technology and financial sectors are facing a huge shift from having complex computing tasks done manually towards more streamlined and automated processes.

When going for cloud adoption, “businesses are pushing PaaS first and that has a lot of positive effects. To begin with, things are made easier right off the bat, because essentially all the building blocks are there, so any initial business can run workloads and get going within a day or two, rather than wasting too much time to set up the foundation,” stated Hentsu CEO, Marko Djukic.

An increasing amount of businesses are implementing grid computing clusters to handle massive workloads.

What is Grid Computing?

Grid Computing refers to making use of the shared power of a cluster of computers to process computationally intensive tasks that would otherwise bog down a single workstation. To put it simply, jobs can be submitted from one computer to the grid, which then processes the data and returns the output to the user. Importantly, multiple people can simultaneously make use of the same grid by intelligently managing how the computers in the grid allocate resources. This allows for significantly improved workflow for companies whose work is optimized for grid computing.

Opening with a much needed refresher on public and private cloud, as well as defining key terminology, the talk flowed into an investigation of the challenges companies face when working with different data sets and a look at solutions currently available to companies.

How Grid Computing Works – Grid Architecture Explained

To recap, grid computing denotes one main computer that distributes information and tasks across multiple networked computers – all of that usually towards one objective. Let us simplify a bit and illustrate how things operate. Grid computing network frequently has three types of machines:

  • Central Control Node – Server/computer or a group of servers working to controls the entire network and preserving the account of the resources within the network pool. Again this part is used for controlling and not for processing.
  • Provider – A computer working to give resources within the network.
  • User/Client – In basics terms, clients or users can actually utilize the computer on the network regardless of geographical location.

Key Advantages of Grid Computing

One of the key aspects of grid computing is flexibility, and more importantly, computing power. In other words, it boils down to having a single computer grid for large amounts of data rather than placing the demand on a single supercomputer.

Here are some of the most frequently asked questions related to grid computing.

Why grid is computing important?
What are the real benefits and biggest advantages of grid computing?

Well, the reasons why so many businesses rely on this particular method of completing joint tasks because it denotes following key advantages:

  • Improved use of existing hardware.
  • General performance increase and quicker handling of complex problems.
  • Easier to collaborate with other organizations.
  • Massive servers for applications can be divided into smaller commodity type servers.
  • With grid environments lead to reduced chances of failure – if one desktop/server fails, other resources pick up the workload.
  • Jobs can be executed in parallel speeding performance.

The Agility of Ephemeral Computing

It has to be highlighted that ephemeral computing has also been a huge part of the innovation process in modern-day tech. It carries tremendous advantages, albeit we have to ask the simple and most obvious question here: what does that mean for businesses and the SaaS industry in particular?

When you describe a process as “ephemeral” it denotes something temporary and brief. Essentially, the notion of dealing with a surplus of servers or indeed a shortage of servers is something that’s not an issue with ephemeral computing. To put it into perspective, ephemeral computing services are agile and will adjust according to the problems and needs at hand.

The Power of Code and Automation

Utilizing ephemeral clusters that scale up and down as needed is quite a boost to handling workloads in general. In short, it means you limit or eliminate convoluted pre-planning and relying on heavy server power.

“It’s basically all about serverless. Code that is distributed across ephemeral compute that handles the analysis and then churns out the answers without having to deal with what’s actually the underlying compute,” says Marko Djukic.

He added: “Compute is just a utility you consume as needed, nothing exists permanently.”

To summarize, in PaaS and SaaS scenarios, giving your business operations and workloads the power to shrink automatically, can completely remove any scalability issues you may be experiencing with traditional server-heavy computing methodology.

Traditional tools and PaaS Offerings

There is a breadth of choices for grid computing and how to migrate workloads into cloud environments. We covered some of those, looking at traditional MATLAB setups to more extreme Platform as a Service (PaaS) environments from Google using their Bigquery and Datalab, and ran some live demos ripping though 2TB of full depth market data.

Key points to take away:

  • Horses for courses – What spec’d machine does your task work best in? Many cores in fewer machines, or many smaller cores on multiple machines? Consider how best to configure your cluster.
  • Reduced upfront costs – Unlike traditional Grid Computing clusters that require upfront purchasing of all the machines needed before they can actually be used, cloud solutions let you skip out on paying for hardware.
  • Flexibility – Publicly available solutions can allow you to quickly scale the size and power of your cluster to ensure that you can crunch the data in the time you need.
  • Reducing worker downtime – Having employees sitting around waiting for their code to execute is wasting time and money. By pushing tasks off individual computers and onto the cloud, the bottleneck is alleviated and workers can continue with work.
  • Full Platform as a Service (PaaS) – Allows some very dynamic and fast access to compute across vast data sets, but will usually require significant re-tooling for major hedge fund production environments. When implementing PaaS type grid computing this also involves a more holistic approach across people, processes and technology.

How Can Hentsu Help?

We’ve built up a wealth of in-house expertise running grid computing workloads across all three major public clouds – Amazon AWS, Microsoft Azure and Google Compute Engine. We can get you up and running quickly with pre-tested designs and architectures, greatly eroding the overall traditional pains and TCO for running grid computing.

Get in touch: hello@hentsu.com, we’d love to hear about your grid computing challenges.

 

Download interview with our CEO Marko Djukić HERE