January 12, 2011
Another IaaS company officially stepped on to the playing field today, which is becoming a common event in the wake of inspired predictions about the meteoric rise in demand for such services.
This particular company, however, emerges with a keen eye on the needs of developers—in a way that might go beyond simple marketing to a targeted base of potential users.
Instead of focusing its business model on developers via razor-sharp marketing with a slew of case studies to prove that it’s viable for the prime target, this new company could be capable of providing some compelling benefits for developers, particularly from a testing and development scalability and ease of use perspective.
Silicon Valley-based startup NephoScale (which, if you speak Greek, would be known as CloudScale) came out of the woodwork with an offering designed to get developers up and running without the need for delays caused by system administrators, who are necessary to get a development environment configured and running.
As the company’s formal announcement stated, its IaaS offerings include “cloud servers, on-demand dedicated servers and object-based cloud storage—all powered by a programmatic interface that gives users unprecedented control over their cloud infrastructure.”
Just when it seemed that the world was in grave danger of running out of variations on the word “cloud” to push in front of another endless array of words implying flexibility so the product offering would be clear, NephoScale stepped in. On the one hand, it seemed like they were arriving somewhat late in the game since the IaaS shakedown is only taking place between a handful of large vendors by now—but the focus on developers and the otherwise competitive offerings hardware and price-wise on the on-demand front do make the new company worth some notice.
To get to the heart of the company and what it might have in store for high-performance computing uses and beyond I spoke with the company’s CTO and co-founder, Telemachus Luu, who helped shape the startup’s technological vision and product strategy.
With a background in engineering and product development at ServePath, GoGrid and his own infrastructure consulting firm and more recent concentration on what developers are seeking from the cloud, Luu was able to provide some insights about how this might change the way development happens.
HPCc: There are already a number of IaaS providers with similar offerings that are targeted toward developers—describe in some detail exactly what is completely unique here?
Luu: One of our unique value propositions is our one-to-many batch processing capabilities for provisioning, de-provisioning, and managing servers and services in your cloud infrastructure. Customers can take advantage of this capability through the use of NephoScale’s CloudScript, a unique programmatic interface which represents a powerful new paradigm for advanced programmable control of your cloud infrastructure. Leveraging NephoScale’s CloudScript, a user can deploy an entire datacenter configuration through a single API submission (JSON post). If you want to deploy 10 cloud servers, five dedicated servers, a firewall, a load balancer, and cloud storage, you can do that with one API submission instead of 18.
HPCc: What is it about the vast developer community that seems ready for a targeted IaaS offering? Can you be more specific about particular developer communities you’re targeting (industry-wise)?
Luu: NephoScale is bridging the gap between system administrators and developers. We’ve built a platform that gives technical users from a variety of backgrounds a simple and standard way to provision and manage their infrastructure. Previously, a system administrator would need to deploy the infrastructure, configure the network and operating systems, install the application stacks, and then hand it over to the developer who would then write and test his code on that infrastructure. Now, a developer can define his entire infrastructure requirements in a single JSON-formatted template, post that template through NephoScale’s API, and begin coding in a matter of minutes.
HPCc: Who are some of your early adopters/customers as you tested this business model? If you cannot give names, can you provide a solid, industry-specific use case that exemplifies not only what makes your offerings different, but work?
Luu: A specific use case would be a web developer that wants to pilot a new social networking site for two weeks. You, the developer, need to deploy three servers - a web server, an application server, and a database server. Since the duration is for only two weeks, you decide to proceed with our cloud servers, which are billed on a usage-based model. You define your multi-server requirements in NephoScale’s CloudScript, post the configuration to our API, and subsequently have your environment up and running in minutes.
After two weeks, you decide you want to proof your site out with an initial batch of users for a three month beta period. However, this time, you want to deploy seven servers in a high-availability configuration: two web servers, two application servers, and two database servers, along with a load balancer. Since you are expecting the database servers to do some heavy writes along with performing multiple joins, you want to deploy your two database servers as high-performing dedicated servers with SAS drives to meet your IO requirements. You can now take your previous NephoScale CloudScript, modify it by adding the additional cloud servers, load balancer, and two dedicated Thermos servers, post the configuration to our API, and subsequently have this new seven-server environment up in minutes.
NephoScale is making the process of managing and migrating between development, staging, pre-production, and production environments simple by giving developers the tools to make provisioning and managing their infrastructure efficient and repeatable.
HPCc: Many of our readers are involved in various ways with the high-performance computing space, particularly on the user side thus they have have complex applications and needs. What does NephoScale have that might make them give a new company a second glance? – I noticed under “high performance solutions” on your site where you discuss hybrid cloud hosting; is there where an answer might, in part, lie or is this more of a term to indicate possibility of high performance capabilities?
Luu: In the question above, I alluded to our dedicated servers. For those customers that have single-tenancy, high memory or high IO requirements that can’t be met on a multi-tenant infrastructure, we have a Thermos server that comes with 16GB of RAM and 4 SAS drives in a RAID1 configuration. We also have an Exos server that comes with 24GB of RAM. Both servers utilize the latest Intel Westmere multi-core processors and can be provisioned in minutes.
In the future, we plan on offering additional high-performance dedicated servers, based on customer demand.
HPCc: Given the complex IaaS competitive environment, how will you plan on staying ahead in 2011 since you are relative newcomers to the game?
Luu: At NephoScale, our leadership team consists of hosting industry veterans and cloud computing pioneers. Our development team consists of experienced virtualization and UI developers that have deep agile background and practice scrum and test driven development. We know the industry well, we listen to our customers, and we will continue to innovate and develop based on where we think the industry is heading and what our customers want.
Targeted Cloud and IaaS Services Set to Grow?
Microsoft and others have been touting their readiness for to attract a stream of developers to the cloud, but it might be possible that a smaller, more niche solution provider could be just the right offering at the right time—after all, like many other businesses, developer time to market is the most critical driving force behind making tough infrastructure decisions.
Additionally, the company steps beyond this more focused offering by providing some of the same services as other on-demand resource providers, making it something of a double-pronged approach to entering the fiercely competitive cloud services and infrastructure market.
Posted by Nicole Hemsoth - January 12, 2011 @ 4:19 PM, Pacific Standard Time
Nicole Hemsoth is the managing editor of HPC in the Cloud and will discuss a range of overarching issues related to HPC-specific cloud topics in posts.
No Recent Blog Comments
The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.