We have created and shared a new Jupyter notebook that shows a better way to combine standard isolated Chameleon networks with DirectStitch capabilities. This more advanced method shows how to separate management of the stitched links from the compute nodes.
We are happy to announce that the Chameleon project has been extended for another 4 years!
That’s four more years of working with a creative and talented user community that always wants to go someplace impossible – and takes us with them!
The next four years will bring us integration with IoT, support for more innovative networking experiments, innovative new hardware, and even more support for reproducibility and experiment sharing. Read all about it in: https://www.cs.uchicago.edu/news/article/chameleon-phase-three/
We are SO looking forward to continuing to provide a platform for your research -- and learning about all the hot and cool things …
Chameleon eliminates the need to involve campus IT staff and enables access to direct public cloud network connections to all Chameleon users. It is now possible for any user to experiment with these advanced cloud networking technologies using Chameleon resources without the need for complicated campus networking configuration. Learn more about the capability in this blog.
As with many projects and programming languages, there is more than one way to achieve a task when orchestrating Chameleon computing and network resources. As a result, experimenters may feel overwhelmed and choose to stick to the orchestration method they are familiar with even when another method might be more effective for the task in hand.
This blog discusses a new experiment deployed on Chameleon called CIEF, a Cyber Infrastructure for Ecological Forecasting (Dietz & Matta, 2018). CIEF supports data-driven research in ecological forecasting to understand our ecosystem and drive policy. Examples include predicting environmental changes, corn production in the near to medium term, types of disease-carrying mosquitos, based on data related to air, land, and water.
The workload traces from data centers facilitate research on the design of computer systems, job scheduling, and resource management. Researchers can analyze the traces and replicate real-life workloads for their experiments. In this blog, we will briefly review some major released traces and introduce the benefits of using a Chameleon-developed trace generator for easily creating traces from cloud providers who use OpenStack.
Introducing a new networking capability: connect your Chameleon networks directly to AWS networks via DirectConnect! And, we discuss the addition of 40 new GPU cards at CHI@UC.
Simpler SDN setups, a new Jupyter tutorial, and a new focus in the new year--more details inside!