In my Technical Marketing role here at Datrium, as well as previous companies I’ve worked for, there always seems to be an element of performance analysis and benchmarking involved with our day to day work – especially with new technologies capable of disrupting the status quo of existing solutions.
In my early days at Datrium (over two years ago now) I wrote about performance and scalability considerations here on Insane Mode and Scalability. Admittedly, these were smaller scale exercises primarily to understand the true potential of the DVX system. They did however give me good insight into what is really possible.
At that time (2016) scalability of the DVX was initially only a single Data Node and up to 32 Compute Node hosts – pretty impressive at the time. Things have changed significantly in the past year or so for us and scalability and performance are just part of that growth.
I was sitting through a recent internal update from our engineering and performance teams on the scale level testing we did in conjunction with DELL and a couple of trusted 3rd party organizations at the end of last year (2017). This was some serious testing and a truly collaborative effort. Building a system that scaled out to our current maximum of 10 Data Nodes and 128 Compute Node across multiple data center racks and requisite switching was a major investment for everyone involved. Serious professional work kudos to everyone connected to the project.
I could go into the details of that testing here but I’ll leave that to the people that were directly involved in the effort and the outcome. In this case I was able to watch from the sidelines with that silly “I knew this was possible” grin on my face. These results are definitely worth the read.