Welcome to the official Microsoft blog for Dryad and DryadLINQ! The purpose of this blog is to share information about the design and implementation of our system, and also about ways that people are using Dryad and DryadLINQ to perform distributed computations over large datasets. We hope that the postings here will be useful to researchers who have downloaded our public non-commercial release, and who want to get tips, or hear how we use the system internally. We will also talk about some features that haven’t made it into the external release, though, since they are based on internal cluster infrastructure. Over time, we are planning to get all the Dryad and DryadLINQ features ported onto our external platform, so you can think of these “internal-only” features as a preview of what will be coming later for everyone. Hopefully some of the design postings will also be of interest to others working on large-scale distributed systems of all sorts.

Postings here will mostly come from the researchers at Microsoft who have worked on Dryad or DryadLINQ, or who use the system in their research. Now and then we’ll get guest postings from other people I’m sure. Please give us feedback in the comments and let us know if there are any postings you’d really like to see in the future. We may not be able to respond immediately, but we will try to get them in a queue to appear before too long.

Michael Isard and Yuan Yu.