News for hackers. Stuff that matters.
Re:Apollo: Scalable and Coordinated Scheduling for Cloud-Sca... by tterrace on Thursday April 16, 2015 @06:22PM (#9391083)
Amazon also has a cloud deployment tool called Apollo (internally only I believe - the public version is called "CodeDeploy"): http://www.allthingsdistributed.com/2014/11/apollo-amazon-de...
Re:Apollo: Scalable and Coordinated Scheduling for Cloud-Sca... by epistasis on Thursday April 16, 2015 @06:13PM (#9391047)
This looks really great honestly. Including IO as a consumable resource is just as important as allocating CPU or memory.
Re:Apollo: Scalable and Coordinated Scheduling for Cloud-Sca... by gcr on Thursday April 16, 2015 @06:08PM (#9391022)
Request to the mods: please drop the "Microsoft" from the title. This is just a Microsoft Research paper. MSR is almost completely separate from the rest of the company.

(edit: whoops, looks like MS actually uses this system internally. sorry, should have read the abstract)

Re:Apollo: Scalable and Coordinated Scheduling for Cloud-Sca... by seanmcdirmid on Thursday April 16, 2015 @06:15PM (#9391055)
Only a few of the authors are MSR (our systems group in Beijing actually); it seems like Eric Boutin in Microsoft is the first author on this one (we have many smart people working for Microsoft outside of MSR).