Medea: scheduling of long running applications in shared production clusters

Medea: scheduling of long running applications in shared production clusters Garefalakis et al., EuroSys'18 (If you don’t have ACM Digital Library access, the paper can be accessed either by following the link above directly from The Morning Paper blog site). We’re sticking with schedulers today, and a really interesting system called Medea which is designed ... Continue Reading

Universal Packet Scheduling

Universal Packet Scheduling - Mittal et al. 2015 (presented at NSDI '16) Is there a universal scheduling algorithm, such that simply by changing its configuration parameters, we can produce any desired schedule? In Universal Packet Scheduling, Mittal et al. show us that in theory there can be no Universal Packet Scheduling (UPS) algorithm which achieves ... Continue Reading

Split-Level IO Scheduling

Split-Level IO Scheduling - Yang et al. 2015 The central idea in today's paper is pretty simple: block-level I/O schedulers (the most common kind) lack the higher level information necessary to perform write-reordering and accurate accounting, whereas system-call level schedulers have the appropriate context but lack the low-level knowledge needed to build efficient schedulers - ... Continue Reading

Cloud Computing Resource Scheduling and a Survey of its Evolutionary Approaches

Cloud Computing Resource Scheduling and a Survey of its Evolutionary Approaches - Zhan et al. 2015 In both academia and industry, the problem of cloud resource scheduling is seen to be as hard as a Nondeterministic Polynomial (NP) optimization problem, that is, an NP-hard problem, whose intractability increases exponentially with the number of variables if ... Continue Reading