K
Kostis Kaffes
Researcher at Stanford University
Publications - 16
Citations - 250
Kostis Kaffes is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Scheduling (computing). The author has an hindex of 5, co-authored 9 publications receiving 105 citations.
Papers
More filters
Proceedings Article
Shinjuku: preemptive scheduling for µsecond-scale tail latency
Kostis Kaffes,Timothy Chong,Jack Tigar Humphries,Adam Belay,David Mazières,Christos Kozyrakis +5 more
TL;DR: It is demonstrated that Shinjuku provides significant tail latency and throughput improvements over IX and ZygOS for a wide range of workload scenarios and achieves up to 6.6× higher throughput and 88% lower tail latency.
Proceedings ArticleDOI
Centralized Core-granular Scheduling for Serverless Functions
TL;DR: This paper argues for a cluster-level centralized and core-granular scheduler for serverless functions that eliminates queue imbalances while the core granularity reduces interference and is expected to increase the adoption of serverless computing platforms by various latency and throughput sensitive applications.
Proceedings Article
RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers.
TL;DR: This work presents RackSched, the first rack-level microsecond-scale scheduler that provides the abstraction of a rack-scale computer to an external service with network-system co-design, and designs a custom switch data plane for the inter-server scheduler, which realizes power-of-k-choices, ensures request affinity, and tracks server loads accurately and efficiently.
Proceedings ArticleDOI
Syrup: User-Defined Scheduling Across the Stack
TL;DR: Syrup as mentioned in this paper is a framework for user-defined scheduling that enables untrusted application developers to express application-specific scheduling policies across these system layers without being burdened with the low-level system mechanisms that implement them.
Proceedings ArticleDOI
Mind the Gap: A Case for Informed Request Scheduling at the NIC
TL;DR: This paper proposes implementing preemptive request scheduling by passing to the NIC up-to-date information about core availability and execution status of active requests, and presents a prototype implementation on a commercial Smart-NIC that indeed shows performance benefits for different workload scenarios.