Software Engineering Empirical Research Radar

Shenango: Achieving High CPU Efficiency for Latency-sensitive Datacenter Workloads

Paper detail page in SEER Radar.

Authors

Amy Ousterhout, Joshua Fried, Jonathan Behrens, Adam Belay, Hari Balakrishnan

Venue / Year

NSDI 2019

Topics

Cloud / Distributed / Service Computing; Industrial Software Engineering

Research directions

SHM Polling, Freshness & CPU Trade-offs

Abstract / Summary

Shenango makes the polling-versus-CPU-efficiency trade-off explicit for microsecond-scale services. A dedicated IOKernel detects demand and reallocates cores at fine granularity, establishing a major systems baseline for any claim about spinning, yielding, CPU placement and tail latency.

External Links

Official / Source Page

PDF

Local PDF is not available on SEER Radar yet. When a public source is recorded, this page will add a local reading link with source attribution.