SLAOrchestrator: Reducing the Cost of Performance SLAs for Cloud Data Analytics

Authors: 

Jennifer Ortiz, Brendan Lee, and Magdalena Balazinska, University of Washington; Johannes Gehrke, Microsoft; Joseph L. Hellerstein, eScience Institute

Abstract: 

SLAOrchestrator is a new system designed to reduce the price increases necessary to support performance SLAs in cloud analytics systems. SLAOrchestrator is designed for SLAs that guarantee per-query execution times. Its core architecture consists of a double learning loop that improves both SLAs and resource management over time. It further utilizes an efficient combination of elastic query scheduling and multi-tenant resource provisioning algorithms to reduce the costs of performance guarantees.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

Presentation Audio

BibTeX
@inproceedings {216035,
author = {Jennifer Ortiz and Brendan Lee and Magdalena Balazinska and Johannes Gehrke and Joseph L. Hellerstein},
title = {SLAOrchestrator: Reducing the Cost of Performance SLAs for Cloud Data Analytics},
booktitle = {2018 {USENIX} Annual Technical Conference ({USENIX} {ATC} 18)},
year = {2018},
isbn = {978-1-931971-44-7},
address = {Boston, MA},
pages = {547--560},
url = {https://www.usenix.org/conference/atc18/presentation/ortiz},
publisher = {{USENIX} Association},
}