log in  |  register  |  feedback?  |  help  |  web accessibility
Logo
DBSeer: Resource and Performance Prediction for Building a Next Generation Database Cloud.
Presented By: Theodoros Rekatsinas - University of Maryland College Park
Tuesday, March 5, 2013, 2:00-3:00 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
Abstract

Authors: Barzan Mozafari, Carlo Curino, Sameul Madden.

Abstract: Cloud computing is characterized by a shared infrastructure and a decoupling between its operators and tenants. These two characteristics impose new challenges to databases applications hosted in the cloud, namely: (i) how to price database services, (ii) how to isolate database tenants, and (iii) how to optimize database performance on this shared infrastructure. Today's solutions, based on virtual-machines, do not properly address these challenges. These three challenges share a common need for accurate predictive models of performance and resource utilization. DBSeer is a research prototype of the predictive models that we have developed for the important class of OLTP/Web workloads.



Link: http://dbseer.org/
Link to CIDR `13 paper: http://people.csail.mit.edu/barzan/papers/cidr_2013.pdf ( I have slides for this one)
Link to SIGMOD `13 paper: http://people.csail.mit.edu/barzan/papers/sigmod_2013.pdf

 

This talk is organized by Abdul Quamar