TY - JOUR
T1 - Multiresource allocation
T2 - Fairness-efficiency tradeoffs in a unifying framework
AU - Joe-Wong, Carlee
AU - Sen, Soumya
AU - Lan, Tian
AU - Chiang, Mung
PY - 2013/12
Y1 - 2013/12
N2 - Quantifying the notion of fairness is underexplored when there are multiple types of resources and users request different ratios of the different resources. A typical example is data centers processing jobs with heterogeneous resource requirements on CPU, memory, network bandwidth, etc. In such cases, a tradeoff arises between equitability, or 'fairness,' and efficiency. This paper develops a unifying framework addressing the fairness-efficiency tradeoff in light of multiple types of resources. We develop two families of fairness functions that provide different tradeoffs, characterize the effect of user requests' heterogeneity, and prove conditions under which these fairness measures satisfy the Pareto efficiency, sharing incentive, and envy-free properties. Intuitions behind the analysis are explained in two visualizations of multiresource allocation. We also investigate people's fairness perceptions through an online survey of allocation preferences.
AB - Quantifying the notion of fairness is underexplored when there are multiple types of resources and users request different ratios of the different resources. A typical example is data centers processing jobs with heterogeneous resource requirements on CPU, memory, network bandwidth, etc. In such cases, a tradeoff arises between equitability, or 'fairness,' and efficiency. This paper develops a unifying framework addressing the fairness-efficiency tradeoff in light of multiple types of resources. We develop two families of fairness functions that provide different tradeoffs, characterize the effect of user requests' heterogeneity, and prove conditions under which these fairness measures satisfy the Pareto efficiency, sharing incentive, and envy-free properties. Intuitions behind the analysis are explained in two visualizations of multiresource allocation. We also investigate people's fairness perceptions through an online survey of allocation preferences.
KW - Data center
KW - efficiency
KW - fairness
KW - multiresource allocation
KW - resource allocation
KW - tradeoff
UR - http://www.scopus.com/inward/record.url?scp=84891625487&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84891625487&partnerID=8YFLogxK
U2 - 10.1109/TNET.2012.2233213
DO - 10.1109/TNET.2012.2233213
M3 - Article
AN - SCOPUS:84891625487
SN - 1063-6692
VL - 21
SP - 1785
EP - 1798
JO - IEEE/ACM Transactions on Networking
JF - IEEE/ACM Transactions on Networking
IS - 6
M1 - 6403598
ER -