An Analysis of Load Imbalance in Scale-out Data Serving

Despite the natural parallelism across lookups, performance of distributed key-value stores is often limited due to load imbalance induced by heavy skew in the popularity distribution of the dataset. To avoid violating service level objectives expressed in terms of tail latency, systems tend to keep server utilization low and organize the data in micro-shards, which in turn provides units of migration and replication for the purpose of load balancing. These techniques reduce the skew, but incur additional monitoring, data replication and consistency maintenance overheads. This work shows that the trend towards extreme scale-out will further exacerbate the skew-induced load imbalance, and hence the overhead of migration and replication.


Published in:
Proceedings of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science
Presented at:
ACM SIGMETRICS, Antibes Juan-Les-Pins, France, June 14-18, 2016
Year:
2016
Keywords:
Laboratories:




 Record created 2016-04-12, last modified 2018-03-18

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)