An Analysis of Load Imbalance in Scale-out Data Serving

Stanko Novakovic, Alexandros Daglis, Edouard Bugnion, Babak Falsafi, Boris Grot

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

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.
Original languageEnglish
Pages (from-to)367-368
Number of pages2
JournalSIGMETRICS Performance Evaluation Review
Issue number1
Publication statusPublished - 1 Jun 2016


Dive into the research topics of 'An Analysis of Load Imbalance in Scale-out Data Serving'. Together they form a unique fingerprint.

Cite this