%0 Conference Paper
%F Oral 
%T TailX: Scheduling Heterogeneous Multiget Queries to Improve Tail Latencies in Key-Value Stores
%+ Laboratoire d'Informatique de Grenoble (LIG)
%+ Distribution, Recherche d'Information et Mobilité (DRIM)
%+ Université Catholique de Louvain = Catholic University of Louvain (UCL)
%A Jaiman, Vikas
%A Ben Mokhtar, Sonia
%A Rivière, Etienne
%< avec comité de lecture
%B 20th International Conference on Distributed Applications and Interoperable Systems
%C Valletta, Malta
%P 73-92
%8 2020-06-15
%D 2020
%R 10.1007/978-3-030-50323-9_5
%K Distributed storage
%K Performance
%K Scheduling
%Z Computer Science [cs]
%Z Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC]
%Z Computer Science [cs]/Performance [cs.PF]Conference papers
%X Users of interactive services such as e-commerce platforms have high expectations for the performance and responsiveness of these services. Tail latency, denoting the worst service times, contributes greatly to user dissatisfaction and should be minimized. Maintaining low tail latency for interactive services is challenging because a request is not complete until all its operations are completed. The challenge is to identify bottleneck operations and schedule them on uncoordinated backend servers with minimal overhead, when the duration of these operations are heterogeneous and unpredictable. In this paper, we focus on improving the latency of multiget operations in cloud data stores. We present TailX, a task-aware multiget scheduling algorithm that improves tail latencies under heterogeneous workloads. TailX schedules operations according to an estimation of the size of the corresponding data, and allows itself to procrastinate some operations to give way to higher priority ones. We implement TailX in Cassandra, a widely used key-value store. The result is an improved overall performance of the cloud data stores for a wide variety of heterogeneous workloads. Specifically, our experiments under heterogeneous YCSB workloads show that TailX outperforms state-of-the-art solutions and reduces tail latencies by up to 70% and median latencies by up to 75%.
%G English
%2 https://hal.science/hal-02917566/document
%2 https://hal.science/hal-02917566/file/Jaiman_DAIS20.pdf
%L hal-02917566
%U https://hal.science/hal-02917566
%~ UGA
%~ CNRS
%~ UNIV-LYON1
%~ UNIV-LYON2
%~ INSA-LYON
%~ EC-LYON
%~ INPG
%~ LIG
%~ LIRIS
%~ GRID5000
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC6
%~ IFIP-WG6-1
%~ IFIP-DAIS
%~ LYON2
%~ INSA-GROUPE
%~ UDL
%~ UNIV-LYON
%~ SILECS
%~ UGA-EPE
%~ IFIP-LNCS-12135
%~ LIG_SIDCH