Vista Equipo: Chisel: Reshaping Queries to Trim Latency in Key-Value Stores

Chisel: Reshaping Queries to Trim Latency in Key-Value Stores

It is challenging for key-value data stores to trim user (tail) latency of requests as the workloads are observed to have skewed number of key-value pairs and commonly retrieved via multiget operation, i.e., all keys at the same time. In this paper we present Chisel, a novel client side solution to...

Descripción completa

Detalles Bibliográficos
Autores Principales:	Birke R., Pérez, Juan F., Mokhtar S.B., Rameshan N., Chen L.Y.
Formato:	Objeto de conferencia (Conference Object)
Lenguaje:	Inglés (English)
Publicado:	Institute of Electrical and Electronics Engineers Inc. 2019
Materias:	Queueing theory Client sides Evaluation results Key-value pairs Key-value stores Latency model Operational regions Queueing model System configurations Tools Key value stores Split merge latency model
Acceso en línea:	https://repository.urosario.edu.co/handle/10336/22861 https://doi.org/10.1109/ICAC.2019.00016

id	ir-10336-22861
recordtype	dspace
spelling	ir-10336-228612022-05-02T12:37:17Z Chisel: Reshaping Queries to Trim Latency in Key-Value Stores Birke R. Pérez, Juan F. Mokhtar S.B. Rameshan N. Chen L.Y. Queueing theory Client sides Evaluation results Key-value pairs Key-value stores Latency model Operational regions Queueing model System configurations Tools Key value stores Split merge latency model It is challenging for key-value data stores to trim user (tail) latency of requests as the workloads are observed to have skewed number of key-value pairs and commonly retrieved via multiget operation, i.e., all keys at the same time. In this paper we present Chisel, a novel client side solution to efficiently reshape the query size at the data store by adaptively splitting big requests into chunks to reap the benefits of parallelism and merge small requests into a single query to amortize latency overheads per request. We derive a novel layered queueing model that can quickly and approximately steer the decisions of Chisel. We extensively evaluate Chisel on memcached clusters hosted on a testbed, across a large number of scenarios with different workloads and system configurations. Our evaluation results show that Chisel can overturn the inherent high variability of requests into a judicious operational region, showcasing significant gains for the mean and 95th percentile of user perceived latency, compared to the state-of-art query processing policy. © 2019 IEEE. 2019 2020-05-25T23:58:25Z info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion https://repository.urosario.edu.co/handle/10336/22861 https://doi.org/10.1109/ICAC.2019.00016 eng info:eu-repo/semantics/openAccess application/pdf Institute of Electrical and Electronics Engineers Inc. instname:Universidad del Rosario
institution	EdocUR - Universidad del Rosario
collection	DSpace
language	Inglés (English)
topic	Queueing theory Client sides Evaluation results Key-value pairs Key-value stores Latency model Operational regions Queueing model System configurations Tools Key value stores Split merge latency model
spellingShingle	Queueing theory Client sides Evaluation results Key-value pairs Key-value stores Latency model Operational regions Queueing model System configurations Tools Key value stores Split merge latency model Birke R. Pérez, Juan F. Mokhtar S.B. Rameshan N. Chen L.Y. Chisel: Reshaping Queries to Trim Latency in Key-Value Stores
description	It is challenging for key-value data stores to trim user (tail) latency of requests as the workloads are observed to have skewed number of key-value pairs and commonly retrieved via multiget operation, i.e., all keys at the same time. In this paper we present Chisel, a novel client side solution to efficiently reshape the query size at the data store by adaptively splitting big requests into chunks to reap the benefits of parallelism and merge small requests into a single query to amortize latency overheads per request. We derive a novel layered queueing model that can quickly and approximately steer the decisions of Chisel. We extensively evaluate Chisel on memcached clusters hosted on a testbed, across a large number of scenarios with different workloads and system configurations. Our evaluation results show that Chisel can overturn the inherent high variability of requests into a judicious operational region, showcasing significant gains for the mean and 95th percentile of user perceived latency, compared to the state-of-art query processing policy. © 2019 IEEE.
format	Objeto de conferencia (Conference Object)
author	Birke R. Pérez, Juan F. Mokhtar S.B. Rameshan N. Chen L.Y.
author_facet	Birke R. Pérez, Juan F. Mokhtar S.B. Rameshan N. Chen L.Y.
author_sort	Birke R.
title	Chisel: Reshaping Queries to Trim Latency in Key-Value Stores
title_short	Chisel: Reshaping Queries to Trim Latency in Key-Value Stores
title_full	Chisel: Reshaping Queries to Trim Latency in Key-Value Stores
title_fullStr	Chisel: Reshaping Queries to Trim Latency in Key-Value Stores
title_full_unstemmed	Chisel: Reshaping Queries to Trim Latency in Key-Value Stores
title_sort	chisel: reshaping queries to trim latency in key-value stores
publisher	Institute of Electrical and Electronics Engineers Inc.
publishDate	2019
url	https://repository.urosario.edu.co/handle/10336/22861 https://doi.org/10.1109/ICAC.2019.00016
_version_	1740172248943165440
score	12,131701

Chisel: Reshaping Queries to Trim Latency in Key-Value Stores

Ejemplares similares