Rein: Taming Tail Latency in Key-ValueStores via Multiget Scheduling
| Autor: | Sean Braithwaite, Marco Canini, Waleed Reda, Lalith Suresh, Dejan Kostic |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Low overhead
Computer science 02 engineering and technology computer.software_genre Bottleneck Scheduling (computing) storage 99th percentile 020204 information systems 0202 electrical engineering electronic engineering information engineering scheduling Latency (engineering) Queue business.industry Computer Sciences Communication Systems Skew 020206 networking & telecommunications multiget Data store Datavetenskap (datalogi) Operating system key-value distributed business computer Kommunikationssystem Computer network |
| Zdroj: | EuroSys |
| Popis: | We tackle the problem of reducing tail latencies in distributed key-value stores, such as the popular Cassandra database. We focus on workloads of multiget requests, which batch together access to several data elements and parallelize read operations across the data store machines. We first analyze a production trace of a real system and quantify the skew due to multiget sizes, key popularity, and other factors. We then proceed to identify opportunities for reduction of tail latencies by recognizing the composition of aggregate requests and by carefully scheduling bottleneck operations that can otherwise create excessive queues. We design and implement a system called Rein, which reduces latency via inter-multiget scheduling using low overhead techniques. We extensively evaluate Rein via experiments in Amazon Web Services (AWS) and simulations. Our scheduling algorithms reduce the median, 95th, and 99th percentile latencies by factors of 1.5, 1.5, and 1.9, respectively. QC 20170502 TCC, WASP |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|