Memory Hierarchy Characterization of NoSQL Applications through Full-System Simulation

Abstract

Abstract-In this work, we conduct a detailed memory characterization of a representative set of modern datamanagement software (Cassandra, MongoDB, OrientDB and Redis) running an illustrative NoSQL benchmark suite (YCSB). These applications are widely popular NoSQL databases with different data models and features such as in-memory storage. We compare how these data-serving applications behave with respect to other well-known benchmarks, such as SPEC CPU2006, PARSEC and NAS Parallel Benchmark. The methodology employed for evaluation relies on state-of-the-art full-system simulation tools, such as gem5. This allows us to explore configurations unattainable using performance monitoring units in actual hardware, being able to characterize memory properties. The results obtained suggest that NoSQL application behavior is not dissimilar to conventional workloads. Therefore, some of the optimizations present in state-of-the-art hardware might have a direct benefit. Nevertheless, there are some common aspects that are distinctive of conventional benchmarks that might be sufficiently relevant to be considered in architectural design. Strikingly, we also found that most database engines, independently of aspects such as workload or database size, exhibit highly uniform behavior. Finally, we show that different data-base engines make highly distinctive demands on the memory hierarchy, some being more stringent than others.

Bivariate, cluster, and suitability analysis of NoSQL solutions for big graph applications

“…Therefore, data can be accessed and acquired from different sources. As a result, the graph data model [46] is popularly used in social media analytics [47] and different specialized fields of big data analytics [48]. It is noteworthy that relational databases were developed for storing structured information available in and generated by enterprises.…”

Farklı İş Yükleri Altında NoSQL Sistemlerinin Performans Analizi

“…Daha sonraları bu "V" grupları 4V (3V'ye ek olarak Gerçeklik-Veracity), 5V(4V'ye ek olarak Değer-Value) [ Veritabanı sistemleri bilgisayar sistemi üzerinde veri tutarlılığını koruyarak sistemi maliyet ve hız açısından dengelerler [9]. Ancak ağ sistemimizde artan çok yönlü veri akışı ile ilişkisel veritabanları daha sınırlayıcı ve esneklikten uzak bir yapı içerisinde olduğu anlaşılmıştır.…”

“…Hadoop teknolojisinin performansını değerlendirmek için geliştirilen HiBench teknolojisi detaylı analizlerde kullanılmaktadır. Colaso ve arkadaşları detaylı bir kıyaslama çalışması yaparak NoSQL teknolojilerini karşılaştırmışlardır [9].…”

Parameter Analysis of Interfering Applications in Multi-Core Environment for Throughput Enhancement

“…Various simulations carried out in gem5 simulator covers state-of-the-art applications like No-SQL, big data, etc. [31]. In these simulations, a comparative analysis of No-SQL benchmarks is done in terms of system parameters related to the memory hierarchy.…”