Using Latency Metrics in NoSQL Database Performance Benchmarking

  • C.-F. Andor Department of Computer Science, Faculty of Mathematics and Computer Science, Babes ¸-Bolyai University, Cluj-Napoca, Romania
  • B. Pârv Department of Computer Science, Faculty of Mathematics and Computer Science, Babes ¸-Bolyai University, Cluj-Napoca, Romania
  • D. M. Suciu Department of Computer Science, Faculty of Mathematics and Computer Science, Babes ¸-Bolyai University, Cluj-Napoca, Romania

Abstract

This paper presents an experimental study evaluating the performance of NoSQL database management systems. The study compares two NoSQL database management systems (Cassandra and MongoDB) and considers the following parameters/factors: workload and degree of parallelism. Two different workloads (update heavy and mostly read) were used, and different numbers of threads. The measured results are related to average latency: update latency and read latency. Our study shows that with the only exception of 1000 operations, both latency indicators have a quasi-parabolic behavior, where the minimum (i.e. the best performance) depends mainly on the number of threads and slightly varies with the increase in the number of operations. In the case of 1000 operations, there is also a maximum point (i.e. worst performance) case, after which the latency decreases.

References

[1] C. F. Andor and B. Pârv. NoSQL Database Performance Benchmarking - A Case Study. Studia Informatica, LXIII(1):80–93, 2018.
[2] Apache Cassandra. http://cassandra.apache.org/. Accessed: 2017-09-25.
[3] F. Chang, J. Dean, S. Ghemawat, W. C. Hsieh, D. A. Wallach, M. Burrows, T. Chandra, A. Fikes, and R. E. Gruber. Bigtable: A Distributed Storage System for Structured Data. OSDI ’06 Proceedings of the 7th USENIX Symposium on Operating Systems Design and Implementation, 7, 2006.
[4] B. F. Cooper, A. Silberstein, E. Tam, R. Ramakrishnan, and R. Sears. Benchmarking Cloud Serving Systems with YCSB. Proceedings of the 1st ACM Symposium on Cloud Computing, pages 143–154, 2010.
[5] CouchDB. http://couchdb.apache.org/. Accessed: 2017-09-25.
[6] G. DeCandia, D. Hastorun, M. Jampani, G. Kakulapati, A. Lakshman, A. Pilchin, S. Sivasubramanian, P. Vosshall, and W. Vogels. Dynamo: Amazon’s Highly Available Key-value Store. Proceedings of 21st ACM SIGOPS Symposium on Operating Systems Principles, oct 2007.
[7] Fixstars. GridDB and Cassandra Performance and Scalability. A YCSB Performance Comparison on Microsoft Azure. Technical report, Fixstars Solutions, 2016.
[8] A. Gandini, M. Gribaudo, W. J. Knottenbelt, R. Osman, and P. Piazzolla. Performance Evaluation of NoSQL Databases. EPEW 2014: Computer Performance Engineering, Lecture Notes in Computer Science, 8721:16–29, 2014.
[9] A. Ghazal, T. Rabl, M. Hu, F. Raab, M. Poess, A. Crolotte, and H.-A. Jacobsen. Big-Bench: Towards an Industry Standard Benchmark for Big Data Analytics. Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, pages 1197–1208, 2013.
[10] HBase. https://hbase.apache.org/. Accessed: 2017-09-25.
[11] JSON. https://www.json.org/. Accessed: 2018-03-16.
[12] J. Klein, I. Gorton, N. Ernst, P. Donohoe, K. Pham, and C. Matser. Performance Evaluation of NoSQL Databases: A Case Study. Proceedings of the 1st Workshop on Performance Analysis of Big Data Systems, pages 5–10, 2015.
[13] A. Lakshman and P. Malik. Cassandra: A Decentralized Structured Storage System. ACM SIGOPS Operating Systems Review, 44:35–40, 2010.
[14] MongoDB. https://www.mongodb.com/. Accessed: 2017-09-25.
[15] R. O. Nambiar and M. Poess. The Making of TPC-DS. VLDB ’06 Proceedings of the 32nd International Conference on Very Large Data Bases, pages 1049–1058, 2006.
[16] OrientDB. http://orientdb.com/. Accessed: 2017-09-25.
[17] R Statistics Package. https://www.r-project.org/. Accessed: 2017-09-25.
[18] Stress Test for Couchbase Client and Cluster. http://docs.couchbase.com/sdk-api/couchbase-c-client-2.4.8/md_doc_cbc-pillowfight.html. Accessed: 2019-01-03.
[19] The cassandra-stress tool. https://docs.datastax.com/en/cassandra/3.0/cassandra/tools/toolsCStress.html. Accessed: 2019-01-03.
[20] The YCSB Core Workloads. https://github.com/brianfrankcooper/YCSB/wiki/Core-Workloads. Accessed: 2017-09-25.
[21] XML. https://www.w3.org/TR/2008/REC-xml-20081126/. Accessed: 2018-03-16.
[22] YAML. http://yaml.org/. Accessed: 2018-03-16.
[23] YCSB Github Wiki. https://github.com/brianfrankcooper/YCSB/wiki. Accessed: 2017-09-25.
Published
2019-06-17
How to Cite
ANDOR, C.-F.; PÂRV, B.; SUCIU, D. M.. Using Latency Metrics in NoSQL Database Performance Benchmarking. Studia Universitatis Babeș-Bolyai Informatica, [S.l.], v. 64, n. 1, p. 39-50, june 2019. ISSN 2065-9601. Available at: <http://www.cs.ubbcluj.ro/~studia-i/journal/journal/article/view/35>. Date accessed: 29 nov. 2020. doi: https://doi.org/10.24193/subbi.2019.1.04.
Section
Articles