Abstract
Lightweight data compression is frequently applied in main memory database systems to improve query performance. The data processed by such systems is highly diverse. Moreover, there is a high number of existing lightweight compression techniques. Therefore, choosing the optimal technique for a given dataset is non-trivial. Existing approaches are based on simple rules, which do not suffice for such a complex decision. In contrast, our vision is a cost-based approach. However, this requires a detailed cost model, which can only be obtained from a systematic benchmarking of many compression algorithms on many different datasets. A naïve benchmark evaluates every algorithm under consideration separately. This yields many redundant steps and is thus inefficient. We propose an efficient and extensible benchmark framework for compression techniques. Given an ensemble of algorithms, it minimizes the overall run time of the evaluation. We experimentally show that our approach outperforms the naïve approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The source code of our framework can be downloaded at https://wwwdb.inf.tu-dresden.de/team/staff/patrick-damme-msc/.
- 2.
Note that, alternatively, a transformation from some already reachable node to X could be added. This could be especially useful, since transformations are faster than compressions in many cases. However, finding the fastest way to make X reachable would require a cost model for the algorithms, which can only be available after the systematic benchmarking.
- 3.
The compressions can be executed in an arbitrary order. The same applies to the decompressions. However, the transformations cannot be applied in an arbitrary order in general, since a transformation could require a source format that is not present after all compressions in \(\mathcal {A}^+\) have been executed, as it is the case for 4G-2-4Ns in our example.
References
Abadi, D., Madden, S., Ferreira, M.: Integrating compression and execution in column-oriented database systems. In: SIGMOD, pp. 671–682 (2006)
Damme, P., Habich, D., Lehner, W.: Direct transformation techniques for compressed data: general approach and application scenarios. In: Morzy, T., Valduriez, P., Ladjel, B. (eds.) ADBIS 2015. LNCS, vol. 9282, pp. 151–165. Springer, Heidelberg (2015)
Färber, F., May, N., Lehner, W., Große, P., Müller, I., Rauhe, H., Dees, J.: The SAP HANA database - an architecture overview. IEEE Data Eng. Bull. 35(1), 28–33 (2012)
Goldstein, J., Ramakrishnan, R., Shaft, U.: Compressing relations and indexes. In: ICDE, pp. 370–379 (1998)
Große, P., Lehner, W., May, N.: Advanced analytics with the SAP HANA database. In: DATA, pp. 61–71 (2013)
Huffman, D.: A method for the construction of minimum-redundancy codes. Proc. IRE 40(9), 1098–1101 (1952)
Lee, J., Kwon, Y.S., Färber, F., Muehle, M., Lee, C., Bensberg, C., Lee, J., Lee, A.H., Lehner, W.: SAP HANA distributed in-memory database system: transaction, session, and metadata management. In: ICDE, pp. 1165–1173 (2013)
Lemire, D., Boytsov, L., Kaser, O., Caron, M., Dionne, L., Lemay, M., Kruus, E., Bedini, A., Petri, M.: The FastPFOR c++ library: Fast integer compression. https://github.com/lemire/FastPFOR
Lemire, D., Boytsov, L.: Decoding billions of integers per second through vectorization (2012). CoRR abs/1209.2137
Lempel, A., Ziv, J.: On the complexity of finite sequences. IEEE Trans. Inf. Theory 22, 75–81 (1976)
Paradies, M., Lemke, C., Plattner, H., Lehner, W., Sattler, K.U., Zeier, A., Krueger, J.: How to juggle columns: an entropy-based approach for table compression. In: IDEAS, pp. 205–215 (2010)
Plattner, H.: A common database approach for OLTP and OLAP using an in-memory column database. In: SIGMOD, pp. 1–2 (2009)
Roth, M.A., Van Horn, S.J.: Database compression. SIGMOD Rec. 22(3), 31–39 (1993)
Schlegel, B., Gemulla, R., Lehner, W.: Fast integer compression using SIMD instructions. In: DaMoN Workshop, pp. 34–40 (2010)
Stepanov, A.A., Gangolli, A.R., Rose, D.E., Ernst, R.J., Oberoi, P.S.: SIMD-based decoding of posting lists. In: CIKM, pp. 317–326 (2011)
Willhalm, T., Popovici, N., Boshmaf, Y., Plattner, H., Zeier, A., Schaffner, J.: SIMD-scan: ultra fast in-memory table scan using on-chip vector processing units. Proc. VLDB Endow. 2(1), 385–394 (2009)
Witten, I.H., Neal, R.M., Cleary, J.G.: Arithmetic coding for data compression. Commun. ACM 30(6), 520–540 (1987)
Zukowski, M., Heman, S., Nes, N., Boncz, P.: Super-scalar RAM-CPU cache compression. In: ICDE, pp. 59–70 (2006)
Acknowledgments
This work was funded by the German Research Foundation (DFG) in the context of the project “Lightweight Compression Techniques for the Optimization of Complex Database Queries” (LE-1416/26-1).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Damme, P., Habich, D., Lehner, W. (2016). A Benchmark Framework for Data Compression Techniques. In: Nambiar, R., Poess, M. (eds) Performance Evaluation and Benchmarking: Traditional to Big Data to Internet of Things. TPCTC 2015. Lecture Notes in Computer Science(), vol 9508. Springer, Cham. https://doi.org/10.1007/978-3-319-31409-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-31409-9_6
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-31408-2
Online ISBN: 978-3-319-31409-9
eBook Packages: Computer ScienceComputer Science (R0)