Skip to main content
SpringerLink
Log in

Enhancing timeliness and saving power in real-time databases

  • Published:
Real-Time Systems Aims and scope Submit manuscript

Abstract

In data-intensive real-time embedded applications, it is desirable to process data service requests in a timely manner using fresh data, spending less power. However, related work is relatively scarce despite the importance. In this paper, we present an effective approach to reduce both deadline misses and power expenditure in real-time databases with one or more processor by merging similar real-time queries to decrease repeated data accesses and processing, while doing dynamic power management. In a simulation study, our approach substantially decreases deadline misses and power consumption compared to state-of-the-art baselines.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. Although we not only aggregate queries but also combine data reads and processing for transactions, we call our approach real-time query aggregation to be consistent with the term ’query aggregation’ used in the database literature (Lang and Patel 2009).

  2. We have adopted Table 1 from a novel work on energy-efficient real-time scheduling (Legout et al. 2015), which has derived the low-power state model summarized in the table by analyzing the ARM Cortex-A family processors and FreeScale Power architecture.

  3. The dynamic power consumption when the CPU is in the active mode is proportional to the clock frequency f and the square of the supply voltage V: \(P_{dyn} \propto f V^2\) (Bambagini et al. 2016).

  4. If a certain data item is accessed by \(T_i\), the corresponding bit in \(R_i\) is set to 1.

  5. Generally, a large \(\kappa \) value provides a lower miss ratio for saving less power or vice versa. In Sect. 5, \(\kappa = 1.5\).

  6. Our DVFS scheme, which switches to the lowest frequency when the idle interval is too short for the C1 state, saves power by less than 2% as discussed in Sect. 5.

References

  • Arce G (2005) Nonlinear signal processing: a statistical approach. Wiley, New York

    MATH  Google Scholar 

  • Babu S, Bizarro P (2005) Adaptive query processing in the looking glass. In: Conference on innovative data systems research

  • Bambagini M, Marinoni M, Aydin H, Buttazzo G (2016) Energy-aware scheduling for real-time systems: a survey. ACM Trans Embedded Comput Syst 15(1):1

  • Baruah S, Bertogna M, Buttazzo G (2014) Multiprocessor scheduling for real-time systems. Springer, Berlin

    MATH  Google Scholar 

  • Bastoni A, Brandenburg BB, Anderson JH (2010) An empirical comparison of global, partitioned, and clustered multiprocessor EDF schedulers. In: IEEE real-time systems symposium

  • Cao G, Ravindran AA (2014) Energy efficient soft real-time computing through cross-layer predictive control. In: International workshop on feedback computing

  • Deshpande A, Ives Z, Raman V (2007) Adaptive query processing. Found Trends Databases 1(1):1–140

    Article  MATH  Google Scholar 

  • Devi U, Anderson J (2008) Tardiness bounds under global EDF scheduling on a multiprocessor. Real-Time Syst 38(2):133–189

    Article  MATH  Google Scholar 

  • D’souza S, Rajkumar R (2017) Thermal implications of energy-saving schedulers. In: Euromicro conference on real-time systems

  • Fu C, Calinescuy G, Wang K, Li M, Xue CJ (2016) Energy-aware real-time task scheduling on local and shared memory system. In: IEEE real-time systems symposium

  • Guo Z, Bhuiyan A, Saifullah A, Guan N, Xiong H (2017) Energy-efficient multi-core scheduling for real-time DAG tasks. In: Euromicro conference on real-time systems

  • Gustafsson T, Hallqvist H, Hansson J (2005) A similarity-aware multiversion concurrency control and updating algorithm for up-to-date snapshots of data. In: Euromicro conference on real-time systems

  • Han S, Chen D, Xiong M, Lam KY, Mok AK, Ramamritham K (2014) Schedulability analysis of deferrable scheduling algorithms for maintaining real-time data freshness. IEEE Trans Comput 63(4):979–994

    Article  MathSciNet  MATH  Google Scholar 

  • Han S, Lam KY, Chen D, Xiong M, Wang J, Ramamritham K, Mok AK (2016) Online mode switch algorithms for maintaining data freshness in dynamic cyber-physicalsystems. IEEE Trans Knowl Data Eng 28(3):756–769

    Article  Google Scholar 

  • Hu S, et al (2015) Data acquisition for real-time decision-making under freshness constraints. In: IEEE real-time systems symposium

  • Imes C, Kim DHK, Maggio M, Hoffmann H (2015) POET: a portable approach to minimizing energy under soft real-time constraints. In: IEEE real-time and embedded technology and applications symposium

  • Irani S, Shukla S, Gupta R (2007) Algorithms for power savings. ACM Trans Algorithms 3(4):41

  • Kang KD (2016) Reducing deadline misses and power consumption in real-time databases. In: IEEE real-time systems symposium

  • Kang W, Chung J (2015) QoS management for embedded databases in multicore-based embedded systems. Mob Inf Syst 14:11

  • Kang W, Chung J (2017) Energy-efficient response time management for embedded databases. Real-Time Syst 53(2):228–253

    Article  MATH  Google Scholar 

  • Kang W, Son SH (2012) Power- and time-aware buffer cache management for real-time embedded databases. J Syst Arch-Embed Syst Des 58(6–7):233–246

    Article  Google Scholar 

  • Kehr S, Quinones E, Langen D, Boeddeker B, Schaefer G (2017) Parcus: energy-aware and robust parallelization of AUTOSAR legacy applications. In: IEEE real-time and embedded technology and applications symposium

  • Kim JE, Abdelzaher T, Sha L, Bar-Noy A, Hobbs R (2016) Sporadic decision-centric data scheduling with normally-off sensors. In: IEEE real-time systems symposium

  • Kim N, Ward BC, Chisholm M, Fu CY, Anderson JH, Smith FD (2017) Attacking the one-out-of-m multicore problem by combining hardware management with mixed-criticality provisioning. Real-time systems (special issue on mixed-criticality, multi-core, and micro-kernels)

  • Kunjir M, Birwa PK, Haritsa JR (2012) Peak power plays in database engines. In: International conference on extending database technology

  • Lam KY, Kuo TW (eds) (2006) Real-time database systems. Kluwer Academic Publishers, Norwell

    Google Scholar 

  • Lang W, Patel JM (2009) Towards eco-friendly database management systems. In: Biennial conference on innovative database systems research

  • Legout V, Jan M, Pautet L (2015) Scheduling algorithms to reduce the static energy consumption of real-time systems. Real-Time Syst 51(2):153–191

    Article  MATH  Google Scholar 

  • Li J, Chen JJ, Xiong M, Li G (2011) Workload-aware partitioning for maintaining temporal consistency on multiprocessor platforms. In: IEEE real-time systems symposium

  • Madden SR, Franklin MJ, Hellerstein JM, Hong W (2005) TinyDB: an acquisitional query processing system for sensor networks. ACM Trans Database Syst 30(1):122–173

    Article  Google Scholar 

  • Mazouz A, Laurent A, Pradelle B, Jalby W (2014) Evaluation of CPU frequency transition latency. Comput Sci-Res Dev 29(3–4):187–195

    Article  Google Scholar 

  • mcobject (2017) eXtremeDB, a fast, reliable and cost-effective embedded database system for embedded systems and intelligent devices. http://www.mcobject.com/emb

  • Nguyen TH, Francesco MD, Yla-Jaaski A (2015) Virtual machine consolidation with multiple usage prediction for energy-efficient cloud data centers. In: IEEE international conference on cloud computing (CLOUD)

  • Phillips CL, Nagle HT (1995) Digital control system analysis and design, 3rd edition. Prentice Hall, Englewood Cliffs

  • Ramamritham K, Son SH, DiPippo L (2004) Real-time databases and data services. Real-Time Syst 28(2–3):179–215

    Article  MATH  Google Scholar 

  • Srikantaiah S, Kansal A, Zhao F (2008) Energy aware consolidation for cloud computing. In: Workshop on power aware computing and systems (HotPower’08), USENIX Association

  • Stankovic JA, Son SH, Hansson J (1999) Misconceptions about real-time databases. IEEE Comput 32(6):29–36

    Article  Google Scholar 

  • Tsiftes N, Dunkels A (2011) A database in every sensor. In: ACM conference on embedded networked sensor systems

  • Tu YC, Wang X, Zeng B, Xu Z (2014) A system for energy-efficient data management. SIGMOD Record 43(1):21–26

    Article  Google Scholar 

  • Valsan PK, Yun H, Farshchi F (2017) Addressing isolation challenges of non-blocking caches for multicore real-time systems. Real-time systems (special issue on mixed-criticality, multi-core, and micro-kernels)

  • Völp M, Hähnel M, Lackorzynski A (2014) Has energy surpassed timeliness? Scheduling energy-constrained mixed-criticality systems. In: IEEE real-time and embedded technology and applications symposium

  • Wires J, Ingram S, Drudi Z, Harvey NJA, Warfield A (2014) Characterizing storage workloads with counter stacks. In: USENIX symposium on operating systems design and implementation

  • Xiong M, Han S, Lam KY, Chen D (2008) Deferrable scheduling for maintaining real-time data freshness: algorithms, analysis, and results. IEEE Trans Comput 57(7):952–964

    Article  MathSciNet  Google Scholar 

  • Xu Z, Wang X, Tu YC (2013) Power-aware throughput control for database management systems. In: International conference on autonomic computing

  • Xu Z, Tu YC, Wang X (2015) Online energy estimation of relational operations in database systems. IEEE Trans Comput 64(11):3223–3236

    Article  MathSciNet  MATH  Google Scholar 

  • Zhang Y, Liu Y, Zhuang L, Liu X, Zhao F, Li Q (2015) Accurate CPU power modeling for multicore smartphones. Technical Report MSR-TR-2015-9, Microsoft

Download references

Acknowledgements

We appreciate anonymous reviewers for their help to improve the paper. This work was supported, in part, by NSF Grant CNS-1526932.

Author information

Authors and Affiliations

  1. Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, USA

    Kyoung-Don Kang

Authors
  1. Kyoung-Don Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kyoung-Don Kang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kang, KD. Enhancing timeliness and saving power in real-time databases. Real-Time Syst 54, 484–513 (2018). https://doi.org/10.1007/s11241-018-9302-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11241-018-9302-2

Keywords

Search

Navigation