Advertisement

Strome: Energy-Aware Data-Stream Processing

  • Christopher EibelEmail author
  • Christian Gulden
  • Wolfgang Schröder-Preikschat
  • Tobias Distler
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10853)

Abstract

Handling workloads generated by a large number of users, data-stream–processing systems also require large amounts of energy. To reduce their energy footprint, such systems typically rely on the operating systems of their servers to adjust processor speeds depending on the current workload by performing dynamic voltage and frequency scaling (DVFS). In this paper, we show that, although effective, this approach still leaves room for significant energy savings due to DVFS making conservative assumptions regarding its impact on application performance. To leverage the unused potential we present Strome, an energy-aware technique to minimize energy demand in data-stream–processing systems by dynamically adapting upper limits for the power demand of hardware components. In contrast to DVFS, Strome exploits information on application performance and is therefore able to achieve energy savings while minimizing its effects on throughput and latency. Our evaluation shows that Strome is particularly effective in the face of varying workloads, reducing power demand by up to 25 % compared with the state-of-the-art data-stream–processing system Heron relying on DVFS.

Notes

Acknowledgments

We thank Heiko Janker for his help towards a precise and accurate total-power measuring device and the anonymous reviewers for their insightful feedback. This work was partially supported by the German Research Council (DFG) under grant no. DI 2097/1-2 (“REFIT”) and grant no. SFB/TR 89 (“InvasIC”).

References

  1. 1.
    Advanced Micro Devices, Inc.: BIOS and kernel developer’s guide (BKDG) for AMD family 15h models 30h–3Fh processors, 49125 rev 3.06 (2015)Google Scholar
  2. 2.
    Advanced Micro Devices, Inc.: Processor programming reference (PPR) for AMD family 17h model 01h, revision B1 processors (2017)Google Scholar
  3. 3.
    Apache Spark Streaming. https://spark.apache.org/streaming/
  4. 4.
  5. 5.
    Atikoglu, B., Xu, Y., Frachtenberg, E., Jiang, S., Paleczny, M.: Workload analysis of a large-scale key-value store. In: SIGMETRICS 2012, pp. 53–64 (2012)Google Scholar
  6. 6.
    Azimi, R., Badiei, M., Zhan, X., Li, N., Reda, S.: Fast decentralized power capping for server clusters. In: HPCA 2017 (2017)Google Scholar
  7. 7.
    Bhattacharya, A.A., Culler, D., Kansal, A., Govindan, S., Sankar, S.: The need for speed and stability in data center power capping. In: IGCC 2012, pp. 1–10 (2012)Google Scholar
  8. 8.
    Biem, A., Bouillet, E., Feng, H., Ranganathan, A., Riabov, A., Verscheure, O., Koutsopoulos, H., Moran, C.: IBM Infosphere Streams for scalable, real-time, intelligent transportation services. In: SIGMOD 2010, pp. 1093–1104 (2010)Google Scholar
  9. 9.
    Cardellini, V., Nardelli, M., Luzi, D.: Elastic stateful stream processing in Storm. In: HPCS 2016, pp. 583–590 (2016)Google Scholar
  10. 10.
    Cerviño, J., Kalyvianaki, E., Salvachúa, J., Pietzuch, P.R.: Adaptive provisioning of stream processing systems in the cloud. In: ICDEW 2012, pp. 295–301 (2012)Google Scholar
  11. 11.
    De Matteis, T., Mencagli, G.: Keep calm and react with foresight: strategies for low-latency and energy-efficient elastic data stream processing. In: PPoPP 2016, pp. 13:1–13:12 (2016)Google Scholar
  12. 12.
    DeCandia, G., Hastorun, D., Jampani, M., Kakulapati, G., Lakshman, A., Pilchin, A., Sivasubramanian, S., Vosshall, P., Vogels, W.: Dynamo: Amazon’s highly available key-value store. In: SOSP 2007, pp. 205–220 (2007)Google Scholar
  13. 13.
    Eibel, C., Distler, T.: Towards energy-proportional state-machine replication. In: ARM 2015, pp. 19–24 (2015)Google Scholar
  14. 14.
    Eibel, C., Do, T.-N., Meißner, R., Distler, T.: Empya: saving energy in the face of varying workloads. In: IC2E 2018 (2018)Google Scholar
  15. 15.
    Esmaeilzadeh, H., Blem, E.R., St. Amant, R., Sankaralingam, K., Burger, D.: Dark silicon and the end of multicore scaling. In: ISCA 2011, pp. 365–376 (2011)Google Scholar
  16. 16.
    Floratou, A., Agrawal, A., Graham, B., Rao, S., Ramasamy, K.: Dhalion: self-regulating stream processing in Heron. Proc. VLDB Endow. 10(12), 1825–1836 (2017)CrossRefGoogle Scholar
  17. 17.
    Gulisano, V.M., Jiménez-Peris, R., Patiño-Martínez, M., Soriente, C., Valduriez, P.: StreamCloud: an elastic and scalable data streaming system. TPDS 23(12), 2351–2365 (2012)Google Scholar
  18. 18.
    Heinze, T., Roediger, L., Meister, A., Ji, Y., Jerzak, Z., Fetzer, C.: Online parameter optimization for elastic data stream processing. In: SoCC 2015, pp. 276–287 (2015)Google Scholar
  19. 19.
    Horowitz, M., Indermaur, T., Gonzalez, R.: Low-power digital design. In: Proceedings of 1994 IEEE Symposium on Low Power Electronics, pp. 8–11 (1994)Google Scholar
  20. 20.
    Intel Corporation: Intel 64 and IA-32 architectures software developer’s manual volume 3 (3A, 3B & 3C): system programming guide (2015)Google Scholar
  21. 21.
    Iyer, A.P., Li, L.E., Das, T., Stoica, I.: Time-evolving graph processing at scale. In: GRADES 2016, pp. 5:1–5:6 (2016)Google Scholar
  22. 22.
    Kazemitabar, S.J., Banaei-Kashani, F., McLeod, D.: Geostreaming in cloud. In: IWGS 2011, pp. 3–9 (2011)Google Scholar
  23. 23.
    Kulkarni, S., Bhagat, N., Fu, M., Kedigehalli, V., Kellogg, C., Mittal, S., Patel, J.M., Ramasamy, K., Taneja, S.: Twitter Heron: stream processing at scale. In: SIGMOD 2015, pp. 239–250 (2015)Google Scholar
  24. 24.
    Li, J., Pu, C., Chen, Y., Gmach, D., Milojicic, D.: Enabling elastic stream processing in shared clusters. In: CLOUD 2016, pp. 108–115 (2016)Google Scholar
  25. 25.
  26. 26.
    Lo, D., Cheng, L., Govindaraju, R., Barroso, L.A., Kozyrakis, C.: Towards energy proportionality for large-scale latency-critical workloads. In: ISCA 2014, pp. 301–312 (2014)Google Scholar
  27. 27.
  28. 28.
    Rountree, B., Ahn, D.H., de Supinski, B.R., Lowenthal, D.K., Schulz, M.: Beyond DVFS: a first look at performance under a hardware-enforced power bound. In: IPDPSW 2012, pp. 947–953 (2012)Google Scholar
  29. 29.
    Semeraro, G., Magklis, G., Balasubramonian, R., Albonesi, D.H., Dwarkadas, S., Scott, M.L.: Energy-efficient processor design using multiple clock domains with dynamic voltage and frequency scaling. In: HPCA 2002, pp. 18–28. IEEE Computer Society (2002)Google Scholar
  30. 30.
    Teich, J.: Invasive algorithms and architectures. IT Inf. Technol. 50(5), 300–310 (2008)Google Scholar
  31. 31.
    Teich, J., Henkel, J., Herkersdorf, A., Schmitt-Landsiedel, D., Schröder-Preikschat, W., Snelting, G.: Invasive computing: an overview. In: Multiprocessor System-on-Chip - Hardware Design and Tool, Integration, pp. 241–268 (2011)Google Scholar
  32. 32.
    Wu, Q., Deng, Q., Ganesh, L., Hsu, C.-H., Jin, Y., Kumar, S., Li, B., Meza, J., Song, Y.J.: Dynamo: Facebook’s data center-wide power management system. In: ISCA 2016, pp. 469–480 (2016)Google Scholar
  33. 33.
    Zaharia, M. Das, T., Li, H., Hunter, T., Shenker, S., Stoica, I.: Discretized streams: fault-tolerant streaming computation at scale. In: SOSP 2013, pp. 423–438 (2013)Google Scholar
  34. 34.
    Zhu, Y., Halpern, M., Reddi, V.J.: Event-based scheduling for energy-efficient QoS (eQoS) in mobile Web applications. In: HPCA 2015, pp. 137–149 (2015)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2018

Authors and Affiliations

  • Christopher Eibel
    • 1
    Email author
  • Christian Gulden
    • 1
  • Wolfgang Schröder-Preikschat
    • 1
  • Tobias Distler
    • 1
  1. 1.Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)ErlangenGermany

Personalised recommendations