{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T16:33:33Z","timestamp":1785602013609,"version":"3.56.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030495558","type":"print"},{"value":"9783030495565","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-49556-5_30","type":"book-chapter","created":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T23:05:06Z","timestamp":1591657506000},"page":"335-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Apache Spark Streaming, Kafka and\u00a0HarmonicIO: A Performance Benchmark and Architecture Comparison for Enterprise and Scientific Computing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1206-1428","authenticated-orcid":false,"given":"Ben","family":"Blamey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7273-7923","authenticated-orcid":false,"given":"Andreas","family":"Hellander","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0302-6276","authenticated-orcid":false,"given":"Salman","family":"Toor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,6,9]]},"reference":[{"key":"30_CR1","unstructured":"Apache Software Foundation: Apache Hadoop. \nhttp:\/\/hadoop.apache.org\/\n\n (2011)"},{"key":"30_CR2","unstructured":"Apache Software Foundation: Cassandra Limitations. \nhttps:\/\/cwiki.apache.org\/confluence\/display\/CASSANDRA2\/CassandraLimitations\n\n (2019)"},{"issue":"1","key":"30_CR3","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1186\/s12859-018-2241-z","volume":"19","author":"K Ausmees","year":"2018","unstructured":"Ausmees, K., John, A., Toor, S.Z., Hellander, A., Nettelblad, C.: BAMSI: a multi-cloud service for scalable distributed filtering of massive genome data. BMC Bioinform. 19(1), 240 (2018). \nhttps:\/\/doi.org\/10.1186\/s12859-018-2241-z","journal-title":"BMC Bioinform."},{"key":"30_CR4","doi-asserted-by":"publisher","unstructured":"Blamey, B., Wrede, F., Karlsson, J., Hellander, A., Toor, S.: Adapting the secretary hiring problem for optimal hot-cold tier placement under Top-K workloads. In: 2019 19th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID). pp. 576\u2013583, May 2019. \nhttps:\/\/doi.org\/10.1109\/CCGRID.2019.00074","DOI":"10.1109\/CCGRID.2019.00074"},{"key":"30_CR5","unstructured":"Carbone, P., Katsifodimos, A., Ewen, S., Markl, V., Haridi, S., Tzoumas, K.: Apache Flink\u2122: stream and batch processing in a single engine. Bull. IEEE Comput. Soc. Techn. Committee Data Eng. 36(4), 28\u201338 (2015)"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Chintapalli, S., et al.: Benchmarking streaming computation engines: storm, flink and spark streaming. In: 2016 IEEE International Parallel and Distributed Processing Symposium Workshops, pp. 1789\u20131792. IEEE (2016)","DOI":"10.1109\/IPDPSW.2016.138"},{"key":"30_CR7","unstructured":"Kreps, J., Narkhede, N., Rao, J., et al.: Kafka: a distributed messaging system for log processing. In: Proceedings of the NetDB, pp. 1\u20137 (2011)"},{"key":"30_CR8","unstructured":"Lugneg\u00e5rd, L.: Building a high throughput microscope simulator using the Apache Kafka streaming framework (M.sc. Thesis) (2018)"},{"key":"30_CR9","doi-asserted-by":"publisher","unstructured":"Marcu, O.C., Costan, A., Antoniu, G., P\u00e9rez-Hern\u00e1ndez, M.S.: Spark versus flink: understanding performance in big data analytics frameworks. In: 2016 IEEE International Conference on Cluster Computing (CLUSTER), pp. 433\u2013442, September 2016. \nhttps:\/\/doi.org\/10.1109\/CLUSTER.2016.22","DOI":"10.1109\/CLUSTER.2016.22"},{"key":"30_CR10","unstructured":"National Energy Research Scientific Computing Center: Characterization of the DOE Mini-apps. \nhttps:\/\/portal.nersc.gov\/project\/CAL\/designforward.htm\n\n, June 2014"},{"key":"30_CR11","doi-asserted-by":"publisher","unstructured":"Qian, S., Wu, G., Huang, J., Das, T.: Benchmarking modern distributed streaming platforms. In: 2016 IEEE International Conference on Industrial Technology (ICIT), pp. 592\u2013598, March 2016. \nhttps:\/\/doi.org\/10.1109\/ICIT.2016.7474816","DOI":"10.1109\/ICIT.2016.7474816"},{"key":"30_CR12","unstructured":"Salvatore Sanfilippo: Redis (2009). \nhttps:\/\/redis.io\/"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Toor, S., et al.: SNIC Science Cloud (SSC): a national-scale cloud infrastructure for Swedish academia. In: 2017 IEEE 13th International Conference On E-Science (e-Science), pp. 219\u2013227. IEEE (2017)","DOI":"10.1109\/eScience.2017.35"},{"key":"30_CR14","doi-asserted-by":"publisher","unstructured":"Torruangwatthana, P., Wieslander, H., Blamey, B., Hellander, A., Toor, S.: HarmonicIO: scalable data stream processing for scientific datasets. In: 2018 IEEE 11th International Conference on Cloud Computing (CLOUD), pp. 879\u2013882, July 2018. \nhttps:\/\/doi.org\/10.1109\/CLOUD.2018.00126","DOI":"10.1109\/CLOUD.2018.00126"},{"issue":"21","key":"30_CR15","doi-asserted-by":"publisher","first-page":"3715","DOI":"10.1242\/jcs.013623","volume":"120","author":"R Wollman","year":"2007","unstructured":"Wollman, R., Stuurman, N.: High throughput microscopy: from raw images to discoveries. J. Cell Sci. 120(21), 3715\u20133722 (2007). \nhttps:\/\/doi.org\/10.1242\/jcs.013623","journal-title":"J. Cell Sci."},{"key":"30_CR16","unstructured":"Xin, R.: Apache Spark the fastest open source engine for sorting a petabyte, October 2014. \nhttps:\/\/databricks.com\/blog\/2014\/10\/10\/spark-petabyte-sort.html"},{"key":"30_CR17","unstructured":"Zaharia, M., et al.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, pp. 2\u20132. NSDI 2012, USENIX Association, San Jose (2012)"},{"issue":"11","key":"30_CR18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia, M., et al.: Apache spark: a unified engine for big data processing. Commun. ACM 59(11), 56\u201365 (2016). \nhttps:\/\/doi.org\/10.1145\/2934664","journal-title":"Commun. ACM"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-49556-5_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T23:09:33Z","timestamp":1591657773000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-49556-5_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030495558","9783030495565"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-49556-5_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denver, CO","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.benchcouncil.org\/bench19\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}