{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:17:17Z","timestamp":1782407837232,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2023JJ40555"],"award-info":[{"award-number":["2023JJ40555"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014472","name":"Scientific Research Foundation of Hunan Provincial Education Department","doi-asserted-by":"crossref","award":["22B0451"],"award-info":[{"award-number":["22B0451"]}],"id":[{"id":"10.13039\/100014472","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2021YFB0301200"],"award-info":[{"award-number":["2021YFB0301200"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s42514-025-00225-2","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T13:00:50Z","timestamp":1744981250000},"page":"465-477","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimization of fault tolerance for iterative graph algorithm in spark GraphX based on high performance computing cluster"],"prefix":"10.1007","volume":"7","author":[{"given":"Mengsi","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3041-6990","authenticated-orcid":false,"given":"Zhongming","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"key":"225_CR1","doi-asserted-by":"publisher","unstructured":"Ali, A.A., Logofatu, D.: An analysis on graph-processing frameworks: Neo4j and spark graphx. In: Maglogiannis I, Iliadis L, Macintyre J, et\u00a0al (eds) Artificial Intelligence Applications and Innovations. Springer International Publishing, Cham, pp 461\u2013470, (2022) https:\/\/doi.org\/10.1007\/978-3-031-08333-4_37","DOI":"10.1007\/978-3-031-08333-4_37"},{"key":"225_CR2","doi-asserted-by":"publisher","unstructured":"Alves, T.A.O.: Distributed checkpointing in dataflow with static scheduling. In: 2023 International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW), pp 77\u201382, (2023) https:\/\/doi.org\/10.1109\/SBAC-PADW60351.2023.00021","DOI":"10.1109\/SBAC-PADW60351.2023.00021"},{"key":"225_CR3","unstructured":"Apache Hadoop (2024). http:\/\/hadoop.apache.org\/"},{"key":"225_CR4","unstructured":"Apache Spark (2024). http:\/\/spark.apache.org\/"},{"key":"225_CR5","doi-asserted-by":"publisher","unstructured":"Benoit, A., Perotin, L., Robert, Y., et\u00a0al.: Checkpointing strategies to tolerate non-memoryless failures on hpc platforms. ACM Trans Parallel Comput 11(1). (2024) https:\/\/doi.org\/10.1145\/3624560","DOI":"10.1145\/3624560"},{"issue":"1","key":"225_CR6","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1109\/TCC.2021.3108043","volume":"11","author":"D Cheng","year":"2023","unstructured":"Cheng, D., Wang, Y., Dai, D.: Dynamic resource provisioning for iterative workloads on apache. IEEE Trans. Cloud Comput. 11(1), 639\u2013652 (2023). https:\/\/doi.org\/10.1109\/TCC.2021.3108043","journal-title":"IEEE Trans. Cloud Comput."},{"key":"225_CR7","doi-asserted-by":"publisher","unstructured":"Czumaj, A., Mishra, G., Mukherjee, A.: Streaming graph algorithms in the massively parallel computation model. In: Proceedings of the 43rd ACM Symposium on Principles of Distributed Computing. Association for Computing Machinery, New York, NY, USA, PODC \u201924, p 496\u2013507, (2024) https:\/\/doi.org\/10.1145\/3662158.3662770","DOI":"10.1145\/3662158.3662770"},{"issue":"3","key":"225_CR8","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1109\/TPDS.2021.3099440","volume":"33","author":"Y Du","year":"2022","unstructured":"Du, Y., Marchal, L., Pallez, G., et al.: Optimal checkpointing strategies for iterative applications. IEEE Trans. Parallel Distrib. Syst. 33(3), 507\u2013522 (2022). https:\/\/doi.org\/10.1109\/TPDS.2021.3099440","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"10","key":"225_CR9","doi-asserted-by":"publisher","first-page":"2406","DOI":"10.1109\/TPDS.2020.2992073","volume":"31","author":"Z Fu","year":"2020","unstructured":"Fu, Z., Tang, Z., Yang, L., et al.: An optimal locality-aware task scheduling algorithm based on bipartite graph modelling for spark applications. IEEE Trans. Parallel Distrib. Syst. 31(10), 2406\u20132420 (2020). https:\/\/doi.org\/10.1109\/TPDS.2020.2992073","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"13","key":"225_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.8081","volume":"36","author":"M Kirti","year":"2024","unstructured":"Kirti, M., Maurya, A.K., Yadav, R.S.: Fault-tolerance approaches for distributed and cloud computing environments: A systematic review, taxonomy and future directions. Concurrency and Computation: Practice and Experience 36(13), e8081 (2024). https:\/\/doi.org\/10.1002\/cpe.8081","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"225_CR11","doi-asserted-by":"publisher","unstructured":"Kweun, M., Lee, W.Y., Kim, G., et\u00a0al.: Lineage checkpoint approach for long-lineage problem in apache spark. In: 2020 IEEE International Conference on Big Data (Big Data), pp 5733\u20135735, (2020) https:\/\/doi.org\/10.1109\/BigData50022.2020.9377896","DOI":"10.1109\/BigData50022.2020.9377896"},{"key":"225_CR12","unstructured":"Leskovec, J., Krevl, A.: SNAP Datasets: Stanford large network dataset collection. http:\/\/snap.stanford.edu\/data (2014)"},{"key":"225_CR13","doi-asserted-by":"publisher","unstructured":"Li, H., Ji, S., Zhong, H., et\u00a0al.: LPW: an efficient data-aware cache replacement strategy for apache spark. Sci China Inf Sci 66(1). (2023) https:\/\/doi.org\/10.1007\/S11432-021-3406-5","DOI":"10.1007\/S11432-021-3406-5"},{"key":"225_CR14","doi-asserted-by":"publisher","unstructured":"Li, X., Li, H., Lu, Y., et al.: Replica-aware data recovery performance improvement for hadoop system with nvm. CCF Trans. High Perform. Comput. 3, 144\u2013156 (2021). https:\/\/doi.org\/10.1007\/s42514-021-00066-9","DOI":"10.1007\/s42514-021-00066-9"},{"issue":"3","key":"225_CR15","doi-asserted-by":"publisher","first-page":"3561","DOI":"10.1007\/S11227-021-04000-2","volume":"78","author":"C Li","year":"2022","unstructured":"Li, C., Cai, Q., Luo, Y.: Data balancing-based intermediate data partitioning and check point-based cache recovery in spark environment. J Supercomput 78(3), 3561\u20133604 (2022). https:\/\/doi.org\/10.1007\/S11227-021-04000-2","journal-title":"J Supercomput"},{"key":"225_CR16","doi-asserted-by":"publisher","unstructured":"Mior, M.J., Salem, K.: Respark: Automatic caching for iterative applications in apache spark. In: 2020 IEEE International Conference on Big Data (Big Data), pp 331\u2013340, (2020) https:\/\/doi.org\/10.1109\/BigData50022.2020.9377866","DOI":"10.1109\/BigData50022.2020.9377866"},{"key":"225_CR17","doi-asserted-by":"publisher","unstructured":"Mohmmed, T., Abdalrahman, N.: A load balancing with fault tolerance algorithm for cloud computing. In: 2020 International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), pp 1\u20136, (2021) https:\/\/doi.org\/10.1109\/ICCCEEE49695.2021.9429597","DOI":"10.1109\/ICCCEEE49695.2021.9429597"},{"key":"225_CR18","doi-asserted-by":"publisher","unstructured":"Phani, A., Rath, B., Boehm, M.: Lima: Fine-grained lineage tracing and reuse in machine learning systems. In: Proceedings of the 2021 International Conference on Management of Data. Association for Computing Machinery, New York, NY, USA, SIGMOD \u201921, p 1426\u20131439, (2021) https:\/\/doi.org\/10.1145\/3448016.3452788","DOI":"10.1145\/3448016.3452788"},{"key":"225_CR19","unstructured":"Reuter, A., Schwenkreis, F.: Contracts - a low-level mechanism for building general-purpose workflow management-systems. In: IEEE Data Engineering Bulletin, (1999) http:\/\/dx.doi.org\/"},{"key":"225_CR20","doi-asserted-by":"publisher","unstructured":"Scherbaum, J., Novotny, M., Vayda, O.: Spline: Spark lineage, not only for the banking industry. In: 2018 IEEE International Conference on Big Data and Smart Computing (BigComp), pp 495\u2013498, (2018) https:\/\/doi.org\/10.1109\/BigComp.2018.00080","DOI":"10.1109\/BigComp.2018.00080"},{"key":"225_CR21","doi-asserted-by":"publisher","unstructured":"Sewal, P., Singh, H.: Performance comparison of apache spark and hadoop for machine learning based iterative GBTR on HIGGS and covid-19 datasets. Scalable Comput Pract Exp 25(3):1373\u20131386. (2024) https:\/\/doi.org\/10.12694\/SCPE.V25I3.2687","DOI":"10.12694\/SCPE.V25I3.2687"},{"issue":"7","key":"225_CR22","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7610","volume":"35","author":"A Sheeba","year":"2023","unstructured":"Sheeba, A., Uma Maheswari, B.: An efficient fault tolerance scheme based enhanced firefly optimization for virtual machine placement in cloud computing. Concurrency and Computation: Practice and Experience 35(7), e7610 (2023). https:\/\/doi.org\/10.1002\/cpe.7610","journal-title":"Concurrency and Computation: Practice and Experience"},{"issue":"1","key":"225_CR23","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/TKDE.2020.2975652","volume":"34","author":"S Tang","year":"2022","unstructured":"Tang, S., He, B., Yu, C., et al.: A survey on spark ecosystem: Big data processing infrastructure, machine learning, and applications. IEEE Trans. Knowl. Data Eng. 34(1), 71\u201391 (2022a). https:\/\/doi.org\/10.1109\/TKDE.2020.2975652","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"6","key":"225_CR24","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1109\/TKDE.2020.3014150","volume":"34","author":"Z Tang","year":"2022","unstructured":"Tang, Z., He, M., Fu, Z., et al.: Incgraph: An improved distributed incremental graph computing model and framework based on spark graphx. IEEE Trans. Knowl. Data Eng. 34(6), 2783\u20132797 (2022b). https:\/\/doi.org\/10.1109\/TKDE.2020.3014150","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"225_CR25","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., et\u00a0al.: Apache hadoop yarn: yet another resource negotiator. Proceedings of the 4th annual Symposium on Cloud Computing (2013) https:\/\/api.semanticscholar.org\/CorpusID:11346384","DOI":"10.1145\/2523616.2523633"},{"key":"225_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Aiken, A.: Efficient fault tolerance for pipelined query engines via write-ahead lineage. (2024). arXiv:2403.08062","DOI":"10.1109\/ICDE60146.2024.00040"},{"key":"225_CR27","doi-asserted-by":"publisher","unstructured":"Wang, S., Liagouris, J., Nishihara, R., et\u00a0al.: Lineage stash: fault tolerance off the critical path. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles. Association for Computing Machinery, New York, NY, USA, SOSP \u201919, p 338\u2013352, (2019) https:\/\/doi.org\/10.1145\/3341301.3359653","DOI":"10.1145\/3341301.3359653"},{"key":"225_CR28","doi-asserted-by":"publisher","unstructured":"Xie, Z., Zhang, J., Zhang, Y., et\u00a0al.: An efficient fault tolerance strategy for multi-task mapreduce models using coded distributed computing. In: Tari Z, Li K, Wu H (eds) Algorithms and Architectures for Parallel Processing. Springer Nature Singapore, Singapore, pp 253\u2013271, (2024) https:\/\/doi.org\/10.1007\/978-981-97-0862-8_16","DOI":"10.1007\/978-981-97-0862-8_16"},{"key":"225_CR29","doi-asserted-by":"publisher","unstructured":"Xu, C., Yang, Y., Pan, Q., et\u00a0al.: Acf2: Accelerating checkpoint-free failure recovery for distributed graph processing. In: Li B, Yue L, Tao C, et\u00a0al (eds) Web and Big Data. Springer Nature Switzerland, Cham, pp 45\u201359, (2023) https:\/\/doi.org\/10.1007\/978-3-031-25158-0_5","DOI":"10.1007\/978-3-031-25158-0_5"},{"key":"225_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, L., Wang, Z., Kong, F.: Optimal checkpointing strategy for real-time systems with both logical and timing correctness. ACM Trans Embed Comput Syst 22(4), (2023) https:\/\/doi.org\/10.1145\/3603172","DOI":"10.1145\/3603172"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00225-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-025-00225-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-025-00225-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:54:01Z","timestamp":1761130441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-025-00225-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,18]]},"references-count":30,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["225"],"URL":"https:\/\/doi.org\/10.1007\/s42514-025-00225-2","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,18]]},"assertion":[{"value":"5 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}