RCBench: an RDMA-enabled transaction framework for analyzing concurrency control algorithms
Authors: 
Hongyao Zhao, Jingyao Li, Wei Lu, Qian Zhang, Wanqing Yang, Jiajia Zhong, Meihui Zhang, Haixiang Li, Xiaoyong Du, Anqun PanAuthors Info & Claims
Abstract
Distributed transaction processing over the TCP/IP network suffers from the weak transaction scalability problem, i.e., its performance drops significantly when the number of involved data nodes per transaction increases. Although quite a few of works over the high-performance RDMA-capable network are proposed, they mainly focus on accelerating distributed transaction processing, rather than solving the weak transaction scalability problem. In this paper, we propose RCBench, an RDMA-enabled transaction framework, which serves as a unified evaluation tool for assessing the transaction scalability of various concurrency control algorithms. The usability and advancement of RCBench primarily come from the proposed concurrency control primitives, which facilitate the convenient implementation of RDMA-enabled concurrency control algorithms. Various optimization principles are proposed to ensure that concurrency control algorithms in RCBench can fully benefit from the advantages offered by RDMA-capable networks. We conduct extensive experiments to evaluate the scalability of mainstream concurrency control algorithms. The results show that by exploiting the capabilities of RDMA, concurrency control algorithms in RCBench can obtain 42X performance improvement, and transaction scalability can be achieved in RCBench.
References
[1]
Abebe, M., Glasbergen, B., Daudjee, K.: Dynamast: adaptive dynamic mastering for replicated systems. In: 36th IEEE international conference on data engineering, ICDE 2020, Dallas, TX, USA, April 20–24, 2020, pp. 1381–1392. IEEE (2020).
[2]
Abebe, M., Glasbergen, B., Daudjee, K.: Morphosys: automatic physical design metamorphosis for distributed database systems. Proc. VLDB Endow. 13(13):3573-3587 (2020).
[3]
Agrawal R, Carey MJ, and Livny M Concurrency control performance modeling: alternatives and implications ACM Trans. Database Syst. 1987 12 4 609-654
[4]
Agrawal, S., Narasayya, V.R., Yang, B.: Integrating vertical and horizontal partitioning into automated physical database design. In: SIGMOD Conference, pp. 359–370. ACM (2004)
[5]
Barthels C, Müller I, Taranov K, Alonso G, and Hoefler T Strong consistency is not hard to get: two-phase locking and two-phase commit on thousands of cores Proc. VLDB Endow. 2019 12 13 2325-2338
[6]
Bernstein, P.A., Goodman, N.: Timestamp-based algorithms for concurrency control in distributed database systems. In: VLDB, pp. 285–300. IEEE Computer Society (1980)
[7]
Bernstein PA and Goodman N Concurrency control in distributed database systems ACM Comput. Surv. 1981 13 2 185-221
[8]
Bhide, A., Stonebraker, M.: A performance comparison of two architectures for fast transaction processing. In: International Conference on Data Engineering (1988)
[9]
Binnig C, Crotty A, Galakatos A, Kraska T, and Zamanian E The end of slow networks: it’s time for a redesign Proc. VLDB Endow. 2016 9 7 528-539
[10]
Carey, M.J.: An abstract model of database concurrency control algorithms. In: SIGMOD Conference, pp. 97–107. ACM Press (1983)
[11]
Carey, M.J., Livny, M.: Distributed concurrency control performance: a study of algorithms, distribution, and replication. In: 14th International Conference on Very Large Data Bases (1988)
[12]
Carey, M.J., Livny, M.: Parallelism and concurrency control performance in distributed database machines. In: SIGMOD Conference, pp. 122–133. ACM Press (1989)
[13]
Carey MJ and Muhanna WA The performance of multiversion concurrency control algorithms ACM Trans. Comput. Syst. 1986 4 4 338-378
[14]
Chen, Y., Wei, X., Shi, J., Chen, R., Chen, H.: Fast and general distributed transactions using RDMA and HTM. In: EuroSys, pp. 26:1–26:17. ACM (2016)
[15]
Cooper, B.F., Silberstein, A., Tam, E., Ramakrishnan, R., Sears, R.: Benchmarking cloud serving systems with YCSB. In: SoCC, pp. 143–154. ACM (2010)
[16]
Curino C, Zhang Y, Jones EPC, and Madden S Schism: a workload-driven approach to database replication and partitioning Proc. VLDB Endow. 2010 3 1 48-57
[17]
Das S, Nishimura S, Agrawal D, and Abbadi AE Albatross: lightweight elasticity in shared storage databases for the cloud using live data migration Proc. VLDB Endow. 2011 4 8 494-505
[18]
Dashti, M., John, S.B., Shaikhha, A., Koch, C.: Transaction repair for multi-version concurrency control. In: SIGMOD Conference, pp. 235–250. ACM (2017)
[19]
Dragojevic, A., Narayanan, D., Castro, M., Hodson, O.: Farm: fast remote memory. In: NSDI, pp. 401–414. USENIX Association (2014)
[20]
Dragojevic, A., Narayanan, D., Nightingale, E.B., Renzelmann, M., Shamis, A., Badam, A., Castro, M.: No compromises: distributed transactions with consistency, availability, and performance. In: SOSP, pp. 54–70. ACM (2015)
[21]
Elmore, A.J., Arora, V., Taft, R., Pavlo, A., Agrawal, D., Abbadi, A.E.: Squall: Fine-grained live reconfiguration for partitioned main memory databases. In: SIGMOD Conference, pp. 299–313. ACM (2015)
[22]
Elmore, A.J., Das, S., Agrawal, D., Abbadi, A.E.: Zephyr: live migration in shared nothing databases for elastic cloud platforms. In: SIGMOD Conference, pp. 301–312. ACM (2011)
[23]
Elmore, A.J., Das, S., Agrawal, D., El Abbadi, A.: Towards an elastic and autonomic multitenant database. In: Proc. of NetDB Workshop. sn (2011)
[24]
Faleiro JM and Abadi DJ Rethinking serializable multiversion concurrency control Proc. VLDB Endow. 2015 8 11 1190-1201
[25]
Faleiro, J.M., Abadi, D.J., Hellerstein, J.M.: High performance transactions via early write visibility. Proc. VLDB Endow. 10(5), 613–624 (2017). https://doi.org/10.14778/3055540.3055553
[26]
Faleiro, J.M., Thomson, A., Abadi, D.J.: Lazy evaluation of transactions in database systems. In: Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, SIGMOD ’14, p. 15-26. Association for Computing Machinery, New York (2014).
[27]
Gray, J., Lorie, R.A., Putzolu, G.R., Traiger, I.L.: Granularity of locks and degrees of consistency in a shared data base. In: Readings in database systems (3rd ed.) (1976)
[28]
Härder T Observations on optimistic concurrency control schemes Inf. Syst. 1984 9 2 111-120
[29]
Harding R, Aken DV, Pavlo A, and Stonebraker M An evaluation of distributed concurrency control PVLDB 2017 10 5 553-564
[30]
Higuchi, K., Tsuji, T.: A linear hashing enabling efficient retrieval for range queries. In: 2009 IEEE International Conference on Systems, Man and Cybernetics, pp. 4557–4562 (2009).
[31]
Huang, J., Stankovic, J.A., Ramamritham, K., Towsley, D.F.: Experimental evaluation of real-time optimistic concurrency control schemes. In: VLDB, pp. 35–46. Morgan Kaufmann (1991)
[32]
Huang Y, Qian W, Kohler E, Liskov B, and Shrira L Opportunities for optimism in contended main-memory multicore transactions Proc. VLDB Endow. 2020 13 5 629-642
[33]
Jipping, M.J., Ford, R.: Predicting performance of concurrency control designs. In: SIGMETRICS, pp. 132–142. ACM (1987)
[34]
Jones, E.P.C.: Fault-tolerant distributed transactions for partitioned OLTP databases. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA, USA (2012)
[35]
Lim, H., Kaminsky, M., Andersen, D.G.: Cicada: dependably fast multi-core in-memory transactions. In: SIGMOD Conference, pp. 21–35. ACM (2017)
[36]
Lin, Y.S., Tsai, C., Lin, T.Y., Chang, Y.S., Wu, S.H.: Don’t look back, look into the future: prescient data partitioning and migration for deterministic database systems. In: Proceedings of the 2021 International Conference on Management of Data, SIGMOD’21, pp. 1156–1168. Association for Computing Machinery, New York (2021).
[37]
Lu, Y., Yu, X., Cao, L., Madden, S.: Aria: A fast and practical deterministic oltp database. Proc. VLDB Endow. 13(12), 2047-2060 (2020).
[38]
Mitchell, C., Geng, Y., Li, J.: Using one-sided RDMA reads to build a fast, cpu-efficient key-value store. In: USENIX Annual Technical Conference, pp. 103–114. USENIX Association (2013)
[39]
Pavlo, A., Curino, C., Zdonik, S.B.: Skew-aware automatic database partitioning in shared-nothing, parallel OLTP systems. In: SIGMOD Conference, pp. 61–72. ACM (2012)
[40]
Peng, D., Dabek, F.: Large-scale incremental processing using distributed transactions and notifications. In: OSDI, pp. 251–264. USENIX Association (2010)
[41]
Qadah, T., Gupta, S., Sadoghi, M.: Q-store: Distributed, multi-partition transactions via queue-oriented execution and communication. In: EDBT, pp. 73–84. OpenProceedings.org (2020)
[42]
Qadah, T.M., Sadoghi, M.: Quecc: a queue-oriented, control-free concurrency architecture. In: Middleware, pp. 13–25. ACM (2018)
[43]
Qin, D., Brown, A.D., Goel, A.: Caracal: contention management with deterministic concurrency control. In: Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles, SOSP’21, pp. 180–194. Association for Computing Machinery, New York (2021).
[44]
Quamar, A., Kumar, K.A., Deshpande, A.: SWORD: scalable workload-aware data placement for transactional workloads. In: EDBT, pp. 430–441. ACM (2013)
[45]
Rosenkrantz, D.J., Stearns, R.E., II, P.M.L.: System level concurrency control for distributed database systems. ACM Trans. Database Syst. 3(2), 178–198 (1978)
[46]
Schiller, O., Cipriani, N., Mitschang, B.: Prorea: live database migration for multi-tenant RDBMS with snapshot isolation. In: EDBT, pp. 53–64. ACM (2013)
[47]
Serafini, M., Taft, R., Elmore, A.J., Pavlo, A., Aboulnaga, A., Stonebraker, M.: Clay: Fine-grained adaptive partitioning for general database schemas. Proc. VLDB Endow. 10(4), 445-456 (2016).
[48]
Shute J, Vingralek R, Samwel B, Handy B, Whipkey C, Rollins E, Oancea M, Littlefield K, Menestrina D, Ellner S, Cieslewicz J, Rae I, Stancescu T, and Apte H F1: a distributed SQL database that scales Proc. VLDB Endow. 2013 6 11 1068-1079
[49]
Stamos, J., Cristian, F.: A low-cost atomic commit protocol. In: Proceedings 9th Symposium on Reliable Distributed Systems, pp. 66–75 (1990).
[50]
Taft, R., Mansour, E., Serafini, M., Duggan, J., Elmore, A.J., Aboulnaga, A., Pavlo, A., Stonebraker, M.: E-store: Fine-grained elastic partitioning for distributed transaction processing systems. Proc. VLDB Endow. 8(3), 245-256 (2014).
[51]
Tanabe T, Hoshino T, Kawashima H, and Tatebe O An analysis of concurrency control protocols for in-memory databases with ccbench Proc. VLDB Endow. 2020 13 3531-3544
[52]
Thomasian A Concurrency control: methods, performance, and analysis ACM Comput. Surv. 1998 30 1 70-119
[53]
Thomson, A., Diamond, T., Weng, S., Ren, K., Shao, P., Abadi, D.J.: Calvin: fast distributed transactions for partitioned database systems. In: SIGMOD Conference, pp. 1–12. ACM (2012)
[54]
Thuraisingham B and Ko H Concurrency control in trusted database management systems: a survey SIGMOD Rec. 1993 22 4 52-59
[55]
TPC-C: http://www.tpc.org/tpcc/ (1988)
[56]
Tran, K.Q., Naughton, J.F., Sundarmurthy, B., Tsirogiannis, D.: Jecb: a join-extension, code-based approach to oltp data partitioning. In: Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, SIGMOD’14, pp. 39–50. Association for Computing Machinery, New York (2014).
[57]
Tu, S., Zheng, W., Kohler, E., Liskov, B., Madden, S.: Speedy transactions in multicore in-memory databases. In: SOSP, pp. 18–32. ACM (2013)
[58]
Wang, C., Qian, X.: Rdma-enabled concurrency control protocols for transactions in the cloud era. IEEE Trans. Cloud Comput. PP, 1–1 (2021)
[59]
Wang T and Kimura H Mostly-optimistic concurrency control for highly contended dynamic workloads on a thousand cores Proc. VLDB Endow. 2016 10 2 49-60
[60]
Wei, X., Dong, Z., Chen, R., Chen, H.: Deconstructing rdma-enabled distributed transactions: hybrid is better! In: OSDI, pp. 233–251. USENIX Association (2018)
[61]
Wei, X., Shi, J., Chen, Y., Chen, R., Chen, H.: Fast in-memory transaction processing using RDMA and HTM. In: SOSP, pp. 87–104. ACM (2015)
[62]
Wu Y, Arulraj J, Lin J, Xian R, and Pavlo A An empirical evaluation of in-memory multi-version concurrency control Proc. VLDB Endow. 2017 10 7 781-792
[63]
Yao C, Agrawal D, Chen G, Lin Q, Ooi BC, Wong W, and Zhang M Exploiting single-threaded model in multi-core in-memory systems IEEE Trans. Knowl. Data Eng. 2016 28 10 2635-2650
[64]
Yoon, D.Y., Chowdhury, M., Mozafari, B.: Distributed lock management with RDMA: decentralization without starvation. In: SIGMOD Conference, pp. 1571–1586. ACM (2018)
[65]
Yu, X., Bezerra, G., Pavlo, A., Devadas, S., Stonebraker, M.: Staring into the abyss: an evaluation of concurrency control with one thousand cores. Proc. VLDB Endow. 8(3) (2014)
[66]
Zamanian, E., Binnig, C., Harris, T., Kraska, T.: The end of a myth: Distributed transactions can scale. Proc. VLDB Endow. 10(6), 685-696 (2017).
[67]
Zamanian, E., Binnig, C., Salama, A.: Locality-aware partitioning in parallel database systems. In: SIGMOD Conference, pp. 17–30. ACM (2015)
[68]
Zhao, Z.: Efficiently supporting adaptive multi-level serializability models in distributed database systems. In: SIGMOD Conference, pp. 2908–2910. ACM (2021)
Index Terms
- RCBench: an RDMA-enabled transaction framework for analyzing concurrency control algorithms
Index terms have been assigned to the content through auto-classification.
Recommendations
Semantics-based concurrency control: beyond commutativity
The concurrency of transactions executing on atomic data types can be enhanced through the use of semantic information about operations defined on these types. Hitherto, commutativity of operations has been exploited to provide enchanced concurrency ...
Multiversion Cautious Schedulers for Database Concurrency Control
Let MC stand for a class of logs (i.e. sequences of read/write steps of transactions) that are serializable when multiple versions of the data items are maintained. The multiversion cautious scheduler, MCS(MC) which is introduced, outputs a sequence ...
Scythe: A Low-latency RDMA-enabled Distributed Transaction System for Disaggregated Memory
Disaggregated memory separates compute and memory resources into independent pools connected by RDMA (Remote Direct Memory Access) networks, which can improve memory utilization, reduce cost, and enable elastic scaling of compute and memory resources. ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 14 December 2023
Accepted: 20 October 2023
Revision received: 30 April 2023
Received: 21 October 2022
Author Tags
Qualifiers
- Research-article
Funding Sources
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 18 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in