Scaling Multicore Databases via Constrained Parallel Execution

Wang, Zhaoguo; Mu, Shuai; Cui, Yang; Han, Yuan; Chen, Haibo; Li, Jinyang

doi:10.1145/2882903.2882934

Cited by 52 publications

(43 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While pre-execution tries to identify records read and written by transactions without any application semantics, recent work has also shown the benefit of using application semantics explicitly to modify transaction run time with the goal of minimizing, or even avoiding, conflicting operations [3,30,38,44,46]. Given that all CC protocols suffer under highconflict workloads, such techniques, if applicable, will definitely assist in improving the scalability of all architectures.…”

Section: Implications Of Our Analysismentioning

confidence: 99%

Analyzing the impact of system architecture on the scalability of OLTP engines for high-contention workloads

et al. 2017

View full text Add to dashboard Cite

Main-memory OLTP engines are being increasingly deployed on multicore servers that provide abundant thread-level parallelism. However, recent research has shown that even the state-of-the-art OLTP engines are unable to exploit available parallelism for high contention workloads. While previous studies have shown the lack of scalability of all popular concurrency control protocols, they consider only one system architecture-a non-partitioned, shared everything one where transactions can be scheduled to run on any core and can access any data or metadata stored in shared memory.In this paper, we perform a thorough analysis of the impact of other architectural alternatives (Data-oriented transaction execution, Partitioned Serial Execution, and Delegation) on scalability under high contention scenarios. In doing so, we present Trireme, a main-memory OLTP engine testbed that implements four system architectures and several popular concurrency control protocols in a single code base. Using Trireme, we present an extensive experimental study to understand i) the impact of each system architecture on overall scalability, ii) the interaction between system architecture and concurrency control protocols, and iii) the pros and cons of new architectures that have been proposed recently to explicitly deal with high-contention workloads.

show abstract

Section: Implications Of Our Analysismentioning

confidence: 99%

Analyzing the impact of system architecture on the scalability of OLTP engines for high-contention workloads

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Two mechanisms are enforced to ensure the serializability. First, because uncommitted data is read, a commit discipline is enforced such that (1) if transaction T operates on uncommitted data from T 0 and T 0 has not committed, T should not commit; and (2) if T 0 aborts, T should also abort [16,36]. Second, dependencies that arise as transactions make conflicting data accesses should be tracked and these dependencies should be enforced by constraining a transaction's subsequent data access.…”

Section: Transaction Pipelinementioning

confidence: 99%

“…In this way, they are able to chop transactions into pieces such that once each piece of transaction code begins to execute, it will not need to delay until the completion of the whole transaction. In the original transaction pipeline approach named IC3 [36], whether two pieces conflict depends on whether they access the same table and one of them contains write. Fine-grained variants are further proposed by regarding two pieces as conflicting pieces if they perform conflicting accesses at runtime [13,16,41].…”

Section: Related Workmentioning

confidence: 99%

“…Transaction pipeline, the state-of-the-art CC mechanism, takes advantage over prior CC mechanisms, including twophase locking (2PL), optimistic concurrency control (OCC) and multi-version concurrency control (MVCC), by allowing more parallel execution among conflicting operations [16,36]. However, it suffers from long-time delays confronted with high-frequency trading (HFT) applications.…”

Section: Introductionmentioning

confidence: 99%

“…Because delay is mainly caused by conflicting operations, much work focuses on extracting more fine-grained contention information from transaction semantics to benefit transaction pipeline [13,36,41,42]. However, finegrained contention information reduces false contention, while Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reordering Transaction Execution to Boost High-Frequency Trading Applications

Zhou

Zhang

et al. 2017

Data Sci. Eng.

View full text Add to dashboard Cite

High-frequency trading (HFT) has always been welcomed because it benefits not only personal benefits but also the whole social welfare. While the recent advance of portfolio selection in HFT market enables to bring about more profit, it yields much contended OLTP workloads. Featuring exploiting the abundant parallelism, transaction pipeline, the state-of-the-art concurrency control (CC) mechanism, however, suffers from limited concurrency confronted with HFT workloads. Its variants that enable more parallel execution by leveraging fine-grained contention information also take little effect. To solve this problem, we for the first time observe and formulate the source of restricted concurrency as harmful ordering of transaction statements. To resolve harmful ordering, we propose PARE, a pipeline-aware reordered execution, to improve application performance by rearranging statements in order of their degrees of contention. In concrete, two mechanisms are devised to ensure the correctness of statement rearrangement and identify the degrees of contention of statements, respectively. We also study the off-line reordering problem. We prove that this problem is NP-hard and present an off-line reordering approach to approximate the optimal reordering strategy. Experiment results show that PARE can improve transaction throughput and reduce transaction latency on HFT applications by up to an order of magnitude than the state-of-the-art CC mechanism.

show abstract