Lazy evaluation of transactions in database systems

Faleiro, Jose M.; Thomson, Alexander; Abadi, Daniel J.

doi:10.1145/2588555.2610529

Cited by 44 publications

(25 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence, ORTHRUS does not incur stalls to access data from disk. ORTHRUS therefore creates exactly the same number of threads as physical CPU cores, and pins each thread to a single core, as is done in several other main-memory database systems [12,13,22,32,35,36,39,42,46,50].…”

Section: Architecturementioning

confidence: 99%

Design Principles for Scaling Multi-core OLTP Under High Contention

Ren

Faleiro

Abadi

2016

Proceedings of the 2016 International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

Although significant recent progress has been made in improving the multi-core scalability of high throughput transactional database systems, modern systems still fail to achieve scalable throughput for workloads involving frequent access to highly contended data. Most of this inability to achieve high throughput is explained by the fundamental constraints involved in guaranteeing ACID -the addition of cores results in more concurrent transactions accessing the same contended data for which access must be serialized in order to guarantee isolation. Thus, linear scalability for contended workloads is impossible. However, there exist flaws in many modern architectures that exacerbate their poor scalability, and result in throughput that is much worse than fundamentally required by the workload.In this paper we identify two prevalent design principles that limit the multi-core scalability of many (but not all) transactional database systems on contended workloads: the multi-purpose nature of execution threads in these systems, and the lack of advanced planning of data access. We demonstrate the deleterious results of these design principles by implementing a prototype system, OR-THRUS, that is motivated by the principles of separation of database component functionality and advanced planning of transactions. We find that these two principles alone result in significantly improved scalability on high-contention workloads, and an order of magnitude increase in throughput for a non-trivial subset of these contended workloads.

show abstract

Section: Architecturementioning

confidence: 99%

Design Principles for Scaling Multi-core OLTP Under High Contention

Ren

Faleiro

Abadi

2016

Proceedings of the 2016 International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…Faleiro et al describe a technique for lazily evaluating transactions in the context of deterministic database systems [12]. This lazy database design separates concurrency control from transaction execution -a design element that is shared by BOHM.…”

Section: Multi-versioned Systems Serializable Snapshot Isolation (Ssi)mentioning

confidence: 99%

Rethinking serializable multiversion concurrency control

2015

Self Cite

View full text Add to dashboard Cite

Multi-versioned database systems have the potential to significantly increase the amount of concurrency in transaction processing because they can avoid read-write conflicts. Unfortunately, the increase in concurrency usually comes at the cost of transaction serializability. If a database user requests full serializability, modern multi-versioned systems significantly constrain read-write concurrency among conflicting transactions and employ expensive synchronization patterns in their design. In main-memory multi-core settings, these additional constraints are so burdensome that multiversioned systems are often significantly outperformed by singleversion systems.We propose BOHM, a new concurrency control protocol for mainmemory multi-versioned database systems. BOHM guarantees serializable execution while ensuring that reads never block writes. In addition, BOHM does not require reads to perform any bookkeeping whatsoever, thereby avoiding the overhead of tracking reads via contended writes to shared memory. This leads to excellent scalability and performance in multi-core settings. BOHM has all the above characteristics without performing validation based concurrency control. Instead, it is pessimistic, and is therefore not prone to excessive aborts in the presence of contention. An experimental evaluation shows that BOHM performs well in both high contention and low contention settings, and is able to dramatically outperform state-of-the-art multi-versioned systems despite maintaining the full set of serializability guarantees.

show abstract

“…Finally, there is also work done in using database application semantics to design concurrency control protocol. Faleiro et al [12] show that lazy transaction processing improves cache locality and achieves better load balancing. It uses contention footprint to help decide which query to delay execution and reduce data contention.…”

Section: Related Workmentioning

confidence: 99%

Leveraging lock contention to improve OLTP application performance

Yan

Cheung

2016

Proc. VLDB Endow.

View full text Add to dashboard Cite

Locking is one of the predominant costs in transaction processing. While much work has focused on designing efficient concurrency control mechanisms, not much has been done on understanding how transaction applications issue queries and leveraging application semantics to improve application performance. This paper presents QURO, a query-aware compiler that automatically reorders queries in transaction code to improve performance. Observing that certain queries within a transaction are more contentious than others as they require locking the same tuples as other concurrently executing transactions, QURO automatically changes the application such that contentious queries are issued as late as possible. We have evaluated QURO on various transaction benchmarks, and our results show that QURO-generated implementations can increase transaction throughput by up to 6.53×, while reduce transaction latency by up to 85%.

show abstract

Lazy evaluation of transactions in database systems

Cited by 44 publications

References 22 publications

Design Principles for Scaling Multi-core OLTP Under High Contention

Design Principles for Scaling Multi-core OLTP Under High Contention

Rethinking serializable multiversion concurrency control

Leveraging lock contention to improve OLTP application performance

Contact Info

Product

Resources

About