Distributed snapshot isolation: global transactions pay globally, local transactions pay locally

Binnig, Carsten; Hildenbrand, Stefan; Färber, Franz; Kossmann, Donald; Lee, Juchang; May, Norman

doi:10.1007/s00778-014-0359-9

Cited by 26 publications

(32 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By maintaining multiple data versions, TxCache [49] ensures that a transaction always reads from a consistent snapshot regardless of whether each read operation comes from the database or the cache. Binning et al [7] show how only distributed snapshot transactions pay the cost of coordination. Serial Safety Net (SSN) [65] is able to make any concurrency control protocol to support serializability by detecting dependency cycles.…”

Section: Related Workmentioning

confidence: 99%

Epoch-based commit and replication in distributed OLTP databases

Cao

et al. 2021

Proc. VLDB Endow.

View full text Add to dashboard Cite

Many modern data-oriented applications are built on top of distributed OLTP databases for both scalability and high availability. Such distributed databases enforce atomicity, durability, and consistency through two-phase commit (2PC) and synchronous replication at the granularity of every single transaction. In this paper, we present COCO, a new distributed OLTP database that supports epoch-based commit and replication. The key idea behind COCO is that it separates transactions into epochs and treats a whole epoch of transactions as the commit unit. In this way, the overhead of 2PC and synchronous replication is significantly reduced. We support two variants of optimistic concurrency control (OCC) using physical time and logical time with various optimizations, which are enabled by the epoch-based execution. Our evaluation on two popular benchmarks (YCSB and TPC-C) show that COCO outperforms systems with fine-grained 2PC and synchronous replication by up to a factor of four.

show abstract

Section: Related Workmentioning

confidence: 99%

Epoch-based commit and replication in distributed OLTP databases

Cao

et al. 2021

Proc. VLDB Endow.

View full text Add to dashboard Cite

show abstract

“…These data anomalies were reported in the 1990s and before. In recent years, there still exist extensive research works that focus on reporting new data anomalies, including Aborted Reads [42], Intermediate Read [2,42], Read-only Transaction Anomaly [25,40], Serial-concurrency-phenomenon and Cross-phenomenon [12]. [16] reports Long Fork, Fractured Reads, and Causality Violation.…”

Section: Related Workmentioning

confidence: 99%

“…Dirty Write and Dirty Read are able to be categorised as single-variable data anomalies based on our framework. Read Skew, Write Skew, together with our proposed Read-Write Skew, Write-Read Skew and Double-Write Skew, are originally proposed in [2,6] between two transactions, and are extended to three or more transactions in [4,12,16,24,25,34].…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, the definitions are made in a case-by-case manner, and lead to a situation that even a senior DBA could not have infallible knowledge of data anomalies, due to a lack of a full understanding of its nature. Except the four data anomalies defined in the ANSI standard, typical data anomalies including Read skew [6], Write Skew [6], Fractured Reads [16], Cross-phenomenon [12], etc. A thorough study on state-of-the-art data anomalies will be conducted in Section 2.…”

Section: Introductionmentioning

confidence: 99%

“…[26] defines some other data anomalies such as Predicate-based Write Skew. In recent years, there still exist extensive research works that focus on reporting new data anomalies, including Intermediate Read [2,42], Serial-concurrency-phenomenon and Cross-phenomenon [12], Long Fork anomaly and Causality Violation anomaly [16]. This let us think how many data anomalies there are?…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Coo: Rethink Data Anomalies In Databases

Li¹,

Li²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Transaction processing technology has three important contents: data anomalies, isolation levels and concurrent control algorithms. Concurrent control algorithms is used to eliminate some or all data anomalies at different isolation levels to ensure data consistency. Isolation levels in the current ANSI standard are defined by disallowing certain kinds of data anomalies. Yet, the definitions of data anomalies in the ANSI standard are controversial. On one hand, the definitions lack a mathematical formalization, and cause ambiguous interpretations. On the other hand, the definitions are made in a case-by-case manner, and lead to a situation that even a senior DBA could not have infallible knowledge of data anomalies, due to a lack of a full understanding of its nature. While revised definitions in exiting literature propose various mathematical formalizations to correct the former argument, how to address the latter argument still remains an open problem. In this paper, we present a general framework called Coo with the capability to systematically define data anomalies. Under this framework, we show that existing reported data anomalies is only a small portion. While we theoretically prove that Coo is complete to mathematically formalize data anomalies, we employ a novel method to classify infinite data anomalies. In addition, we use this framework to define a new isolation levels and quantitatively describe the concurrency and rollback rate of mainstream concurrency control algorithms. These works show that the C and I of ACID can be quantitatively analyzed based on all data anomalies.

show abstract

Big Data Processing

Özsu

Valduriez

2019

Principles of Distributed Database Systems

View full text Add to dashboard Cite

Distributed snapshot isolation: global transactions pay globally, local transactions pay locally

Cited by 26 publications

References 24 publications

Epoch-based commit and replication in distributed OLTP databases

Epoch-based commit and replication in distributed OLTP databases

Coo: Rethink Data Anomalies In Databases

Big Data Processing

Contact Info

Product

Resources

About