Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Building consistent transactions with inconsistent replication
Zhang I., Sharma N., Szekeres A., Krishnamurthy A., Ports D. ACM Transactions on Computer Systems35 (4):1-37,2018.Type:Article
Date Reviewed: Aug 18 2020

Large-scale transaction processing systems must balance the need for minimal response times with maintaining the integrity of the data being processed. In theory, transactions are processed sequentially in the order received. Very large systems exceed the capacity of even a supercomputer; therefore, the data processing must be divided among multiple systems. Consider the classic example: an airline reservation system. Multiple agents globally enter hundreds of thousands (or millions) of transactions daily, linking customers to available seats on specific flights. The traditional way to handle such a huge transaction load takes two forms. First, the total database is divided into “shards,” that is, segments that are parts of the whole but can be treated independently. Within each shard there may be replicas, that is, multiple instances of the same data in that shard. The redundancy ensures the integrity of the data. In this complex system there remains the requirement of apparent serial processing, that is, transactions handled in chronological sequence. This implies coordination and synchronization among the replicas in a shard because their data cannot be treated independently. A strict synchronization protocol further implies fairly large overhead as replicas communicate with each other to maintain the integrity of the process.

The paper proposes to reduce processing overhead by means of an “inconsistent” replication protocol that permits replicas to process transactions in different sequences. Maintaining the correct sequence of transaction processing is accomplished by pushing the maintenance of serial integrity up to the transaction processing and application layers. This reduces the replication overhead significantly.

The authors provide a detailed description of the inconsistent replication (IR) protocol and associated transaction processing system, transactional application protocol for inconsistent replication (TAPIR), including handling failures and offering proofs of correctness regarding transaction consistency. They compare the proposed system to multiple existing systems, including experimental results running TAPIR-IR plus two similar systems built using traditional protocols. The experiments involved transaction processing and data replication in the US, Europe, and Asia. The experimental results show increased throughput by up to a factor of three times versus the two conventional systems.

Given the potential performance increase, real-world testing is needed to verify the experimental results. The text is clearly written, supplemented with useful and readable charts. Many comparisons to earlier systems and a large set of references are provided. This paper should be of interest to those who design and implement large-scale transaction processing systems.

Reviewer:  G. R. Mayforth Review #: CR147040 (2102-0036)
Bookmark and Share
 
Distributed Architectures (C.1.4 ... )
 
 
Fault Tolerance (C.4 ... )
 
 
Reliability, Testing, And Fault-Tolerance (B.2.3 )
 
 
Database Management (H.2 )
 
Would you recommend this review?
yes
no
Other reviews under "Distributed Architectures": Date
Distributed and parallel computing
El-Rewini H., Lewis T. (ed), Manning Publications Co., Greenwich, CT, 1998. Type: Book (9780137955923)
Mar 1 1999
In search of clusters (2nd ed.)
Pfister G., Prentice-Hall, Inc., Upper Saddle River, NJ, 1998. Type: Book (9780138997090)
Nov 1 1998
A correctness condition for high-performance multiprocessors
Attiya H., Friedman R. SIAM Journal on Computing 27(6): 1637-1670, 1998. Type: Article
May 1 1999
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy