Filters








29,747 Hits in 4.6 sec

Building consistent transactions with inconsistent replication

Irene Zhang, Naveen Kr. Sharma, Adriana Szekeres, Arvind Krishnamurthy, Dan R. K. Ports
2015 Proceedings of the 25th Symposium on Operating Systems Principles - SOSP '15  
This paper presents TAPIR -the Transaction Application Protocol for Inconsistent Replication -the first transaction protocol to use a replication protocol, inconsistent replication, that provides fault-tolerance  ...  with no consistency.  ...  Inconsistent Replication The main objective of TAPIR is to build a protocol for consistent, linearizable transactions on top of a replication layer with no consistency guarantees.  ... 
doi:10.1145/2815400.2815404 dblp:conf/sosp/ZhangSSKP15 fatcat:3ods4xy7dff77m46exobgtzek4

Cost-Based Data Consistency in a Data-as-a-Service Cloud Environment

Ilir Fetai, Heiko Schuldt
2012 2012 IEEE Fifth International Conference on Cloud Computing  
level with the goal of minimizing the overall costs (consistency and inconsistency costs); third, it provides a protocol that guarantees that anomalies in the transaction mixes supported by C3 are avoided  ...  However, the Cloud is increasingly being promoted as environment for running a wide range of different types of applications on top of replicated data -of which not all will be satisfied with weak consistency  ...  Currently, Cloud data environments are oriented towards scalability by providing replication solutions with weak consistency guarantees.  ... 
doi:10.1109/cloud.2012.38 dblp:conf/IEEEcloud/FetaiS12 fatcat:luufums2ejgd5f2jb2c76sdu2u

Distributed Database Management Systems: Architectural Design Choices for the Cloud [chapter]

Joarder Mohammad Mustafa Kamal, Manzur Murshed
2014 Computer Communications and Networks  
Besides, distributed data replication and rapid partitioning are the two fundamental hammers to nail down these challenges.  ...  While replication ensures database read scalability and georeachability, data partitioning favours database write scalability and system-level load balance.  ...  However, inconsistencies may occur due to 'lost update' from another transaction in progress.  ... 
doi:10.1007/978-3-319-10530-7_2 fatcat:raz6wxqtczbwdcdn4l27mac6y4

Distributing Control Systems Using Active Rules 1

Sten F. Andler, Joakim Eriksson, Mats Lundin
1999 IFAC Proceedings Volumes  
Particular attention is paid to the e ect of reduced consistency, assuming eventual consistency.  ...  Temporal constraints at individual nodes may be met at the expense of temporary inconsistencies in the database.  ...  The second level, with eventual consistency, is less costly when no inconsistencies occur; it has almost the same delays as when no consistency is guaranteed at all the third level.  ... 
doi:10.1016/s1474-6670(17)39970-6 fatcat:qo2drai5ybdsrpdccu2xjdcu74

A Token-Based Synchronization Scheme using Epsilon-Serializability and Its Performance for Real-Time Distributed Database Systems

Sang H. Son, Spiros Kouloumbis
1993 Database Systems for Advanced Applications '93  
Schedulers for real-time distributed replicated databases must satisfy timing constraints of transactions and preserve data consistency.  ...  The algorithm adopts a token-based scheme for replication control and attempts to incorporate the urgency of real-time transactions into the conflict resolution policies.  ...  On the other hand, asynchronous replication control methods that would allow more transactions to meet their deadlines suffer from a basic problem: the system enters an inconsistent state in which replicated  ... 
doi:10.1142/9789814503730_0027 fatcat:zlqzlvhtffhvrbgxcdzbohxg64

Isolation-only transactions for mobile computing

Qi Lu, M. Satyanaranyanan
1994 ACM SIGOPS Operating Systems Review  
How can we preserve upward compatibility with the large body of existing Unix software, while offering improved consistency in a mobile computing environment?  ...  This position paper puts forth our solution, a new transaction model called isolation only transaction (IOT).  ...  Building upon well-known ideas in the database community, we are extending the Coda file system with an explicit isolation-only transaction service.  ... 
doi:10.1145/198153.198164 fatcat:kebha3tq4jaatfz2qhfbn7nbkq

Scalable consistency in Scatter

Lisa Glendenning, Ivan Beschastnikh, Arvind Krishnamurthy, Thomas Anderson
2011 Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles - SOSP '11  
Our prototype implementation demonstrates that even with very short node lifetimes, it is possible to build a scalable and consistent system with practical performance.  ...  This paper describes the design, implementation, and evaluation of Scatter, a scalable and consistent distributed key-value storage system.  ...  In keeping with our goal to build on classic fault-tolerant distributed algorithms rather than inventing ad-hoc protocols, we chose to structure group membership updates as distributed transactions across  ... 
doi:10.1145/2043556.2043559 dblp:conf/sosp/GlendenningBKA11 fatcat:57x2f75q7rfe3ao4dcpmi2ctsm

Principles for Inconsistency [article]

Shel Finkelstein
2009 arXiv   pre-print
However, there are good reasons why consistency may have to be weakened to achieve other business goals.  ...  Data consistency is very desirable because strong semantic properties make it easier to write correct programs that perform as users expect.  ...  systems with synchronous commits to backups, active/active replication with subjective/eventual consistency, and replication with strong consistency.  ... 
arXiv:0909.1782v1 fatcat:yivynfkg7jgfxhc27sltozy7ny

Dependable Distributed Computing Using Free Databases [chapter]

Christof Fetzer, Trevor Jim
2005 Lecture Notes in Computer Science  
Databases provide features like transactions and replication that can help in the implementation of dependable applications.  ...  providing a simple implementation that works for freely-available databases, on automatic tuning of the partitions for best performance, and on applying the fault tolerance mechanisms of the databases to build  ...  Instead of building features such as transactions and replication into DOSE itself, DOSE relies on the database for them.  ... 
doi:10.1007/11560333_11 fatcat:fzkmksqadzhkxbcctwp6gxdumi

Distributed computing column 53

Jennifer L. Welch
2014 ACM SIGACT News  
We may classify current approaches to deal with the challenges of building distributed applications into the following two categories: • Strong Consistency and Transactions: Strong consistency means that  ...  Bettina's talk advocates the idea of quantifying inconsistency with respect to strong consistency (e.g., serializability).  ... 
doi:10.1145/2596583.2596600 fatcat:lruhrujqvnccxdqj3tkbrhxeku

Dagstuhl seminar review

Bettina Kemme, André Schiper, G. Ramalingam, Marc Shapiro
2014 ACM SIGACT News  
We may classify current approaches to deal with the challenges of building distributed applications into the following two categories: • Strong Consistency and Transactions: Strong consistency means that  ...  Bettina's talk advocates the idea of quantifying inconsistency with respect to strong consistency (e.g., serializability).  ... 
doi:10.1145/2596583.2596601 fatcat:cdnh5juczjggjnhyoozzpsgkjm

Some ideas on support for fault tolerance in COMANDOS, an object oriented distributed system

Brendan Tangney, Vinny Cahill, Chris Horn, Dominic Herity, Alan Judge, Gradimir Starovic, Mark Sheppard
1991 ACM SIGOPS Operating Systems Review  
In some other cases a limited inconsistency is acceptable. 6 Based on DAT or optical disk. A storage system build on this model is made reliable by replicating the append only storage device.  ...  prudent to then use transactions as the main building block for continuity.  ... 
doi:10.1145/122120.122139 fatcat:sxfdzetwsrbpvbben726hzf6yy

Some ideas on support for fault tolerance in COMANDOS, an object oriented distributed system

Brendan Tangney, Vinny Cahill, Chris Horn, Dominic Herity, Alan Judge, Gradimir Starovic, Mark Sheppard
1990 Proceedings of the 4th workshop on ACM SIGOPS European workshop - EW 4  
In some other cases a limited inconsistency is acceptable. 6 Based on DAT or optical disk. A storage system build on this model is made reliable by replicating the append only storage device.  ...  prudent to then use transactions as the main building block for continuity.  ... 
doi:10.1145/504136.504160 dblp:conf/sigopsE/TangneyCHHJSS90 fatcat:swej2ufvsjh4ffelon47mhkbsm

When Is Operation Ordering Required in Replicated Transactional Storage?

Irene Zhang, Naveen Kr. Sharma, Adriana Szekeres, Arvind Krishnamurthy, Dan R. K. Ports
2016 IEEE Data Engineering Bulletin  
Today's replicated transactional storage systems typically have a layered architecture, combining protocols for transaction coordination, consistent replication, and concurrency control.  ...  These systems generally require costly strongly-consistent replication protocols like Paxos, which assign a total order to all operations.  ...  TAPIR provides strict serializable isolation of transactions, but relies on a weakly consistent underlying replication protocol, inconsistent replication (IR).  ... 
dblp:journals/debu/ZhangSSKP16 fatcat:m7y4e3fbcnhctg7kekw2yidv2u

Consistency Improvisation in MongoDB during Lag on secondary

Abuzar Kamal, Mr. Saravana Kumar K
2017 IJARCCE  
server, however if there is huge lag then it can result into inconsistent data.  ...  Replication lag in Mongo database is serious problem in replication environment if the reporting is done through secondary server, In replication environment the read only query can be routed to secondary  ...  REPLICATION LAG Replication lag is the time delay between the last transaction committed on primary and that the last transaction applied on secondary [13] .  ... 
doi:10.17148/ijarcce.2017.63164 fatcat:eexqt6j3qffkvbentfepupqouy
« Previous Showing results 1 — 15 out of 29,747 results