Filters








37,302 Hits in 1.8 sec

Update Consistency for Wait-Free Concurrent Objects

Matthieu Perrin, Achour Mostefaoui, Claude Jard
2015 2015 IEEE International Parallel and Distributed Processing Symposium  
Update consistency is stronger than eventual consistency, so we can replace eventually consistent objects with update consistent ones in any program.  ...  This paper introduces and formalizes a new consistency criterion, called update consistency, that requires the state of a replicated object to be consistent with a linearization of all the updates.  ...  Research (ANR) in the "Investing for the Future" program under reference Nb.  ... 
doi:10.1109/ipdps.2015.39 dblp:conf/ipps/PerrinMJ15 fatcat:xjjsfmiw4ffzzepos26mvz6hci

Update Consistency for Wait-free Concurrent Objects [article]

Matthieu Perrin, Achour Mostefaoui, Claude Jard
2015 arXiv   pre-print
Update consistency is stronger than eventual consistency, so we can replace eventually consistent objects with update consistent ones in any program.  ...  This paper introduces and formalizes a new consistency criterion, called update consistency, that requires the state of a replicated object to be consistent with a linearization of all the updates.  ...  Research (ANR) in the "Investing for the Future" program under reference Nb.  ... 
arXiv:1501.02165v1 fatcat:qycyl34pozeefgp7cjfnbo6sva

On the Implementation of Concurrent Objects [chapter]

Michel Raynal
2011 Lecture Notes in Computer Science  
It is now largely accepted that linearizability (or atomicity) is an appropriate consistency condition for concurrent objects.  ...  This paper visits three progress conditions suited to concurrent objects in presence of failures, namely obstruction-freedom, non-blocking and wait-freedom.  ...  1 Introduction Consistency and progress conditions for concurrent objects Concurrent objects A concurrent object is an object that can be concurrently accessed by several processes.  ... 
doi:10.1007/978-3-642-24541-1_33 fatcat:vk5rtt4z3vbj5paoo6uyoi4ydu

A Wait-Free Universal Construct for Large Objects [article]

Andreia Correia, Pedro Ramalhete, Pascal Felber
2019 arXiv   pre-print
Wait-free universal constructs are attractive as they can turn a sequential implementation of any object into an equivalent, yet concurrent and wait-free, implementation.  ...  This need has pushed for generic solutions and specific concurrent data structures.  ...  A wait-free universal construct is a generic mechanism meant to provide concurrent wait-free access to a sequential implementation of an object or group of objects, e.g., a data structure.  ... 
arXiv:1911.01676v1 fatcat:y6cfg4do3vhijmwiddteolhy2e

A methodology for implementing highly concurrent data objects

Maurice Herlihy
1993 ACM Transactions on Programming Languages and Systems  
This paper proposes a new methodology for constructing lock-free and wait-free implementations of concurrent objects.  ...  By contrast, a concurrent object implementation is lock free if it always guarantees that some process will complete an operation in a finite number of steps, and it is wait free if it guarantees that  ...  This paper proposes a new methodology for constructing lock-free and wait-free implementations of concurrent objects.  ... 
doi:10.1145/161468.161469 fatcat:gctjsakpinfind3eo67gam23im

Non-monotonic Snapshot Isolation: Scalable and Strong Consistency for Geo-replicated Transactional Systems

Masoud Saeida Ardekani, Pierre Sutra, Marc Shapiro
2013 2013 IEEE 32nd International Symposium on Reliable Distributed Systems  
To minimize this cost, we identify the following essential scalability properties: (i) only replicas updated by a transaction T make steps to execute T ; (ii) a read-only transaction never waits for concurrent  ...  Transactional consistency is essential for application developers; however, the corresponding concurrency control and commitment protocols are costly in a geo-replicated setting.  ...  ACKNOWLEDGMENTS We thank Pierpaolo Cincilla for his contribution to an early version of Jessy.  ... 
doi:10.1109/srds.2013.25 dblp:conf/srds/ArdekaniSS13 fatcat:vo6sro3tnvf7xjwxeb6r4njsfi

A Consistency Framework for Iteration Operations in Concurrent Data Structures

Yiannis Nikolakopoulos, Anders Gidenstam, Marina Papatriantafilou, Philippas Tsigas
2015 2015 IEEE International Parallel and Distributed Processing Symposium  
Besides linearizability, we propose a set of consistency specifications for such bulk operations, including also concurrency-aware properties by building on Lamport's systematic definitions for registers  ...  Iterations in several of these contexts have been treated as sequential in nature and may provide weak consistency guarantees when running concurrently with the native operations of the data structures  ...  We are thankful to Panagiota Fatourou for her feedback in earlier stages of this work.  ... 
doi:10.1109/ipdps.2015.84 dblp:conf/ipps/NikolakopoulosG15 fatcat:ci54l4p4avaxlp7ki5bu6uydni

Graphical Representation of Optimistic Locking and Concurrency Control for Temporal Database using Oracle 12c Enterprise Manager

Jaypalsinh A., Prashant M.
2016 International Journal of Computer Applications  
In a multiuser database environment, multiple simultaneous transactions may update the same data. Transactions executing simultaneously must produce meaningful and consistent results.  ...  To minimize the concurrency problem the locking approach is used.  ...  TX enqueues are not waiting for a row, but for the completion of the transaction that has updated the row.  ... 
doi:10.5120/ijca2016911214 fatcat:rg3ij2wh7fgbxhbqlvnlrwapoy

Towards a practical snapshot algorithm

Yaron Riany, Nir Shavit, Dan Touitou
2001 Theoretical Computer Science  
The design of wait-free implementations of a t o m i c r u a p r h t m e m o n e r has been the subject of extensive theoretical research in recent years.  ...  This paper introducem the coordinated-colleci algorithm, a novel wait-free atomic 8napshot construction which we believe b a flrst step in taking snapshots from theory t o practice.  ...  sensors generate updates concurrently with multiple requests for consistent system states.  ... 
doi:10.1016/s0304-3975(00)00412-6 fatcat:2bzwkrtfznhdfmgsz5wcupeday

On limitations of using cloud storage for data replication

Christian Cachin, Birgit Junker, Alessandro Sorniotti
2012 IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN 2012)  
Cloud storage services often provide a key-value store (KVS) functionality, an object-based interface for accessing a collection of unstructured data items or blobs.  ...  In the simplest form, a key-value store provides only methods for writing and reading an entire blob, for removing blobs, and for listing all defined keys.  ...  ACKNOWLEDGMENTS We thank Sabrina Pérez and Marko Vukolić for interesting discussions and helpful comments.  ... 
doi:10.1109/dsnw.2012.6264683 dblp:conf/dsn/CachinJS12 fatcat:kswkmubtrjgg5cgtsk2lcrmfbi

Comparison of Concurrency Control and Deadlock Handing in Different OODBMS

Sonal Kanungo, Dr. R. D. Morena
2016 International Journal of Engineering Research and  
Transactions involving complex objects can continue for several hours, or even several days.  ...  Object databases are very good at storing the complex data model. Many applications can runs efficiently with many concurrent users.  ...  An example of a complex deadlock is "A waiting for B waiting for C waiting for D waiting for A".  ... 
doi:10.17577/ijertv5is050615 fatcat:hdf5ffb665efzlwggeakf4luku

The Inherent Cost of Remembering Consistently

Nachshon Cohen, Rachid Guerraoui, Igor Zablotchi
2018 Proceedings of the 30th on Symposium on Parallelism in Algorithms and Architectures - SPAA '18  
But in order to take advantage of the durability of NVM, programmers need to design persistent objects which maintain consistent state across system crashes and restarts.  ...  Concurrent implementations of persistent objects typically make heavy use of expensive persistent fence instructions to order NVM accesses, thus negating some of the performance benefits of NVM.  ...  ACKNOWLEDGMENTS We wish to thank the anonymous reviewers for their helpful comments on improving the paper.  ... 
doi:10.1145/3210377.3210400 dblp:conf/spaa/CohenGZ18 fatcat:meutuc3uubh2bfpedi22nty6mm

A Wait-free Multi-word Atomic (1,N) Register for Large-scale Data Sharing on Multi-core Machines [article]

Mauro Ianni, Alessandro Pellegrini, Francesco Quaglia
2017 arXiv   pre-print
We present a multi-word atomic (1,N) register for multi-core machines exploiting Read-Modify-Write (RMW) instructions to coordinate the writer and the readers in a wait-free manner.  ...  Beyond assessing ARC on physical platforms, we carry out as well an experimentation on virtualized infrastructures, which shows the resilience of wait-free synchronization as provided by ARC with respect  ...  Wait-freedom appears as a mandatory means to efficiently handle concurrent operations on shared-objects in systems with large/huge amounts of concurrent threads.  ... 
arXiv:1707.07478v1 fatcat:czi5r7g65zfircbct4kqzdcexq

A performance evaluation of lock-free synchronization protocols

Anthony LaMarca
1994 Proceedings of the thirteenth annual ACM symposium on Principles of distributed computing - PODC '94  
In this paper, we investigate the practicat performance of lock-free techniques that provide synchronization on shared-memory multiprocessors.  ...  Accordingly, we introduce a protocol, based on a combination of existing lock-free techniques, which satisfies these criteria.  ...  In Herlihy's wait-free protocol, threads register their intended operations in the object before beginning their update.  ... 
doi:10.1145/197917.197975 dblp:conf/podc/LaMarca94 fatcat:yzcpmxccofacjbxkl4ymznyvae

Software Transactional Memory as a Building Block for Parallel Embedded Real-Time Systems

Antonio Barros, Luis Miguel Pinho
2011 2011 37th EUROMICRO Conference on Software Engineering and Advanced Applications  
snapshots, progressing in a wait-free manner.  ...  snapshots, progressing in a wait-free manner.  ...  To determine the number of versions required for any object we have to: 1) determine the maximum number of updates for each object in a given interval, and 2) determine the time each object must store  ... 
doi:10.1109/seaa.2011.46 dblp:conf/euromicro/BarrosP11 fatcat:2r7cmiqpkjd4rlrz65qsrcz2m4
« Previous Showing results 1 — 15 out of 37,302 results