973 Hits in 4.3 sec

Erasure Coding Vs. Replication: A Quantitative Comparison [chapter]

Hakim Weatherspoon, John D. Kubiatowicz
2002 Lecture Notes in Computer Science  
In this paper, we quantitatively compare building a distributed storage infrastructure that is self-repairing and resilient to faults using either a replicated system or an erasure-resilient system.  ...  We show that systems employing erasure codes have mean time to failures many orders of magnitude higher than replicated systems with similar storage and bandwidth requirements.  ...  We quantitatively compared systems based on replication to systems based on erasure codes.  ... 
doi:10.1007/3-540-45748-8_31 fatcat:6wvupx7q7zf7vcwzznoa6ke25u

A Quantitative Comparison of Reactive and Proactive Replicated Storage Systems

Rossana Motta, Joseph Pasquale
2012 2012 IEEE 31st Symposium on Reliable Distributed Systems  
Our work presents a quantitative analysis that compares reactive and proactive through analytical models and simulations, considering exponentially distributed failures and reactive repairs, and periodic  ...  Our results indicate that a proactive strategy leads to multiple times higher storage requirements than a reactive strategy.  ...  Glacier [9] focuses on erasure coding, dealing with massive correlated failures and the traffic due to replication.  ... 
doi:10.1109/srds.2012.1 dblp:conf/srds/MottaP12 fatcat:fgyebuwljvdirfwmuzsecguvbu

Storage and network resource usage in reactive and proactive replicated storage systems

R. Motta, J. Pasquale
2013 2013 International Conference on Computing, Networking and Communications (ICNC)  
Our work presents a quantitative analysis that compares reactive and proactive through simulations and verified analytically where possible.  ...  In particular, we systematically compare how the strategy of replication affects the usage of storage and network resources, at peak consumption as well as on average, to achieve a given lifetime for a  ...  Tempo also presents a quantitative comparison with Carbonite, thus offering a rare comparison of a proactive system with a reactive one.  ... 
doi:10.1109/iccnc.2013.6504221 dblp:conf/iccnc/MottaP13 fatcat:g4d5d6yf55d3pflwsp7k5tbvse

Dependability Evaluation of Cooperative Backup Strategies for Mobile Devices

Ludovic Courtes, Ossama Hamouda, Mohamed Kaaniche, Marc-Olivier Killijian, David Powell
2007 13th Pacific Rim International Symposium on Dependable Computing (PRDC 2007)  
Several data replication and scattering strategies are presented,including the use of erasure codes. A methodology to model and evaluate them using Petri nets and Markov chains is described.  ...  Participating devices leverage encounters with other devices to temporarily replicate critical data.  ...  This is confirmed analytically by computing the following ratio, for any p > 1 such that pk and pn are integers: Erasure Coding vs.  ... 
doi:10.1109/prdc.2007.21 dblp:conf/prdc/CourtesHKKP07 fatcat:z2jrqnhtqfc7hmwx7utdtnrh3y


Huaxia Xia, Andrew A. Chien
2007 Proceedings of the 2007 ACM/IEEE conference on Supercomputing - SC '07  
We propose RobuSTore, a storage architecture that combines erasure codes and speculative access mechanisms for parallel write and read in distributed environments.  ...  For example, for a 1GB data access using 64 disks, RobuSTore achieves average bandwidth of 186MBps for write and 400MBps for read, nearly 6x and 15x that achieved by a RAID-0 system.  ...  To give a quantitative sense of how much flexibility erasure codes provide, we theoretically analyzed the number of blocks required for data reconstruction in both erasure-coded schemes and plain-text  ... 
doi:10.1145/1362622.1362682 dblp:conf/sc/XiaC07 fatcat:ukojijue75bm7plahfvdioonf4

Toward high-performance key-value stores through GPU encoding and locality-aware encoding

Dongfang Zhao, Ke Wang, Kan Qiao, Tonglin Li, Iman Sadooghi, Ioan Raicu
2016 Journal of Parallel and Distributed Computing  
Instead of migrating full-size replicas over the network, we split the original file into smaller chunks and encode them with a few additional parity codes using GPUs before dispersing them onto remote  ...  Although distributed key-value store is becoming increasingly popular in compensating the conventional distributed file systems, it is often criticized due to its costly full-size replication for high  ...  For a fair comparison, we slightly change the setup of the previous experiment: the replication mechanism makes the same number of replicas as the additional parities in erasure coding.  ... 
doi:10.1016/j.jpdc.2016.04.015 fatcat:qg5u7jatfzcm3hhsb45phj5juq

Redundantly grouped cross-object coding for repairable storage

Anwitaman Datta, Frédérique Oggier
2012 Proceedings of the Asia-Pacific Workshop on Systems - APSYS '12  
The problem of replenishing redundancy in erasure code based fault-tolerant storage has received a great deal of attention recently, leading to the design of several new coding techniques [3] , aiming  ...  In this paper, we adopt a different point of view, by proposing to code across different already encoded objects to alleviate the repair problem.  ...  Acknowledgement A. Datta's work was partially supported by NTU/MoE Tier-1 grant number RG 29/09. F.  ... 
doi:10.1145/2349896.2349898 dblp:conf/apsys/DattaO12 fatcat:vqmn5ll2cbhodgciv35j6we4ta

An Overview of Codes Tailor-made for Better Repairability in Networked Distributed Storage Systems [article]

Anwitaman Datta, Frederique Oggier
2013 arXiv   pre-print
of these codes, and discussing their pros and cons, before concluding with a quantitative comparison among them.  ...  Instead, it provides an overview of the major code families in a manner easily accessible to a broad audience, by presenting the big picture of advances in coding techniques for distributed storage solutions  ...  QUANTITATIVE COMPARISON Self-repairing codes, pyramid and hierarchical codes sacrifice the MDS property in order to achieve regeneration using d < k live nodes.  ... 
arXiv:1109.2317v2 fatcat:bgj5muqfpfenvcgt77l4kkfghy

DNA methylation is required to maintain DNA replication timing precision and 3D genome integrity [article]

Qian Du, Grady C Smith, Phuc Loi Luu, James M Ferguson, Nicola J Armstrong, C Elizabeth Caldon, Elyssa Campbell, Shalima S Nair, Elena Zotenko, Cathryn M Gould, Michael Buckley, Dominik Kaczorowski (+8 others)
2020 bioRxiv   pre-print
Second, hypomethylated regions that undergo a large change in replication timing also show loss of allelic replication timing, including at cancer-related genes.  ...  First, we find that the hypomethylated cells show a striking loss of replication timing precision with gain of intra-population replication timing heterogeneity and loss of 3D genome compartmentalisation  ...  This indicates that although compartment switches do cross the midline that defines A vs.  ... 
doi:10.1101/2020.10.15.338855 fatcat:x52uwmbdxfaiblzyuo7su25pem

Network Coding for Distributed Storage Systems [article]

Alexandros G. Dimakis, P. Brighten Godfrey, Yunnan Wu, Martin J. Wainwright, Kannan Ramchandran
2008 arXiv   pre-print
Storing data using an erasure code, in fragments spread across nodes, requires less redundancy than simple replication for the same level of reliability.  ...  For an erasure coded system, a common practice to repair from a node failure is for a new node to download subsets of data stored at a number of surviving nodes, reconstruct a lost coded block using the  ...  Ideal Erasure Codes: For comparison, we show the bandwidth and availability of a hypothetical (n, k) erasure code strategy which can "magically" create a new packet while transferring just M/k bytes (i.e  ... 
arXiv:0803.0632v1 fatcat:ylm5ysrglvdahg3uhjlgten6jq

Availability modelling of a virtual black box for automotive systems

Ossama Hamouda, Mohamed Kaâniche, Karama Kanoun
2010 Proceedings of the 2nd International Workshop on Software Engineering for Resilient Systems - SERENCE '10  
However, instead of using a classical hardware based black-box that could induce a high cost, a more cost effective solution would be to use a software based mechanism that consists in storing the recorded  ...  To protect the data against potential losses before an access to the fixed infrastructure is available, the data can be replicated and temporarily stored on neighbouring encountered vehicles using wireless  ...  by fragmentation strategy using an erasure code (n ,k) (denoted as UA(n,k)).  ... 
doi:10.1145/2401736.2401742 dblp:conf/serene/HamoudaKK10 fatcat:4phy3dgrandhlmq4i3titkoxwy

Efficient Network Coded Data Transmissions in Disruption Tolerant Networks

Y. Lin, B. Li, B. Liang
2008 IEEE INFOCOM 2008 - The 27th Conference on Computer Communications  
over replication-based protocols.  ...  By making an analogy between the routing protocol and low-density erasure codes, we investigate the information-theoretical optimal number of data transmissions in delivering data.  ...  A. Delivery Delay vs.  ... 
doi:10.1109/infocom.2008.210 dblp:conf/infocom/LinLL08 fatcat:n4ketaybirhvtdfa2gs3w3ahha

Efficient Network Coded Data Transmissions in Disruption Tolerant Networks

Y. Lin, B. Li, B. Liang
2008 2008 Proceedings IEEE INFOCOM - The 27th Conference on Computer Communications  
over replication-based protocols.  ...  By making an analogy between the routing protocol and low-density erasure codes, we investigate the information-theoretical optimal number of data transmissions in delivering data.  ...  A. Delivery Delay vs.  ... 
doi:10.1109/infocom.2007.210 fatcat:qc3b5rtv5vf3nl2zulx4gkvxnm

Benchmarking data warehouse systems in the cloud

Rim Moussa
2013 2013 ACS International Conference on Computer Systems and Applications (AICCSA)  
The proposed requirements should allow a fair comparison of different cloud systems providers' offerings.  ...  Finally, we present new requirements for implementing a benchmark for data warehouse systems in the cloud.  ...  Fig. 3 . 3 Replication vs. Erasure Codes for a group of 4 data blocks. Fig. 4 . 4 Pig performances (sec) for 1.1GB of TPC-H data (SF=1).  ... 
doi:10.1109/aiccsa.2013.6616442 dblp:conf/aiccsa/Moussa13 fatcat:y4mcf7xk3zdjzgd473dufhpeau

Diversity/Parallelism Trade-off in Distributed Systems with Redundancy [article]

Pei Peng, Emina Soljanin, Philip Whiting
2021 arXiv   pre-print
Redundancy, in the form of task replication and erasure coding, provides diversity that allows a job to be completed when only a subset of redundant tasks is executed, thus removing the dependency on the  ...  In this paper, we characterize the diversity vs. parallelism trade-off and identify the optimal strategy, among replication, coding and splitting, which minimizes the expected job completion time.  ...  There is a large body of literature on replication and erasure codes for classical machine learning and other algorithms (see e.g.  ... 
arXiv:2010.02147v3 fatcat:hhcwrytdnbeyfgrzpqpsnmgrwe
« Previous Showing results 1 — 15 out of 973 results