35,877 Hits in 1e+01 sec

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  
We answer this question by analyzing existing transaction processing designs in terms of which replicated operations require ordering and which simply require fault tolerance.  ...  To avoid this cost, we ask whether all replicated operations in these systems need to be strictly ordered.  ...  In the next subsection we further analyze the ordering requirements for 2PC operations when integrating different concurrency control mechanisms.  ... 
dblp:journals/debu/ZhangSSKP16 fatcat:m7y4e3fbcnhctg7kekw2yidv2u

Violet: A Storage Stack for IOPS/Capacity Bifurcated Storage Environments

Douglas Santry, Kaladhar Voruganti
2014 USENIX Annual Technical Conference  
In this paper we describe a storage system called Violet that efficiently marries fine-grained host side data management with capacity optimized backend disk systems.  ...  when they are persisting these data structures to protect them from node failures.  ...  The serial numbers totally order the transactions. Their use is explained in §4. The replication facility offers two modes of operation.  ... 
dblp:conf/usenix/SantryV14 fatcat:33olr72qgre2vcsppj6f2z3cia

Scalable Byzantine fault-tolerant storage

Ricardo Padilha, Fernando Pedone
2011 2011 IEEE/IFIP 41st International Conference on Dependable Systems and Networks Workshops (DSN-W)  
We propose in this short paper to build scalable Byzantine fault-tolerant storage systems based on the concept of mini-transactions.  ...  Byzantine fault-tolerance is costly, both in terms of increased latency and limited scalability.  ...  BFT agreement is only executed at the end to ensure the client submitted the same operations in the same order to all log servers.  ... 
doi:10.1109/dsnw.2011.5958808 dblp:conf/dsn/PadilhaP11 fatcat:f7dfdjddozb25keuzktn2rzbty

Transactional storage for geo-replicated systems

Yair Sovran, Russell Power, Marcos K. Aguilera, Jinyang Li
2011 Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles - SOSP '11  
These hosts should observe a consistent storage state. For example, in a social network, a user expects to see her own posts immediately and in order.  ...  A geo-replicated storage system replicates objects across multiple sites. The system is managed by a single administrative entity.  ...  These applications require a storage system that is geo-replicated-that is, replicated across many sites-to keep user data, such as status updates, photos, and messages in a social networking application  ... 
doi:10.1145/2043556.2043592 dblp:conf/sosp/SovranPAL11 fatcat:3s5i2vrgxjhglgars3eribb664

Reducing Storage for Quorum Consensus Algorithms

Divyakant Agrawal, Amr El Abbadi
1988 Very Large Data Bases Conference  
In this paper, we first develop a fragmentation method that reduces the storage overhead of replicated objects.  ...  Although this protocol reduces storage requirements, it does not achieve the same level of resiliency for both read and write operations.  ...  In particular, when an object is updated, the storage requirements of the copies of the log increase temporarily.  ... 
dblp:conf/vldb/AgrawalA88 fatcat:kwoox2zpp5hizipvifwcu4rrp4

DAOS: A Scale-Out High Performance Storage Stack for Storage Class Memory [chapter]

Zhen Liang, Johann Lombardi, Mohamad Chaarawi, Michael Hennecke
2020 Lecture Notes in Computer Science  
The Distributed Asynchronous Object Storage (DAOS) is an open source scale-out storage system that is designed from the ground up to support Storage Class Memory (SCM) and NVMe storage in user space.  ...  In this paper we present the architecture of the DAOS storage engine and its high-level application interfaces. We also describe initial performance results of DAOS for IO500 benchmarks.  ...  In order to enable OS-bypass for those performance sensitive operations, an interception library has been added to the stack.  ... 
doi:10.1007/978-3-030-48842-0_3 fatcat:5mnbru2fm5a63dot53xtouuo6a

Megastore: structured storage for Big Data

Oswaldo Moscoso Zea
2012 Enfoqute  
In this paper an analysis of Google's data infrastructure is made, startingwith a review of the core components that have been developed in recent years until theimplementation of Megastore.  ...  An analysis is also made of the most important  ...  costs when developing web solutions that require a scalable and reliable data storage (Severance, 2009) .  ... 
doi:10.29019/enfoqueute.v3n2.1 fatcat:gbvyvzm77fbcnc6sdb37mkuiie

Consistency Management in Cloud Storage Systems [chapter]

Houssem-Eddine Chihoub, Shadi Ibrahim, Gabriel Antoniu, Maria Perez
2014 Large Scale and Big Data  
Blue operations are executed locally and replicated lazily. Therefore, their ordering can vary from site to site. In contrast, Red operations require a stronger consistency.  ...  If accepted, the operation is then delegated to the local data writer in order to be executed in the storage engine.  ... 
doi:10.1201/b17112-11 fatcat:mj4le7nhvnahpd33ulqktssvuu

Consistency in Non-Transactional Distributed Storage Systems [article]

Paolo Viotti, Marko Vukolić
2016 arXiv   pre-print
The scope of this paper is restricted to non-transactional semantics, i.e., those that apply to single storage object operations.  ...  We further provide a partial order among different consistency predicates, ordering them by their semantic "strength", which we believe will reveal useful in future research.  ...  This research was supported in part by the EU projects CloudSpaces (FP7-317555) and SUPERCLOUD (Horizon 2020 programme, grant No. 643964).  ... 
arXiv:1512.00168v4 fatcat:nv7qzsrkmje6dpbxhztrmso2iu

The Lustre Storage Architecture [article]

Peter Braam
2019 arXiv   pre-print
This lengthy document often referred to as the "Lustre Book", contains a detailed outline of Lustre file system architecture, as it was created between 2001 and 2005, in accordance with the requirements  ...  Now, in 2019, most features have been implemented, but some only recently, and some along different lines of thought.  ...  The second set of operations is required when the OSC is acting as a replicator.  ... 
arXiv:1903.01955v1 fatcat:fuq664grqzcexcovxzd2n7f5ji

Stronger Semantics for Low-Latency Geo-Replicated Storage

Wyatt Lloyd, Michael J. Freedman, Michael Kaminsky, David G. Andersen
2013 Symposium on Networked Systems Design and Implementation  
We present the first scalable, geo-replicated storage system that guarantees low latency, offers a rich data model, and provides "stronger" semantics.  ...  can access data in a causallyconsistent fashion with read-only and write-only transactional support, even for keys spread across many servers.  ...  In order to scale, the storage cluster in each datacenter is typically partitioned across 10s to 1000s of machines.  ... 
dblp:conf/nsdi/LloydFKA13 fatcat:ghrxzhiworbidohu3wjtvb4eqi

Towards elastic transactional cloud storage with range query support

Hoang Tam Vo, Chun Chen, Beng Chin Ooi
2010 Proceedings of the VLDB Endowment  
In this paper, we propose ecStore -an elastic cloud storage system that supports automated data partitioning and replication, load balancing, efficient range query, and transactional access.  ...  Cloud storage is an emerging infrastructure that offers Platforms as a Service (PaaS).  ...  In contrast, there is a decline in the transaction throughput when the ratio of update transactions increases as in the case of ordering mix.  ... 
doi:10.14778/1920841.1920907 fatcat:igcu5btk35eino33rsa64dppy4

Proteus: Autonomous Adaptive Storage for Mixed Workloads

Michael Abebe, Horatiu Lazu, Khuzaima Daudjee
2022 Proceedings of the 2022 International Conference on Management of Data  
Proteus generates physical execution plans that utilize storage-aware operators for ecient transaction execution.  ...  Distributed HTAP systems typically maintain a complete copy of data in row-oriented storage format that is well-suited for OLTP workloads and a second complete copy in column-oriented storage format optimized  ...  In contrast to these architectures, Proteus makes granular storage layout decisions, replicating when it benets system performance.  ... 
doi:10.1145/3514221.3517834 fatcat:jdjuy2cbzjfyrhn2qusjcp5tgm

A simple approach to shared storage database servers

Luís Soares, José Pereira
2009 Proceedings of the Third Workshop on Dependable Distributed Data Management - WDDM '09  
This makes it possible to use any shared-nothing database server software in a shared or partially shared storage configuration, thus allowing large cluster configurations with a small number of copies  ...  Instead, the core of the proposal is the combination of a replication protocol and a surprisingly simple modification to the common copy-on-write logical volume management technique: One of the servers  ...  APPROACH At the core of our approach is an additional layer underneath a replicated DBMS when running in a shared-storage cluster, as shown in Fig. 1(c) .  ... 
doi:10.1145/1518691.1518698 fatcat:sijvxgi7pfdqjkw5dtnogsptim

Blockchain Storage Load Balancing Among DHT Clustered Nodes [article]

Ryosuke Abe
2019 arXiv   pre-print
Thus, to operate Full Nodes, the required storage capacity would grow too large for resource-constrained devices.  ...  The transactions are stored in ledger called "Blockchain. " Blockchain is an append-only data structure.  ...  As a result, when operators want to deploy N nodes, the required storage capacity is only Blockchain.  ... 
arXiv:1902.02174v1 fatcat:c2wjoegycfgkzkoz4jknfnzkau
« Previous Showing results 1 — 15 out of 35,877 results