Results 1 - 10
of
275
The Hadoop Distributed File System
"... Abstract—The Hadoop Distributed File System (HDFS) is designed to store very large data sets reliably, and to stream those data sets at high bandwidth to user applications. In a large cluster, thousands of servers both host directly attached storage and execute user application tasks. By distributin ..."
Abstract
-
Cited by 343 (1 self)
- Add to MetaCart
(Show Context)
Abstract—The Hadoop Distributed File System (HDFS) is designed to store very large data sets reliably, and to stream those data sets at high bandwidth to user applications. In a large cluster, thousands of servers both host directly attached storage and execute user application tasks. By distributing storage and computation across many servers, the resource can grow with demand while remaining economical at every size. We describe the architecture of HDFS and report on experience using HDFS to manage 25 petabytes of enterprise data at Yahoo!.
PNUTS: Yahoo!’s hosted data serving platform
- IN PROC. 34TH VLDB
, 2008
"... We describe PNUTS, a massively parallel and geographically distributed database system for Yahoo!’s web applications. PNUTS provides data storage organized as hashed or ordered tables, low latency for large numbers of concurrent requests including updates and queries, and novel per-record consistenc ..."
Abstract
-
Cited by 241 (11 self)
- Add to MetaCart
(Show Context)
We describe PNUTS, a massively parallel and geographically distributed database system for Yahoo!’s web applications. PNUTS provides data storage organized as hashed or ordered tables, low latency for large numbers of concurrent requests including updates and queries, and novel per-record consistency guarantees. It is a hosted, centrally managed, and geographically distributed service, and utilizes automated load-balancing and failover to reduce operational complexity. The first version of the system is currently serving in production. We describe the motivation for PNUTS and the design and implementation of its table storage and replication layers, and then present experimental results.
DEPSKY: Dependable and Secure Storage in a Cloud-of-Clouds
, 2013
"... The increasing popularity of cloud storage services has lead companies that handle critical data to think about using these services for their storage needs. Medical record databases, large biomedical datasets, historical information about power systems and financial data are some examples of critic ..."
Abstract
-
Cited by 85 (15 self)
- Add to MetaCart
The increasing popularity of cloud storage services has lead companies that handle critical data to think about using these services for their storage needs. Medical record databases, large biomedical datasets, historical information about power systems and financial data are some examples of critical data that could be moved to the cloud. However, the reliability and security of data stored in the cloud still remain major concerns. In this work we present DEPSKY, a system that improves the availability, integrity and confidentiality of information stored in the cloud through the encryption, encoding and replication of the data on diverse clouds that form a cloud-of-clouds. We deployed our system using four commercial clouds and used PlanetLab to run clients accessing the service from different countries. We observed that our protocols improved the perceived availability and, in most cases, the access latency when compared with cloud providers individually. Moreover, the monetary costs of using DEPSKY on this scenario is at most twice the cost of using a single cloud, which is optimal and seems to be a reasonable cost, given the benefits.
Finding a Needle in Haystack: Facebook’s Photo Storage
- In Proc. of OSDI
, 2010
"... Abstract: This paper describes Haystack, an object storage system optimized for Facebook’s Photos application. Facebook currently stores over 260 billion images, which translates to over 20 petabytes of data. Users upload one billion new photos (∼60 terabytes) each week and Facebook serves over one ..."
Abstract
-
Cited by 81 (0 self)
- Add to MetaCart
(Show Context)
Abstract: This paper describes Haystack, an object storage system optimized for Facebook’s Photos application. Facebook currently stores over 260 billion images, which translates to over 20 petabytes of data. Users upload one billion new photos (∼60 terabytes) each week and Facebook serves over one million images per second at peak. Haystack provides a less expensive and higher performing solution than our previous approach, which leveraged network attached storage appliances over NFS. Our key observation is that this traditional design incurs an excessive number of disk operations because of metadata lookups. We carefully reduce this per photo metadata so that Haystack storage machines can perform all metadata lookups in main memory. This choice conserves disk operations for reading actual data and thus increases overall throughput. 1
Pergamum: Replacing tape with energy efficient, reliable, disk-based archival storage
- IN FAST-2008: 6TH USENIX CONFERENCE ON FILE AND STORAGE TECHNOLOGIES
, 2008
"... As the world moves to digital storage for archival purposes, there is an increasing demand for reliable, lowpower, cost-effective, easy-to-maintain storage that can still provide adequate performance for information retrieval and auditing purposes. Unfortunately, no current archival system adequatel ..."
Abstract
-
Cited by 64 (14 self)
- Add to MetaCart
(Show Context)
As the world moves to digital storage for archival purposes, there is an increasing demand for reliable, lowpower, cost-effective, easy-to-maintain storage that can still provide adequate performance for information retrieval and auditing purposes. Unfortunately, no current archival system adequately fulfills all of these requirements. Tape-based archival systems suffer from poor random access performance, which prevents the use of inter-media redundancy techniques and auditing, and requires the preservation of legacy hardware. Many diskbased systems are ill-suited for long-term storage because their high energy demands and management requirements make them cost-ineffective for archival purposes. Our solution, Pergamum, is a distributed network of intelligent, disk-based, storage appliances that stores data reliably and energy-efficiently. While existing MAID systems keep disks idle to save energy, Pergamum adds NVRAM at each node to store data signatures, metadata, and other small items, allowing deferred writes, metadata requests and inter-disk data verification to be performed while the disk is powered off. Pergamum uses both intra-disk and inter-disk redundancy to guard against data loss, relying on hash tree-like structures of algebraic signatures to efficiently verify the correctness of stored data. If failures occur, Pergamum uses staggered rebuild to reduce peak energy usage while rebuilding large redundancy stripes. We show that our approach is comparable in both startup and ongoing costs to other archival technologies and provides very high reliability. An evaluation of our implementation of Pergamum shows that it provides adequate performance.
A nine year study of file system and storage benchmarking
- ACM Transactions on Storage
, 2008
"... Benchmarking is critical when evaluating performance, but is especially difficult for file and storage systems. Complex interactions between I/O devices, caches, kernel daemons, and other OS components result in behavior that is rather difficult to analyze. Moreover, systems have different features ..."
Abstract
-
Cited by 55 (8 self)
- Add to MetaCart
Benchmarking is critical when evaluating performance, but is especially difficult for file and storage systems. Complex interactions between I/O devices, caches, kernel daemons, and other OS components result in behavior that is rather difficult to analyze. Moreover, systems have different features and optimizations, so no single benchmark is always suitable. The large variety of workloads that these systems experience in the real world also adds to this difficulty. In this article we survey 415 file system and storage benchmarks from 106 recent papers. We found that most popular benchmarks are flawed and many research papers do not provide a clear indication of true performance. We provide guidelines that we hope will improve future performance evaluations. To show how some widely used benchmarks can conceal or overemphasize overheads, we conducted a set of experiments. As a specific example, slowing down read operations on ext2 by a factor of 32 resulted in only a 2–5 % wall-clock slowdown in a popular compile benchmark. Finally, we discuss future work to improve file system and storage benchmarking.
Disco: Distributed co-clustering with map-reduce. ICDM
, 2008
"... Huge datasets are becoming prevalent; even as researchers, we now routinely have to work with datasets that are up to a few terabytes in size. Interesting real-world applications produce huge volumes of messy data. The mining process involves several steps, starting from pre-processing the raw data ..."
Abstract
-
Cited by 53 (1 self)
- Add to MetaCart
(Show Context)
Huge datasets are becoming prevalent; even as researchers, we now routinely have to work with datasets that are up to a few terabytes in size. Interesting real-world applications produce huge volumes of messy data. The mining process involves several steps, starting from pre-processing the raw data to estimating the final models. As data become more abundant, scalable and easyto-use tools for distributed processing are also emerging. Among those, Map-Reduce has been widely embraced by both academia and industry. In database terms, Map-Reduce is a simple yet powerful execution engine, which can be complemented with other data storage and management components, as necessary. In this paper we describe our experiences and findings in applying Map-Reduce, from raw data to final models, on an important mining task. In particular, we focus on co-clustering, which has been studied in many applications such as text mining, collaborative filtering, bio-informatics, graph mining. We propose the Distributed Co-clustering (DisCo) framework, which introduces practical approaches for distributed data pre-processing, and co-clustering. We develop DisCo using Hadoop, an open source Map-Reduce implementation. We show that DisCo can scale well and efficiently process and analyze extremely large datasets (up to several hundreds of gigabytes) on commodity hardware. 1
CRUSH: Controlled, scalable, decentralized placement of replicated data
- IN PROCEEDINGS OF THE 2006 ACM/IEEE CONFERENCE ON SUPERCOMPUTING (SC ’06
, 2006
"... Emerging large-scale distributed storage systems are faced with the task of distributing petabytes of data among tens or hundreds of thousands of storage devices. Such systems must evenly distribute data and workload to efficiently utilize available resources and maximize system performance, while f ..."
Abstract
-
Cited by 53 (14 self)
- Add to MetaCart
Emerging large-scale distributed storage systems are faced with the task of distributing petabytes of data among tens or hundreds of thousands of storage devices. Such systems must evenly distribute data and workload to efficiently utilize available resources and maximize system performance, while facilitating system growth and managing hardware failures. We have developed CRUSH, a scalable pseudorandom data distribution function designed for distributed object-based storage systems that efficiently maps data objects to storage devices without relying on a central directory. Because large systems are inherently dynamic, CRUSH is designed to facilitate the addition and removal of storage while minimizing unnecessary data movement. The algorithm accommodates a wide variety of data replication and reliability mechanisms and distributes data in terms of userdefined policies that enforce separation of replicas across failure domains.
Blobseer: Next-generation data management for large scale infrastructures
- J. Parallel Distrib. Comput
, 2011
"... As data volumes increase at a high speed in more and more application fields of science, engineering, information services, etc., the challenges posed by data-intensive computing gain an increasing importance. The emergence of highly scalable infrastructures, e.g. for cloud computing and for petasca ..."
Abstract
-
Cited by 47 (22 self)
- Add to MetaCart
(Show Context)
As data volumes increase at a high speed in more and more application fields of science, engineering, information services, etc., the challenges posed by data-intensive computing gain an increasing importance. The emergence of highly scalable infrastructures, e.g. for cloud computing and for petascale computing and beyond introduces additional issues for which scalable data management becomes an immediate need. This paper brings several contributions. First, it proposes a set of principles for designing highly scalable distributed storage systems that are optimized for heavy data access concurrency. In particular, we highlight the potentially large benefits of using versioning in this context. Second, based on these principles, we propose a set of versioning algorithms, both for data and metadata, that enable a high throughput under concurrency. Finally, we implement and evaluate these algorithms in the BlobSeer prototype, that we integrate as a storage backend in the Hadoop MapReduce framework. We perform extensive microbenchmarks as well as experiments with real MapReduce applications: they demonstrate that applying the principles defended in our approach brings substantial benefits to data intensive applications.
W.: I/o performance challenges at leadership scale
- In Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis (New
, 2009
"... Today’s top high performance computing systems run ap-plications with hundreds of thousands of processes, contain hundreds of storage nodes, and must meet massive I/O re-quirements for capacity and performance. These leadership-class systems face daunting challenges to deploying scalable I/O systems ..."
Abstract
-
Cited by 39 (10 self)
- Add to MetaCart
(Show Context)
Today’s top high performance computing systems run ap-plications with hundreds of thousands of processes, contain hundreds of storage nodes, and must meet massive I/O re-quirements for capacity and performance. These leadership-class systems face daunting challenges to deploying scalable I/O systems. In this paper we present a case study of the I/O challenges to performance and scalability on Intrepid, the IBM Blue Gene/P system at the Argonne Leadership Computing Facility. Listed in the top 5 fastest supercomput-ers of 2008, Intrepid runs computational science applications with intensive demands on the I/O system. We show that Intrepid’s file and storage system sustain high performance under varying workloads as the applications scale with the number of processes. 1.
