The Google file system
19 Oct 2003-Vol. 37, Iss: 5, pp 29-43
TL;DR: This paper presents file system interface extensions designed to support distributed applications, discusses many aspects of the design, and reports measurements from both micro-benchmarks and real world use.
Abstract: We have designed and implemented the Google File System, a scalable distributed file system for large distributed data-intensive applications. It provides fault tolerance while running on inexpensive commodity hardware, and it delivers high aggregate performance to a large number of clients. While sharing many of the same goals as previous distributed file systems, our design has been driven by observations of our application workloads and technological environment, both current and anticipated, that reflect a marked departure from some earlier file system assumptions. This has led us to reexamine traditional choices and explore radically different design points. The file system has successfully met our storage needs. It is widely deployed within Google as the storage platform for the generation and processing of data used by our service as well as research and development efforts that require large data sets. The largest cluster to date provides hundreds of terabytes of storage across thousands of disks on over a thousand machines, and it is concurrently accessed by hundreds of clients. In this paper, we present file system interface extensions designed to support distributed applications, discuss many aspects of our design, and report measurements from both micro-benchmarks and real world use.
Citations
More filters
06 Dec 2004
TL;DR: This paper presents the implementation of MapReduce, a programming model and an associated implementation for processing and generating large data sets that runs on a large cluster of commodity machines and is highly scalable.
Abstract: MapReduce is a programming model and an associated implementation for processing and generating large data sets. Users specify a map function that processes a key/value pair to generate a set of intermediate key/value pairs, and a reduce function that merges all intermediate values associated with the same intermediate key. Many real world tasks are expressible in this model, as shown in the paper.
Programs written in this functional style are automatically parallelized and executed on a large cluster of commodity machines. The run-time system takes care of the details of partitioning the input data, scheduling the program's execution across a set of machines, handling machine failures, and managing the required inter-machine communication. This allows programmers without any experience with parallel and distributed systems to easily utilize the resources of a large distributed system.
Our implementation of MapReduce runs on a large cluster of commodity machines and is highly scalable: a typical MapReduce computation processes many terabytes of data on thousands of machines. Programmers find the system easy to use: hundreds of MapReduce programs have been implemented and upwards of one thousand MapReduce jobs are executed on Google's clusters every day.
20,309 citations
TL;DR: This presentation explains how the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks.
Abstract: MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real-world tasks. Users specify the computation in terms of a map and a reduce function, and the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks. Programmers find the system easy to use: more than ten thousand distinct MapReduce programs have been implemented internally at Google over the past four years, and an average of one hundred thousand MapReduce jobs are executed on Google's clusters every day, processing a total of more than twenty petabytes of data per day.
17,663 citations
Book•
23 May 2011TL;DR: It is argued that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas.
Abstract: Many problems of recent interest in statistics and machine learning can be posed in the framework of convex optimization. Due to the explosion in size and complexity of modern datasets, it is increasingly important to be able to solve problems with a very large number of features or training examples. As a result, both the decentralized collection or storage of these datasets as well as accompanying distributed solution methods are either necessary or at least highly desirable. In this review, we argue that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas. The method was developed in the 1970s, with roots in the 1950s, and is equivalent or closely related to many other algorithms, such as dual decomposition, the method of multipliers, Douglas–Rachford splitting, Spingarn's method of partial inverses, Dykstra's alternating projections, Bregman iterative algorithms for l1 problems, proximal methods, and others. After briefly surveying the theory and history of the algorithm, we discuss applications to a wide variety of statistical and machine learning problems of recent interest, including the lasso, sparse logistic regression, basis pursuit, covariance selection, support vector machines, and many others. We also discuss general distributed optimization, extensions to the nonconvex setting, and efficient implementation, including some details on distributed MPI and Hadoop MapReduce implementations.
17,433 citations
Journal Article•
TL;DR: This work focuses on SaaS Providers (Cloud Users) and Cloud Providers, which have received less attention than SAAS Users, and uses the term Private Cloud to refer to internal datacenters of a business or other organization, not made available to the general public.
Abstract: Cloud Computing, the long-held dream of computing as a utility, has the potential to transform a large part of the IT industry, making software even more attractive as a service and shaping the way IT hardware is designed and purchased. Developers with innovative ideas for new Internet services no longer require the large capital outlays in hardware to deploy their service or the human expense to operate it. They need not be concerned about overprovisioning for a service whose popularity does not meet their predictions, thus wasting costly resources, or underprovisioning for one that becomes wildly popular, thus missing potential customers and revenue. Moreover, companies with large batch-oriented tasks can get results as quickly as their programs can scale, since using 1000 servers for one hour costs no more than using one server for 1000 hours. This elasticity of resources, without paying a premium for large scale, is unprecedented in the history of IT. Cloud Computing refers to both the applications delivered as services over the Internet and the hardware and systems software in the datacenters that provide those services. The services themselves have long been referred to as Software as a Service (SaaS). The datacenter hardware and software is what we will call a Cloud. When a Cloud is made available in a pay-as-you-go manner to the general public, we call it a Public Cloud; the service being sold is Utility Computing. We use the term Private Cloud to refer to internal datacenters of a business or other organization, not made available to the general public. Thus, Cloud Computing is the sum of SaaS and Utility Computing, but does not include Private Clouds. People can be users or providers of SaaS, or users or providers of Utility Computing. We focus on SaaS Providers (Cloud Users) and Cloud Providers, which have received less attention than SaaS Users. From a hardware point of view, three aspects are new in Cloud Computing.
6,590 citations
Cites background from "The Google file system"
...However, because of the phenomenal growth of Web services through the early 2000’s, many large Internet companies, including Amazon, eBay, Google, Microsoft and others, were already doing so. Equally important, these companies also had to develop scalable software infrastructure (such as MapReduce, the Google File System, BigTable, and Dynamo [16, 20 , 14, 17]) and the operational expertise to armor their datacenters against potential ......
[...]
TL;DR: Google Earth Engine is a cloud-based platform for planetary-scale geospatial analysis that brings Google's massive computational capabilities to bear on a variety of high-impact societal issues including deforestation, drought, disaster, disease, food security, water management, climate monitoring and environmental protection.
6,262 citations
References
More filters
01 Jun 1988
TL;DR: Five levels of RAIDs are introduced, giving their relative cost/performance, and a comparison to an IBM 3380 and a Fujitsu Super Eagle is compared.
Abstract: Increasing performance of CPUs and memories will be squandered if not matched by a similar performance increase in I/O. While the capacity of Single Large Expensive Disks (SLED) has grown rapidly, the performance improvement of SLED has been modest. Redundant Arrays of Inexpensive Disks (RAID), based on the magnetic disk technology developed for personal computers, offers an attractive alternative to SLED, promising improvements of an order of magnitude in performance, reliability, power consumption, and scalability. This paper introduces five levels of RAIDs, giving their relative cost/performance, and compares RAID to an IBM 3380 and a Fujitsu Super Eagle.
3,015 citations
Additional excerpts
...As disks are relatively cheap and replication is simpler than more sophisticated RAID [9] approaches, GFS currently uses only replication for redundancy and so consumes more raw storage than xFS or Swift....
[...]
...As disks are relatively cheap and replication is simpler than more sophisticated RAID [9] approaches, GFS currently uses only replication for redundancy and so consumes more raw storage than xFS or Swift....
[...]
...A case for redundant arrays of inexpensive disks (RAID)....
[...]
TL;DR: Observations of a prototype implementation are presented, changes in the areas of cache validation, server process structure, name translation, and low-level storage representation are motivated, and Andrews ability to scale gracefully is quantitatively demonstrated.
Abstract: The Andrew File System is a location-transparent distributed tile system that will eventually span more than 5000 workstations at Carnegie Mellon University. Large scale affects performance and complicates system operation. In this paper we present observations of a prototype implementation, motivate changes in the areas of cache validation, server process structure, name translation, and low-level storage representation, and quantitatively demonstrate Andrews ability to scale gracefully. We establish the importance of whole-file transfer and caching in Andrew by comparing its performance with that of Sun Microsystems NFS tile system. We also show how the aggregation of files into volumes improves the operability of the system.
1,604 citations
Proceedings Article•
IBM1
TL;DR: GPFS is IBM's parallel, shared-disk file system for cluster computers, available on the RS/6000 SP parallel supercomputer and on Linux clusters, and discusses how distributed locking and recovery techniques were extended to scale to large clusters.
Abstract: GPFS is IBM's parallel, shared-disk file system for cluster computers, available on the RS/6000 SP parallel supercomputer and on Linux clusters. GPFS is used on many of the largest supercomputers in the world. GPFS was built on many of the ideas that were developed in the academic community over the last several years, particularly distributed locking and recovery technology. To date it has been a matter of conjecture how well these ideas scale. We have had the opportunity to test those limits in the context of a product that runs on the largest systems in existence. While in many cases existing ideas scaled well, new approaches were necessary in many key areas. This paper describes GPFS, and discusses how distributed locking and recovery techniques were extended to scale to large clusters.
1,434 citations
"The Google file system" refers methods in this paper
...GPFS: A shared-disk.le system for large computing clusters....
[...]
...Some distributed file systems like Frangipani, xFS, Minnesota’s GFS[11] and GPFS [10] remove the centralized server and rely on distributed algorithms for consistency and man-...
[...]
...Some distributed .le systems like Frangipani, xFS, Minnesota s GFS[11] and GPFS [10] remove the centralized server and rely on distributed algorithms for consistency and management....
[...]
TL;DR: It is found that most people use few search terms, few modified queries, view few Web pages, and rarely use advanced search features, and the language of Web queries is distinctive.
Abstract: In studying actual Web searching by the public at large, we analyzed over one million Web queries by users of the Excite search engine. We found that most people use few search terms, few modified queries, view few Web pages, and rarely use advanced search features. A small number of search terms are used with high frequency, and a great many terms are unique; the language of Web queries is distinctive. Queries about recreation and entertainment rank highest. Findings are compared to data from two other large studies of Web queries. This study provides an insight into the public practices and choices in Web searching.
1,153 citations
TL;DR: Googless architecture features clusters of more than 15,000 commodity-class PCs with fault tolerant software that achieves superior performance at a fraction of the cost of a system built from fewer, but more expensive, high-end servers.
Abstract: Amenable to extensive parallelization, Google's web search application lets different queries run on different processors and, by partitioning the overall index, also lets a single query use multiple processors. to handle this workload, Googless architecture features clusters of more than 15,000 commodity-class PCs with fault tolerant software. This architecture achieves superior performance at a fraction of the cost of a system built from fewer, but more expensive, high-end servers.
1,129 citations