Results 1 - 10
of
725
Pregel: A system for large-scale graph processing
- IN SIGMOD
, 2010
"... Many practical computing problems concern large graphs. Standard examples include the Web graph and various social networks. The scale of these graphs—in some cases billions of vertices, trillions of edges—poses challenges to their efficient processing. In this paper we present a computational model ..."
Abstract
-
Cited by 472 (0 self)
- Add to MetaCart
(Show Context)
Many practical computing problems concern large graphs. Standard examples include the Web graph and various social networks. The scale of these graphs—in some cases billions of vertices, trillions of edges—poses challenges to their efficient processing. In this paper we present a computational model suitable for this task. Programs are expressed as a sequence of iterations, in each of which a vertex can receive messages sent in the previous iteration, send messages to other vertices, and modify its own state and that of its outgoing edges or mutate graph topology. This vertex-centric approach is flexible enough to express a broad set of algorithms. The model has been designed for efficient, scalable and fault-tolerant implementation on clusters of thousands of commodity computers, and its implied synchronicity makes reasoning about programs easier. Distributionrelated details are hidden behind an abstract API. The result is a framework for processing large graphs that is expressive and easy to program.
DryadLINQ: A System for General-Purpose Distributed Data-Parallel Computing Using a High-Level Language
"... DryadLINQ is a system and a set of language extensions that enable a new programming model for large scale distributed computing. It generalizes previous execution environments such as SQL, MapReduce, and Dryad in two ways: by adopting an expressive data model of strongly typed.NET objects; and by s ..."
Abstract
-
Cited by 264 (27 self)
- Add to MetaCart
(Show Context)
DryadLINQ is a system and a set of language extensions that enable a new programming model for large scale distributed computing. It generalizes previous execution environments such as SQL, MapReduce, and Dryad in two ways: by adopting an expressive data model of strongly typed.NET objects; and by supporting general-purpose imperative and declarative operations on datasets within a traditional high-level programming language. A DryadLINQ program is a sequential program composed of LINQ expressions performing arbitrary sideeffect-free transformations on datasets, and can be written and debugged using standard.NET development tools. The DryadLINQ system automatically and transparently translates the data-parallel portions of the program into a distributed execution plan which is passed to the Dryad execution platform. Dryad, which has been in continuous operation for several years on production clusters made up of thousands of computers, ensures efficient, reliable execution of this plan. We describe the implementation of the DryadLINQ compiler and runtime. We evaluate DryadLINQ on a varied set of programs drawn from domains such as web-graph analysis, large-scale log mining, and machine learning. We show that excellent absolute performance can be attained—a general-purpose sort of 1012 Bytes of data executes in 319 seconds on a 240-computer, 960disk cluster—as well as demonstrating near-linear scaling of execution time on representative applications as we vary the number of computers used for a job. 1
A comparison of approaches to large-scale data analysis
- In SIGMOD ’09: Proceedings of the 35th SIGMOD international conference on Management of data
, 2009
"... There is currently considerable enthusiasm around the MapReduce (MR) paradigm for large-scale data analysis [17]. Although the basic control flow of this framework has existed in parallel SQL database management systems (DBMS) for over 20 years, some have called MR a dramatically new computing model ..."
Abstract
-
Cited by 246 (7 self)
- Add to MetaCart
(Show Context)
There is currently considerable enthusiasm around the MapReduce (MR) paradigm for large-scale data analysis [17]. Although the basic control flow of this framework has existed in parallel SQL database management systems (DBMS) for over 20 years, some have called MR a dramatically new computing model [8, 17]. In this paper, we describe and compare both paradigms. Furthermore, we evaluate both kinds of systems in terms of performance and development complexity. To this end, we define a benchmark consisting of a collection of tasks that we have run on an open source version of MR as well as on two parallel DBMSs. For each task, we measure each system’s performance for various degrees of parallelism on a cluster of 100 nodes. Our results reveal some interesting trade-offs. Although the process to load data into and tune the execution of parallel DBMSs took much longer than the MR system, the observed performance of these DBMSs was strikingly better. We speculate about the causes of the dramatic performance difference and consider implementation concepts that future systems should take from both kinds of architectures.
BCube: A High Performance, Server-centric Network Architecture for Modular Data Centers
- In SIGCOMM
, 2009
"... This paper presents BCube, a new network architecture specifically designed for shipping-container based, modular data centers. At the core of the BCube architecture is its server-centric network structure, where servers with multiple network ports connect to multiple layers of COTS (commodity off-t ..."
Abstract
-
Cited by 238 (29 self)
- Add to MetaCart
(Show Context)
This paper presents BCube, a new network architecture specifically designed for shipping-container based, modular data centers. At the core of the BCube architecture is its server-centric network structure, where servers with multiple network ports connect to multiple layers of COTS (commodity off-the-shelf) mini-switches. Servers act as not only end hosts, but also relay nodes for each other. BCube supports various bandwidth-intensive applications by speedingup one-to-one, one-to-several, and one-to-all traffic patterns, and by providing high network capacity for all-to-all traffic. BCube exhibits graceful performance degradation as the server and/or switch failure rate increases. This property is of special importance for shipping-container data centers, since once the container is sealed and operational, it becomes very difficult to repair or replace its components. Our implementation experiences show that BCube can be seamlessly integrated with the TCP/IP protocol stack and BCube packet forwarding can be efficiently implemented in both hardware and software. Experiments in our testbed demonstrate that BCube is fault tolerant and load balancing and it significantly accelerates representative bandwidthintensive applications.
Hedera: Dynamic flow scheduling for data center networks
- In Proc. of Networked Systems Design and Implementation (NSDI) Symposium
, 2010
"... Today’s data centers offer tremendous aggregate bandwidth to clusters of tens of thousands of machines. However, because of limited port densities in even the highest-end switches, data center topologies typically consist of multi-rooted trees with many equal-cost paths between any given pair of hos ..."
Abstract
-
Cited by 216 (7 self)
- Add to MetaCart
(Show Context)
Today’s data centers offer tremendous aggregate bandwidth to clusters of tens of thousands of machines. However, because of limited port densities in even the highest-end switches, data center topologies typically consist of multi-rooted trees with many equal-cost paths between any given pair of hosts. Existing IP multipathing protocols usually rely on per-flow static hashing and can cause substantial bandwidth losses due to longterm collisions. In this paper, we present Hedera, a scalable, dynamic flow scheduling system that adaptively schedules a multi-stage switching fabric to efficiently utilize aggregate network resources. We describe our implementation using commodity switches and unmodified hosts, and show that for a simulated 8,192 host data center, Hedera delivers bisection bandwidth that is 96 % of optimal and up to 113 % better than static load-balancing methods. 1
The Multikernel: A new OS architecture for scalable multicore systems
, 2009
"... Commodity computer systems contain more and more processor cores and exhibit increasingly diverse architectural tradeoffs, including memory hierarchies, interconnects, instruction sets and variants, and IO configurations. Previous high-performance computing systems have scaled in specific cases, but ..."
Abstract
-
Cited by 206 (20 self)
- Add to MetaCart
Commodity computer systems contain more and more processor cores and exhibit increasingly diverse architectural tradeoffs, including memory hierarchies, interconnects, instruction sets and variants, and IO configurations. Previous high-performance computing systems have scaled in specific cases, but the dynamic nature of modern client and server workloads, coupled with the impossibility of statically optimizing an OS for all workloads and hardware variants pose serious challenges for operating system structures. We argue that the challenge of future multicore hardware is best met by embracing the networked nature of the machine, rethinking OS architecture using ideas from distributed systems. We investigate a new OS structure, the multikernel, that treats the machine as a network of independent cores, assumes no inter-core sharing at the lowest level, and moves traditional OS functionality to a distributed system of processes that communicate via message-passing. We have implemented a multikernel OS to show that the approach is promising, and we describe how traditional scalability problems for operating systems (such as memory management) can be effectively recast using messages and can exploit insights from distributed systems and networking. An evaluation of our prototype on multicore systems shows that, even on present-day machines, the performance of a multikernel is comparable with a conventional OS, and can scale better to support future hardware.
Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing
, 2011
"... We present Resilient Distributed Datasets (RDDs), a distributed memory abstraction that lets programmers perform in-memory computations on large clusters in a fault-tolerant manner. RDDs are motivated by two types of applications that current computing frameworks handle inefficiently: iterative algo ..."
Abstract
-
Cited by 200 (24 self)
- Add to MetaCart
(Show Context)
We present Resilient Distributed Datasets (RDDs), a distributed memory abstraction that lets programmers perform in-memory computations on large clusters in a fault-tolerant manner. RDDs are motivated by two types of applications that current computing frameworks handle inefficiently: iterative algorithms and interactive data mining tools. In both cases, keeping data in memory can improve performance by an order of magnitude. To achieve fault tolerance efficiently, RDDs provide a restricted form of shared memory, based on coarsegrained transformations rather than fine-grained updates to shared state. However, we show that RDDs are expressive enough to capture a wide class of computations, including recent specialized programming models for iterative jobs, such as Pregel, and new applications that these models do not capture. We have implemented RDDs in a system called Spark, which we evaluate through a variety of user applications and benchmarks. 1
SCOPE: Easy and Efficient Parallel Processing of Massive Data Sets
"... Companies providing cloud-scale services have an increasing need to store and analyze massive data sets such as search logs and click streams. For cost and performance reasons, processing is typically done on large clusters of shared-nothing commodity machines. It is imperative to develop a programm ..."
Abstract
-
Cited by 192 (9 self)
- Add to MetaCart
(Show Context)
Companies providing cloud-scale services have an increasing need to store and analyze massive data sets such as search logs and click streams. For cost and performance reasons, processing is typically done on large clusters of shared-nothing commodity machines. It is imperative to develop a programming model that hides the complexity of the underlying system but provides flexibility by allowing users to extend functionality to meet a variety of requirements. In this paper, we present a new declarative and extensible scripting language, SCOPE (Structured Computations Optimized for Parallel Execution), targeted for this type of massive data analysis. The language is designed for ease of use with no explicit parallelism, while being amenable to efficient parallel execution on large clusters. SCOPE borrows several features from SQL. Data is modeled as sets of rows composed of typed columns. The select statement is retained with inner joins, outer joins, and aggregation allowed. Users can easily define their own functions and implement their own versions of operators: extractors (parsing and constructing rows from a file), processors (row-wise processing), reducers (group-wise processing), and combiners (combining rows from two inputs). SCOPE supports nesting of expressions but also allows a computation to be specified as a series of steps, in a manner often preferred by programmers. We also describe how scripts are compiled into efficient, parallel execution plans and executed on large clusters. 1.
Spark: Cluster Computing with Working Sets
"... MapReduce and its variants have been highly successful in implementing large-scale data-intensive applications on commodity clusters. However, most of these systems are built around an acyclic data flow model that is not suitable for other popular applications. This paper focuses on one such class o ..."
Abstract
-
Cited by 191 (8 self)
- Add to MetaCart
(Show Context)
MapReduce and its variants have been highly successful in implementing large-scale data-intensive applications on commodity clusters. However, most of these systems are built around an acyclic data flow model that is not suitable for other popular applications. This paper focuses on one such class of applications: those that reuse a working set of data across multiple parallel operations. This includes many iterative machine learning algorithms, as well as interactive data analysis tools. We propose a new framework called Spark that supports these applications while retaining the scalability and fault tolerance of MapReduce. To achieve these goals, Spark introduces an abstraction called resilient distributed datasets (RDDs). An RDD is a read-only collection of objects partitioned across a set of machines that can be rebuilt if a partition is lost. Spark can outperform Hadoop by 10x in iterative machine learning jobs, and can be used to interactively query a 39 GB dataset with sub-second response time. 1
Delay Scheduling: A Simple Technique for Achieving Locality and Fairness in Cluster Scheduling
- In Proc. EuroSys
, 2010
"... As organizations start to use data-intensive cluster computing systems like Hadoop and Dryad for more applications, there is a growing need to share clusters between users. However, there is a conflict between fairness in scheduling and data locality (placing tasks on nodes that contain their input ..."
Abstract
-
Cited by 190 (21 self)
- Add to MetaCart
(Show Context)
As organizations start to use data-intensive cluster computing systems like Hadoop and Dryad for more applications, there is a growing need to share clusters between users. However, there is a conflict between fairness in scheduling and data locality (placing tasks on nodes that contain their input data). We illustrate this problem through our experience designing a fair scheduler for a 600-node Hadoop cluster at Facebook. To address the conflict between locality and fairness, we propose a simple algorithm called delay scheduling: when the job that should be scheduled next according to fairness cannot launch a local task, it waits for a small amount of time, letting other jobs launch tasks instead. We find that delay scheduling achieves nearly optimal data locality in a variety of workloads and can increase throughput by up to 2x while preserving fairness. In addition, the simplicity of delay scheduling makes it applicable under a wide variety of scheduling policies beyond fair sharing.
