It is cost-efficient for a tenant with a limited budget to establish a virtual MapReduce cluster by renting multiple virtual private servers (VPSs) from a VPS provider. To provide an appropriate scheduling scheme for this type of computing environment, we propose in this paper a hybrid job-driven scheduling scheme (JoSS for short) from a tenant's perspective. JoSS provides not only job level scheduling, but also map-task level scheduling and reduce-task level scheduling. JoSS classifies MapReduce jobs based on job scale and job type and designs an appropriate scheduling policy to schedule each class of jobs. The goal is to improve data locality for both map tasks and reduce tasks, avoid job starvation, and improve job execution performance. Two variations of JoSS are further introduced to separately achieve a better map-data locality and a faster task assignment. We conduct extensive experiments to evaluate and compare the two variations with current scheduling algorithms supported by Hadoop. The results show that the two variations outperform the other tested algorithms in terms of map-data locality, reduce-data locality, and network overhead without incurring significant overhead. In addition, the two variations are separately suitable for different MapReduce-workload scenarios and provide the best job performance among all tested algorithms.
MapReduce is emerged as a prominent programming model for data-intensive computation. In this work, we study power-aware MapReduce scheduling in the speed scaling setting first introduced by Yao et al. [FOCS 1995]. We focus on the minimization of the total weighted completion time of a set of MapReduce jobs under a given budget of energy. Using a linear programming relaxation of our problem, we derive a polynomial time constant-factor approximation algorithm. We also propose a convex programming formulation that we combine with standard list scheduling policies, and we evaluate their performan…
Job scheduling for a MapReduce cluster has been an active research topic in recent years. However, measurement traces from real-world production environment show that the duration of tasks within a job vary widely. The overall elapsed time of a job, i.e. the so-called flowtime, is often dictated by one or few slowly-running tasks within a job, generally referred as the "stragglers". The cause of stragglers include tasks running on partially/intermittently failing machines or the existence of some localized resource bottleneck(s) within a MapReduce cluster. To tackle this online job scheduling …
MapReduce is a popular parallel computing paradigm for Big Data processing in clusters and data centers. It is observed that different job execution orders and MapReduce slot configurations for a MapReduce workload have significantly different performance with regarding to the makespan, total completion time, system utilization and other performance metrics. There are quite a few algorithms on minimizing makespan of multiple MapReduce jobs. However, these algorithms are heuristic or suboptimal. The best known algorithm for minimizing the makespan is 3-approximation by applying Johnson rule. In…
The efficiency of MapReduce is closely related to its load balance. Existing works on MapReduce load balance focus on coarse-grained scheduling. This study concerns fine-grained scheduling on MapReduce operations, with each operation representing one invocation of the Map or Reduce function. By default, MapReduce adopts the hash-based method to schedule Reduce operations, which often leads to poor load balance. In addition, the copy phase of Reduce tasks overlaps with Map tasks, which significantly hinders the progress of Map tasks due to I/O contention. Moreover, the three phases of Reduce ta…
Hadoop MapReduce is now a popular choice for performing large-scale data analytics. This technical report describes a detailed set of mathematical performance models for describing the execution of a MapReduce job on Hadoop. The models describe dataflow and cost information at the fine granularity of phases within the map and reduce tasks of a job execution. The models can be used to estimate the performance of MapReduce jobs as well as to find the optimal configuration settings to use when running the jobs.
K-means is a popular clustering method used in data mining area. To work with large datasets, researchers propose PKMeans, which is a parallel k-means on MapReduce. However, the existing k-means parallelization methods including PKMeans have many limitations. PKMeans can't finish all its iterations in one MapReduce job, so it has to repeat cascading MapReduce jobs in a loop until convergence. On the most popular MapReduce platform, Hadoop, every MapReduce job introduces significant I/O overheads and extra execution time at stages of job start-up and shuffling. Even worse, it has been proved th…
Cloud Computing is emerging as a new computational paradigm shift. Hadoop-MapReduce has become a powerful Computation Model for processing large data on distributed commodity hardware clusters such as Clouds. In all Hadoop implementations, the default FIFO scheduler is available where jobs are scheduled in FIFO order with support for other priority based schedulers also. In this paper we study various scheduler improvements possible with Hadoop and also provided some guidelines on how to improve the scheduling in Hadoop in Cloud Environments.
Undoubtedly, the MapReduce is the most powerful programming paradigm in distributed computing. The enhancement of the MapReduce is essential and it can lead the computing faster. Therefore, here are many scheduling algorithms to discuss based on their characteristics. Moreover, there are many shortcoming to discover in this field. In this article, we present the state-of-the-art scheduling algorithm to enhance the understanding of the algorithms. The algorithms are presented systematically such that there can be many future possibilities in scheduling algorithm through this article. In this pa…
Load balance is important for MapReduce to reduce job duration, increase parallel efficiency, etc. Previous work focuses on coarse-grained scheduling. This study concerns fine-grained scheduling on MapReduce operations. Each operation represents one invocation of the Map or Reduce function. Scheduling MapReduce operations is difficult due to highly screwed operation loads, no support to collect workload statistics, and high complexity of the scheduling problem. So current implementations adopt simple strategies, leading to poor load balance. To address these difficulties, we design an algorith…
Nowadays, a computing cluster in a typical data center can easily consist of hundreds of thousands of commodity servers, making component/ machine failures the norm rather than exception. A parallel processing job can be delayed substantially as long as one of its many tasks is being assigned to a failing machine. To tackle this so-called straggler problem, most parallel processing frameworks such as MapReduce have adopted various strategies under which the system may speculatively launch additional copies of the same task if its progress is abnormally slow or simply because extra idling resou…
MapReduce has become a popular programming model for running data intensive applications on the cloud. Completion time goals or deadlines of MapReduce jobs set by users are becoming crucial in existing cloud-based data processing environments like Hadoop. There is a conflict between the scheduling MR jobs to meet deadlines and "data locality" (assigning tasks to nodes that contain their input data). To meet the deadline a task may be scheduled on a node without local input data for that task causing expensive data transfer from a remote node. In this paper, a novel scheduler is proposed to add…
Cloud infrastructures enable the efficient parallel execution of data-intensive tasks such as entity resolution on large datasets. We investigate challenges and possible solutions of using the MapReduce programming model for parallel entity resolution. In particular, we propose and evaluate two MapReduce-based implementations for Sorted Neighborhood blocking that either use multiple MapReduce jobs or apply a tailored data replication.
We propose constant approximation algorithms for generalizations of the Flexible Flow Shop (FFS) problem which form a realistic model for non-preemptive scheduling in MapReduce systems. Our results concern the minimization of the total weighted completion time of a set of MapReduce jobs on unrelated processors and improve substantially on the model proposed by Moseley et al. (SPAA 2011) in two directions. First, we consider each job consisting of multiple Map and Reduce tasks, as this is the key idea behind MapReduce computations, and we propose a constant approximation algorithm. Then, we int…
In this paper we describe our work on designing a web based, distributed data analysis system based on the popular MapReduce framework deployed on a small cloud; developed specifically for analyzing web server logs. The log analysis system consists of several cluster nodes, it splits the large log files on a distributed file system and quickly processes them using MapReduce programming model. The cluster is created using an open source cloud infrastructure, which allows us to easily expand the computational power by adding new nodes. This gives us the ability to automatically resize the cluste…
We present the Hadoop Fair Sojourn Protocol (HFSP) scheduler, which implements a size-based scheduling discipline for Hadoop. The benefits of size-based scheduling disciplines are well recognized in a variety of contexts (computer networks, operating systems, etc...), yet, their practical implementation for a system such as Hadoop raises a number of important challenges. With HFSP, which is available as an open-source project, we address issues related to job size estimation, resource management and study the effects of a variety of preemption strategies. Although the architecture underlying H…
Recently, businesses have started using MapReduce as a popular computation framework for processing large amount of data, such as spam detection, and different data mining tasks, in both public and private clouds. Two of the challenging questions in such environments are (1) choosing suitable values for MapReduce configuration parameters e.g., number of mappers, number of reducers, and DFS block size, and (2) predicting the amount of resources that a user should lease from the service provider. Currently, the tasks of both choosing configuration parameters and estimating required resources are…
Recently, businesses have started using MapReduce as a popular computation framework for processing large amount of data, such as spam detection, and different data mining tasks, in both public and private clouds. Two of the challenging questions in such environments are (1) choosing suitable values for MapReduce configuration parameters -e.g., number of mappers, number of reducers, and DFS block size-, and (2) predicting the amount of resources that a user should lease from the service provider. Currently, the tasks of both choosing configuration parameters and estimating required resources a…
The effectiveness and scalability of MapReduce-based implementations of complex data-intensive tasks depend on an even redistribution of data between map and reduce tasks. In the presence of skewed data, sophisticated redistribution approaches thus become necessary to achieve load balancing among all reduce tasks to be executed in parallel. For the complex problem of entity resolution, we propose and evaluate two approaches for such skew handling and load balancing. The approaches support blocking techniques to reduce the search space of entity resolution, utilize a preprocessing MapReduce job…
One of the hot problems in grid computing is job scheduling. It is known that the job scheduling is NP-complete, and thus the use of heuristics is the de facto approach to deal with this practice in its difficulty. The proposed is an imagination to fish swarm, job dispatcher and Visualization gridsim to execute some jobs.
The ever-growing processing power of supercomputers in recent decades enables us to explore increasing complex scientific problems. Effective scheduling these jobs is crucial for individual job performance and system efficiency. The traditional job schedulers in high performance computing (HPC) are simple and concentrate on improving CPU utilization. The emergence of new hardware resources and novel hardware structure impose severe challenges on traditional schedulers. The increasing diverse workloads, including compute-intensive and data-intensive applications, require more efficient schedule…
Diverse workloads such as interactive supercomputing, big data analysis, and large-scale AI algorithm development, requires a high-performance scheduler. This paper presents a novel node-based scheduling approach for large scale simulations of short running jobs on MIT SuperCloud systems, that allows the resources to be fully utilized for both long running batch jobs while simultaneously providing fast launch and release of large-scale short running jobs. The node-based scheduling approach has demonstrated up to 100 times faster scheduler performance that other state-of-the-art systems.
The use of meta-schedulers for resource management in large-scale distributed systems often leads to a hierarchy of schedulers. In this paper, we discuss why existing meta-scheduling hierarchies are sometimes not sufficient for Grid systems due to their inability to re-organise jobs already scheduled locally. Such a job re-organisation is required to adapt to evolving loads which are common in heavily used Grid infrastructures. We propose a peer-to-peer scheduling model and evaluate it using case studies and mathematical modelling. We detail the DIANA (Data Intensive and Network Aware) schedul…
Grid computing is the recently growing area of computing that share data, storage, computing across geographically dispersed area. This paper proposes a novel fuzzy approach using Differential Evolution (DE) for scheduling jobs on computational grids. The fuzzy based DE generates an optimal plan to complete the jobs within a minimum period of time. We evaluate the performance of the proposed fuzzy based DE algorithm with Genetic Algorithm (GA), Simulated Annealing (SA), Differential Evolution and fuzzy PSO. Experimental results have shown that the new algorithm produces more optimal solutions …
High-performance computing (HPC) is undergoing significant changes. Next generation HPC systems are equipped with diverse global and local resources, such as I/O burst buffer resources, memory resources (e.g., on-chip and off-chip RAM, external RAM/NVRA), network resources, and possibly other resources. Job schedulers play a crucial role in efficient use of resources. However, traditional job schedulers are single-objective and fail to efficient use of other resources. In this paper, we propose ROME, a novel multi-dimensional job scheduling framework to explore potential tradeoffs among multip…
Huge amounts of data being generated continuously by digitally interconnected systems of humans, organizations and machines. Data comes in variety of formats including structured, unstructured and semi-structured, what makes it impossible to apply the same standard approaches, techniques and algorithms to manage and process this data. Fortunately, the enterprise level distributed platform named Hadoop Ecosystem exists. This paper explores Apache Hive component that provides full stack data managements functionality in terms of Data Definition, Data Manipulation and Data Processing. Hive is a d…
Many big data algorithms executed on MapReduce-like systems have a shuffle phase that often dominates the overall job execution time. Recent work has demonstrated schemes where the communication load in the shuffle phase can be traded off for the computation load in the map phase. In this work, we focus on a class of distributed algorithms, broadly used in deep learning, where intermediate computations of the same task can be combined. Even though prior techniques reduce the communication load significantly, they require a number of jobs that grows exponentially in the system parameters. This …
We propose throughput and cost optimal job scheduling algorithms in cloud computing platforms offering Infrastructure as a Service. We first consider online migration and propose job scheduling algorithms to minimize job migration and server running costs. We consider algorithms that assume knowledge of job-size on arrival of jobs. We characterize the optimal cost subject to system stability. We develop a drift-plus-penalty framework based algorithm that can achieve optimal cost arbitrarily closely. Specifically this algorithm yields a trade-off between delay and costs. We then relax the job-s…
MapReduce is a widely used framework for distributed computing. Data shuffling between the Map phase and Reduce phase of a job involves a large amount of data transfer across servers, which in turn accounts for increase in job completion time. Recently, Coded MapReduce has been proposed to offer savings with respect to the communication cost incurred in data shuffling. This is achieved by creating coded multicast opportunities for shuffling through repeating Map tasks at multiple servers. We consider a server-rack architecture for MapReduce and in this architecture, propose to divide the total…
Nowadays many companies have available large amounts of raw, unstructured data. Among Big Data enabling technologies, a central place is held by the MapReduce framework and, in particular, by its open source implementation, Apache Hadoop. For cost effectiveness considerations, a common approach entails sharing server clusters among multiple users. The underlying infrastructure should provide every user with a fair share of computational resources, ensuring that Service Level Agreements (SLAs) are met and avoiding wastes. In this paper we consider two mathematical programming problems that mode…
With the rapidly growing demand of graph processing in the real scene, they have to efficiently handle massive concurrent jobs. Although existing work enable to efficiently handle single graph processing job, there are plenty of memory access redundancy caused by ignoring the characteristic of data access correlations. Motivated such an observation, we proposed two-level scheduling strategy in this paper, which enables to enhance the efficiency of data access and to accelerate the convergence speed of concurrent jobs. Firstly, correlations-aware job scheduling allows concurrent jobs to process…
In hadoop, the job scheduling is an independent module, users can design their own job scheduler based on their actual application requirements, thereby meet their specific business needs. Currently, hadoop has three schedulers: FIFO, computing capacity scheduling and fair scheduling policy, all of them are take task allocation strategy that considerate data locality simply. They neither support data locality well nor fully apply to all cases of jobs scheduling. In this paper, we took the concept of resources-prefetch into consideration, and proposed a job scheduling algorithm based on data lo…
In data-intensive applications data transfer is a primary cause of job execution delay. Data access time depends on bandwidth. The major bottleneck to supporting fast data access in Grids is the high latencies of Wide Area Networks and Internet. Effective scheduling can reduce the amount of data transferred across the internet by dispatching a job to where the needed data are present. Another solution is to use a data replication mechanism. Objective of dynamic replica strategies is reducing file access time which leads to reducing job runtime. In this paper we develop a job scheduling policy …
The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-the-art online cluster job schedulers use history-based learning, which uses past job execution information to estimate the runtime properties of newly arrived jobs. However, with fast-paced development in cluster technology (in both hardware and software) and changing user inputs, job runtime properties can change over time, which lead to inaccurate predictions. In this paper, we explore the potential and limitation of real-time learning of job runtime properties, by proactively…
Nowadays large-scale distributed machine learning systems have been deployed to support various analytics and intelligence services in IT firms. To train a large dataset and derive the prediction/inference model, e.g., a deep neural network, multiple workers are run in parallel to train partitions of the input dataset, and update shared model parameters. In a shared cluster handling multiple training jobs, a fundamental issue is how to efficiently schedule jobs and set the number of concurrent workers to run for each job, such that server resources are maximally utilized and model training can…
In job scheduling, the concept of malleability has been explored since many years ago. Research shows that malleability improves system performance, but its utilization in HPC never became widespread. The causes are the difficulty in developing malleable applications, and the lack of support and integration of the different layers of the HPC software stack. However, in the last years, malleability in job scheduling is becoming more critical because of the increasing complexity of hardware and workloads. In this context, using nodes in an exclusive mode is not always the most efficient solution…
For a cloud service provider, delivering optimal system performance while fulfilling Quality of Service (QoS) obligations is critical for maintaining a viably profitable business. This goal is often hard to attain given the irregular nature of cloud computing jobs. These jobs expect high QoS on an on-demand fashion, that is on random arrival. To optimize the response to such client demands, cloud service providers organize the cloud computing environment as a multi-tier architecture. Each tier executes its designated tasks and passes the job to the next tier; in a fashion similar, but not iden…
Despite the fact that size-based schedulers can give excellent results in terms of both average response times and fairness, data-intensive computing execution engines generally do not employ size-based schedulers, mainly because of the fact that job size is not known a priori. In this work, we perform a simulation-based analysis of the performance of size-based schedulers when they are employed with the workload of typical data-intensive schedules and with approximated size estimations. We show results that are very promising: even when size estimation is very imprecise, response times of siz…
Efficient scheduling of distributed deep learning (DL) jobs in large GPU clusters is crucial for resource efficiency and job performance. While server sharing among jobs improves resource utilization, interference among co-located DL jobs occurs due to resource contention. Interference-aware job placement has been studied, with white-box approaches based on explicit interference modeling and black-box schedulers with reinforcement learning. In today's clusters containing thousands of GPU servers, running a single scheduler to manage all arrival jobs in a timely and effective manner is challeng…
In a large-scale computing cluster, the job completions can be substantially delayed due to two sources of variability, namely, variability in the job size and that in the machine service capacity. To tackle this issue, existing works have proposed various scheduling algorithms which exploit redundancy wherein a job runs on multiple servers until the first completes. In this paper, we explore the impact of variability in the machine service capacity and adopt a rigorous analytical approach to design scheduling algorithms using redundancy and checkpointing. We design several online scheduling a…
The ever-increasing gap between compute and I/O performance in HPC platforms, together with the development of novel NVMe storage devices (NVRAM), led to the emergence of the burst buffer concept - an intermediate persistent storage layer logically positioned between random-access main memory and a parallel file system. Despite the development of real-world architectures as well as research concepts, resource and job management systems, such as Slurm, provide only marginal support for scheduling jobs with burst buffer requirements, in particular ignoring burst buffers when backfilling. We inve…
The current Cloud infrastructure services (IaaS) market employs a resource-based selling model: customers rent nodes from the provider and pay per-node per-unit-time. This selling model places the burden upon customers to predict their job resource requirements and durations. Inaccurate prediction by customers can result in over-provisioning of resources, or under-provisioning and poor job performance. Thanks to improved resource virtualization and multi-tenant performance isolation, as well as common frameworks for batch jobs, such as MapReduce, Cloud providers can predict job completion time…
We study the problem of scheduling jobs on fault-prone machines communicating via a shared channel, also known as multiple-access channel. We have $n$ arbitrary length jobs to be scheduled on $m$ identical machines, $f$ of which are prone to crashes by an adversary. A machine can inform other machines when a job is completed via the channel without collision detection. Performance is measured by the total number of available machine steps during the whole execution. Our goal is to study the impact of preemption (i.e., interrupting the execution of a job and resuming later in the same or differ…
MapReduce is a commonly used framework for executing data-intensive jobs on distributed server clusters. We introduce a variant implementation of MapReduce, namely "Coded MapReduce", to substantially reduce the inter-server communication load for the shuffling phase of MapReduce, and thus accelerating its execution. The proposed Coded MapReduce exploits the repetitive mapping of data blocks at different servers to create coding opportunities in the shuffling phase to exchange (key,value) pairs among servers much more efficiently. We demonstrate that Coded MapReduce can cut down the total inter…
Several research works have focused on supporting index access in MapReduce systems. These works have allowed users to significantly speed up selective MapReduce jobs by orders of magnitude. However, all these proposals require users to create indexes upfront, which might be a difficult task in certain applications (such as in scientific and social applications) where workloads are evolving or hard to predict. To overcome this problem, we propose LIAH (Lazy Indexing and Adaptivity in Hadoop), a parallel, adaptive approach for indexing at minimal costs for MapReduce systems. The main idea of LI…
This paper discussed some job scheduling algorithms for Hadoop platform, and proposed a jobs scheduling optimization algorithm based on Bayes Classification viewing the shortcoming of those algorithms which are used. The proposed algorithm can be summarized as follows. In the scheduling algorithm based on Bayes Classification, the jobs in job queue will be classified into bad job and good job by Bayes Classification, when JobTracker gets task request, it will select a good job from job queue, and select tasks from good job to allocate JobTracker, then the execution result will feedback to the …
The MapReduce distributed programming framework has become popular, despite evidence that current implementations are inefficient, requiring far more hardware than a traditional relational databases to complete similar tasks. MapReduce jobs are amenable to many traditional database query optimizations (B+Trees for selections, column-store- style techniques for projections, etc), but existing systems do not apply them, substantially because free-form user code obscures the true data operation being performed. For example, a selection in SQL is easily detected, but a selection in a MapReduce pro…
We consider a distributed computing network consisting of a master and multiple workers processing tasks of different types. The master is running multiple applications. Each application stochastically generates real-time jobs with a strict job deadline, where each job is a collection of tasks of some types specified by the application. A real-time job is completed only when all its tasks are completed by the corresponding workers within the deadline. Moreover, we consider unreliable workers, whose processing speeds are uncertain. Because of the limited processing abilities of the workers, an …
MapReduce is a programming system for distributed processing large-scale data in an efficient and fault tolerant manner on a private, public, or hybrid cloud. MapReduce is extensively used daily around the world as an efficient distributed computation tool for a large class of problems, e.g., search, clustering, log analysis, different types of join operations, matrix multiplication, pattern matching, and analysis of social networks. Security and privacy of data and MapReduce computations are essential concerns when a MapReduce computation is executed in public or hybrid clouds. In order to ex…
The University of Tokyo（东京大学）；Preferred Networks, Inc.（优选网络公司）
One significant challenge in the job scheduling of computing clusters for the development of deep learning algorithms is the efficient scheduling of trial-and-error (TE) job, the type of job in which the users seek to conduct small-scale experiments while monitoring their processes. Unfortunately, the existing job schedulers to date do not feature well-balanced scheduling for the mixture of TE jobs and best-effort (BE) jobs, or they can handle the mixture in limited situations at most. To fill in this niche, we propose an algorithm that can significantly reduce the latency of TE jobs in versat…
We are interested in the optimal scheduling of a collection of multi-component application jobs in an edge computing system that consists of geo-distributed edge computing nodes connected through a wide area network. The scheduling and placement of application jobs in an edge system is challenging due to the interdependence of multiple components of each job, and the communication delays between the geographically distributed data sources and edge nodes and their dynamic availability. In this paper we explore the feasibility of applying Deep Reinforcement Learning (DRL) based design to address…
One of the main challenges in Grid systems is designing an adaptive, scalable, and model-independent method for job scheduling to achieve a desirable degree of load balancing and system efficiency. Centralized job scheduling methods have some drawbacks, such as single point of failure and lack of scalability. Moreover, decentralized methods require a coordination mechanism with limited communications. In this paper, we propose a multi-agent approach to job scheduling in Grid, named Centralized Learning Distributed Scheduling (CLDS), by utilizing the reinforcement learning framework. The CLDS i…
Computational Grids are a new trend in distributed computing systems. They allow the sharing of geographically distributed resources in an efficient way, extending the boundaries of what we perceive as distributed computing. Various sciences can benefit from the use of grids to solve CPU-intensive problems, creating potential benefits to the entire society. Job scheduling is an integrated part of parallel and distributed computing. It allows selecting correct match of resource for a particular job and thus increases the job throughput and utilization of resources. Job should be scheduled in an…
