Local Resource Manager Research Articles

Migrating INFN-T1 from CREAM-CE/LSF to HTCondor-CE/HTCondor

The INFN Tier-1 datacentre provides computing resources to several HEP and Astrophysics experiments. These are organized in Virtual Organizations submitting jobs to our computing facilities through Computing Elements, acting as Grid interfaces to the Local Resource Manager. We are phasing-out our current LRMS (IBM/Platform LSF 9.1.3) and CEs (CREAM) set to adopt HTCondor as a replacement for LSF and HTCondor-CE in place of CREAM. A small instance has been set up to practice with the cluster management and evaluate the feasibility of our migration plans to a new LRMS and CE set. A second cluster instance has been setup to work on production. A number of management tools have been adapted or rewritten in order to integrate the new system with the existing infrastructure. Two different accounting solution for the HTCondor-CE have been implemented, and the more reliable one have been adopted. A python tool has been written to disentangle the management of HTCondor machines from our puppet instance, and to enable a quicker configuration of the cluster nodes. The monitoring tools tied to the old system are being adapted to also work on the new one. Finally, the most relevant setup steps have been documented in a public wiki page and a support mailing has been created to help other INFN sites willing to migrate their LRMS and CE to HTCondor. This document reports about our experience with HTCondor-CE on top of HTCondor and the integration of this system into our infrastructure.

Эффективный запуск гибридных параллельных задач в ГРИДе

The method of efficient submission of hybrid tasks using both MPI and OpenMP technologies is considered. For flexible control of parameters of the parallel tasks submission to supercomputers (SC), the specification of the task description language was expanded. Support of the new attributes was implemented for all key components of the infrastructure. Interaction of the submission web service with a local resource manager is organized through special handlers for tasks of different types (single, openmp, mpi or hybrid). This provides transmission of the correct parameters for reservation of resources and task submission to the local SC-manager. The provided solution was tested on a grid testbed deployed on the basis of GridNNN middleware.

Implementation of seismic data inversion as grid-backed web service

The essence of probability approach in solving inverse problems is use of a posteriory probability density function (APDF). APDF bears a priory system signature and the way the corresponding model parameter set describes the observational data. APDF importance sampling is carried out independently in different points thus the problem is a good target for distributed computing. The software implementation make use of virtualization to lower the hardware cost: all Globus Toolkit services, except for GridFTP, run as virtual guests on execution nodes. Due to very insignificant resources utilization the guests make no footprint on node’s computation power. The execution nodes local resource manager is TORQUE. The main thought for web interface is to hide complex middleware interaction from user. Such interaction usually takes place during start-up and result collection and analysis procedures. The implemented minimalistic web service allows defining of models, estimation of calculation time for user-specified parameter set, task start-up, management, results acquisition and visualization. The specific pilot problem we implemented is determination of seismic anisotropy of mantle and upper crust by teleseismic data.

방재자원 통합 서비스 체계 연구

방재자원은 재난 발생 시 긴급히 투입되는 자원으로 장비, 자재, 인력 등으로 구성되어 있다. 현재까지의 방재 자원 관리는 중앙의 NDMS와 시 군 구 재난관리시스템의 Client/Server 모델로 구성 운영되었다. 장기적으로 방재자원은 정부 기관이 보유한 자원뿐만 아니라 민간 보유 자원까지 총체적으로 파악할 수 있는 체계가 필요하다. 본 연구는 이러한 관점에서 다양한 자원 관리 모델을 분석하였고 이를 기반으로 분산 방재 자원의 효과적 관리 및 서비스 모델을 도출하였다. 이는 각 기관에 분산된 자원 정보로부터 핵심 정보를 통합 관리하는 중앙 시스템(IDRM)을 가지는 것이다. 중앙 시스템과 각 기관 시스템(LDRM) 사이 자원의 등록, 동기화, 검색, 요청 등 발생할 수 있는 다양한 기능과 핵심 정보에 대한 표준 서비스 체계를 도출하였다. 방재자원 관리 시스템은 궁극적으로 재난 현장 관리 시스템과 연계되어 운영될 수 있는 체계로 진행되어야 할 것이다. When disaster is occurred, disaster resources which consist of the equipments, supplies, and human resources are used to recover and restore. Currently, the disaster resource management is operated with NDMS(National Disaster Management System) and Local government Disaster Management System. Eventually, it is necessary that all disaster resources distributed in the governmental institutes and private sectors are managed. In this paper, we analyzed the several resource management models, and then defined the disaster resource management model. It makes a new central integrated disaster resource manager(IDRM) which collects the resource information from the local disaster resource manager(LDRM). IDRM communicates with LDRM using the protocols such as to publish, register, subscribe, and synchronize. Also we defined the standard core data using XML schema. In the future, IDRM must be supporting the disaster field management system.

Description of a Low Level Virtual-Resource QoS CPU Manager

We present the description of a QoS aware dynamic virtualization manager. The proposal is a set of definitions for the low-level framework, named QoS CPU manager, which is part of a Local Resource Manager (LRM). In this work, we give a formal specification of the internals of our LRM. We give the relationships of the CPU capacity management component that is in charge of managing and mapping each application goal to low-level scheduler parameters, and the VM CPU consumption component which allows the LRM to offer adaptive management through the lifetime of the VM.

Human disturbance of the Waitomo catchment, New Zealand

The karst disturbance index (KDI) consists of 31 environmental indicators categorized within the five broad categories of geomorphology, hydrology, atmosphere, biota, and culture. This article discusses the application of the KDI to the rural karst region of Waitomo, New Zealand. Previous applications of the KDI measured disturbance to urban areas as delineated by geo-political boundaries while this study used a physical boundary of a small karst catchment. Such an approach ensures greater environmental specificity of measured disturbance levels compared to those determined according to arbitrary, politically defined areas. The study included a comparison of a local resource manager and a visiting karst expert's determinations of disturbance levels for the catchment. Overall, the Waitomo catchment was found to be moderately disturbed. The only significant, direct disturbances were deforestation and erosion; however, these lead to the indirect disturbance of cave biota, water quality and accelerated sedimentation of the catchment's waterways. We have a high degree of confidence in the validity of these results due to the ability to assess all of the applicable indicators in the index, and the consistency of scoring by both individuals who applied the index. The benefit of applying the KDI at the catchment level is the greater accuracy measuring disturbance as opposed to applying the index within geo-political boundaries that incorporate both karst and non-karst terrains. With disturbance data for a highly specific area, the Waitomo resource managers have the improved ability to effectively identify, target, remediate, and manage human disturbance of the karst landscape.

Guest Editors' Introduction: Special Section on Many-Task Computing

IT is our honor to serve as guest editors of this special section of the IEEE Transactions on Parallel and Distributed Systems (TPDS) on many-task computing (MTC). This section focuses on the methods required to manage and execute large multiple program multiple data (MPMD) computations on large clusters, grids, clouds, and supercomputers. We are pleased to present 10 high-quality contributions chosen from 42 submissions, on resource management, data-intensive computing, applications, and MTC on supercomputers, grids, and clouds. We introduce the term many-task computing (MTC) [2] for computations that bridge the gap between high-performance computing (HPC) and high-throughput computing (HTC) [1]. MTC differs from HTC in its emphasis on using many computing resources over short periods of time to accomplish many computational tasks (both dependent and independent), for which primary metrics are measured in seconds (e.g., FLOPS, tasks/sec., MB/s I/O rates), as opposed to jobs per month. MTC computations comprise multiple distinct activities, coupled via files, shared memory, or message passing. Tasks may be small or large, uniprocessor or multiprocessor, or compute-intensive or data-intensive. The set of tasks may be static or dynamic, homogeneous or heterogeneous, or loosely coupled or tightly coupled. The number of tasks, quantity of computing, and volumes of data may be large. Today’sHPCsystemsareaviableplatformforMTC[3],but large MTC applications can stress HPC hardware and sotware. Challenges include local resource manager scalability and granularity, efficient utilization of raw hardware, parallel file system contention and scalability, data management, I/O management, reliability at scale, application scalability, and understanding the limitations of HPC systems in order to identify good candidate MTC applications [4]. MTC applications can also be executed on cloud systems, but face other challenges there, for example, relating to internode communication performance. Three recent MTC workshops (MTAGS, http://dsl.cs. uchicago.edu/MTAGS10/) and this special section attracted 142 abstracts and 110 paper submissions, from which 41 papers were accepted. Papers covered resource management, data-intensive computing, applications, and MTC on supercomputers, grids, and clouds. More than 1,000 people have participated as coauthors, program committee members, reviewers, and attendees in these venues. We are well beyond a critical mass for a new, thriving community, which is quickly expanding.

Middleware support for many-task computing

Many-task computing aims to bridge the gap between two computing paradigms, high throughput computing and high performance computing. Many-task computing denotes high-performance computations comprising multiple distinct activities, coupled via file system operations. The aggregate number of tasks, quantity of computing, and volumes of data may be extremely large. Traditional techniques found in production systems in the scientific community to support many-task computing do not scale to today's largest systems, due to issues in local resource manager scalability and granularity, efficient utilization of the raw hardware, long wait queue times, and shared/parallel file system contention and scalability. To address these limitations, we adopted a "top-down" approach to building a middleware called Falkon, to support the most demanding many-task computing applications at the largest scales. Falkon (Fast and Light-weight tasK executiON framework) integrates (1) multi-level scheduling to enable dynamic resource provisioning and minimize wait queue times, (2) a streamlined task dispatcher able to achieve orders-of-magnitude higher task dispatch rates than conventional schedulers, and (3) data diffusion which performs data caching and uses a data-aware scheduler to co-locate computational and storage resources. Micro-benchmarks have shown Falkon to achieve over 15K+ tasks/s throughputs, scale to hundreds of thousands of processors and to millions of queued tasks, and execute billions of tasks per day. Data diffusion has also shown to improve applications scalability and performance, with its ability to achieve hundreds of Gb/s I/O rates on modest sized clusters, with Tb/s I/O rates on the horizon. Falkon has shown orders of magnitude improvements in performance and scalability than traditional approaches to resource management across many diverse workloads and applications at scales of billions of tasks on hundreds of thousands of processors across clusters, specialized systems, Grids, and supercomputers. Falkon's performance and scalability have enabled a new class of applications called Many-Task Computing to operate at previously so-believed impossible scales with high efficiency.

Enhancing virtual environments with QoS aware resource management

Nowadays, the consolidation of application servers is the most common use for current virtualization solutions. Each application server takes the form of a virtual machine (VM) that can be hosted into one physical machine. In a default Xen implementation, the scheduler is configured to handle equally all of the VMs that run on a single machine. As a consequence, the scheduler shares equally all of the available physical CPU resources among the running VMs. However, when the applications that run in the VM dynamically change their resource requirements, a different solution is needed. Furthermore, if the resource usage is associated with service-level agreements, a predefined equal share of the processor power is insufficient for the VMs. Within the Xen’s primitives, even though it is possible to tune the scheduler parameters, there is no tool to achieve the dynamic change of the share of the processor power assigned to each VM. A combination of a number of primitives, however, appears to be suited as a base for achieving this. In this paper, we present an approach to efficiently manage the quality of service (QoS) of virtualized resources in multicore machines. We evaluate different alternatives within Xen for building an enhanced management of virtual CPU resources. We compare these alternatives in terms of performance, flexibility, and ease of use. We devise an architecture to build a high-level service that combines interdomain communication mechanisms with monitoring and control primitives for local resource management. We achieve this by our solution, a local resource manager (LRM), which adjusts the resources needed by each VM according to an agreed QoS. The LRM has been implemented as a prototype and deployed on Xen-virtualized machines. By means of experiments, we show that the implemented management component can meet the service-level objectives even under dynamic conditions by adapting the resources assigned to the virtualized machines according to demand. With the LRM, we therefore achieve both fine-grain resource allocation and efficient assignment.

3-Hierarchical resource management model on web grid service architecture

In this paper, we developed a framework for efficient resource management within the grid service environment. For considering the grid service architecture and functions, the resource management is the most important to grid service; therefore, GridRMF (Grid Resource Management Framework) is modeled and developed in order to respond to such variable characteristics of resources as accordingly as possible. GridRMF uses the participation level of grid resource as a basis of its hierarchical management. This hierarchical management divides managing domains into two parts: VMS (Virtual Organization Management System) for virtual organization management and RMS (Resource Management System) for metadata management. VMS mediates resources according to optimal virtual organization selection mechanism, and responds to malfunctions of the virtual organization by LRM (Local Resource Manager) automatic recovery mechanism. RMS, on the other hand, responds to load balance and fault by applying resource status monitoring information into adaptive performance-based task allocation algorithm.

Grid enabled, hierarchical distributed metamodel-assisted evolutionary algorithms for aerodynamic shape optimization

A Grid-enabled optimization environment is presented. It is based on Metamodel-Assisted Evolutionary Algorithms ( MAEAs), where radial basis function networks, trained on the fly on selected subsets of the previously evaluated individuals, are used to pre-evaluate the population members. The search follows a Hierarchical and Distributed scheme ( HDMAEA), with more than one search level, each of which is associated with a different problem-specific evaluation tool and a different number of semi-isolated demes. Irrespective of the use of cluster or Grid computing, the HDMAEA drastically reduces the number of evaluations required to reach the optimal solution(s). The Grid-enabled HDMAEA, based on the master–slave model with simultaneously evaluated population members, aims at solving large scale optimization problems in affordable wall clock time. In the proposed Grid–computing setup, Condor is used as the local resource manager on each contributing cluster, authentication and interfacing is carried out via the Globus Toolkit and the unification of Grid resources under a common queue is undertaken by the Gridway metascheduler. If more than one search level are used (hierarchical search), the optimization of Grid resources’ allocation relies on the distinction between computationally demanding, high-accuracy and less demanding, low-accuracy evaluation tools. The proposed Grid-enabled problem solving environment is demonstrated on three aerodynamic shape optimization problems, namely the design of a compressor cascade and two 3D elbow ducts, on three remote clusters.

Ethical Leadership and Administrative Discretion: The Fire Chief's Hiring Dilemma

Recent efforts to reform government are challenging many of the basic theoretical and managerial assumptions of governance at the federal, state, and local levels. Under the political rubric of reinventing government, reform initiatives have devolved administrative decision making to more local levels. In practice this can result in ethical dilemmas for local government administrators as they attempt to reconcile constitutional governance, legal accountability and political environments with the search for flexibility, innovation, and productivity while mimicking private sector processes and practices. This article describes such an ethical dilemma faced by a local government human resource manager and fire chief who were confronted with the decision to succumb to political pressure from prominent citizens, volunteer fire chiefs and city council members to hire unqualified firefighter candidates, or to discount their input and reject the candidates. The authors describe the ethical dilemma and discuss the importance of practicing ethical leadership to build public trust and accountability in the responsible use of administrative discretion while pursuing the public interest.