Characterizing the Impact of Job Execution on the Occurrence of Memory Failures on a Petascale HPC System
Explore the source record for details and available documents.
Levy, Scott Larson Nicoll↗
SEARCH · Search NASA
Results for “job execution”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Characterizing the Impact of Job Execution on the Occurrence of Memory Failures on a Petascale HPC System
Explore the source record for details and available documents.
Hemmert, Joshua David↗
SchedInspector: A Batch Job Scheduling Inspector Using Reinforcement Learning
Improving the performance of job executions is an important goal of HPC batch job schedulers, such as minimizing job waiting time, slowdown, or completion time. Such a goal is often accomplished using carefully designed heuristics based on job features, such as job size and job duration. However, these heuristics overlook important runtime factors (e.g., cluster availability and waiting job patterns), which may vary across time and make a previously sound scheduling decision not hold any longer. In this study, we propose a new approach to incorporate runtime factors into batch job scheduling for better job execution performance. The key idea is to add a scheduling inspector on top of the base job scheduler to scrutinize its scheduling decisions. The inspector will take the runtime factors into consideration and accordingly determine the fitness of the scheduled job. It then either accepts the scheduled job or rejects it and asks the base schedulers to try again later. We realize such an inspector, namely SchedInspector, by leveraging the intelligence of reinforcement learning. Through extensive experiments, we show SchedInspector can intelligently integrate the runtime factors into various batch job scheduling policies, including the state-of-the-art one, to gain better job execution performance, such as smaller average bounded job slowdown (up to 69% better) or average job waiting time (up to 52% better), across various real-world workloads. We also show that although rejecting scheduling decisions may leave the resources idle hence affect the system utilization, SchedInspector is able to achieve the job execution performance improvement with marginal impact on the system utilization (typically less than 1%). We consider one key advantage of SchedInspector is it automatically learns to work with and improve existing job scheduling policies without changing them, which makes it promising to serve as a generic enhancer for various batch job scheduling policies.
Zhang, Di↗
Accelerating Scientific Workflows on HPC Platforms with In Situ Processing
Scientific workflows drive most modern large-scale science breakthroughs by allowing scientists to define their computations as a set of jobs executed in a given order based on their data dependencies. Workflow management systems (WMSs) have become key to automating scientific workflows-executing computational jobs and orchestrating data transfers between those jobs running on complex high-performance computing (HPC) platforms. Traditionally, WMSs use files to communicate between jobs: a job writes out files that are read by other jobs. However, HPC machines face a growing gap between their storage and compute capabilities. To address that concern, the scientific community has adopted a new approach called in situ, which bypasses costly parallel filesystem I/O operations with faster in-memory or in-network communications. When using in situ approaches, communication and computations can be interleaved. In this work, we leverage the Decaf in situ dataflow framework to accelerate task-based scientific workflows managed by the Pegasus WMS, by replacing file communications with faster MPI messaging. We propose a new execution engine that uses Decaf to manage communications within a sub-workflow (i.e., set of jobs) to optimize inter-job communications. We consider two workflows in this study: (i) a synthetic workflow that benchmarks and compares file- and MPI-based communication; and (ii) a realistic bioinformatics workflow that computes mu-tational overlaps in the human genome. Experiments show that in situ communication can improve the bioinformatics workflow execution time by 22% to 30% compared with file communication. Our results motivate further opportunities and challenges for bridging traditional WMSs with in situ frameworks.
Decaf↗
Digital-flight-control-system software written in automated-engineering-design language: A user's guide of verification and validation tools
The user guide of verification and validation (V&V) tools for the Automated Engineering Design (AED) language is specifically written to update the information found in several documents pertaining to the automated verification of flight software tools. The intent is to provide, in one document, all the information necessary to adequately prepare a run to use the AED V&V tools. No attempt is made to discuss the FORTRAN V&V tools since they were not updated and are not currently active. Additionally, the current descriptions of the AED V&V tools are contained and provides information to augment the NASA TM 84276. The AED V&V tools are accessed from the digital flight control systems verification laboratory (DFCSVL) via a PDP-11/60 digital computer. The AED V&V tool interface handlers on the PDP-11/60 generate a Univac run stream which is transmitted to the Univac via a Remote Job Entry (RJE) link. Job execution takes place on the Univac 1100 and the job output is transmitted back to the DFCSVL and stored as a PDP-11/60 printfile.
Saito, Jim↗
Scaling a Podman Container Factory in the Cloud
This technical report describes an implementation of a scalable continuous integration/continuous deployment infrastructure using Microsoft Azure™ and GitLab™ resources. We utilize GitLab continuous integration podman executors to provide rootless container operations in both privileged and unprivileged modes of operation. We utilize the GitLab Fleeting plugin for Azure to manage the scaling of continuous integration execution resources. This creates a scalable, rootless, and isolate continuous integration/continuous deployment job execution infrastructure.
97 MATHEMATICS AND COMPUTING↗
Job-mix modeling and system analysis of an aerospace multiprocessor.
An aerospace guidance computer organization, consisting of multiple processors and memory units attached to a central time-multiplexed data bus, is described. A job mix for this type of computer is obtained by analysis of Apollo mission programs. Multiprocessor performance is then analyzed using: 1) queuing theory, under certain 'limiting case' assumptions; 2) Markov process methods; and 3) system simulation. Results of the analyses indicate: 1) Markov process analysis is a useful and efficient predictor of simulation results; 2) efficient job execution is not seriously impaired even when the system is so overloaded that new jobs are inordinately delayed in starting; 3) job scheduling is significant in determining system performance; and 4) a system having many slow processors may or may not perform better than a system of equal power having few fast processors, but will not perform significantly worse.
Mallach, E. G.↗
Flexible Pilot Jobs Framework for Distributed High Throughput Computing
Experimental particle physics has been at the forefront of analyzing the world’s largest datasets for decades. The high-energy physics (HEP) community was among the first to develop suitable software and computing tools for this purpose. GlideinWMS is a Glidein-based workload management system whose purpose is to provide experiments like CMS at CERN, DUNE at Fermilab, and others, a way to access and efficiently use vast amounts of computing resources. This system wants to provide a simple way to submit jobs to a set of computing resources, that will be provided to users behind the scenes. Glideins are the pilot jobs executed on the worker nodes at the grid sites, performing operations such as hardware detection, environment setup, and error handling. After all these operations, they will launch the actual user job. Many grid sites are supported, such as shared clusters, Google CE, and AWS. My internship aimed to design and code a flexible pilot jobs framework that will replace the one used by GlideinWMS, developing a modular and flexible skeleton of the Glidein and adding further functionalities. My project also focused on the application of machine learning techniques as support to this management system.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Method for resource control in parallel environments using program organization and run-time support
A system and method for dynamic scheduling and allocation of resources to parallel applications during the course of their execution. By establishing well-defined interactions between an executing job and the parallel system, the system and method support dynamic reconfiguration of processor partitions, dynamic distribution and redistribution of data, communication among cooperating applications, and various other monitoring actions. The interactions occur only at specific points in the execution of the program where the aforementioned operations can be performed efficiently.
Ekanadham, Kattamuri↗
Method for resource control in parallel environments using program organization and run-time support
A system and method for dynamic scheduling and allocation of resources to parallel applications during the course of their execution. By establishing well-defined interactions between an executing job and the parallel system, the system and method support dynamic reconfiguration of processor partitions, dynamic distribution and redistribution of data, communication among cooperating applications, and various other monitoring actions. The interactions occur only at specific points in the execution of the program where the aforementioned operations can be performed efficiently.
Ekanadham, Kattamuri↗
Facilitating the Portability of User Applications in Grid Environments
Grid computing promises the ability to connect geographically and organizationally distributed resources to increase effective computational power, resource utilization, and resource accessibility. For grid computing to be successful, however, users must be able to easily execute the same application on different resources. Different resources, however, may be administered by different organizations with different software installed, different file system structures, and different default environment settings. Even within the same organization, the set of software installed on a given resource is in constant flux with additions, upgrades, and removals. Users cannot be expected to understand all of the idiosyncrasies of each resource they may wish to execute jobs on, thus must be provided with automated assistance. This paper describes a new OGSI-compliant grid service (the Portability Manager) that has been implemented as part of NASA's Information Power Grid (IPG) project to automatically estab!ish the execution environment for user applications.
Kolano, Paul Z.↗
Using Wearable Computers in Shuttle Processing: A Feasibility Study
Shuttle processing operations are performed following prescribed instructions compiled in a Work Authorization Document (WAD). Until very recently, WADs were printed so that they could be properly executed, including the buy off of each and every step by the appropriate authorizing agent. However, with the development of EPICs, Maximo, and PeopleSoft applications, some of these documents are now available in electronic format; hence, it is possible for technicians and engineers to access them on line and buy off the steps electronically. To take full advantage of these developments, technicians need access to such documents at the point of job execution. Body wearable computers present an opportunity to develop a WAD delivery system that enables access while preserving technician's mobility, safety levels, and quality of work done. The primary objectives of this project were to determine if body wearable computers are a feasible delivery system for WADs. More specifically, identify and recommend specific brands of body wearable computers readily available on the market. Thus, this effort has field-tested this technology in two areas of shuttle processing, and it has examined the usability of the technology. Results of two field tests and a Human Factors Usability Test are presented. Section 2 provides a description of the body wearable computer technology. Section 3 presents the test at the Space Shuttle Main Engine (SSME) Shop. Section 4 presents the results of the integration test at the Solid Rocket Boosters Assembly and Refurbishing Facility (SRBARF). Section 5 presents the results of the usability test done at the Operations Support Building (OSB).
Centeno, Martha A.↗
Towards an Introspective Dynamic Model of Globally Distributed Computing Infrastructures
Large-scale scientific collaborations like ATLAS, Belle II, CMS, DUNE, and others involve hundreds of research institutes and thousands of researchers spread across the globe. These experiments generate petabytes of data, with volumes soon expected to reach exabytes. Consequently, there is a growing need for computation, including structured data processing from raw data to consumer-ready derived data, extensive Monte Carlo simulation campaigns, and a wide range of end-user analysis. To manage these computational and storage demands, centralized workflow and data management systems are implemented. However, decisions regarding data placement and payload allocation are often made disjointly and via heuristic means. A significant obstacle in adopting more effective heuristic or AI-driven solutions is the absence of a quick and reliable introspective dynamic model to evaluate and refine alternative approaches. In this study, we aim to develop such an interactive system using real-world data. By examining job execution records from the PanDA workflow management system, we have pinpointed key performance indicators such as queuing time, error rate, and the extent of remote data access. The dataset includes five months of activity. Additionally, we are creating a generative AI model to simulate time series of payloads, which incorporate visible features like category, event count, and submitting group, as well as hidden features like the total computational load—derived from existing PanDA records and computing site capabilities. These hidden features, which are not visible to job allocators, whether heuristic or AI-driven, influence factors such as queuing times and data movement.
kilic, Ozgur Ozan [Brookhaven National Laboratory ↗
Power Profile Monitoring and Tracking Evolution of System-Wide HPC Workloads
The power & energy demands of HPC machines have grown significantly. Modern exascale HPC systems require tens of megawatts of combined power for computing resources and cooling facilities at full capacity. The current energy trend is not sustainable for future HPC systems, and there is a need to work toward the energy efficiency aspect of HPC performance. Energy awareness of the HPC applications at the job level is essential for running an efficient HPC system. This work aims to develop a pipeline to provide a production-level system-wide overview of the HPC workloads' power profile while handling evolving workloads exhibiting new power trends. We developed an open-set classification model for HPC jobs based on the properties of power profiles to continuously provide a system-wide holistic view of recently completed jobs. The pipeline helps continuously monitor the job-level power usage pattern of HPC and enables us to capture the new trends in applications' power behavior. We employed a comprehensive set of techniques to generate job-level data, custom-designed feature extraction methods to extract critical features from jobs' power profiles, clustering techniques powered by generative modeling, and open-set classification for identifying job profiles into known classes or an unknown set. With extensive evaluations, we demonstrate the effectiveness of each component in our pipeline. We provide an analysis of the resulting clusters that characterize the power profile landscape of the Summit supercomputer from more than 60K jobs executed in a year. The open-set classification classifies the known data sets into known classes with high accuracy and identifies unknown data noints with over 85% accuracy.
Karimi, Ahmad Maroof↗
Modernizing GlideinWMS Factory Monitoring with Prometheus & Grafana
Large-scale scientific experiments like CMS and DUNE rely on the distributed workload management system GlideinWMS to efficiently utilize computing resources across heterogeneous computing environments. GlideinWMS currently records Factory statistics using Round Robin Databases (RRDBs), XML, and JSON files, and these statistics are displayed via custom monitoring Web pages, thereby limiting integration with modern observability platforms. This project investigates the use of Prometheus-based instrumentation to expose Factory metrics using OpenTelemetry principles. Factory statistics related to Glidein submission and job execution are exported as Prometheus metrics through the Prometheus Python Client Library and are served via an HTTP metrics endpoint. The collected metrics are inspected using the Prometheus web-based interface and are visualized through Grafana dashboards within the Landscape monitoring infrastructure at Fermilab. This project significantly streamlines the integration of modern monitoring technologies into GlideinWMS and establishes a framework for extending observability across additional system components.
Appiah, Gideon [Grambling State U.]↗
The VLBA correlator: Real-time in the distributed era
The correlator is the signal processing engine of the Very Long Baseline Array (VLBA). Radio signals are recorded on special wideband (128 Mb/s) digital recorders at the 10 telescopes, with sampling times controlled by hydrogen maser clocks. The magnetic tapes are shipped to the Array Operations Center in Socorro, New Mexico, where they are played back simultaneously into the correlator. Real-time software and firmware controls the playback drives to achieve synchronization, compute models of the wavefront delay, control the numerous modules of the correlator, and record FITS files of the fringe visibilities at the back-end of the correlator. In addition to the more than 3000 custom VLSI chips which handle the massive data flow of the signal processing, the correlator contains a total of more than 100 programmable computers, 8-, 16- and 32-bit CPUs. Code is downloaded into front-end CPU's dependent on operating mode. Low-level code is assembly language, high-level code is C running under a RT OS. We use VxWorks on Motorola MVME147 CPU's. Code development is on a complex of SPARC workstations connected to the RT CPU's by Ethernet. The overall management of the correlation process is dependent on a database management system. We use Ingres running on a Sparcstation-2. We transfer logging information from the database of the VLBA Monitor and Control System to our database using Ingres/NET. Job scripts are computed and are transferred to the real-time computers using NFS, and correlation job execution logs and status flow back by the route. Operator status and control displays use windows on workstations, interfaced to the real-time processes by network protocols. The extensive network protocol support provided by VxWorks is invaluable. The VLBA Correlator's dependence on network protocols is an example of the radical transformation of the real-time world over the past five years. Real-time is becoming more like conventional computing. Paradoxically, 'conventional' computing is also adopting practices from the real-time world: semaphores, shared memory, light-weight threads, and concurrency. This appears to be a convergence of thinking.
Wells, D. C.↗
An Execution Service for Grid Computing
This paper describes the design and implementation of the IPG Execution Service that reliably executes complex jobs on a computational grid. Our Execution Service is part of the IPG service architecture whose goal is to support location-independent computing. In such an environment, once n user ports an npplicntion to one or more hardware/software platfrms, the user can describe this environment to the grid the grid can locate instances of this platfrm, configure the platfrm as required for the application, and then execute the application. Our Execution Service runs jobs that set up such environments for applications and executes them. These jobs consist of a set of tasks for executing applications and managing data. The tasks have user-defined starting conditions that allow users to specih complex dependencies including task to execute when tasks fail, afiequent occurrence in a large distributed system, or are cancelled. The execution task provided by our service also configures the application environment exactly as specified by the user and captures the exit code of the application, features that many grid execution services do not support due to dflculties interfacing to local scheduling systems.
Smith, Warren↗
Grid Task Execution
IPG Execution Service is a framework that reliably executes complex jobs on a computational grid, and is part of the IPG service architecture designed to support location-independent computing. The new grid service enables users to describe the platform on which they need a job to run, which allows the service to locate the desired platform, configure it for the required application, and execute the job. After a job is submitted, users can monitor it through periodic notifications, or through queries. Each job consists of a set of tasks that performs actions such as executing applications and managing data. Each task is executed based on a starting condition that is an expression of the states of other tasks. This formulation allows tasks to be executed in parallel, and also allows a user to specify tasks to execute when other tasks succeed, fail, or are canceled. The two core components of the Execution Service are the Task Database, which stores tasks that have been submitted for execution, and the Task Manager, which executes tasks in the proper order, based on the user-specified starting conditions, and avoids overloading local and remote resources while executing tasks.
Hu, Chaumin↗