The OSG open facility: A sharing ecosystem

The Open Science Grid (OSG) is a large, robust computing grid that started primarily as a collection of sites associated with large HEP experiments such as ATLAS, CDF, CMS, and DZero, but has evolved in recent years to a much larger user and resource platform. In addition to meeting the US LHC community’s computational needs, the OSG continues to be one of the largest providers of distributed high-throughput computing (DHTC) to researchers from a wide variety of disciplines via the OSG Open Facility. The Open Facility consists of OSG resources that are available opportunistically to users other than resource owners and their collaborators. In the past two years, the Open Facility has doubled its annual throughput to over 200 million wall hours. More than half of these resources are used by over 100 individual researchers from over 60 institutions in fields such as biology, medicine, math, economics, and many others. Over 10% of these individual users utilized in excess of 1 million computational hours each in the past year. The largest source of these cycles is temporary unused capacity at institutions affiliated with US LHC computational sites. An increasing fraction, however, comes from university HPC clusters and large national infrastructure supercomputers offering unused capacity. Such expansions have allowed the OSG to provide ample computational resources to both individual researchers and small groups as well as sizable international science collaborations such as LIGO, AMS, IceCube, and sPHENIX. Opening up access to the Fermilab FabrIc for Frontier Experiments (FIFE) project has also allowed experiments such as mu2e and NOvA to make substantial use of Open Facility resources, the former with over 40 million wall hours in a year. We present how this expansion was accomplished as well as future plans for keeping the OSG Open Facility at the forefront of enabling scientific research by way of DHTC.

We present a system that allows individual researchers and virtual organizations (VOs) to access allocations on Stampede2 and Bridges through the Open Science Grid (OSG), a national grid infrastructure for running high throughput computing (HTC) tasks. Using this system, VOs and researchers are able to run larger workflows than can be done with OSG resources alone. This system allows a VO or user to run on XSEDE resources (with their allocation) using the same framework used with OSG resources. The system consists of two parts: the compute element (CE) that routes workloads to the appropriate user accounts and allocation on XSEDE resources, and simulated access to the CernVM Filesystem (CVMFS) servers used by OSG and VOs to distribute software and data. This allows jobs submitted through this system to work on a homogeneous environment regardless of whether they run on XSEDE HPC resources (like Stampede2 and Bridges) or OSG.

The Open Science Grid(OSG) is a world-wide computing system which facilitates distributed computing for scientific research. It can distribute a computationally intensive job to geo-distributed clusters and process job's tasks in parallel. For compute clusters on the OSG, physical resources may be shared between OSG and cluster's local user-submitted jobs, with local jobs preempting OSG-based ones. As a result, job preemptions occur frequently in OSG, sometimes significantly delaying job completion time. We have collected job data from OSG over a period of more than 80 days. We present an analysis of the data, characterizing the preemption patterns and different types of jobs. Based on observations, we have grouped OSG jobs into 5 categories and analyze the runtime statistics for each category. we further choose different statistical distributions to estimate probability density function of job runtime for different classes.

Throughout the last decade the Open Science Grid (OSG) has been fielding requests from user communities, resource owners, and funding agencies to provide information about utilization of OSG resources. Requested data include traditional accounting - core-hours utilized - as well as users certificate Distinguished Name, their affiliations, and field of science. The OSG accounting service, Gratia, developed in 2006, is able to provide this information and much more. However, with the rapid expansion and transformation of the OSG resources and access to them, we are faced with several challenges in adapting and maintaining the current accounting service. The newest changes include, but are not limited to, acceptance of users from numerous university campuses, whose jobs are flocking to OSG resources, expansion into new types of resources (public and private clouds, allocation-based HPC resources, and GPU farms), migration to pilot-based systems, and migration to multicore environments. In order to have a scalable, sustainable and expandable accounting service for the next few years, we are embarking on the development of the next-generation OSG accounting service, GRACC, that will be based on open-source technology and will be compatible with the existing system. It will consist of swappable, independent components, such as Logstash, Elasticsearch, Grafana, and RabbitMQ, that communicate through a data exchange. GRACC will continue to interface EGI and XSEDE accounting services and provide information in accordance with existing agreements. We will present the current architecture and working prototype.

We present a novel computational framework that connects Blue Waters, the NSF-supported, leadership-class supercomputer operated by NCSA, to the Laser Interferometer Gravitational-Wave Observatory (LIGO) Data Grid via Open Science Grid technology. To enable this computational infrastructure, we configured, for the first time, a LIGO Data Grid Tier-1 Center that can submit heterogeneous LIGO workflows using Open Science Grid facilities. In order to enable a seamless connection between the LIGO Data Grid and Blue Waters via Open Science Grid, we utilize Shifter to containerize LIGO's workflow software. This work represents the first time Open Science Grid, Shifter, and Blue Waters are unified to tackle a scientific problem and, in particular, it is the first time a framework of this nature is used in the context of large scale gravitational wave data analysis. This new framework has been used in the last several weeks of LIGO's second discovery campaign to run the most computationally demanding gravitational wave search workflows on Blue Waters, and accelerate discovery in the emergent field of gravitational wave astrophysics. We discuss the implications of this novel framework for a wider ecosystem of Higher Performance Computing users.

It is common at research institutions to maintain multiple clusters that represent different owners or generations of hardware, or that fulfill different needs and policies. Many of these clusters are consistently under utilized while researchers on campus could greatly benefit from these unused capabilities. By leveraging principles from the Open Science Grid it is now possible to utilize these resources by forming a lightweight campus grid. The campus grids framework enables jobs that are submitted to one cluster to overflow, when necessary, to other clusters within the campus using whatever authentication mechanisms are available on campus. This framework is currently being used on several campuses to run HEP and other science jobs. Further, the framework has in some cases been expanded beyond the campus boundary by bridging campus grids into a regional grid, and can even be used to integrate resources from a national cyberinfrastructure such as the Open Science Grid. This paper will highlight 18 months of operational experiences creating campus grids in the US, and the different campus configurations that have successfully utilized the campus grid infrastructure.

The HTCondor-CE is the next-generation gateway software for the Open Science Grid (OSG). This is responsible for providing a network service which authorizes remote users and provides a resource provisioning service (other well-known gateways include Globus GRAM, CREAM, Arc-CE, and Openstacks Nova). Based on the venerable HTCondor software, this new CE is simply a highly-specialized configuration of HTCondor. It was developed and adopted to provide the OSG with a more flexible, scalable, and easier-to-manage gateway software. Further, the focus of the HTCondor-CE is not job submission (as in GRAM or CREAM) but resource provisioning. This software does not exist in a vacuum: to deploy this gateway across the OSG, we had to integrate it with the CE configuration, deploy a corresponding information service, coordinate with sites, and overhaul our documentation.

Grids enable uniform access to resources by implementing standard interfaces to resource gateways. In the Open Science Grid (OSG), privileges are granted on the basis of the user's membership to a Virtual Organization (VO). However, Grid sites are solely responsible to determine and control access privileges to resources using users' identity and personal attributes, which are available through Grid credentials. While this guarantees full control on access rights to the sites, it makes VO privileges heterogeneous throughout the Grid and hardly fits with the Grid paradigm of uniform access to resources. To address these challenges, we are developing the Scalable Virtual Organization Privileges Management Environment (SVOPME), which provides tools for VOs to define and publish desired privileges and assists sites to provide the appropriate access policies. Moreover, SVOPME provides tools for Grid sites to analyze site access policies for various resources, verify compliance with preferred VO policies, and generate directives for site administrators on how the local access policies can be amended to achieve such compliance without taking control of local configurations away from site administrators. This paper discusses what access policies are of interest to the OSG community and how SVOPME implements privilege management for OSG.

MCwrapper is a set of systems that manages the entire Monte Carlo production workflow for GlueX and provides standards for how that Monte Carlo is produced. MCwrapper was designed to be able to utilize a variety of batch systems in a way that is relatively transparent to the user, thus enabling users to quickly and easily produce valid simulated data at home institutions worldwide. Additionally, MCwrapper supports an autonomous system that takes user’s project submissions via a custom web application. The system then atomizes the project into individual jobs, matches these jobs to resources, and monitors the jobs status. The entire system is managed by a database which tracks almost all facets of the systems from user submissions to the individual jobs themselves. Users can interact with their submitted projects online via a dashboard or, in the case of testing failure, can modify their project requests from a link contained in an automated email. Beginning in 2018 the GlueX Collaboration began to utilize the Open Science Grid (OSG) to handle a bulk of simulation tasks; these tasks are currently being performed on the OSG automatically via MCwrapper. This talk will outline the entire system of MCwrapper, its use cases, and the unique challenges facing the system.

High throughput computing (HTC) systems are widely adopted in scientific discovery and engineering research. They are responsible for scheduling submitted batch jobs to utilize the cluster resources. Current systems mostly focus on managing computing resources like CPU and memory, however, they lack flexible and fine-grained management mechanisms for network resources. This has increasingly been an urgent need as current batch systems may be distributed among dozens of sites around the globe like Open Science Grid. The Lark project was motivated by this need to re-examine how the HTC layer interacts with the network layer. In this paper, we present the system architecture of Lark and its implementation as a plugin of HTCondor which is a popular HTC software project. Lark achieves lightweight network virtualization at per-job granularity for HTCondor by utilizing Linux container and virtual Ethernet devices, this provides each batch job with a unique network address in a private network namespace. We extended HTCondor's description language, Class Ads, so users can specify networking requirements in the job submission script. HTCondor can perform matchmaking to make sure user-specified network requirements and resource-specific policies are fulfilled. We also extended the job agent, condor starter, so that it can manage and configure the job's network environment. Given this important building block as the core, we implement bandwidth management functionality at both the host and network levels utilizing software-defined networking (SDN). Our experiments and evaluations show that Lark can effectively manage network resources within the cluster with low overhead. It provides the users with better predictability of their job execution and the administrators more flexibility in network resource consumption policies.

Single-photon emission computed tomography (SPECT) is the leading medical-imaging method for the study myocardial perfusion, which is important for the diagnosis and treatment of coronary-artery disease, the number-one killer in the western world. C-SPECT is a proposed dedicated cardiac SPECT system designed to achieve at least double the geometric efficiency compared to general-purpose dual-head gamma cameras, for the same resolution. This improvement can be used to reduce patient radiation dose, achieve fast or dynamic imaging, and enhance the quality of images. The system consists of stationary detector modules of pixelated NaI(Tl), a slit-slat collimator with interchangeable slits and collapsible slats, and an integrated CT for attenuation correction. The collimator slits provide pinhole collimation in the transverse plane, whereas the slats offer parallel-beam collimation in the axial direction. The adaptive power of the collimator allows us to adjust, in situ, the sensitivity and resolution depending on the imaging task. This way, superior reconstructed-image resolution could be achieved if the system operates with the usual geometric efficiency of the industry's benchmark. The system gantry wraps around patients' left-front thorax and provides a transverse projection minification of ~50%, for a maximal number of minimally-overlapping projections, given the limitations from the spatial resolution of the pixelated detector. We present the design principles and preliminary imaging performance using three-dimensional iterative reconstruction with resolution recovery and data from the newly-built laboratory prototype as well as Monte-Carlo (MC) simulations of the full system. This work was supported by NIH grant HL108119 and utilized resources provided by the Open Science Grid, which is supported by the National Science Foundation and the U.S. Department of Energy's Office of Science.

Before scientific analyses run on shared infrastructure, such as the Open Science Grid or XSEDE, scientists must often transfer or stage key data sets those resources. Often these datasets consist of many files that may be transferred by multiple clients in parallel. We study two techniques that improve the use of available resources for these large, long-running, multi-file transfers. First, we adapt transfer parameters for multi-file transfers based on recent transfer performance. Second, we use VO and site policies to influence the allocation of system resources for transfers, such as available transfer streams. We describe our system design and summarize its implementation and performance.

The execution of scientific workflows in Grid environments imposes many challenges due to the dynamic nature of such environments and the characteristics of scientific applications. This work presents an algorithm that dynamically schedules tasks of workflows to Grid sites based on the performance of these sites when running previous jobs from the same workflow. The algorithm captures the dynamic characteristics of Grid environments without the need to probe the remote sites. We evaluated the algorithm running a workflow in the Open Science Grid using twelve sites. The results showed improvements up to 150% relative to other four usual scheduling strategies.

We describe how we integrate, build, and test the Open Science Grid (OSG) software stack, which is used to provide a production quality infrastructure for grid sites and users across OSG to run their grid jobs. The software stack is sufficiently complex that building and testing the software stack is non-trivial and requires a variety of types of testing including internal integration testing as well as end-user testing.

Gratia originated as an accounting system for batch systems and Linux process accounting. In production since 2006 at FNAL, it was adopted by the Open Science Grid as a distributed, grid-wide accounting system in 2007. Since adoption Gratia's next challenge has been to adapt to an explosive increase in data volume and to handle several new categories of accounting data. Gratia now accounts for regular grid jobs, file transfers, glide-in jobs, and the state of grid services. We show that Gratia gives access to a thorough picture of the OSG and discuss the complexity caused by newer grid techniques such as pilot jobs, job forwarding, and backfill.