Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallel file systems”

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.

At least 271 records · Page 15

Initial Characterization of Parallel NFS Implementations

Parallel NFS (pNFS) is touted as an emergent standard protocol for parallel I/O access in various storage environments. Several pNFS prototypes have been implemented for initial validation and protocol examination. Previous efforts have focused on realizing the pNFS protocol to expose the best bandwidth potential from underlying file and storage systems. In this presentation, we provide an initial characterization of two pNFS prototype implementations, lpNFS (a Lustre-based parallel NFS implementation) and spNFS (another reference implementation from Network Appliance, Inc.). We show that both lpNFS and spNFS can faithfully achieve the primary goal of pNFS, i.e., aggregating I/O bandwidth from many storage servers. However, they both face the challenge of scalable metadata management. Particularly, the throughput of sp-NFS metadata operations degrades significanlty with an increasing number of data servers. Even for the better-performing lpNFS, we discuss its architecture and propose a direct I/O request flow protocol to improve its performance.

97 MATHEMATICS AND COMPUTING↗

Automated Concurrent Blackboard System Generation in C++

In his 1992 Ph.D. thesis, "Design and Analysis Techniques for Concurrent Blackboard Systems", John McManus defined several performance metrics for concurrent blackboard systems and developed a suite of tools for creating and analyzing such systems. These tools allow a user to analyze a concurrent blackboard system design and predict the performance of the system before any code is written. The design can be modified until simulated performance is satisfactory. Then, the code generator can be invoked to generate automatically all of the code required for the concurrent blackboard system except for the code implementing the functionality of each knowledge source. We have completed the port of the source code generator and a simulator for a concurrent blackboard system. The source code generator generates the necessary C++ source code to implement the concurrent blackboard system using Parallel Virtual Machine (PVM) running on a heterogeneous network of UNIX(trademark) workstations. The concurrent blackboard simulator uses the blackboard specification file to predict the performance of the concurrent blackboard design. The only part of the source code for the concurrent blackboard system that the user must supply is the code implementing the functionality of the knowledge sources.

Kaplan, J. A.↗

HOSS!

The Hall-D Online Skim System (HOSS) was developed to simultaneously solve two issues for the high intensity GlueX experiment. One was to parallelize the writing of raw data files to disk in order to improve bandwidth. The other was to distribute the raw data across multiple compute nodes in order to produce calibration skims of the data online. The highly configurable system employs RDMA, RAM disks, and zeroMQ driven by Python to simultaneously store and process the full high intensity GlueX data stream.

Lawrence, David↗

A Secure Web Application Providing Public Access to High-Performance Data Intensive Scientific Resources - ScalaBLAST Web Application

This work presents the ScalaBLAST Web Application (SWA), a web based application implemented using the PHP script language, MySQL DBMS, and Apache web server under a GNU/Linux platform. SWA is an application built as part of the Data Intensive Computer for Complex Biological Systems (DICCBS) project at the Pacific Northwest National Laboratory (PNNL). SWA delivers accelerated throughput of bioinformatics analysis via high-performance computing through a convenient, easy-to-use web interface. This approach greatly enhances emerging fields of study in biology such as ontology-based homology, and multiple whole genome comparisons which, in the absence of a tool like SWA, require a heroic effort to overcome the computational bottleneck associated with genome analysis. The current version of SWA includes a user account management system, a web based user interface, and a backend process that generates the files necessary for the Internet scientific community to submit a ScalaBLAST parallel processing job on a dedicated cluster.

43 PARTICLE ACCELERATORS↗

Bulk Data Mover

Bulk Data Mover (BDM) is a high-level data transfer management tool. BDM handles the issue of large variance in file sizes and a big portion of small files by managing the file transfers with optimized transfer queue and concurrency management algorithms. For example, climate simulation data sets are characterized by large volume of files with extreme variance in file sizes. The BDN achieves high performance using a variety of techniques, including multi-threaded concurrent transfer connections, data channel caching, load balancing over multiple transfer servers, and storage i/o pre-fetching. Logging information from the BDM is collected and analyzed to study the effectiveness of the transfer management algorithms. The BDM can accept a request composed of multiple files or an entire directory. The request also contains the target site and directory where the replicated files will reside. If a directory is provided at the source, then the BDM will replicate the structure of the source directory at the target site. The BDM is capable of transferring multiple files concurrently as well as using parallel TCP streams. The optimal level of concurrency or parallel streams depends on the bandwidth capacity of the storage systems at both ends of the transfer as well as achievable bandwidth of the wide-area network. Hardware req.-PC, MAC, Multi-platform & Workstation; Software req.: Compile/version-Java 1.50_x or above; Type of files: source code, executable modules, installation instructions other, user guide; URL: http://sdm.lbl.gov/bdm/

Natarajan, Vijaya↗

Calibrated simulation analysis for integration of evaporative cooling and radiant cooling system for different Indian climatic zones

Radiant cooling system (RCS) has proven to be an energy efficient system for meeting a building's cooling requirements. RCS is energy efficient and provides better thermal comfort compared to conventional all-air heating ventilation air conditioning (HVAC) system. To further improve the efficiency of RCS, a parallel evaporative cooling system (cooling tower) is coupled with RCS and analyzed for different climatic condition using calibrated model. A statistical analysis of weather files (based on wet bulb temperature), was used to identify the availability of useful water for cooling tower integration with RCS. A comprehensive simulation feasibility study of the application of cooling tower in RCS was performed for different cities to cover every climatic zones of India. It was found that in summer, the wet bulb temperature (WBT) of different climatic zones, except warm-humid, is suitable for the integration of cooling tower with RCS. An experimental setup was designed and developed for integration of parallel chiller and cooling tower with panel-based RCS for cooling and a dedicated outdoor air system (DOAS) for dehumidification and ventilation. Experiments were conducted for chiller and cooling tower operated RCS in Composite climate of Jaipur, Rajasthan, India. Building Energy Models (BEM) were developed for both the chiller-operated RCS and cooling tower-operated RCS in EnergyPlus and calibrated with the measured data. Using the calibrated models, performance of the system was analyzed for different climatic zones of India. A chiller-operated RCS was considered as a baseline to compare the annual energy saving potential and monthly performance of the cooling tower integrated RCS. Here, in the cooling tower–operated RCS, a total annual savings of 7% in hot and dry climates, 11% in composite climates and 20% in temperate climates was achieved compared to the chiller-operated RCS.

54 ENVIRONMENTAL SCIENCES↗

Characterization and identification of HPC applications at leadership computing facility

High Performance Computing (HPC) is an important method for scientific discovery via large-scale simulation, data analysis, or artificial intelligence. Leadership-class supercomputers are expensive, but essential to run large HPC applications. The Petascale era of supercomputers began in 2008, with the first machines achieving performance in excess of one petaflops, and with the advent of new supercomputers in 2021 (e.g., Aurora, Frontier), the Exascale era will soon begin. However, the high theoretical computing capability (i.e., peak FLOPS) of a machine is not the only meaningful target when designing a supercomputer, as the resources demand of applications varies. A deep understanding of the characterization of applications that run on a leadership supercomputer is one of the most important ways for planning its design, development and operation. In order to improve our understanding of HPC applications, user demands and resource usage characteristics, we perform correlative analysis of various logs for different subsystems of a leadership supercomputer. This analysis reveals surprising, sometimes counter-intuitive patterns, which, in some cases, conflicts with existing assumptions, and have important implications for future system designs as well as supercomputer operations. For example, our analysis shows that while the applications spend significant time on MPI, most applications spend very little time on file I/O. Combined analysis of hardware event logs and task failure logs show that the probability of a hardware FATAL event causing task failure is low. Combined analysis of control system logs and file I/O logs reveals that pure POSIX I/O is used more widely than higher level parallel I/O. Based on holistic insights of the application gained through combined and co-analysis of multiple logs from different perspectives and general intuition, we engineer features to "fingerprint" HPC applications. We use t-SNE (a machine learning technique for dimensionality reduction) to validate the explainability of our features and finally train machine learning models to identify HPC applications or group those with similar characteristic. To the best of our knowledge, this is the first work that combines logs on file I/O, computing, and inter-node communication for insightful analysis of HPC applications in production.

Liu, Zhengchun↗

A Path to Operating System and Runtime Support for Extreme Scale Tools

In this project, we cast distributed resource access as operations on files in a global name space and developed a common, scalable solution for group operations on distributed processes and files. The resulting solution enables tool and middleware developers to quickly create new scalable software or easily improve the scalability of existing software. The cornerstone of the project was the design of a new programming idiom called group file operations that eliminates iterative behavior when a single process must apply the same set of file operations to a group of related files. To demonstrate our novel and scalable ideas for group file operations and global name space composition, we developed a group file system called TBON-FS that leverages a tree-based overlay network (TBON), specifically MRNet, for logarithmic communication and distributed data aggregation. We also developed proc++, a new synthetic file system co-designed for use in scalable group file operations. Over the course of the project, we evaluated the utility and performance of group file operations, global name space composition, TBON-FS, and proc++ in three case studies. The first study focused on the ease in using group file operations and TBON-FS to quickly develop several new scalable tools for distributed system administration and monitoring. The second study evaluated the integration of group file operation and TBON-FS within the Ganglia Distributed Monitoring System to improve its scalability for clusters. The final study involved the integration of group file operations, TBON-FS, and proc++ within TotalView, the widely-used parallel debugger. For this project, the work of the Oak Ridge National Laboratory (ORNL) team occurred primarily in two directions: bringing the MRNet tree-based overlay network (TBON) implementation to the Cray XT platform, and investigating techniques for predicting the performance of MRNet topologies on such systems. Rogue Wave Software (RWS), formerly TotalView Technologies Inc., worked with the University ofWisconsin (UW) team on the design and prototyping of a scalable version of the TotalView debugger. RWS assisted UW with their "proc++" design effort. RWS assisted UW with strategy for integrating proc++ into TotalView.

97 MATHEMATICS AND COMPUTING↗

Online data analysis and reduction: An important co-design motif for extreme-scale computers

A growing disparity between supercomputer computation speeds and I/O rates means that it is rapidly becoming infeasible to analyze supercomputer application output only after that output has been written to a file system. Instead, data-generating applications must run concurrently with data reduction and/or analysis operations, with which they exchange information via high-speed methods such as interprocess communications. The resulting parallel computing motif, online data analysis and reduction (ODAR), has important implications for both application and HPC systems design. Here we introduce the ODAR motif and its co-design concerns, describe a co-design process for identifying and addressing those concerns, present tools that assist in the co-design process, and present case studies to illustrate the use of the process and tools in practical settings.

Data Analysis↗

Evaluating the Shared Root File System Approach for Diskless High-Performance Computing Systems

Diskless high-performance computing (HPC) systems utilizing networked storage have become popular in the last several years. Removing disk drives significantly increases compute node reliability as they are known to be a major source of failures. Furthermore, networked storage solutions utilizing parallel I/O and replication are able to provide increased scalability and availability. Reducing a compute node to processor(s), memory and network interface(s) greatly reduces its physical size, which in turn allows for large-scale dense HPC solutions. However, one major obstacle is the requirement by certain operating systems (OSs), such as Linux, for a root file system. While one solution is to remove this requirement from the OS, another is to share the root file system over the networked storage. This paper evaluates three networked file system solutions, NFSv4, Lustre and PVFS2, with respect to their performance, scalability, and availability features for servicing a common root file system in a diskless HPC configuration. Our findings indicate that Lustre is a viable solution as it meets both, scaling and performance requirements. However, certain availability issues regarding single points of failure and control need to be considered.

97 MATHEMATICS AND COMPUTING↗

The Automated Instrumentation and Monitoring System (AIMS) reference manual

Whether a researcher is designing the 'next parallel programming paradigm,' another 'scalable multiprocessor' or investigating resource allocation algorithms for multiprocessors, a facility that enables parallel program execution to be captured and displayed is invaluable. Careful analysis of execution traces can help computer designers and software architects to uncover system behavior and to take advantage of specific application characteristics and hardware features. A software tool kit that facilitates performance evaluation of parallel applications on multiprocessors is described. The Automated Instrumentation and Monitoring System (AIMS) has four major software components: a source code instrumentor which automatically inserts active event recorders into the program's source code before compilation; a run time performance-monitoring library, which collects performance data; a trace file animation and analysis tool kit which reconstructs program execution from the trace file; and a trace post-processor which compensate for data collection overhead. Besides being used as prototype for developing new techniques for instrumenting, monitoring, and visualizing parallel program execution, AIMS is also being incorporated into the run-time environments of various hardware test beds to evaluate their impact on user productivity. Currently, AIMS instrumentors accept FORTRAN and C parallel programs written for Intel's NX operating system on the iPSC family of multi computers. A run-time performance-monitoring library for the iPSC/860 is included in this release. We plan to release monitors for other platforms (such as PVM and TMC's CM-5) in the near future. Performance data collected can be graphically displayed on workstations (e.g. Sun Sparc and SGI) supporting X-Windows (in particular, Xl IR5, Motif 1.1.3).

Yan, Jerry↗

Parallel In Situ Coupling of a Simulation with a Fully Featured Visualization System

There is a widening gap between compute performance and the ability to store computation results. Complex scientific codes are the most affected since they must save massive files containing meshes and fields for offline analysis. Time and storage costs instead dictate that data analysis and visualization be combined with the simulations themselves, being done in situ so data are transformed to a manageable size before they are stored. Earlier approaches to in situ processing involved combining specific visualization algorithms into the simulation code, limiting flexibility. We introduce a new library which instead allows a fully-featured visualization tool, VisIt, to request data as needed from the simulation and apply visualization algorithms in situ with minimal modification to the application code.

99 GENERAL AND MISCELLANEOUS↗

LCIO

Performance of file systems shift during their life cycles. Evaluating this performance change over time is not trivial. Complexity arises in the interplay between external (i.e. application I/O workloads) and internal (i.e. the filesystem state) factors. Many benchmarks can test how a filesystem performs at the current snapshot state, but to observe the change over time necessitates that the filesystem state mutate (age) between benchmark runs. For a large-scale HPC parallel filesystem, the sheer scale and amount of interacting components during I/O operations magnify these challenges. LCIO addresses the question - how will the filesystem perform at different stages of its life cycle? LCIO is a synthetic benchmark, which provides the file system aging process to increase the amount of information that existing benchmarks like IOR and MDTest yield, as well as provide additional points of data that will be useful to system architects and engineers.

Bachstein, Matthew↗

Production Application Performance Data Streaming for System Monitoring

In this article, we present an approach to streaming collection of application performance data. Practical application performance tuning and troubleshooting in production high-performance computing (HPC) environments requires an understanding of how applications interact with the platform, including (but not limited to) parallel programming libraries such as Message Passing Interface (MPI). Several profiling and tracing tools exist that collect heavy runtime data traces either in memory (released only at application exit) or on a file system (imposing an I/O load that may interfere with the performance being measured). Although these approaches are beneficial in development stages and post-run analysis, a systemwide and low-overhead method is required to monitor deployed applications continuously. This method must be able to collect information at both the application and system levels to yield a complete performance picture. In our approach, an application profiler collects application event counters. A sampler uses an efficient inter-process communication method to periodically extract the application counters and stream them into an infrastructure for performance data collection. We implement a tool-set based on our approach and integrate it with the Lightweight Distributed Metric Service (LDMS) system, a monitoring system used on large-scale computational platforms. LDMS provides the infrastructure to create and gather streams of performance data in a low overhead manner. We demonstrate our approach using applications implemented with MPI, as it is one of the most common standards for the development of large-scale scientific applications. We utilize our tool-set to study the impact of our approach on an open source HPC application, Nalu. Our tool-set enables us to efficiently identify patterns in the behavior of the application without source-level knowledge. We leverage LDMS to collect system-level performance data and explore the correlation between the system and application events. Finally, we demonstrate how our tool-set can help detect anomalies with a low latency. We run tests on two different architectures: a system enabled with Intel Xeon Phi and another system equipped with Intel Xeon processor. Our overhead study shows our method imposes at most 0.5% CPU usage overhead on the application in realistic deployment scenarios.

59 BASIC BIOLOGICAL SCIENCES↗

High Performance Access to Archival Data Stored in HDF4 and HDF5 on Cloud Object Stores Without Reformatting the Files

Cloud computing offers numerous advantages for users of extensive Earth science data collections. These benefits encompass direct online access to data files and granules from any location, scalable access supporting parallel computing workflows, and flexible computing tools enabling innovative experimentation with processing techniques. However, older archival file formats designed for distinct computing systems hinder efficient access to decade-long time-series data when compared to data stored in modern cloud-optimized formats like Web Object Stores (WOS), exemplified by Amazon Web Services’ Simple Storage Service (S3). We describe DMR++ (Dataset Metadata Response plus plus), a technology facilitating efficient access to HDF5 (Hierarchical Data Format, version 5) and HDF4 files stored on WOS systems without requiring data reformatting. DMR++ achieves performance comparable to technologies like Zarr while preserving the original file structure, a substantial benefit considering the vast quantity of archival files held by organizations such as NASA. Moreover, DMR++ typically outperforms cloud-optimized versions of HDF5. Essentially an XML (Extensible Markup Language) document usually stored alongside the described data, DMR++ can also be generated on-the-fly but is generally created during data staging to the WOS. Archival files that use HDF4/5 often store large arrays of numerical data. The data in these files is often compressed, typically reducing their size by a factor of four or more. To achieve efficient access to portions of those arrays, they are 'chunked' into smaller sub-arrays, each individually compressed. The chunk size is a compromise, where spinning disks can efficiently access data in smaller chunks while S3 favors larger chunks. A simple optimization of aggregating smaller chunks that are stored adjacently, transferring them in a single access and then individually decompressing them will improve performance. NASA data pose an additional challenge: special Application Programmer Interface (API) libraries are often needed to compute some variables. These libraries are incompatible with WOS environments. Our solution involves storing computed values in the DMR++ document or a companion file, making them accessible like other variables and eliminating the need for specialized APIs. We outline specific optimizations for both satellite grid and swath data stored in HDF4-EOS2 (Earth Observing System).

James Gallagher↗

Lessons learned at 208K: Towards Debugging Millions of Cores

Petascale systems will present several new challenges to performance and correctness tools. Such machines may contain millions of cores, requiring that tools use scalable data structures and analysis algorithms to collect and to process application data. In addition, at such scales, each tool itself will become a large parallel application--already, debugging the full Blue-Gene/L (BG/L) installation at the Lawrence Livermore National Laboratory requires employing 1664 tool daemons. To reach such sizes and beyond, tools must use a scalable communication infrastructure and manage their own tool processes efficiently. Some system resources, such as the file system, may also become tool bottlenecks. In this paper, we present challenges to petascale tool development, using the Stack Trace Analysis Tool (STAT) as a case study. STAT is a lightweight tool that gathers and merges stack traces from a parallel application to identify process equivalence classes. We use results gathered at thousands of tasks on an Infiniband cluster and results up to 208K processes on BG/L to identify current scalability issues as well as challenges that will be faced at the petascale. We then present implemented solutions to these challenges and show the resulting performance improvements. We also discuss future plans to meet the debugging demands of petascale machines.

99 GENERAL AND MISCELLANEOUS↗

Applied Parallel Metadata Indexing

The GPFS Archive is parallel archive is a parallel archive used by hundreds of users in the Turquoise collaboration network. It houses 4+ petabytes of data in more than 170 million files. Currently, users must navigate the file system to retrieve their data, requiring them to remember file paths and names. A better solution might allow users to tag data with meaningful labels and searach the archive using standard and user-defined metadata, while maintaining security. last summer, I developed the backend to a tool that adheres to these design goals. The backend works by importing GPFS metadata into a MongoDB cluster, which is then indexed on each attribute. This summer, the author implemented security and developed the user interfae for the search tool. To meet security requirements, each database table is associated with a single user, which only stores records that the user may read, and requires a set of credentials to access. The interface to the search tool is implemented using FUSE (Filesystem in USErspace). FUSE is an intermediate layer that intercepts file system calls and allows the developer to redefine how those calls behave. In the case of this tool, FUSE interfaces with MongoDB to issue queries and populate output. A FUSE implementation is desirable because it allows users to interact with the search tool using commands they are already familiar with. These security and interface additions are essential for a usable product.

97 MATHEMATICS AND COMPUTING↗

Online Monitoring of Medium Voltage Cable Systems with Spread Spectrum Time Domain and Frequency Domain Reflectometry

In-service failures of wave energy convertor (WEC) cable systems can have a significant cost and power availability impact. Close parallel research 2019 data showed > 1B£ and 9 Terra-Watt-Hours associated with global off-shore wind (OSW) cable failures (Strang-Moran 2020). OSW is a closely related technology but currently is significantly cheaper than WEC technology. For wave energy to compete, the problem of reliable cable transmission must be mitigated. This project develops isolation technology to allow online high frequency reflectometry testing of medium voltage cables (1 to 10 kV and higher) without arcing or damage to the test instrument. Online spread spectrum time domain reflectometry (SSTDR) testing has been established for low voltage cable systems in the aircraft and rail industry and the ability to detect and locate cable flaws of interest is well understood. Extending reflectometry testing to medium voltage systems could enable detection of cable damage before failures occur thereby allowing repair and replacement of damaged cable segments to be scheduled and managed. The seedling project succeeded to pass and receive high frequency SSTDR signals onto a cable up to 1 kV using a parallel trace isolation circuit board that can be connected onto the test cable. The approach used a novel circuit design for which an invention disclosure has been filed. A proposed sapling project would extend the technology toward the higher operating voltages used by WEC systems, thereby enabling online SSTDR cable monitoring. The goal of the seedling project was to extend the capability of the ARENA cable/motor test bed to address medium voltages and to develop a high pass filter isolation architecture to protect the reflectometry instrument from the low frequency (DC – 60 Hz) line voltage while allowing the high frequency diagnostic signal to pass to and from the test instrument to the live line. Initial efforts focused on passive LCR filter circuits to reduce 60 Hz levels below 10 volts from a 10 kV line while allowing the MHz high frequency chirps to pass onto the cables and for mV signals to be detected. We discovered that the parasitic loss behavior of real high voltage components precluded this approach from working. An alternate approach was adapted for the electric field to couple between two parallel traces on a printed circuit board much like a radio-frequency coupler. The challenge here was and is to have the parallel traces close enough to each other to effectively pass the high frequency chirp onto the live line and receive any reflected signal from any encountered impedance change along the cable. This reflected signal will be in the mV range. The traces however must be far enough apart to not allow arcing on the board. A design with 3 mm spacing was determined to allow the high frequency signal to pass onto the live line and receive the mV signal back into the instrument while reducing the 60 Hz voltage amplitude by >80 dB (more than a factor of 10,000) without allowing arcing from across the parallel traces. This was confirmed by simulation and test.

16 TIDAL AND WAVE POWER↗