SEARCH · Engineering Papers
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.
Set of subroutines provides the FORTRAN user with protected, permanent, disk storage of data on an IBM 1620 Monitor 11-D system. The program consists of a set of four subroutines and a utility program. It allows block data to be transferred directly between assigned core locations and disk storage.
Full-3D seismic waveform tomography (F3DT) is the latest seismic tomography technique that can assimilate broadband, multi-component seismic waveform observations into high-resolution 3D subsurface seismic structure models. The main drawback in the current F3DT implementation, in particular the scattering-integral implementation (F3DT-SI), is the high disk storage cost and the associated I/O overhead of archiving the 4D space-time wavefields of the receiver- or source-side strain tensors. The strain tensor fields are needed for computing the data sensitivity kernels, which are used for constructing the Jacobian matrix in the Gauss-Newton optimization algorithm. In this study, we have successfully integrated a lossy compression algorithm into our F3DT SI workflow to significantly reduce the disk space for storing the strain tensor fields. The compressor supports a user-specified tolerance for bounding the error, and can be integrated into our finite-difference wave-propagation simulation code used for computing the strain fields. The decompressor can be integrated into the kernel calculation code that reads the strain fields from the disk and compute the data sensitivity kernels. During the wave-propagation simulations, we compress the strain fields before writing them to the disk. To compute the data sensitivity kernels, we read the compressed strain fields from the disk and decompress them before using them in kernel calculations. Experiments using a realistic dataset in our California statewide F3DT project have shown that we can reduce the strain-field disk storage by at least an order of magnitude with acceptable loss, and also improve the overall I/O performance of the entire F3DT-SI workflow significantly. The integration of the lossy online compressor may potentially open up the possibilities of the wide adoption of F3DT-SI in routine seismic tomography practices in the near future.
Abstract not provided.
The RACF (RHIC-ATLAS Computing Facility) has operated a large, multi-purpose dedicated computing facility since the mid-l 990's, serving a worldwide, geographically diverse scientific community that is a major contributor to various HEPN projects. A central component of the RACF is the Linux-based worker node cluster that is used for both computing and data storage purposes. It currently has nearly 50,000 computing cores and over 23 PB of storage capacity distributed over 12,000+ (non-SSD) disk drives. The majority of the 12,000+ disk drives provide a cost-effective solution for dCache/XRootD-managed storage, and a key concern is the reliability of this solution over the lifetime of the hardware, particularly as the number of disk drives and the storage capacity of individual drives grow. We report initial results of a long-term study to measure lifetime PB read/written to disk drives in the worker node cluster. We discuss the historical disk drive mortality rate, disk drive manufacturers' published MPTF (Mean PB to Failure) data and how they are correlated to our results. The results help the RACF understand the productivity and reliability of its storage solutions and have implications for other highly-available storage systems (NFS, GPFS, CVMFS, etc) with large I/0 requirements.
Data are concurrently recorded on disk by one minicomputer and accessed by another, using format of memory blocks, buffering algorithm, and time-sequence addressing. Buffering algorithm works at data rates up to 68,000 words per second; modifications up rate to 160,000 words per second.
The Kodak Digital Science OD System 2000E automated disk library (ADL) base module and write-once drive are being developed as the next generation commercial product to the currently available System 2000 ADL. Under government sponsorship with the Air Force's Rome Laboratory, Kodak is developing magneto-optic (M-O) subsystems compatible with the Kodak Digital Science ODW25 drive architecture, which will result in a multifunction (MF) drive capable of reading and writing 25 gigabyte (GB) WORM media and 15 GB erasable media. In an OD system 2000 E ADL configuration with 4 MF drives and 100 total disks with a 50% ration of WORM and M-O media, 2.0 terabytes (TB) of versatile near line mass storage is available.
Energy saving has become a crucial concern in datacenters as several reports predict that the anticipated energy costs over a three year period will exceed hardware acquisition. In particular, saving energy for storage is of major importance as storage devices (and cooling them off) may contribute over 25 percent of the total energy consumed in a datacenter. Recent work introduced the concept of energy proportionality and argued that it is a more relevant metric than just energy saving as it takes into account the tradeoff between energy consumption and performance. In this paper, we present a novel approach, called FREP (Fractional Replication for Energy Proportionality), for energy management in large datacenters. FREP includes areplication strategy and basic functions to enable flexible energy management. Specifically, our method provides performance guarantees by adaptively controlling the power states of a group of disks based on observed and predicted workloads. Our experiments, using a set of real and synthetic traces, show that FREP dramatically reduces energy requirements with a minimal response time penalty.
There is a growing need within the Air Force for more and better data storage solutions. Rome Laboratory, the Air Force's Center of Excellence for C3I technology, has sponsored the development of a number of operational prototypes to deal with this growing problem. This paper will briefly summarize the various prototype developments with examples of full mil-spec and best commercial practice. These prototypes have successfully operated under severe space, airborne and tactical field environments. From a technical perspective these prototypes have included rewritable optical media ranging from a 5.25-inch diameter format up to the 14-inch diameter disk format. Implementations include an airborne sensor recorder, a deployable optical jukebox and a parallel array of optical disk drives. They include stand-alone peripheral devices to centralized, hierarchical storage management systems for distributed data processing applications.
Abstract not provided.
A parallel supercomputing cluster includes compute nodes interconnected in a mesh of data links for executing an MPI job, and solid-state storage nodes each linked to a respective group of the compute nodes for receiving checkpoint data from the respective compute nodes, and magnetic disk storage linked to each of the solid-state storage nodes for asynchronous migration of the checkpoint data from the solid-state storage nodes to the magnetic disk storage. Each solid-state storage node presents a file system interface to the MPI job, and multiple MPI processes of the MPI job write the checkpoint data to a shared file in the solid-state storage in a strided fashion, and the solid-state storage node asynchronously migrates the checkpoint data from the shared file in the solid-state storage to the magnetic disk storage and writes the checkpoint data to the magnetic disk storage in a sequential fashion.
The current Life Sciences Laboratory Equipment (LSLE) microcomputer for life sciences experiment data acquisition is now obsolete. Among the weaknesses of the current microcomputer are small memory size, relatively slow analog data sampling rates, and the lack of a bulk data storage device. While life science investigators normally prefer data to be transmitted to Earth as it is taken, this is not always possible. No down-link exists for experiments performed in the Shuttle middeck region. One important aspect of a replacement microcomputer is provision for in-flight storage of experimental data. The Write Once, Read Many (WORM) optical disk was studied because of its high storage density, data integrity, and the availability of a space-qualified unit. In keeping with the goals for a replacement microcomputer based upon commercially available components and standard interfaces, the system studied includes a Small Computer System Interface (SCSI) for interfacing the WORM drive. The system itself is designed around the STD bus, using readily available boards. Configurations examined were: (1) master processor board and slave processor board with the SCSI interface; (2) master processor with SCSI interface; (3) master processor with SCSI and Direct Memory Access (DMA); (4) master processor controlling a separate STD bus SCSI board; and (5) master processor controlling a separate STD bus SCSI board with DMA.
This is a report on Data Storage Disk Evaluation and characterization. The purpose of this memo is to capture new recipients due to some recent characterization issues with the Hammer Mill process. The Data Storage Disk Evaluation report was generated utilizing data acquired during 2009 and 2010 from submitted storage media.
The specifications and techniques related to the development of the NASA Spaceflight Optical Disk Recorder (SODR) are presented. The system is being developed for the temporary storage of high-resolution sensor data that will be collected at high data rates by future space programs. Typical spaceflight recording requirements are given for the Space Station Freedom, the Earth Observing System, and some planetary missions. SODR module characteristics are listed, emphasizing the two independent optical disk recorders and the random access to 5 gigabytes of data on each side of the disks. The modular design includes two I/O ports providing 150 Mbits/sec user data rate each, and multimodule reconfigurable architecture permitting the synchronization of up to 16 modules with a maximum data rate of 4.8 gigabits/sec.
An overall space information system is considered. It is found that data storage is required in all elements of the system with the possible exception of the wideband communication link. The data capture facility is the first ground facility to handle space-acquired data. A typical nine-day Spacelab mission is expected to generate up to 10 to the 13th bits of data. The current storage medium for this data is approximately 4000 magnetic tapes. It is pointed out that optical disk storage provides an attractive alternative to magnetic disk and tape storage. Options to install an optical disk storage system in the GSFC data capture facility in the 1986 time frame are evaluated by NASA. Attention is given to data capture and data base applications, onboard data storage applications, and numerical computation applications.
This paper examines the problem of implementing rollback recovery in multicomputer distributed shared virtual memory environments, in which the shared memory is implemented in software and exists only virtually. A user-transparent checkpointing recovery scheme and new twin-page disk storage management are presented to implement a recoverable distributed shared virtual memory. The checkpointing scheme is integrated with the shared virtual memory management. The twin-page disk approach allows incremental checkpointing without an explicit undo at the time of recovery. A single consistent checkpoint state is maintained on stable disk storage. The recoverable distributed shared virtual memory allows the system to restart computation from a previous checkpoint due to a processor failure without a global restart.
Traditionally, the Lustre file system has relied on the ldiskfs file system with reliable RAID (Redundant Array of Independent Disks) storage underneath. As of Lustre 2.4, ZFS was added as a backend file system, with built-in software RAID, thereby removing the need of expensive RAID controllers. ZFS was designed to work with JBOD (Just a Bunch Of Disks) storage enclosures under the Solaris Operating System, which provided a rich device management system. Long time users of the Lustre file system have relied on the RAID controllers to provide metrics and enclosure monitoring and management services, with rich APIs and command line interfaces. This paper will study a hybrid approach using an advanced full featured RAID enclosure which is presented to the host as a JBOD, This RBOD (RAIDed Bunch Of Disks) allows ZFS to do the RAID protection and error correction, while the RAID controller handles management of the disks and monitors the enclosure. It was hoped that the value of the RAID controller features would offset the additional cost, and that performance would not suffer in this mode. The test results revealed that the hybrid RBOD approach did suffer reduced performance.
A background/foreground data acquisition and analysis system incorporating a high level control language was developed for acquiring both singles and dual parameter coincidence data from scintillation detectors at the Radiation Counting Laboratory at the NASA Manned Spacecraft Center in Houston, Texas. The system supports acquisition of gamma ray spectra in a 256 x 256 coincidence matrix (utilizing disk storage) and simultaneous operation of any of several background support and data analysis functions. In addition to special instruments and interfaces, the hardware consists of a PDP-9 with 24K core memory, 256K words of disk storage, and Dectape and Magtape bulk storage.
One important outcome of the 7th International e-VLBI Workshop in Shanghai in June 2008 was the creation of a task force to study and recommend a universal VLBI data format that is suitable for both on-the-wire e-VLBI data transfer, as well as direct disk storage. This task force, called the VLBI Data Interchange Format (VDIF) Task Force, is the first part of a two-part effort, the second of which will address standardization of e-VLBI data-transmission-protocols. The formation of the VDIF Task Force was prompted particularly by increased e-VLBI activity and the difficulties encountered when data arrive at a correlator in different formats from various instruments in various parts of the world. The task force created a streaming packetized data format that may be used for real-time and non-realtime e-VLBI, as well as direct disk storage. The data may contain multiple channels of time-sampled data with an arbitrary number of channels, arbitrary #bits/sample up to 32, and real or complex data; data rates in excess of 100 Gbps are supported. Each data packet is completely self-identifying via a short header, and data may be decoded without reference to any external information. The VDIF task force has completed its work, and the VDIF standard was ratified at the 2009 e-VLBI workshop in Madrid.