Search NASA⌕ Search

SEARCH · Search NASA

Results for “throughput”

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 1,495 records · Page 83

Life in the fast lane for protein crystallization and X-ray crystallography

The common goal for structural genomic centers and consortiums is to decipher as quickly as possible the three-dimensional structures for a multitude of recombinant proteins derived from known genomic sequences. Since X-ray crystallography is the foremost method to acquire atomic resolution for macromolecules, the limiting step is obtaining protein crystals that can be useful of structure determination. High-throughput methods have been developed in recent years to clone, express, purify, crystallize and determine the three-dimensional structure of a protein gene product rapidly using automated devices, commercialized kits and consolidated protocols. However, the average number of protein structures obtained for most structural genomic groups has been very low compared to the total number of proteins purified. As more entire genomic sequences are obtained for different organisms from the three kingdoms of life, only the proteins that can be crystallized and whose structures can be obtained easily are studied. Consequently, an astonishing number of genomic proteins remain unexamined. In the era of high-throughput processes, traditional methods in molecular biology, protein chemistry and crystallization are eclipsed by automation and pipeline practices. The necessity for high-rate production of protein crystals and structures has prevented the usage of more intellectual strategies and creative approaches in experimental executions. Fundamental principles and personal experiences in protein chemistry and crystallization are minimally exploited only to obtain "low-hanging fruit" protein structures. We review the practical aspects of today's high-throughput manipulations and discuss the challenges in fast pace protein crystallization and tools for crystallography. Structural genomic pipelines can be improved with information gained from low-throughput tactics that may help us reach the higher-bearing fruits. Examples of recent developments in this area are reported from the efforts of the Southeast Collaboratory for Structural Genomics (SECSG).

Review↗

NEXT Long-Duration Test After 11,570 h and 237 kg of Xenon Processed

The NASA s Evolutionary Xenon Thruster (NEXT) program is developing the next-generation ion propulsion system with significant enhancements beyond the state-of-the-art in ion propulsion to provide future NASA science missions with enhanced mission capabilities at a low total development cost. As part of a comprehensive thruster service life assessment utilizing both testing and analyses, a Long-Duration Test (LDT) was initiated to validate and qualify the NEXT propellant throughput capability to a qualification-level of 450 kg, 1.5 times the mission-derived throughput requirement of 300 kg. This wear test is being conducted with a modified, flight-representative NEXT engineering model ion thruster, designated EM3. As of September 1, 2007, the thruster has accumulated 11,570 h of operation primarily at the thruster full-input-power of 6.9 kW with 3.52 A beam current and 1800 V beam power supply voltage. The thruster has processed 237 kg of xenon surpassing the NSTAR propellant throughput demonstrated during the extended life testing of the Deep Space 1 (DS1) flight spare. The NEXT LDT has demonstrated a total impulse of 9.78 10(exp 6) N(dot)s; the highest total impulse ever demonstrated by an ion thruster. Thruster performance tests are conducted periodically over the entire NEXT throttle table with input power ranging 0.5 to 6.9 kW. Thruster performance parameters including thrust, input power, specific impulse, and thruster efficiency have been nominal with little variation to date. Lifetime-limiting component erosion rates have been consistent with the NEXT service life assessment, which predicts the earliest failure sometime after 750 kg of xenon propellant throughput; well beyond the mission-derived lifetime requirement. The NEXT wear test data confirm that the erosion of the discharge keeper orifice, enlarging of nominal-current-density accelerator grid aperture cusps at full-power, and the decrease in cold grid-gap observed during NSTAR wear testing have been mitigated in the NEXT design. NEXT grid-gap data indicate a hot grid-gap at full-power that is 60 percent of the nominal cold grid-gap. This paper presents the status of the NEXT LDT to date with emphasis on comparison to the NSTAR extended life test results.

Soulas, George C.↗

NEXT Long-Duration Test Plume and Wear Characteristics after 16,550 h of Operation and 337 kg of Xenon Processed

The NASA s Evolutionary Xenon Thruster (NEXT) program is developing the next-generation ion propulsion system with significant enhancements beyond the state-of-the-art. The NEXT ion propulsion system provides improved mission capabilities for future NASA science missions to enhance and enable Discovery, New Frontiers, and Flagship-type NASA missions. As part of a comprehensive thruster service life assessment utilizing both testing and analyses, a Long-Duration Test (LDT) was initiated to validate and qualify the NEXT propellant throughput capability to a qualification-level of 450 kg, 1.5 times the mission-derived throughput requirement of 300 kg. This wear test is being conducted with a modified, flight-representative NEXT engineering model ion thruster, designated EM3. As of June 25, 2008, the thruster has accumulated 16,550 h of operation: the first 13,042 h at the thruster full-input-power of 6.9 kW with 3.52 A beam current and 1800 V beam power supply voltage. Operation since 13,042 h, i.e., the most recent 3,508 h, has been at an input power of 4.7 kW with 3.52 A beam current and 1180 V beam power supply voltage. The thruster has processed 337 kg of xenon (Xe) surpassing the NSTAR propellant throughput demonstrated during the extended life testing of the Deep Space 1 flight spare. The NEXT LDT has demonstrated a total impulse of 13.3 106 N s; the highest total impulse ever demonstrated by an ion thruster. Thruster plume diagnostics and erosion measurements are obtained periodically over the entire NEXT throttle table with input power ranging 0.5 to 6.9 kW. Observed thruster component erosion rates are consistent with predictions and the thruster service life assessment. There have not been any observed anomalous erosion and all erosion estimates indicate a thruster throughput capability that exceeds ~750 kg of Xe, an equivalent of 36,500 h of continuous operation at the full-power operating condition. This paper presents the erosion measurements and plume diagnostic results for the NEXT LDT to date with emphasis on the change in thruster operating condition and resulting impact on wear characteristics. Ion optics grid-gap data, both cold and operating, are presented. Performance and wear predictions for the LDT throttle profile are presented.

Herman, Daniel A.↗

Incorporating Active Runway Crossings in Airport Departure Scheduling

A mixed integer linear program is presented for deterministically scheduling departure and ar rival aircraft at airport runways. This method addresses different schemes of managing the departure queuing area by treating it as first-in-first-out queues or as a simple par king area where any available aircraft can take-off ir respective of its relative sequence with others. In addition, this method explicitly considers separation criteria between successive aircraft and also incorporates an optional prioritization scheme using time windows. Multiple objectives pertaining to throughput and system delay are used independently. Results indicate improvement over a basic first-come-first-serve rule in both system delay and throughput. Minimizing system delay results in small deviations from optimal throughput, whereas minimizing throughput results in large deviations in system delay. Enhancements for computational efficiency are also presented in the form of reformulating certain constraints and defining additional inequalities for better bounds.

Gupta, Gautam↗

Lifetime Assessment of the NEXT Ion Thruster

Ion thrusters are low thrust, high specific impulse devices with required operational lifetimes on the order of 10,000 to 100,000 hr. The NEXT ion thruster is the latest generation of ion thrusters under development. The NEXT ion thruster currently has a qualification level propellant throughput requirement of 450 kg of xenon, which corresponds to roughly 22,000 hr of operation at the highest throttling point. Currently, a NEXT engineering model ion thruster with prototype model ion optics is undergoing a long duration test to determine wear characteristics and establish propellant throughput capability. The NEXT thruster includes many improvements over previous generations of ion thrusters, but two of its component improvements have a larger effect on thruster lifetime. These include the ion optics with tighter tolerances, a masked region and better gap control, and the discharge cathode keeper material change to graphite. Data from the NEXT 2000 hr wear test, the NEXT long duration test, and further analysis is used to determine the expected lifetime of the NEXT ion thruster. This paper will review the predictions for all of the anticipated failure mechanisms. The mechanisms will include wear of the ion optics and cathode s orifice plate and keeper from the plasma, depletion of low work function material in each cathode s insert, and spalling of material in the discharge chamber leading to arcing. Based on the analysis of the NEXT ion thruster, the first failure mode for operation above a specific impulse of 2000 sec is expected to be the structural failure of the ion optics at 750 kg of propellant throughput, 1.7 times the qualification requirement. An assessment based on mission analyses for operation below a specific impulse of 2000 sec indicates that the NEXT thruster is capable of double the propellant throughput required by these missions.

VanNoord, Jonathan L.↗

Fast and Adaptive Lossless Onboard Hyperspectral Data Compression System

Modern hyperspectral imaging systems are able to acquire far more data than can be downlinked from a spacecraft. Onboard data compression helps to alleviate this problem, but requires a system capable of power efficiency and high throughput. Software solutions have limited throughput performance and are power-hungry. Dedicated hardware solutions can provide both high throughput and power efficiency, while taking the load off of the main processor. Thus a hardware compression system was developed. The implementation uses a field-programmable gate array (FPGA). The implementation is based on the fast lossless (FL) compression algorithm reported in Fast Lossless Compression of Multispectral-Image Data (NPO-42517), NASA Tech Briefs, Vol. 30, No. 8 (August 2006), page 26, which achieves excellent compression performance and has low complexity. This algorithm performs predictive compression using an adaptive filtering method, and uses adaptive Golomb coding. The implementation also packetizes the coded data. The FL algorithm is well suited for implementation in hardware. In the FPGA implementation, one sample is compressed every clock cycle, which makes for a fast and practical realtime solution for space applications. Benefits of this implementation are: 1) The underlying algorithm achieves a combination of low complexity and compression effectiveness that exceeds that of techniques currently in use. 2) The algorithm requires no training data or other specific information about the nature of the spectral bands for a fixed instrument dynamic range. 3) Hardware acceleration provides a throughput improvement of 10 to 100 times vs. the software implementation. A prototype of the compressor is available in software, but it runs at a speed that does not meet spacecraft requirements. The hardware implementation targets the Xilinx Virtex IV FPGAs, and makes the use of this compressor practical for Earth satellites as well as beyond-Earth missions with hyperspectral instruments.

Aranki, Nazeeh I.↗

High Count-Rate Study of Two TES X-Ray Microcalorimeters With Different Transition Temperatures

We have developed transition-edge sensor (TES) microcalorimeter arrays with high count-rate capability and high energy resolution to carry out x-ray imaging spectroscopy observations of various astronomical sources and the Sun. We have studied the dependence of the energy resolution and throughput (fraction of processed pulses) on the count rate for such microcalorimeters with two different transition temperatures T(sub c). Devices with both transition temperatures were fabricated within a single microcalorimeter array directly on top of a solid substrate where the thermal conductance of the microcalorimeter is dependent upon the thermal boundary resistance between the TES sensor and the dielectric substrate beneath. Because the thermal boundary resistance is highly temperature dependent, the two types of device with different T(sub c)(sup s) had very different thermal decay times, approximately one order of magnitude different. In our earlier report, we achieved energy resolutions of 1.6 and 2.eV at 6 keV from lower and higher T(sub c) devices, respectively, using a standard analysis method based on optimal filtering in the low flux limit. We have now measured the same devices at elevated x-ray fluxes ranging from 50 Hz to 1000 Hz per pixel. In the high flux limit, however, the standard optimal filtering scheme nearly breaks down because of x-ray pile-up. To achieve the highest possible energy resolution for a fixed throughput, we have developed an analysis scheme based on the socalled event grade method. Using the new analysis scheme, we achieved 5.0 eV FWHM with 96 Percent throughput for 6 keV x-rays of 1025 Hz per pixel with the higher T(sub c) (faster) device, and 5.8 eV FWHM with 97 Percent throughput with the lower T(sub c) (slower) device at 722 Hz.

Lee, Sang-Jun↗

Prediction of Weather Impacts on Airport Arrival Meter Fix Capacity

This paper introduces a data driven model for predicting airport arrival capacity with a look-ahead time 2-8 hour forecast. The model is suitable for air traffic flow management by explicitly investigating the impact of convective weather on airport arrival meter fix throughput. Estimation of the arrival airport capacity under arrival meter fix flow constraints due to severe weather is an important part of Air Traffic Management (ATM). Airport arrival capacity can be reduced if one or more airport arrival meter fixes are partially or completely blocked by convective weather. When the predicted airport arrival demands exceed the predicted available airport's arrival capacity for a sustained period, Ground Delay Program (GDP) operations will be triggered by ATM system. Serious imbalances between demand and capacity occur most frequently when the airport capacity is severely degraded due to either bad airport terminal surface weather or inclement convective weather around airport arrival fixes. A model that predicts the weather-impacted airport arrival meter fix throughput may help ATM personnel to plan GDP operations more efficiently. This paper identifies the characteristics of air traffic flow across arrival meter fixes at Newark Liberty International Airport (EWR). The proposed approach, based on machine-learning methods, is developed to predict the weather impacted EWR arrival Meter Fix (MF) throughput. Sector forecast coverage is used to envision the weather impact on airport arrival MF flow, and the validation is accomplished by using Convective Weather Avoidance Model (CWAM) 0.5 to 2-hour and Collaborative Convective Forecast Product (CCFP) 4 to 8-hour look-ahead forecast data for the period of April-September in 2014. Furthermore, the regression tree ensemble learning of random forests approach for translating a sector forecast coverage model to an EWR arrival meter fix throughput model is examined. The results suggest that ATM decision makers in charge of MF flow control and GDP planning may benefit from adopting the airport arrival meter capacity prediction models to estimate the inclement weather impacts.

Wang, Yao X.↗

22 N HPGP Thruster Life Testing

In the ever-changing paradigm of efficient and capable spacecraft design, scientific missions continue pushing the envelope enabling spacecraft subsystems to deliver effective solutions to meet challenging new mission/spacecraft needs. From an in-space storable liquid chemical propulsion perspective, monopropellant hydrazine has been, and continues to be, a dependable propellant with considerable flight heritage, a variety of engine thrust classes available from multiple vendors, with repeatable and reliable performance. Additionally, the space propulsion industry has learned to successfully handle hydrazine, its regulations, the safety protocols, the personnel protective equipment, and the unique training standards–all requisite for loading spacecraft propulsion systems with toxic hypergolic hydrazine. The question now arises as to “what is next for in-space chemical propulsion?” Further, with the evolution and concrete advancements in innovative in-space green propellant technologies, capable of providing realizable benefits to scientific missions, concern over the reliability and availability of this higher performing and safer to handle class of propellants is waning. As science missions move forward with the potential flight in fusion of High Performance Green Propulsion (HPGP), NASA and its industry partners are working to address any gaps in system reliability, performance, or unique operational considerations. Propellant technology that offers both higher performance and significant reduction in personnel hazards compared to hydrazine presents an attractive propulsion subsystem design opportunity. Increased propulsion subsystem performance can result in lower spacecraft launch mass, larger scientific payloads, or extended on-orbit lifetimes. Mission trades using green propulsion technologies have been documented on multiple NASA Goddard Space Flight Center (GSFC) mission classes, examining various parameters and requirements to support mission architectures in Low Earth Orbit (LEO), High Earth Orbit (HEO), geostationary, lunar, planetary, and Quasi-halo orbit around Sun-Earth Lagrange point (L2). The results of these trade studies show promising, attainable benefits. The perceived programmatic risk of flying a newer propulsion technology has, unfortunately, not outweighed the benefits to date. To take advantage of the improved performance and mitigate programmatic risk, HPGP engines must demonstrate life testing at higher propellant throughputs than have currently been demonstrated. In an effort to proactively address the challenges with technology infusion into a risk-averse community, NASA and the Swedish National Space Agency (SNSA) outlined a collaborative Implementing Arrangement (IA) for the respective agencies to pursue increased HPGP technology maturation. This initial IA effort began in 2013, fresh off the heels of the successful PRISMA HPGP technology demonstration mission. The IA targeted objective is to reduce risk to potential future HPGP missions and fully characterize the LMP-103S propellant and associated engine performance. Over the past eight years, HPGP has flown in propulsion systems on twenty-five(25) spacecraft from seven(7) different Launch Ranges around the globe and on seven (7) different Launch Vehicles. Six(6) of these launches involved multiple loading operations for multiple spacecraft. For U.S. Range operations, nine (9) HPGP systems have been processed at Vandenberg Space Force Base(VSFB):six(6) in 2017, and three (3) in 2018. Six (6) more have been processed at Cape Canaveral Air Force Station (CCAFS)in May 2020, with three (3) systems launched in June 2020 and the remaining three (3) system were left loaded and ready until their launch in August of 2020. Three (3) more systems have been processed at Wallops Flight Facility(WFF)and launched in June 2021. In addition, these propulsion subsystems employed heritage propulsion subsystem component such as valves, filters, and pressure transducers, and have further demonstrated nominal functionality in both diaphragm and Propellant Management Device (PDM) propellant tanks. Based on these successes, HPGP technology continues to be considered for NASA Science Mission Directorate missions at GSFC. The work presented herein represents many years of development and collaborative efforts to successfully align higher performance, low toxicity hydrazine alternatives into scientific missions. NASA GSFC Propulsion Engineering, in collaboration with Bradford ECAPS, has developed mission specific thruster design and testing requirements to establish GSFC’s desired test conditions and firing sequences.In2017, the first flight-like 22N HPGP thruster Engineering Qualification Model (EQM-1)was designed and built by Bradford ECAPS to prove out the thruster design, materials, build process, and test campaign with respect to NASA GSFC critical component and mission requirements. This test program was developed to comprehensively test the thruster, the technology, and ultimately increase the 22N HPGP Technology Readiness Level(TRL). EQM-1was tested to environmental qualification levels prior to hot fire performance testing to represent the relevant end-to-end environment (launch to on-orbit operation)with required margin. This thruster demonstrated steady-state and pulse mode operational capability with propellant thruster throughput up to~53kg.At this throughput level, the EQM-1 engine began to present off-nominal performance and the test campaign was halted to allow for non-destructive testing and identify the root cause for the an omalous performance. Capitalizing on the successful elements of the EQM-1 campaign, an upgraded 22N HPGP EQM-2 has been manufactured by Bradford ECAPS to meet the complete GSFC requirements. The EQM-2 thruster’s test campaign has further demonstrated the robustness of the HPGP propulsion technology and increased the Technology Readiness Level (TRL) by undergoing a full acceptance test program, then proceeding into qualification, including environmental testing (vibration and shock to qualification levels),as well as hot-fire life testing, operating at steady-state and pulse modes with increased propellant thruster throughput to~150kg. The HPGP thruster performance testing enables effective HPGP thruster readiness evaluation to meet NASA candidate mission requirements in the future.

High↗

Life in the fast lane for protein crystallization and X-ray crystallography

The common goal for structural genomic centers and consortiums is to decipher as quickly as possible the three-dimensional structures for a multitude of recombinant proteins derived from known genomic sequences. Since X-ray crystallography is the foremost method to acquire atomic resolution for macromolecules, the limiting step is obtaining protein crystals that can be useful of structure determination. High-throughput methods have been developed in recent years to clone, express, purify, crystallize and determine the three-dimensional structure of a protein gene product rapidly using automated devices, commercialized kits and consolidated protocols. However, the average number of protein structures obtained for most structural genomic groups has been very low compared to the total number of proteins purified. As more entire genomic sequences are obtained for different organisms from the three kingdoms of life, only the proteins that can be crystallized and whose structures can be obtained easily are studied. Consequently, an astonishing number of genomic proteins remain unexamined. In the era of high-throughput processes, traditional methods in molecular biology, protein chemistry and crystallization are eclipsed by automation and pipeline practices. The necessity for high-rate production of protein crystals and structures has prevented the usage of more intellectual strategies and creative approaches in experimental executions. Fundamental principles and personal experiences in protein chemistry and crystallization are minimally exploited only to obtain 'low-hanging fruit' protein structures. We review the practical aspects of today's high-throughput manipulations and discuss the challenges in fast pace protein crystallization and tools for crystallography. Structural genomic pipelines can be improved with information gained from low-throughput tactics that may help us reach the higher-bearing fruits. Examples of recent developments in this area are reported from the efforts of the Southeast Collaboratory for Structural Genomics (SECSG).

59 BASIC BIOLOGICAL SCIENCES↗

QoS support for end users of I/O-intensive applications using shared storage systems

I/O-intensive applications are becoming increasingly common on today's high-performance computing systems. While performance of compute-bound applications can be effectively guaranteed with techniques such as space sharing or QoS-aware process scheduling, it remains a challenge to meet QoS requirements for end users of I/O-intensive applications using shared storage systems because it is difficult to differentiate I/O services for different applications with individual quality requirements. Furthermore, it is difficult for end users to accurately specify performance goals to the storage system using I/O-related metrics such as request latency or throughput. As access patterns, request rates, and the system workload change in time, a fixed I/O performance goal, such as bounds on throughput or latency, can be expensive to achieve and may not lead to a meaningful performance guarantees such as bounded program execution time. We propose a scheme supporting end-users QoS goals, specified in terms of program execution time, in shared storage environments. We automatically translate the users performance goals into instantaneous I/O throughput bounds using a machine learning technique, and use dynamically determined service time windows to efficiently meet the throughput bounds. We have implemented this scheme in the PVFS2 parallel file system and have conducted an extensive evaluation. Our results show that this scheme can satisfy realistic end-user QoS requirements by making highly efficient use of the I/O resources. The scheme seeks to balance programs attainment of QoS requirements, and saves as much of the remaining I/O capacity as possible for best-effort programs.

97 MATHEMATICS AND COMPUTING↗

Evaluation of Alternative Filter Media for the Rotary Microfilter

The Savannah River Site is currently developing and testing several processes to treat high level radioactive liquid waste. Each of these processes has a solid-liquid separation process that limits its throughput. Savannah River National Laboratory researchers identified and tested the rotary microfilter as a technology to increase solid-liquid separation throughput. The authors believe the rotary microfilter throughput can be improved by using a better filter membrane. Previous testing showed that asymmetric filters composed of a ceramic membrane on top of a stainless steel support produced higher filter flux than 100% stainless steel symmetric filters in crossflow filter tests. Savannah River National Laboratory and Oak Ridge National Laboratory are working together to develop asymmetric ceramic ? stainless steel composite filters and asymmetric 100% stainless steel filters to improve the throughput of the rotary microfilter. The Oak Ridge National Laboratory Inorganic Membrane Group fabricated samples of alternative filter membranes. In addition, Savannah River National Laboratory obtained samples of filter membranes from Pall, Porvair, and SpinTek. They tested these samples in a static test cell with feed slurries containing monosodium titanate and simulated sludge.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Determination of Erosion/Corrosion Rates in Hanford Tank Farms Radioactive Waste Transfer System Pipelines

The twenty-eight double-shell underground radioactive waste storage tanks at the U. S. Department of Energy’s Hanford Site near Richland, WA are interconnected by the Waste Transfer System network of buried steel encased pipelines and pipe jumpers in below-grade pits. The pipeline material is stainless steel or carbon steel in 51 mm to 152 mm (2 in. to 6 in.) sizes. The pipelines carry slurries ranging up to 20 volume percent solids and supernatants with less than one volume percent solids at velocities necessary to prevent settling. The pipelines, installed between 1976 and 2011, were originally intended to last until the 2028 completion of the double-shell tank storage mission. The mission has been subsequently extended. In 2010 the Tank Operating Contractor began a systematic evaluation of the Waste Transfer System pipeline conditions applying guidelines from API 579-1/ASME FFS-1 (2007), Fitness-For-Service. Between 2010 and 2014 Fitness-for-Service examinations of the Waste Transfer System pipeline materials, sizes, and components were completed. In parallel, waste throughput histories were prepared allowing side-by-side pipeline wall thinning rate comparisons between carbon and stainless steel, slurries and supernatants and throughput volumes. The work showed that for transfer volumes up to 6.1E+05 m 3 (161 million gallons), the highest throughput of any pipeline segment examined, there has been no detectable wall thinning in either stainless or carbon steel pipeline material regardless of waste fluid characteristics or throughput. The paper describes the field and laboratory evaluation methods used for the Fitness-for-Service examinations, the results of the examinations, and the data reduction methodologies used to support Hanford Waste Transfer System pipeline wall thinning conclusions.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Measurements of file transfer rates over dedicated long-haul connections

Wide-area file transfers are an integral part of several High-Performance Computing (HPC) scenarios. Dedicated network connections with high capacity, low loss rate and low competing traffic, are increasingly being provisioned over current HPC infrastructures to support such transfers. To gain insights into these file transfers, we collected transfer rate measurements for Lustre and xfs file systems between dedicated multi-core servers over emulated 10 Gbps connections with round trip times (rtt) in 0-366 ms range. Memory transfer throughput over these connections is measured using iperf, and file IO throughput on host systems is measured using xddprof. We consider two file system configurations: Lustre over IB network and xfs over SSD connected to PCI bus. Files are transferred using xdd across these connections, and the transfer rates are measured, which indicate the need to jointly optimize the connection and host file IO parameters to achieve peak transfer rates. In particular, these measurements indicate that (i) peak file transfer rate is lower than peak connection and host IO throughput, in some cases by as much as 50% or lower, (ii) xdd request sizes that achieve peak throughput for host file IO do not necessarily lead to peak file transfer rates, and (iii) parallelism in host IO and TCP transport does not always improve the file transfer rates.

log-haul connections↗

Measurements of file transfer rates over dedicated long-haul connections

Wide-area file transfers are an integral part of several High-Performance Computing (HPC) scenarios. Dedicated network connections with high capacity, low loss rate and low competing traffic, are increasingly being provisioned over current HPC infrastructures to support such transfers. To gain insights into these file transfers, we collected transfer rate measurements for Lustre and xfs file systems between dedicated multi-core servers over emulated 10 Gbps connections with round trip times (rtt) in 0-366 ms range. Memory transfer throughput over these connections is measured using iperf, and file IO throughput on host systems is measured using xddprof. We consider two file system configurations: Lustre over IB network and xfs over SSD connected to PCI bus. Files are transferred using xdd across these connections, and the transfer rates are measured, which indicate the need to jointly optimize the connection and host file IO parameters to achieve peak transfer rates. In particular, these measurements indicate that (i) peak file transfer rate is lower than peak connection and host IO throughput, in some cases by as much as 50% or lower, (ii) xdd request sizes that achieve peak throughput for host file IO do not necessarily lead to peak file transfer rates, and (iii) parallelism in host IO and TCP transport does not always improve the file transfer rates.

Rao, Nageswara S↗

LTE Band 13 and Band 14 Interference Test Summary

Introduction Verizon Wireless operates a nationwide commercial LTE system in Band 13 in the United States. FirstNet will deploy a nationwide Public Safety LTE system in the neighboring Band 14 spectrum to provide first responders with much needed broadband data services. The Idaho National Laboratory’s (INL) Wireless Test Bed (WTB) conducted interference testing between LTE Band 13 and Band 14 systems at typical vertical separation distances encountered on towers with co-located systems. The test configuration mimicked a co-location scenario where Band 13 and Band 14 systems are placed on the same tower with a vertical separation distance of 10 feet. The Band 13 and Band 14 interference testing was conducted in an open-air environment in a location off the INL Test Range that does not have RF emissions in either Band 13 or Band 14. A 30-mile area in the Little Lost River Valley in South Central Idaho was identified that is northwest of the INL range that meets that criterion. The GPS coordinates of the test area are 44° 9’ 14.89” N, 113° 21’ 56.58” W. Based on the noise floor measurements, very little RF noise is present in LTE Band 13 and Band 14 in the remote test location in the Little Lost River Valley in Idaho. This RF isolated area provides a great place to conduct testing of LTE Band 13 and Band 14 performance without effecting or being effected by existing LTE Band 13 or Band 14 systems. The Band 13 baseline average overall throughput was 72.0 Mbps which compares to an overall average throughput of 73.7 Mbps when both Band 13 and Band 14 were transmitting with a typical 10 foot vertical separation. This separation is also required for the antennas to be isolated from each other and not interfere with each other [2]. The Band 14 baseline average overall throughput was 65.2 Mbps which compares to an overall average throughput of 65.9 Mbps when both Band 13 and Band 14 were transmitting with a typical 10 foot vertical separation. These results indicate neither Band 13 nor Band 14 was affected by adjacent channel interference in a co-location scenario with 10 foot vertical separation between radiation centers. Horizontal separation testing should be conducted to verify interference would not exist in a nearby site scenario where Band 13 and Band 14 systems are placed on either adjacent towers or on rooftops of adjacent buildings in close proximity to each other. Interference testing should also be conducted between LTE Band 14 systems and the adjacent Public Safety Narrowband LMR systems. The 1 MHz guard band between LTE Band 14 and the LMR band may not be sufficient enough to prevent interference between these disparate systems. The LMR handsets transmit up to 5W in narrowband channels as narrow as 6.25 kHz bandwidth, which could de-sensitize the Band 14 eNodeB receivers especially in a near-far scenario.

42 ENGINEERING↗

On Data Transfers Over Wide-Area Dedicated Connections

Dedicated wide-area network connections are employed in big data and high-performance computing scenarios, since the absence of cross-traffic promises to make it easier to analyze and optimize data transfers over them. However, nonlinear transport dynamics and end-system complexity due to multi-core hosts and distributed file systems make these tasks surprisingly challenging. We present an overview of methods to analyze memory and disk file transfers using extensive measurements over 10 Gbps physical and emulated connections with 0–366 ms round trip times (RTTs). For memory transfers, we derive performance profiles of TCP and UDT throughput as a function of RTT, which show concave regions in contrast to entirely convex regions predicted by previous models. These highly desirable concave regions can be expanded by utilizing large buffers and more parallel flows. We also present Poincar´e maps and Lyapunov exponents of TCP and UDT throughputtraces that indicate complex throughput dynamics. For disk file transfers, we show that throughput can be optimized using a combination of parallel I/O and network threads under direct I/O mode. Our initial throughput measurements of Lustre filesystems mounted over long-haul connections using LNet routers show convex profiles indicative of I/O limits.

Rao, Nageswara S.↗

Measurement-based performance profiles and dynamics of UDT over dedicated connections

Wide-area data transfers in high-performance computing and big data scenarios are increasingly being carried over dedicated network connections that provide high capacities at low loss rates. UDP-based transport protocols are expected to be particularly well-suited for such transfers but their performance is relatively unexplored over a wide range of connection lengths, compared to TCP over shared connections. We present extensive throughput measurements of UDP-based Data Transfer (UDT) over a suite of physical and emulated 10 Gbps connections. In sharp contrast to current UDT analytical models, these measurements indicate much more complex throughput dynamics that are sensitive to the connection modality, protocol parameters, and round-trip times. Lyapunov exponents estimated from the Poincare maps of UDT traces clearly indicate regions of instability and complex dynamics. We propose a simple model based on the ramp-up and sustainment regimes of a generic transport protocol, which qualitatively illustrates the dominant monotonicity and concavity properties of throughput profiles and relates them to Lyapunov exponents. These measurements and analytical results together enable us to comprehensively evaluate UDT performance and select parameters to achieve high throughput, and they also provide guidelines for designing effective transport protocols for dedicated connections.

Foster, Ian↗