Search NASA⌕ Search

SEARCH · Search NASA

Results for “storage cache”

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 37 records · Page 2

/Scratch as a Cache: Rethinking HPC Center Scratch Storage

To sustain emerging data-intensive scientific applications, High Performance Computing (HPC) centers invest a notable fraction of their operating budget on a specialized fast storage system, scratch space, which is designed for storing the data of currently running and soon-to-run HPC jobs. Instead, it is often used as a standard file system, wherein users arbitrarily store their data, without any consideration to the center's overall performance. To remedy this, centers periodically scan the scratch in an attempt to purge transient and stale data. This practice of supporting a cache workload using a file system and disjoint tools for staging and purging results in suboptimal use of the scratch space. In this paper, we address the above issues by proposing a new perspective, where the HPC scratch space is treated as a cache, and data population, retention, and eviction tools are integrated with scratch management. In our approach, data is moved to the scratch space only when it needed, and unneeded data is removed as soon as possible. We also design a new job-workflow-aware caching policy that leverages user-supplied hints for managing the cache. Our evaluation using three-year job logs from the Jaguar supercomputer, shows that compared to the widely-used purge approach, workflow-aware caching optimizes scratch utilization by reducing the average amount of data read by 9.3%, and by reducing job scheduling delays associated with data staging, on average, by 282.0%.

99 GENERAL AND MISCELLANEOUS↗

Data preservation at the Fermilab Tevatron

The Fermilab Tevatron collider's data-taking run ended in September 2011, yielding a dataset with rich scientific potential. The CDF and DO experiments each have nearly 9 PB of collider and simulated data stored on tape. A large computing infrastructure consisting of tape storage, disk cache, and distributed grid computing for physics analysis with the Tevatron data is present at Fermilab. The Fermilab Run II data preservation project intends to keep this analysis capability sustained through the year 2020 or beyond. To achieve this, we are implementing a system that utilizes virtualization, automated validation, and migration to new standards in both software and data storage technology as well as leveraging resources available from currently-running experiments at Fermilab. Furthermore, these efforts will provide useful lessons in ensuring long-term data access for numerous experiments throughout high-energy physics, and provide a roadmap for high-quality scientific output for years to come.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Data preservation at the Fermilab Tevatron

The Fermilab Tevatron collider's data-taking run ended in September 2011, yielding a dataset with rich scientific potential. The CDF and D0 experiments each have approximately 9 PB of collider and simulated data stored on tape. A large computing infrastructure consisting of tape storage, disk cache, and distributed grid computing for physics analysis with the Tevatron data is present at Fermilab. The Fermilab Run II data preservation project intends to keep this analysis capability sustained through the year 2020 and beyond. To achieve this goal, we have implemented a system that utilizes virtualization, automated validation, and migration to new standards in both software and data storage technology and leverages resources available from currently-running experiments at Fermilab. Lastly, these efforts have also provided useful lessons in ensuring long-term data access for numerous experiments, and enable high-quality scientific output for years to come.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Improving Data Availability for Better Access Performance: A Study on Caching Scientific Data on Distributed Workstations

Client-side data caching serves as an excellent mechanism to store and analyze the rapidly growing amount of scientific data. In our previous work, we built a distributed local cache on unreliable desktop storage contributions. This offers several desirable properties, such as performance impedance matching, improved space utilization, and high parallel I/O bandwidth. Such a low-cost, best-effort cache, however, is faced with the vagaries of storage node availability: these donated machines may be significantly less reliable than dedicated systems and cannot be controlled centrally. In this paper, we address %the tradeoffs between techniques that favor %availability or performance when it comes to cache management. the performance impact of data availability in the distributed scientific data cache setting. We then present a novel approach to storage cache management, {\em remote partial data recovery (RPDR)}. We compare our approach to two standard techniques, namely replication and erasure coding, both extended to the target caching environment. Our evaluation uses a trace-driven simulation parameterized with benchmarking results from our distributed cache prototype. The results with multiple real-world traces indicate that RPDR significantly outperforms both replication and erasure coding in many cases and overall the combination of RPDR and erasure coding yields the best performance.

99 GENERAL AND MISCELLANEOUS↗

Multi-level Hybrid Cache: Impact and Feasibility

Storage class memories, including flash, has been attracting much attention as promising candidates fitting into in today's enterprise storage systems. In particular, since the cost and performance characteristics of flash are in-between those of DRAM and hard disks, it has been considered by many studies as an secondary caching layer underneath main memory cache. However, there has been a lack of studies of correlation and interdependency between DRAM and flash caching. This paper views this problem as a special form of multi-level caching, and tries to understand the benefits of this multi-level hybrid cache hierarchy. We reveal that significant costs could be saved by using Flash to reduce the size of DRAM cache, while maintaing the same performance. We also discuss design challenges of using flash in the caching hierarchy and present potential solutions.

99 GENERAL AND MISCELLANEOUS↗

Caching data from remote memories

An approach is disclosed that caches distant memories within the storage a local node. The approach provides a memory caching infrastructure that supports virtual addressing by utilizing memory in the local node as a cache of distant memories for data granules. The data granules are accessed along with metadata and an ECC associated with the data granule. The metadata is updated to indicate storage of the selected data granule in the cache.

Johns, Charles Ray↗

Evaluate data lake design for the accelerator control system

Increasing precision in automation for modern particle accelerators not only creates a requirement to gather data from all devices but also demands scalable and high-performance data infrastructure with the capability of handling vast incoming device data. A well architected data lake is suitable for such a system which integrates real-time data acquisition, transient data caching, and long-term storage. This paper evaluates data lake architecture for an Accelerator Control System (ACS), focusing on two critical components of a data lake, data cache and long-term storage.

Jaikar, Amol [Fermilab]↗

The Scalable Checkpoint/Restart Library

The Scalable Checkpoint/Restart (SCR) library provides an interface that codes may use to worite our and read in application-level checkpoints in a scalable fashion. In the current implementation, checkpoint files are cached in local storage (hard disk or RAM disk) on the compute nodes. This technique provides scalable aggregate bandwidth and uses storage resources that are fully dedicated to the job. This approach addresses the two common drawbacks of checkpointing a large-scale application to a shared parallel file system, namely, limited bandwidth and file system contention. In fact, on current platforms, SCR scales linearly with the number of compute nodes. It has been benchmarked as high as 720GB/s on 1094 nodes of Atlas, which is nearly two orders of magnitude faster thanthe parallel file system.

ECP↗

QoS-Enabled, High-performance Storage Systems for Data-Intensive Scientific Computing (Final Report)

This project's work resulted in the following research projects: (1) BORG - Block-reORGanization for Self-optimizing Storage Systems; (2) ABLE - Active Block Layer Extensions; (3) EXCES - EXternal Caching in Energy-Saving Storage Systems; and (4) GRIO - Guaranteed-Rate I/O Scheduler. These projects together help in substantially advancing the over-arching project goal of developing "QoS-Enabled, High-Performance Storage Systems".

99 GENERAL AND MISCELLANEOUS↗

Data Movement Dominates: Final Report

Over the past three years in this project, what we have observed is that the primary reason for data movement in large-scale systems is that the per-node capacity is not large enough—i.e., one of the solutions to the data-movement problem (certainly not the only solution that is required, but a significant one nonetheless) is to increase per-node capacity so that inter-node traffic is reduced. This unfortunately is not as simple as it sounds. Today’s main memory systems for datacenters, enterprise computing systems, and supercomputers, fail to provide high per-socket capacity [Dirik & Jacob 2009; Cooper-Balis et al. 2012], except at extremely high price points (factors of 10–100x the cost/bit of consumer main-memory systems) [Stokes 2008]. The reason is that our choice of technology for today’s main memory systems—i.e., DRAM, which we have used as a main-memory technology since the 1970s [Jacob et al. 2007]—can no longer keep up with our needs for density and price per bit. Main memory systems have always been built from the cheapest, densest, lowest-power memory technology available, and DRAM is no longer the cheapest, the densest, nor the lowest-power storage technology out there. It is now time for DRAM to go the way that SRAM went: move out of the way for a cheaper, slower, denser storage technology, and become a cache instead. This inflection point has happened before, in the context of SRAM yielding to DRAM. There was once a time that SRAM was the storage technology of choice for all main memories [Tomasulo 1967; Thornton 1970; Kidder 1981]. However, once DRAM hit volume production in the 1970s and 80s, it supplanted SRAM as a main memory technology because it was cheaper, and it was denser. It also happened to be lower power, but that was not the primary consideration of the day. At the time, it was recognized that DRAM was much slower than SRAM, but it was only at the supercomputer level (For instance the Cray X-MP in the 1980s and its follow-on, the Cray Y-MP, in the 1990s) that could one afford to build ever- larger main memories out of SRAM—the reasoning for moving to DRAM was that an appropriately designed memory hierarchy, built of DRAM as main memory and SRAM as a cache, would approach the performance of SRAM, at the price-per-bit of DRAM [Mashey 1999]. Today it is quite clear that, were one to build an entire multi-gigabyte main memory out of SRAM instead of DRAM, one could improve the performance of almost any computer system by up to an order of magnitude—but this option is not even considered, because to build that system would be prohibitively expensive. It is now time to revisit the same design choice in the context of modern technologies and modern systems. For reasons both technical and economic, we can no longer afford to build ever-larger main memory systems out of DRAM. Flash memory, on the other hand, is significantly cheaper and denser than DRAM and therefore should take its place. While it is true that flash is significantly slower than DRAM, one can afford to build much larger main memories out of flash than out of DRAM, and we show that an appropriately designed memory hierarchy, built of flash as main memory and DRAM as a cache, will approach the performance of DRAM, at the price-per-bit of flash. In our studies as part of this project, we have investigated Non-Volatile Main Memory (NVMM), a new main-memory architecture for large-scale computing systems, one that is specifically designed to address the weaknesses described previously. In particular, it provides the following features: non-volatility: The bulk of the storage is comprised of NAND flash, and in this organization DRAM is used only as a cache, not as main memory. Furthermore, the flash is journaled, which means that operations such as checkpoint/restore are already built into the system. 1+ terabytes of storage per socket: SSDs and DRAM DIMMs have roughly the same form factor (several square inches of PCB surface area), and terabyte SSDs are now commonplace. performance approaching that of DRAM: DRAM is used as a cache to the flash system. price-per-bit approaching that of NAND: Flash is currently well under $0.50 per gigabyte; DDR3 SDRAM is currently just over $10 per gigabyte [Newegg 2014]. Even today, one can build an easily affordable main memory system with a terabyte or more of NAND storage per CPU socket (which would be extremely expensive were one to use DRAM), and our cycle- accurate, full-system experiments show that this can be done at a performance point that lies within a factor of two of DRAM.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Lightweight storage and overlay networks for fault tolerance.

The next generation of capability-class, massively parallel processing (MPP) systems is expected to have hundreds of thousands to millions of processors, In such environments, it is critical to have fault-tolerance mechanisms, including checkpoint/restart, that scale with the size of applications and the percentage of the system on which the applications execute. For application-driven, periodic checkpoint operations, the state-of-the-art does not provide a scalable solution. For example, on today's massive-scale systems that execute applications which consume most of the memory of the employed compute nodes, checkpoint operations generate I/O that consumes nearly 80% of the total I/O usage. Motivated by this observation, this project aims to improve I/O performance for application-directed checkpoints through the use of lightweight storage architectures and overlay networks. Lightweight storage provide direct access to underlying storage devices. Overlay networks provide caching and processing capabilities in the compute-node fabric. The combination has potential to signifcantly reduce I/O overhead for large-scale applications. This report describes our combined efforts to model and understand overheads for application-directed checkpoints, as well as implementation and performance analysis of a checkpoint service that uses available compute nodes as a network cache for checkpoint operations.

99 GENERAL AND MISCELLANEOUS↗

Improving Performance of Tape Restore Request Scheduling in the Storage System dCache

Given the anticipated increase in the amount of scientific data, it is widely accepted that primarily disk based storage will become prohibitively expensive. Tape based storage, on the other hand, provides a viable and affordable solution for the ever increasing demand for storage space. Coupled with a disk caching layer that temporarily holds a small fraction of the total data volume to allow for low latency access, it turns tape based systems into active archival storage (write once, read many) that imposes additional demands on data flow optimization compared to traditional backup setups (write once, read never). In order to preserve the lifetime of tapes and minimize the inherently higher access latency, different tape usage strategies are being evaluated. As an important disk storage system for scientific data that transparently handles tape access, dCache is making efforts to evaluate its recall optimization potential and is introducing a proof-of-concept, high-level stage request scheduling component within its SRM implementation.

Morschel, Lea↗

PCM-Based Durable Write Cache for Fast Disk I/O

Flash based solid-state devices (FSSDs) have been adopted within the memory hierarchy to improve the performance of hard disk drive (HDD) based storage system. However, with the fast development of storage-class memories, new storage technologies with better performance and higher write endurance than FSSDs are emerging, e.g., phase-change memory (PCM). Understanding how to leverage these state-of-the-art storage technologies for modern computing systems is important to solve challenging data intensive computing problems. In this paper, we propose to leverage PCM for a hybrid PCM-HDD storage architecture. We identify the limitations of traditional LRU caching algorithms for PCM-based caches, and develop a novel hash-based write caching scheme called HALO to improve random write performance of hard disks. To address the limited durability of PCM devices and solve the degraded spatial locality in traditional wear-leveling techniques, we further propose novel PCM management algorithms that provide effective wear-leveling while maximizing access parallelism. We have evaluated this PCM-based hybrid storage architecture using applications with a diverse set of I/O access patterns. Our experimental results demonstrate that the HALO caching scheme leads to an average reduction of 36.8% in execution time compared to the LRU caching scheme, and that the SFC wear leveling extends the lifetime of PCM by a factor of 21.6.

99 GENERAL AND MISCELLANEOUS↗

Accelerating Application Bulk Synchronous Writes in HPC Environments

High-bandwidth storage tiers are becoming more common for their capability to absorb high-rate, bursty I/Os. Notably, the designs of these fast storage tiers differ from system to system. The variation of these layers and non-uniform methods of access can pose chal- lenges for applications seeking to run at multiple HPC facilities. Therefore, in this work, we present Spectral, a rapid-output ab- straction library to accelerate application, bulk-synchronous writes on HPC systems. We design Spectral to enable applications to use high-bandwidth storage, such as node-local storage and dis- tributed, write-caches (e.g., burst buffers) transparently without requiring modifications to the application or file system source code. The key idea is to allow applications to spend most of the time performing productive work and to not require any source code changes for maximum portability on different HPC archi- tectures. Spectral internally re-routes write-only files through available, high-performance I/O resources before ultimately mi- grating them to the shared global parallel file system. For instance, on Summit, Spectral transparently places application outputs on node-local storage and then utilizes asynchronous migration to the center-wide GPFS file system. We evaluate Spectral on the Summit HPC system (1024 nodes) using the IOR benchmark and real scientific applications. Spectral shows linear performance scaling, improving application write performance by over an order of magnitude when compared to GPFS.

Khan, Awais↗

Hvac: Removing I/O Bottleneck for Large-Scale Deep Learning Applications

Scientific communities are increasingly adopting deep learning (DL) models in their applications to accelerate scientific discovery processes. However, with rapid growth in the computing capabilities of HPC supercomputers, large-scale DL applications have to spend a significant portion of training time performing I/O to a parallel storage system. Previous research works have investigated optimization techniques such as prefetching and caching. Unfortunately, there exist non-trivial challenges to adopting the existing solutions on HPC supercomputers for large-scale DL training applications, which include non-performance and/or failures at extreme scale, lack of portability and generality in design, complex deployment methodology, and being limited to a specific application or dataset. To address these challenges, we propose High-Velocity AI Cache (HVAC), a distributed read-cache layer that targets and fully exploits the node-local storage or near node-local storage technology. HVAC seamlessly accelerates read I/O by aggregating node-local or near node-local storage, avoiding metadata lookups and file locking while preserving portability in the application code. We deploy and evaluate HVAC on 1,024 nodes (with over 6000 NVIDIA V100 GPUS) of the Summit supercomputer. In particular, we evaluate the scalability, efficiency, accuracy, and load distribution of HVAC compared to GPFS and XFS-on-NVMe. With four different DL applications, we observe an average 25 % performance improvement atop GPFS and 9% drop against XFS-on-NVMe, which scale linearly and are considered the performance upper bound. We envision HVAC as an important caching library for upcoming HPC supercomputers such as Frontier.

Khan, Awais↗

Quota management in dCache or making a perfectly normal file system normal

dCache (https://dcache.org) is a highly scalable storage system providing location-independent access to data. The data are stored across multiple data servers as complete files presented to the end-user via a single-rooted namespace. From its inception, dCache has been designed as a caching disk buffer to a tertiary tape storage system with the assumption that the latter has virtually unlimited capacity. dCache can also be configured as a disk-only storage system with no tape backend. Owing to the idea that a tape resource is infinite, or purely physically limited by budget considerations, the system has never provided for any restrictions on how much data can be stored on tape. Likewise, in the disk-only configuration, the capacity of the system is only limited by the aggregate disk capacity of the data servers. In a multi-user environment, however, this has become problematic. This presentation will describe the design and implementation of a user- and group-based quota system, that allows to manage tape and disk space allocations, as part of dCache namespace.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

HDF5 in the exascale era: Delivering efficient and scalable parallel I/O for exascale applications

Accurately modeling real-world systems requires scientific applications at exascale to generate massive amounts of data and manage data storage efficiently. However, parallel input and output (I/O) faces challenges due to new application workflows and the state-of-the-art memory, interconnect, and storage architectures considered in exascale designs. The storage hierarchy has expanded with node-local persistent memory, solid-state storage, and traditional disk and tape-based storage, thus requiring efficiency at each layer and much more efficient data movement among these layers. This paper discusses how the ExaHDF5 project improved the I/O performance and data management for exascale architectures by enhancing HDF5, a widely used parallel I/O library. The team developed an Asynchronous I/O Virtual Object Layer (VOL) connector that allowed overlapping I/O with computation. They also created a Cache VOL to complement asynchronous I/O by incorporating fast storage layers, such as burst buffer and node-local storage, into the parallel I/O workflow through caching and staging data. Additionally, the team enabled data aggregation and I/O at the node level by using a Subfiling Virtual File Driver (VFD). To demonstrate superior I/O performance with HDF5 at exascale, the ExaHDF5 team collaborated with several exascale applications. In this paper, we show I/O performance improvements for three applications: Cabana (a particle-based simulation library), EQSIM (a regional earthquake simulation software), and E3SM (a climate system modeling library).

Asynchronous I/Ol↗

ROOT RNTuple and EOS: The Next Generation of Event Data I/O

For several years, the ROOT team is developing the new RNTuple I/O subsystem in preparation of the next generation of collider experiments. Both HL-LHC and DUNE are expected to start data taking by the end of this decade. They pose unprecedented challenges to event data I/O in terms of data rates, event sizes, and event complexity. At the same time, the I/O landscape is becoming more diverse. HPC cluster file systems and object stores, NVMe disk cache layers in analysis facilities, and S3 storage on cloud resources are mixing with traditional XRootD-managed spinning disk pools.The ROOT team will finalize a first production version of the RNTuple binary format by the end of 2024. After this point, ROOT will provide backward compatibility for RNTuple data. This contribution provides an overview of the RNTuple feature set, the related R&D activities and the long-term vision for RNTuple. We report on performance, interface design, tooling, robustness, integration with experiment frameworks, and validation results, as well as recent R&D on parallel reading and writing and exploitation of modern hardware and storage systems. We will give an outlook on possible future features after a first production release.Collaboratively, the IT and EP departments at CERN have launched a formal project within the Research and Computing sector to evaluate the novel data format for physics analysis data utilized in LHC experiments and other fields. This part of the project focuses on validating the scalability of the EOS storage backend during the transition from the over 25 years old TTree production format to the newly developed RNTuple format, using both replicated and erasure-coded storage profiles.

Blomer, Jakob [CERN]↗