A very fast parallel object store for very fast applications

Chapter 6 - Secondary Storage

Various architectural components of ORION-1 and ORION-1SX are described and a review of the current implementation is provided. The message handler receives all messages sent to the ORION system. The object subsystem provides high-level data management functions, including query optimization, schema management, long data management (including text search) and support for versionable objects, composite objects, and multimedia objects. The transaction management subsystem coordinates concurrent object accesses and provides recovery capabilities. The storage subsystem manages persistent storage of objects and controls the flow of objects between the secondary storage device and main memory buffers. In ORION-1, all subsystems reside in one computer. The ORION-1SX architecture is significantly different from ORION-1 in the management of shared data structures and distribution of these subsystems and their components.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Byte addressable non-volatile (NV) memory, such as STT-RAM, MRAM, and PCM, is the next generation memory that can be used as both main memory and secondary storage. While it can persistently store data without power supply, its access speed is comparable to DRAM. While there have been the active researches on its use for either main memory or secondary storage, these researches were conducted independently. This paper presents the integration methods of the main memory and file system management for NV memory, so that it can be used as both main memory and storage. The presented methods use a file system as their basis for the NV memory management; thus, the internal data structures of a file system can have impacts upon the performance of the integration methods. We implemented the proposed methods in the Linux kernel, and performed the evaluation on a system emulator. The evaluation results show that 1) the proposed methods can perform comparably to the existing DRAM memory allocator and significantly better than the page swapping, 2) their performance is affected by the internal data structures of a file system, and 3) the data structures appropriate for traditional hard disk drives do not always work effectively for byte addressable NV memory.

Efficient buffering for concurrent disk and tape I/O

Exploring new electrolyte materials is important to comprehend high performance secondary charge storage devices for effective utilization of renewable energy. Ionic liquids with broad electrochemical voltage window and wide range of thermal stability are prospective materials for the same. As an improved version of this class of materials, we report herein, on the synthesis of novel pyrrolidinium based ionic liquid tethered nanoparticle hybrid electrolytes and compared their conductivity and electrochemical cycling behaviors. Hybrid electrolytes are prepared by covalently grafting N-Methyl-N-propylpyrrolidinium bis(trifluoromethanesulfonyl) imide to the surfaces of pre-synthesized TiO2 nanoparticles at three different core volume fractions, ranging from 0.11 to 0.46. Uniform dispersion of the core nanoparticle within the matrix of the electrolytes improves their mechanical properties. With increasing core volume fractions, the electrical conductivity slightly decreases due to increasing viscosity. Nevertheless, nanoparticle grafting significantly improves the electrochemical performance of the electrolytes. The electrolytes show very good capacitance retentivity (>90%) and long-term cycling stability above room temperature even at the lowest grafting density within symmetric stainless steel electrodes. Impressive room temperature electrochemical performance of these materials within symmetric supercapacitor cell containing CMS graphite as electrodes further demonstrates the applicability of these hybrid materials as promising electrolytes for secondary charge storage devices.

An archiving model for a hierarchical information storage environment

Object Based Storage Device (OSD) takes object as the purpose of storage and management, OSD can be regarded as the convergence of two technologies: files and blocks. The most distinct difference between OSD and traditional storage device is the storage interface, and different storage mediums also affect the performance notability. NAND flash based solid state storage has become the mainstream of next generation data storage, because it's outstanding performance. A NAND flash based OSD framework is discussed and the approaches of data rewriting and address mapping are given in this paper.

This paper addresses the problem of garbage collection in persistent object stores that are multilevel. The proposed approach is able to preserve referential integrity, while ensuring that security is not violated. we first discuss some general principles that should underlie any approach to garbage collection in secure environments. Then, we present a secure garbage collection algorithm, based on the copying approach. >

One of the key components of a hybrid electric vehicle (HEV) drive train is its secondary energy storage device. The automotive industry is still in the process of debating on the fact, as to which device provides the best option in HEVs, for the purpose of load leveling. This paper aims at providing a fair idea with regards to the selection of secondary energy sources, based on vehicle performance characteristics and overall drive train efficiency. The performances of lead-acid (PBA), lithium-ion (Li-Ion), nickel-cadmium (Ni-Cd), nickel-metal hydride (Ni-MH), and nickel-zinc (Ni-Zn) batteries, as well as ultra-capacitors (UC) are investigated over city and highway driving schedules for a heavy-duty diesel-parallel hybrid transit bus application. Based on the simulation studies for the above-mentioned storage devices, the Ni-MH, PBA, and the ultra-capacitor technologies demonstrate best results in terms of fuel economy and percentage drive train efficiency. On the other hand, the Ni-Zn and Li-Ion batteries show much promise, but still demand a great deal of research and development work, before they become a viable option for HEV applications. Finally, the paper compares and summarizes critical performance characteristics for the energy storage devices under investigation.

Performance analysis of an Injera baking machine by using solar energy

Most computer systems currently consist of DRAM as main memory and hard disk drives (HDDs) as storage devices. Due to the volatile nature of DRAM, the main memory may suffer from data loss in the event of power failures or system crashes. With rapid development of new types of non-volatile memory (NVRAM), such as PCM, Memristor, and STT-RAM, it becomes likely that one of these technologies will replace DRAM as main memory in the not-too-distant future. In an NVRAM based buffer cache, any updated pages can be kept longer without the urgency to be flushed to HDDs. This opens opportunities for designing new buffer cache policies that can achieve better storage performance. However, it is challenging to design a policy that can also increase the cache hit ratio. In this paper, we propose a buffer cache policy, named I/O-Cache, that regroups and synchronizes long sets of consecutive dirty pages to take advantage of HDDs' fast sequential access speed and the non-volatile property of NVRAM. In addition, our new policy can dynamically separate the whole cache into a dirty cache and a clean cache, according to the characteristics of the workload, to decrease storage writes. We evaluate our scheme with various traces. The experimental results show that I/O-Cache shortens I/O completion time, decreases the number of I/O requests, and improves the cache hit ratio compared with existing cache policies.

Main memories are becoming sufficiently large that most OLTP databases can be stored entirely in main memory, but this may not be the best solution. OLTP workloads typically exhibit skewed access patterns where some records are hot (frequently accessed) but many records are cold (infrequently or never accessed). It is more economical to store the coldest records on secondary storage such as flash. As a first step towards managing cold data in databases optimized for main memory we investigate how to efficiently identify hot and cold data. We propose to log record accesses - possibly only a sample to reduce overhead - and perform offline analysis to estimate record access frequencies. We present four estimation algorithms based on exponential smoothing and experimentally evaluate their efficiency and accuracy. We find that exponential smoothing produces very accurate estimates, leading to higher hit rates than the best caching techniques. Our most efficient algorithm is able to analyze a log of 1B accesses in sub-second time on a workstation-class machine.

Storage and retrieval of database constraints

A write blocker allows read-only access to digital data on a secondary storage device by placing a hardware or software filter between the host computer and the storage device. The filter monitors I/O commands sent from the application on the host computer, only allowing commands to the device that make no changes to its data. This paper examines the I/O commands used to access secondary storage devices and discusses their implications for BIOS-based and hardware-based write blockers.

This paper presents a nonlinear feed-forward controller applied to single-phase uninterruptible power supplies (UPS). The controller was conceived by using a one-cycle based PWM generator and an output-current feedforward, in order to cancel input-voltage disturbances and nonlinear load currents, respectively. It also includes an external control loop to ensure good output-voltage tracking. The controller design is based on a large-signal approach, introduced to achieve good transient response and stability in a wide range of parameter variations. Besides, in spite of the nonlinear nature of the controller, we obtain a linear average output-voltage dynamic response. The proposed control provides the following features: fast transient response, low THD sine-wave output-voltage, fixed switching frequency, and high robustness against load and line step changes. Simulation results show the effectiveness of this control technique for inverters in UPS applications, especially when nonlinear loads must to be supplied and UPS DC-link has large undesirable ripple.