Hard Disk Research Articles

Filesystem Fragmentation on Modern Storage Systems

Filesystem fragmentation has been one of the primary reasons for computer systems to get slower over time. However, there have been rapid changes in modern storage systems over the past decades, and modern storage devices such as solid state drives have different mechanisms to access data, compared with traditional rotational ones. In this article, we revisit filesystem fragmentation on modern computer systems from both performance and fairness perspectives. According to our extensive experiments, filesystem fragmentation not only degrades I/O performance of modern storage devices, but also incurs various problems related to I/O fairness, such as performance interference. Unfortunately, conventional defragmentation tools are designed primarily for hard disk drives and thus generate an unnecessarily large amount of I/Os for data migration. To mitigate such problems, this article present FragPicker, a new defragmentation tool for modern storage devices. FragPicker analyzes the I/O behaviors of each target application and defragments only necessary pieces of data whose migration can contribute to performance improvement, thereby effectively minimizing the I/O amount for defragmentation. Our evaluation with YCSB workload-C shows FragPicker reduces the total amount of I/O for defragmentation by around 66% and the elapsed time by around 84%, while showing a similar level of defragmentation effect.

Position error-free control of magnetic domain-wall devices via spin-orbit torque modulation

Magnetic domain-wall devices such as racetrack memory and domain-wall shift registers facilitate massive data storage as hard disk drives with low power portability as flash memory devices. The key issue to be addressed is how perfectly the domain-wall motion can be controlled without deformation, as it can replace the mechanical motion of hard disk drives. However, such domain-wall motion in real media is subject to the stochasticity of thermal agitation with quenched disorders, resulting in severe deformations with pinning and tilting. To sort out the problem, we propose and demonstrate a new concept of domain-wall control with a position error-free scheme. The primary idea involves spatial modulation of the spin-orbit torque along nanotrack devices, where the boundary of modulation possesses broken inversion symmetry. In this work, by showing the unidirectional motion of domain wall with position-error free manner, we provide an important missing piece in magnetic domain-wall device development.

Cost aware LSTM model for predicting hard disk drive failures based on extremely imbalanced S.M.A.R.T. sensors data

Failure prediction in a population of hard drives remains challenging due to the extreme class imbalance. Many existing failure prediction methods rely on problematic resampling approaches. Besides, existing deep learning methods in the failure prediction domain typically employ the sigmoid cross-entropy loss function which is not capable of solving the class imbalance problem. To address these challenges, this study proposes long-short term memory networks that leverage the sequential time series self monitoring analysis and reporting technology sensors data provided by the Backblaze data center. These models employ a new, modified focal loss function combined with weighted cross-entropy loss to tackle the negative influence of the class imbalance during training the long-short term memory networks. The long-short term memory networks models are compared to two traditional machine learning algorithms: random forest and logistic regression. This study focuses on daily snapshot data of the Seagate ST4000DM000 hard drive model from the Backblaze data center to maintain the homogeneity of the SMART attributes. Long-short term memory networks with modified focal loss function model provides the highest geometric mean score of 0.786±0.011 while keeping the failure detection rate higher without compromising the false alarm rate. Hence, it demonstrates that the proposed focal loss function in long-short term memory networks leads to improved performance compared to other approaches under the class imbalance.

A Study on Accelerating SP Decoding by Neural Network in SMR System

We have previously studied low-density parity-check (LDPC) coding and iterative decoding in the shingled magnetic recording (SMR) system as a signal processing method to realize ultra-high-density hard disk drives (HDD). In addition, we have proposed the application of the neural network to improve decoding performance and realize the automation of iterative decoding. In this study, we apply a neural network to accelerate iterative decoding in the sum-product (SP) decoder. As the result, the SP decoder with the neural network realized ”no errors” at the fewest times of the iterative decoding compared to our previous studies.

Feasibility Study of Reduction in Sound-Pressure-Induced Vibration in Hard Disk Drives Using Adaptive Feed-Forward Control

Feasibility Study of Reduction in Sound-Pressure-Induced Vibration in Hard Disk Drives Using Adaptive Feed-Forward Control

Effect of Humidity on Head Smear Generation in Head-Assisted Magnetic Recording

The causes of head smears deposited on the magnetic head surface due to laser heating in heat-assisted magnetic recording should be investigated to achieve high recording densities of hard disk drives. These factors, such as outgassing from components and humidity, also affect smear formation in hard disk drives. In this study, we focused on the effect of relative humidity on smears generated via laser heating. Three types of lubricant film (dipped, ultraviolet-treated, and rinsed) were prepared, and the amount of smear generated on a glass pin surface was evaluated using a pin-on-disk tester with a laser heating system. It was confirmed that the amount of smear increased as the humidity increased, and lubricant films with higher chemical bonding fractions showed less smear generation and lower dependence on humidity. In addition, time-of-flight secondary ion mass spectroscopy confirmed that the migration of cobalt from the magnetic layer was accelerated by laser heating and humidity.

Sunflower hard disk graphs

Sunflower hard disk graphs

Deep Learning-Based Video Compression for Surveillance Footage

The utilization of closed-circuit television (CCTV) monitoring plays a pivotal role in the realm of video processing, providing an effective means for vigilant surveillance. However, a significant challenge associated with this practice is the substantial demand it places on storage space. Traditionally, surveillance footage is stored on hard disk drives, and due to limited storage capacities, it often necessitates periodic deletion. To tackle this issue, we have introduced an innovative method for compressing CCTV video, named “Detection-Based video Compression” (DBVC). Our DBVC model is a two-step process. In the first step, we employ advanced neural network approaches such as Mask-RCNN and YOLOv4 to determine active and idle frames within the surveillance video. These cutting-edge techniques enable precise identification of objects and events of interest in the video feed. In the second step, we construct a new video composed solely of the active frames, eliminating redundant or uneventful segments. After conducting a comprehensive analysis of the experimental results, it is evident that Mask-RCNN stands out with an impressive detection accuracy of 98% on the COCO dataset, making it a robust choice for identifying objects and events in the surveillance footage. Consequently, we chose to leverage the output generated by Mask-RCNN and YOLOv4 for subsequent processing stages. Our DBVC approach is a breakthrough in video compression technology, significantly reducing the storage space required for CCTV footage. In fact, it achieves an average compression ratio of up to 85% when using YOLOv4, surpassing the capabilities of existing state-of-the-art compression methods. This innovation not only optimizes storage efficiency but also maintains a high level of surveillance data integrity, making it a valuable advancement in the field of CCTV video processing and storage management.

Prevalence and Causes of Software Piracy among Tertiary Students in Ghana

In the era of the Knowledge Economy, Intellectual Property Rights (IPRs) have become a crucial aspect of the twenty-first-century environment. Software piracy, characterized by the unauthorized copying, downloading, sharing, selling, or installation of copyrighted software, remains a serious problem worldwide, and Ghana is no exception. Various forms of software piracy, such as software lifting, hard disk loading, counterfeiting, and unauthorized renting, are prevalent in the country, leading to negative economic consequences. These consequences include distorted competition, loss of tax revenue and jobs due to the absence of a legitimate market, and increased costs for recovery. The impact of software piracy affects the social well-being of the Ghanaian citizenry. This research aims to explore the causes and effects of software piracy in Ghana, especially among tertiary students, and proposes potential solutions. A quantitative survey design was used via an online questionnaire to collect data from a sample of 47 students in the tertiary institutions especially public universities in Ghana with backgrounds in IT and are familiar with evolving trends in IT. The findings revealed that software piracy is prevalent in the country as a result of a lack of awareness, poor economic conditions, and weak legal framework and/or enforcement. The study recommends increased public education and awareness, strict enforcement of laws related to software piracy, and the promotion of domestic software development as measures to address the menace.

Designing and Modelling of Pivotal Friction Compensator of Actuator of Hard Disk Drives

Nowadays, hard disk drives are one of the most common devices for storing data. The growing demand for storing the bulk amount of data and retrieving the data as fast as possible from hard disk drives (HDDs) has posed manufacturers with various challenges. To overcome these hurdles different methods, techniques, and control systems are developed to improve the transient response of the HDDs. The transient response of a system is characterized by numerous specifications such as overshooting, peak time, settling time, delay, and rise time. This can also be achieved by using several stages of actuators servomechanism that can also help us to store a large amount of data, it also helps to increase the accuracy of head-positioning of the actuator that eventually leads to enhancement of the transient response of hard disk drives (HDDs). By increasing the accuracy of read/write head actuator there is a challenge to cater the friction at pivot of actuator. This friction can significantly reduce the speed of the actuator and that ultimately leads to the reduced transient responses of the system. This paper aims to design a new modelled-base friction compensator for the servo control of hard disk drives that can improve the transient response of HDDs. Thus, improving the transient responses of HDDs can make the computer more efficient than ever and can save a lot of time while making complex calculations. To achieve this aim measured and replicated responses will be used as guidance and the friction design of HDD will iteratively improve. This can be done by feeding the measured friction forces back to the voice coil motor (VCM) so that the frequencies of the actuator’s head and current be linearized. This proposed design will help in the cancelation scheme and the model-based compensator will be implemented. By improving the tracking seek of HDDs we can also write the data much faster on the HDD and by using numerous techniques we can store a large amount of data on HDDs. Our aim is also to integrate a PID controller into our control system so that we can improve the transient response as much as possible. Our work can be considered important as there are very few frictions compensator control designs that have integrated the PID controller. We are aiming to achieve a significantly improved pivotal friction compensator that can help us to achieve improved transient response of the hard disk drive (HDD).

The storage capacity of a directed graph and nodewise autonomous, ubiquitous learning.

The brain, an exceedingly intricate information processing system, poses a constant challenge to memory research, particularly in comprehending how it encodes, stores, and retrieves information. Cognitive psychology studies memory mechanism from behavioral experiment level and fMRI level, and neurobiology studies memory mechanism from anatomy and electrophysiology level. Current research findings are insufficient to provide a comprehensive, detailed explanation of memory processes within the brain. Numerous unknown details must be addressed to establish a complete information processing mechanism connecting micro molecular cellular levels with macro cognitive behavioral levels. Key issues include characterizing and distributing content within biological neural networks, coexisting information with varying content, and sharing limited resources and storage capacity. Compared with the hard disk of computer mass storage, it is very clear from the polarity of magnetic particles in the bottom layer, the division of tracks and sectors in the middle layer, to the directory tree and file management system in the high layer, but the understanding of memory is not sufficient. Biological neural networks are abstracted as directed graphs, and the encoding, storage, and retrieval of information within directed graphs at the cellular level are explored. A memory computational model based on active directed graphs and node-adaptive learning is proposed. First, based on neuronal local perspectives, autonomous initiative, limited resource competition, and other neurobiological characteristics, a resource-based adaptive learning algorithm for directed graph nodes is designed. To minimize resource consumption of memory content in directed graphs, two resource-occupancy optimization strategies-lateral inhibition and path pruning-are proposed. Second, this paper introduces a novel memory mechanism grounded in graph theory, which considers connected subgraphs as the physical manifestation of memory content in directed graphs. The encoding, storage, consolidation, and retrieval of the brain's memory system correspond to specific operations such as forming subgraphs, accommodating multiple subgraphs, strengthening connections and connectivity of subgraphs, and activating subgraphs. Lastly, a series of experiments were designed to simulate cognitive processes and evaluate the performance of the directed graph model. Experimental results reveal that the proposed adaptive connectivity learning algorithm for directed graphs in this paper possesses the following four features: (1) Demonstrating distributed, self-organizing, and self-adaptive properties, the algorithm achieves global-level functions through local node interactions; (2) Enabling incremental storage and supporting continuous learning capabilities; (3) Displaying stable memory performance, it surpasses the Hopfield network in memory accuracy, capacity, and diversity, as demonstrated in experimental comparisons. Moreover, it maintains high memory performance with large-scale datasets; (4) Exhibiting a degree of generalization ability, the algorithm's macroscopic performance remains unaffected by the topological structure of the directed graph. Large-scale, decentralized, and node-autonomous directed graphs are suitable simulation methods. Examining storage problems within directed graphs can reveal the essence of phenomena and uncover fundamental storage rules hidden within complex neuronal mechanisms, such as synaptic plasticity, ion channels, neurotransmitters, and electrochemical activities.

Recycling of Hard Disk Drive Platters via Plastic Consolidation.

The paper presents the comparison of two methods of recycling aluminum from HDD platters-the melting method and the method of plastic consolidation. The main elements of HDD memory, i.e., data carriers (platters), were examined via the percentage share of the total HDD mass and also via EDS analysis. The most common are platters made of the aluminum alloy series 5XXX, which are covered with a thin magnetic layer made of nickel. The research involved removing data carriers from about 30 HDDs and fragmenting them. The next step was to divide the platters into three groups; one was melted, the second was subjected to plastic consolidation, and the third group was fragmented into chips and also subjected to the consolidation process. Then, in the process of co-extrusion, rods were extruded from each material, and were subjected to EDS analysis, microstructure testing, Vickers hardness, and uniaxial tensile tests, and then the obtained results were compared. The obtained results of the microstructural tests in the case of gravity cast material confirmed the presence of the Al3Ni globular phase in the matrix. In the case of pressed and extruded materials, the Al3Ni phase appeared at the Ni-AlMg contact. After plastic consolidation, all the tested rods were characterized by their comparable strength properties (a tensile strength of 250 MPa and yield strength of 105 MPa).

Three-dimensional magnetic recording

Magnetic recording in current hard disk drives is basically two dimensional, with information stored in a thin recording structure covering the surface of the disk. This review examines the prospects for three dimensional magnetic recording using multiple recording structures, and the technologies that may help its realisation. In particular, energy-assisted recording techniques are discussed as these appear to have the greatest potential.

SISTEM PAKAR UNTUK DIAGNOSA KERUSAKAN KOMPUTER MENGGUNAKAN METODE FORWARD CHAINING DAN CERTAINTY FACTOR BERBASIS WEB

Damage to the computer is caused by several problematic components such as problematic RAM, hard disk or VGA. This condition is a condition of minor damage which sometimes users consider this to be fatal damage due to a lack of knowledge about computer components, which is why an expert system is needed to help users understand. damage to the computer. In this research, the Forward chaining method will be used in the system that will be used in the program. This research will focus on a system that produces and adopts knowledge from an expert in the field and to be able to diagnose computer damage using a web-based method. An expert system is an application that uses the expertise or knowledge of an expert in a particular field and this expertise is implemented in a system.

Disk failure prediction based on association analysis and SSA-LSTM

Hard disk is the main storage device for cloud service, and there always contain massive disks deployed in a data center. Disk failure occur frequently in data center, which may lead to data loss and other disasters, so there have urgent needs for a failure prediction method of hard disk so as to ensure service reliability. This paper proposes a temporal prediction model based on LSTM. Firstly, the SMART data of the disk is analyzed, and the Pearson correlation coefficient is used to analyze the correlation between the monitoring time series data of the faulty disk and the normal disk, and the monitoring index with the lowest correlation is selected as the fault feature; secondly, for the problem of serious imbalance of positive and negative samples in the SMART dataset, the SMOTEENN algorithm is introduced for oversampling to obtain a balanced dataset of positive and negative samples. The proposed method improves accuracy by 8.268% and F1-score by 8.657% compared to the conventional method.

Two-dimensional ordering of bacteriorhodopsins in a lipid bilayer and effects caused by repulsive core between lipid molecules on lateral depletion interaction: A study based on a thermodynamic perturbation theory

Using binary hard disk mixture models, we studied the two-dimensional ordering of bacteriorhodopsins in a lipid bilayer. The phase diagrams were calculated using the thermodynamic perturbation theory. We examined two types of effective interactions to discuss the lateral depletion effects caused by repulsive core interaction between lipid molecules. The results indicate that the core repulsions drastically broaden the coexistence region for the fluid-ordered phase.

DEAD FORENSIC ANALYSIS OF QUTEBROWSER AND LIBREWOLF BROWSERS USING THE NIST 800-86 METHOD

A browser is software used to access web pages to obtain clear and readable information. Information resources are identified by a Uniform Resource Identifier (URI) and can be web pages, images, videos, or other content. When a browser user engages in online activities, they usually leave traces on the device such as history, cookies, cache files, and even emails and passwords. Such traces can usually help users access a website or input something, such as emails and passwords. The purpose of this research is to obtain digital evidence in the form of a cache on the hard disk in the Librewolf and Qutebrowser browsers. In this study, researchers used the National Institute of Standards and Technology (NIST) 800-86 method which consists of four stages, namely collection, examination, analysis, and reporting. which focuses on the Qutebrowser and LibreWolf browsers. The results obtained from this study were found to be 21 caches, 2 Sessions, 6 Cookies, 8 Network Persistent State, 9 QuotaManager, 11 IndexedDB, 24 LevelDB, 48 Cache Storage, 14 Favicons, 3 History, 6 Database, 3 StartupCache, 4 Alternate Services, 6 Content-Pref, Notification amounted to 1, Permission amounted to 7, Service Worker amounted to 6, SiteSecuristyServiceState amounted to 7, Webappstore amounted to 8, Sessionstore-Backups amounted to 5, Storage amounted to 47 NIST 800-86 method can be properly used in the acquisition of digital evidence and the most crucial data obtained in the Librewolf browser on the telegram and whatsapp sites.

The Dirty Secret of SSDs: Embodied Carbon

Scalable Solid-State Drives (SSDs) have ushered in a transformative era in data storage and accessibility, spanning both data centers and portable devices. However, the strides made in scaling this technology can bear significant environmental consequences. On a global scale, a notable portion of semiconductor manufacturing relies on electricity derived from coal and natural gas sources. A striking example of this is the manufacturing process for a single Gigabyte of Flash memory, which emits approximately 0.16 Kg of CO 2 - a considerable fraction of the total carbon emissions attributed to the system. Remarkably, the manufacturing of storage devices alone contributed to an estimated 20 million metric tonnes of CO 2 emissions in the year 2021. In light of these environmental concerns, this paper delves into an analysis of the sustainability trade-offs inherent in Solid-State Drives (SSDs) when compared to traditional Hard Disk Drives (HDDs). Moreover, this study proposes methodologies to gauge the embodied carbon costs associated with storage systems effectively. The research encompasses four key strategies to enhance the sustainability of storage systems. Firstly, the paper offers insightful guidance for selecting the most suitable storage medium, be it SSDs or HDDs, considering the broader ecological impact. Secondly, the paper advocates for implementing techniques that extend the lifespan of SSDs, thereby mitigating premature replacements and their attendant environmental toll. Thirdly, the paper emphasizes the need for efficient recycling and reuse of high-density multi-level cell-based SSDs, underscoring the significance of minimizing electronic waste. Lastly, for handheld devices, the paper underscores the potential of harnessing the elasticity offered by cloud storage solutions as a means to curtail the ecological repercussions of localized data storage. In summation, this study critically addresses the embodied carbon issues associated with SSDs, comparing them with HDDs, and proposes a comprehensive framework of strategies to enhance the sustainability of storage systems.

Design and Experiment of a Fully Automatic Plate Lifting Machine for Rice Hard Disk Seedling Cultivation

To mitigate the challenges associated with labor intensity and labor expenses in the rice seedling-raising process within greenhouses located in northern China, a comprehensive solution was developed in the form of a completely automated rice seedling-raising machine. The investigation of the first procedure was carried out through the utilization of EDEM software to ascertain the most favorable range of parameters. Performance tests were conducted on the automatic lifting machine designed for rice hard disk seedling cultivation. Based on the findings of the regression model, it can be inferred that when the rake angle is set at 21.278°, the locomotive speed is 0.333 m/s, and the longitudinal conveyor speed is 0.17 m/s, the completeness rate of seed trays reaches 99.48%. Additionally, the lifting efficiency is measured at 510 trays per hour, while the disk jam rate stands at 0.4%. These results indicate that the lifting machine satisfies the specified requirements.

Vision System for Reading Serial Numbers of Hard Disk Drive Slider Bar and Barcode on Its Fixture

Part traceability is one of the inevitable requirements in most modern manufacturing processes. In a hard disk drive (HDD), magnetic head dictates the performance of read/write operations. A number of manufacturing processes are involved to transform a wafer disc to slider bars and finally gliding sliders of the head. In this work, we concentrate on reading serial numbers of slider bar and its attached fixture prior to a bar-lapping process. Since the serial numbers on a bar are in the scale of 18x30 microns and their reflectance nature is rather poor, special optics and lighting components are required. As nature of high optical magnification with limited depth of focus (DOF), conventional image acquisition system can not cover the bar attachment position variation due to wide tolerance of the slider bar fixture. We proposed a serial number reading system using autofocus module to cope with it. Liquid lens and image processing algorithms are introduced to evaluate and adjust the focus automatically. Since our system has to be augmented to an existing machine, footprint is also another main concern. We therefore designed a special rig so the system meets all the fore-mentioned requirements. The system was tested in the production line and had 98% and 90% accuracy for serial number and barcode decoding, respectively. The main cause of barcode reading inaccuracy was from many cycles of the fixture reuse and cleaning in the production line.