Magnetic Hard Disk Research Articles

In-Storage Computing for Hadoop MapReduce Framework: Challenges and Possibilities

Solid State Drives (SSDs) were initially developed as faster storage devices intended to replace conventional magnetic Hard Disk Drives (HDDs). However, high computational capabilities enable SSDs to be computing nodes, not just faster storage devices. Such capability is generally called ”In-Storage Computing (ISC)”. Today’s Hadoop MapReduce framework has become a de facto standard for big data processing. This paper explores In-Storage Computing challenges and opportunities for the Hadoop MapReduce framework. For this, we integrate a Hadoop MapReduce system with ISC SSD devices that implement the Hadoop Mapper inside real SSD firmware. This offloads Map tasks from the host MapReduce system to the ISC SSDs. We additionally optimize the host Hadoop system to make the best use of our proposed ISC Hadoop system. Experimental results demonstrate our ISC Hadoop MapReduce system achieves a remarkable performance gain (2.3 faster) as well as significant energy savings (11.5 lower) compared to a typical Hadoop MapReduce system. Further, the experiment suggests such ISC augmented systems can provide a very promising computing model in terms of a system scalability.

High Temperature Mechanics, Friction, Wear and Adhesion of Heat-Assisted Magnetic Recording

The majority of data generated today is stored in magnetic storage hard disk drives (HDD) of enterprise-level data centers. The HDD industry is striving for higher areal density capacity to meet increasing demand for data storage. Heat-assisted magnetic recording (HAMR) has been proposed as the next-generation technology that will bring revolutionary areal density gains. However, the technology comes with elevated temperature conditions and inevitably brings corresponding challenges to the head–disk interface (HDI). HDI high temperature tribology is the primary failure mode of HDDs and is discussed in the present work. Temperature dependence of mechanical properties, friction, wear and adhesion are reported based on experimental results from nanoindentation, nanoscratch, nanowear and adhesion experiments. The data reveals quantitative variations of Young’s modulus, hardness, coefficient of friction, and surface energy with temperature. In addition, XPS analysis is performed to measure chemical surface changes, and correlated with the nanomechanical findings.

DSTL

Shingled magnetic recording (SMR) is regarded as a promising technology for resolving the areal density limitation of conventional magnetic recording hard disk drives. Among different types of SMR drives, drive-managed SMR (DM-SMR) requires no changes on the host software and is widely used in today’s consumer market. DM-SMR employs a shingled translation layer (STL) to hide its inherent sequential-write constraint from the host software and emulate the SMR drive as a block device via maintaining logical to physical block address mapping entries. However, because most existing STL designs do not simultaneously consider the access pattern and the data update frequency of incoming workloads, those mapping entries maintained within the STL cannot be effectively managed, thus inducing unnecessary performance overhead. To resolve the inefficiency of existing STL designs, this article proposes a demand-based STL (DSTL) to simultaneously consider the access pattern and update frequency of incoming data streams to enhance the access performance of DM-SMR. The proposed design was evaluated by a series of experiments, and the results show that the proposed DSTL can outperform other SMR management approach by up to 86.69% in terms of read/write performance.

A three level hierarchical architecture for an efficient storage of industry 4.0 data

The increasing interest among manufacturers in monitoring and analyzing industrial systems is generating a problem related to the considerable costs associated with the storage of the captured data. This paper presents a three level hierarchical architecture for Industry 4.0 time-series data storage on cloud environments that helps to manage and reduce those costs. In the first level, new raw time series can be stored for a short-period of time on electronic non-volatile storage such as Solid-State Drives (SSDs). In the second level, recent time series can be stored for a medium-period of time on magnetic Hard Disk Drives (HDDs). In the third level, a reduced representation of the time series obtained by applying time series reduction techniques can also be stored in HDDs for a longer period of time.The main contribution of this paper is related to the third level of the architecture, that allows to decrease the required data storage resources by storing reduced representations of time-series data, without almost hampering the use of those data for further analysis purposes. The proposed architecture, has been implemented by using some of the top Database Management Systems (DBMSs) from four different categories: Time series DBMS, Wide column stores, Document stores and Graph DBMS. It has been tested by using industrial time series coming from a real manufacturing environment, and with four different types of queries proposed by domain experts. The performance results regarding storage space, storage costs and total query time for each DBMS are shown and contrasted in this paper.

Storing data in glass: Optical storage media is advancing from CDs and DVDs to small glass squares - [News

Magnetic tape and hard disk drives hold much of the world's archival data. Compared with other memory and storage technologies, tape and disk drives cost less and are more reliable. They're also nonvolatile, meaning they don't require a constant power supply to preserve data. Cultural institutions, financial firms, government agencies, and film companies have relied on these technologies for decades, and will continue to do so far into the future.

A Diode-Enhanced Scheme for Giant Magnetoresistance Amplification and Reconfigurable Logic

Magnetoresistance (MR) effects have been intensively investigated and widely recognized as an effective path for realizing information sensing, storage, and processing. In particular, giant MR (GMR) effect discovered in ferromagnetic/nonmagnetic multilayers or junctions exhibits high magnetic-field sensitivity and has been successfully applied in magnetic sensors and hard disk drive (HDD) read heads. However, the relatively small MR ratio becomes the Achilles' Heel for its further application in high-reliability electronic systems. In this paper, we propose a scheme to amplify the GMR effect of a multilayer strip by utilizing the nonlinear transport property of a diode. MR ratio up to 6947% is obtained with a magnetic field as small as 50 Oe. A theoretical model is established to describe the amplification behavior and various factors influencing MR ratio are experimentally analyzed. Based on this scheme, reliable logic functions have been carried out, which can be reconfigured by changing the working current. Our work can be extended to enhance the MR effect of any two-terminal MR device and has the potential to build emerging high-performance computing systems.

Demonstration of spin transfer torque (STT) magnetic recording

In the magnetic hard disk drive industry, a continuous increase in the recording density requires higher anisotropy media in order to maintain thermal stability. However, further advances by scaling have run into a stumbling block due to limitations on the required magnetic fields, particularly for writing, which is currently being addressed by alternative approaches such as heat-assisted magnetic recording and microwave-assisted magnetic recording technologies. In this work, we investigate and demonstrate another alternative approach which is based on the effect of the spin transfer torque (STT). The approach uses tunneling spin-polarized currents, instead of magnetic fields, between a nanoscale magnetic probe and a magnetic recording media, both with a perpendicular anisotropy. Writing is performed by spin polarized electrons injected from the probe into the media, due to the STT effect. Reading is produced by the tunneling magnetoresistance (TMR) effect between the two magnetic layers, in the probe writer and the media substrate, respectively. The energy-efficient switching, with an energy of 3.1 MA/cm2, is confirmed through the TMR and the magneto-optical Kerr effect. The demonstrated STT-based magnetic recording overcomes the magnetic field limitations to both writing and reading and thus paves the way for the next-generation energy-efficient and extremely high-density recording.

Disjoining Pressure Derived from the Lennard–Jones Potential, Diffusion Equation, and Diffusion Coefficient for Submonolayer Liquid Film

In magnetic hard disk drives, it is important to evaluate the replenishment effect of a submonolayer lubricant film under a more severe condition that the head–disk spacing has to be reduced from the current 0.7 nm to ~0.5 nm. In contrast to the prevailing conventional diffusion equation validated for multilayer liquid film, the author has already proposed a new diffusion equation more suitable for submonolayer film by intuitively incorporating the density reduction effect in the submonolayer liquid film. This paper presents a rigorous derivation of the disjoining pressure (DP) from Lennard–Jones potential (LJP) and formulated the diffusion equation incorporating the DP. The difference in the rigorous DP and diffusion equation from the previous versions is negligibly small except in a small film thickness less than the van der Waals (vdW) distance. The theoretical relationship between the vdW distance in the DP and the molecular force equilibrium distance in the LJP is elucidated. Rigorous derivations of the DP and diffusion equation for multilayer liquid film from the LJP are also presented. The superiority of the submonolayer diffusion equation over the conventional equation in the submonolayer film regime is demonstrated by comparing their theoretical diffusion coefficients with Waltman’s experimental data.

Enhancement of hard disk drive manipulator using piezoelectric actuator mechanisms

This paper discusses the employment of piezoelectric actuators (PEA) to encompass high precision-scale movement capability of magnetic hard disk drive servo systems. To overcome path/positioning limitations of previous hard disk servo systems, a new design consisting of three PEAs links is proposed. Two different controllers, namely PI and fuzzy, are designed and simulated to assess the performance of the proposed design over a couple of paths under the presence of noise and disturbance. Simulation results show that the proposed design is able to track complex paths over a wider spectrum of motion than conventional hard drive servo systems. This improves the read–write process by affording nanoscale motion and provides high levels of positioning accuracy, as well as wide spectrum of positioning capability. Moreover, both controllers reveal the ability to drive the mechanism with quick response and minimal overshoot, with the fuzzy controller outperforming the PI controller under the presence of noise and disturbance.

Magnetic properties of free-standing finite linear Co chains

The ground state magnetic properties of Co_N linear atomic chains with 1 ≤ N ≤ 10 are studied within density functional theory using the generalized gradient approximation . A linear scaling between the binding energy per atom and the inverse of the number of atoms in the chain is found. For the optimized geometries, our results show a dimerization effect for chains of few atoms but for bigger ones the phenomena disappear in the center but remains at the ends due to finite size effects. The spin moment, the orbital moment and the magnetic anisotropy energy were investigated. For large chains, the orbital and spin moments have a tendency to become uniform. Enhanced spin and orbital moments were found due to the reduced coordination number compared to the cobalt in bulk. The cobalt chain of five atoms has the biggest magnetic anisotropy energy with an outstanding 8 meV, suggesting that it could have applications in ultrahigh density magnetic memories and hard disk.

Multilevel process on large area wafers for nanoscale devices

Spintronic nanodevices are consolidating a highly reputed position in advanced manufacturing industry, not only due to progresses in magnetic hard disk sensors, but also the memory market. The ability to integrate magnetic thin films on large area wafers and subsequent nanofabrication into functional devices is key for such success. This work describes methodologies used for definition of sub-100 nm pillars, using reliable via opening to contact nanopillars buried in a dielectric film. A two consecutive step electron beam lithography process is used to fabricate current-perpendicular-to plane nanodevices. The first step is required to pattern nanopillars down to 30 nm. The second provides access to nanopillar top through nanovias definition and reactive ion etching. Optimum alignment of multilevel exposures ensures the most accurate positioning in the shortest time. Most importantly, the results are obtained on 150 mm diameter wafers, where additional challenges of uniformity of resists, oxides and metals are critical for end-point control and improved yield of fabricated devices. The design of customized test structures allowed control of etching end-point.

EAD: elasticity aware deduplication manager for datacenters with multi-tier storage systems

The popularity of Big Data applications places pressures on storage systems to efficiently scale to meet the demand. At the same time, new developments like solid-state drives have changed to traditional storage hierarchy. Cloud storage systems are transitioning towards a hybrid architecture consisting of large amounts of memory, solid-state disks (SSDs), and traditional magnetic hard disks (HD). This paper presents elasticity aware deduplication (EAD), a data deduplication framework designed for multi-tier cloud storage architectures consisting of SSD and HD. EAD dynamically adjusts the deduplication parameters at runtime in order to improve performance. Experimental results indicate that EAD is able to detect more than 98% of all duplicate data, but it only consumes less than 5% of expected memory space. Additionally, EAD saves approximately 74% of overall IO access cost compared to the traditional design.

Improving the SSD Performance by Exploiting Request Characteristics and Internal Parallelism

With the explosive growth in the data volume, the I/O bottleneck has become an increasingly daunting challenge for big data analytics. It is urgent and important to introduce high-performance flash-based solid state drives (SSDs) into the storage systems. However, since the existing systems are primarily designed for conventional magnetic hard disk drives, directly incorporating SSDs in the existing systems cannot fully exploit SSDs’ performance advantages. In this paper, we propose a new I/O scheduler for SSDs, namely Amphibian, that exploits the high-level request characteristics and low-level parallelism of flash chips to improve the performance of SSD-based storage systems. Amphibian includes two performance enhancement schemes: 1) size-based request ordering, which prioritizes requests with small sizes in processing and 2) garbage collection (GC)-aware request dispatching that delays issuing requests to flash chips that are in the GC state. These two schemes employed in Amphibian significantly reduce the average waiting times of the requests from the host. Our extensive evaluation results derived from three types of SSDs show that, compared with the existing I/O schedulers, Amphibian greatly improves both throughput and average response times for SSD-based storage systems, thus improving the I/O performance of the systems.

Rigorous derivation of diffusion equation for submonolayer lubricant film

In magnetic hard disk drives, it is important to secure the stability and durability of head–disk interface in relation to a submonolayer lubricant film because the spacing between a head and lubricant surface has to be reduced to ~0.5 nm to achieve a high density recording far beyond 2 Tb/in2. As a succeeding paper of the newly proposed diffusion equation for a submonolayer liquid film, this paper presents a rigorous derivation of the disjoining pressure (DP) from the Lennard–Jones potential (LJP) and formulated the rigorous diffusion equation incorporating the DP. The flow equation for a submonolayer film and viscosity model are the same as in the previous paper. The difference of the rigorous DP and diffusion equation from the previous ones are not significant except in a small thickness regime less than the van der Walls (vdW) distance. Theoretical relationship between the vdW distance in DP and the molecular force equilibrium distance in LJP is elucidated. Rigorous expressions of the conventional DP and diffusion equation for multilayer film are shown. Superiority of the submonolayer diffusion theories to the conventional theory are demonstrated by comparing their theoretical diffusion coefficients with Waltman’s experimental data.

Impact of radius and skew angle on areal density in heat assisted magnetic recording hard disk drives

This study aims to investigate the impact that factors such as skew, radius, and transition curvature have on areal density capability in heat-assisted magnetic recording hard disk drives. We explore a “ballistic seek” approach for capturing in-situ scan line images of the magnetization footprint on the recording media, and extract parametric results of recording characteristics such as transition curvature. We take full advantage of the significantly improved cycle time to apply a statistical treatment to relatively large samples of experimental curvature data to evaluate measurement capability. Quantitative analysis of factors that impact transition curvature reveals an asymmetry in the curvature profile that is strongly correlated to skew angle. Another less obvious skew-related effect is an overall decrease in curvature as skew angle increases. Using conventional perpendicular magnetic recording as the reference case, we characterize areal density capability as a function of recording position.

Simultaneous readout of two adjacent bit tracks with a spin-torque oscillator

We propose a novel setup for a spin-torque oscillator reader in magnetic hard disk drive technology. Two adjacent bit tracks are to be read simultaneously, leading to high data transfer rate and increased resilience to noise as the lateral size of the oscillator device is allowed to remain larger than the bit width. We perform micromagnetic simulations of an example system and find that the magnetization response has a clear unimodal character, which enables for detection of two bit values at the same time. We analyze the frequency of the device under the influence of two different external fields and conduct a simulation of a successful dynamic readout. We estimate the signal linewidth and signal-to-noise ratios of the setup and show that it may be potentially beneficial for magnetic readout applications.

Multihead Multitrack Detection for Next Generation Magnetic Recording, Part II: Complexity Reduction — Algorithms and Performance Analysis

To achieve large storage capacity on magnetic hard disk drives, very high track density is required, causing severe intertrack interference (ITI). Multihead multitrack (MHMT) detection has been proposed to better combat the effects of ITI. Such detection, however, has prohibitive implementation complexity. Reduced-state sequence estimation (RSSE) is a promising technique for significantly reducing the complexity, while retaining good performance. In this paper, several different MHMT models are considered, including symmetric and asymmetric 2H2T systems, and a symmetric 3H3T system. By carefully evaluating the effective distance between two input symbols, we propose optimized set partition trees for each channel model. Different trellis configurations for RSSE are constructed based on the desired performance/complexity tradeoff. Simulation results show that the reduced MHMT detector can achieve near maximum-likelihood (ML) performance with a small fraction of the original number of trellis states. We also use error event analysis to explain the behavior of RSSE. The proposed algorithm could be potentially applied to next generation magnetic recording systems, especially when the ML detector is infeasible due to the high computational complexity.

DaC scan: a novel scan operator for exploiting SSD internal parallelism

SummarySolid‐state drives (SSDs) have become an attractive alternative for storing large databases. Solid‐state drives do not present mechanical parts in their assembly. Consequently, SSDs have different characteristics and capabilities than magnetic disks Hard Disk Drives (HDDs). One of the most important features of SSDs is the fact that they implement different levels of internal parallelism for executing read/write operations. In database query processing, the table scan operator is responsible for reading an entire table. Generally, a scan operator is utilized whenever there is no index defined on the table to be accessed. This paper introduces a novel scan operator, denoted DaC Scan, for reading database tables stored in SSDs. The key goal of the proposed operator is to explore IO parallelism. Thus, the idea is to make DaC Scan able to read different regions of a single table simultaneously. For validation of DaC Scan efficiency, experiments with a prototype have been conducted over the TPC‐H benchmark database, scale factors 10 and 20. The results show that DaC Scan is efficient, presenting significant gains w.r.t. classical scan operators.

Fermi Surface Manipulation by External Magnetic Field Demonstrated for a Prototypical Ferromagnet

The functionality of today's technology in magnetic hard disks or memories relies on tiny relativistic effects in electron behavior that were previously believed to be too small to be directly observed. Researchers visualize these effects, for the first time, by showing how the electronic structure of iron responds to the direction of a magnetic field.

Review Article: FePt heat assisted magnetic recording media

Heat-assisted magnetic recording (HAMR) media status, requirements, and challenges to extend the areal density (AD) of magnetic hard disk drives beyond current records of around 1.4 Tb/in.2 are updated. The structural properties of granular high anisotropy chemically ordered L10 FePtX-Y HAMR media by now are similar to perpendicular CoCrPt-based magnetic recording media. Reasonable average grain diameter ⟨D⟩ = 8–10 nm and distributions σD/D ∼ 18% are possible despite elevated growth temperatures TG = 650–670 °C. A 2× reduction of ⟨D⟩ down to 4–5 nm and lowering σD/D < 10%–15% are ongoing efforts to increase AD to ∼4 Tb/in.2. X = Cu ∼ 10 at. % reduces the Curie temperature TC by ∼100 K below TC,bulk = 750 K, thereby lowering the write head heat energy requirement. Multiple FePtX-Y granular layers with Y = 30–35 vol. % grain-to-grain segregants like carbides, oxides, and/or nitrides are used to fully exchange decouple the grains and achieve cylindrical shape. FePt is typically grown on fcc MgO (100) seedlayers to form well oriented FePt (002). A FePt lattice parameter ratio c/a ∼0.96 and high chemical order S > 0.90 result in magnetic anisotropy KU ∼ 4.5 × 107 erg/cm3, and only 25% below the FePt single crystal value KU = 6.6 × 107 erg/cm3 has been achieved in 7–8 nm diameter grains. Switching field distributions depend on anisotropy field (HK) distributions, which are currently of the order of ΔHK/HK ∼ 10% (ΔHK ∼ 10–12 kOe, HK ∼ 10–11 T) at room temperature. High thermal conductivity heat sink layers, including Ag, Au, Cu, and Cr, are used to optimize the cooling rate and maximize the down- and cross-track thermal gradient, which determines the achievable track density.