Virtual Disk Research Articles

Comparison Performance Analysis of HDD, SSD and NVME for OLTP Database Server

Databases are an essential component of life in modern society. The database has become an online Transaction Processing (OLTP) operational support company. This study discusses the storage configuration in a virtual server database for OLTP Database with a benchmark against three storage configurations for four databases: SQL Server, MySQL, PostgreSQL, and MariaDB for Windows Server virtualization. Benchmarks using TPC-C to get the best performance from all three configurations have been tested. The results of this study show that the storage configuration of HDD as a virtual disk drive OS and NVME as a virtual disk drive database get better performance as online transaction processing (OLTP) compared to HDD as a virtual disk drive OS and HDD or SSD as a virtual disk drive database. Using the TPC-C benchmark, the study tested the performance of four databases (SQL Server, MySQL, PostgreSQL, and MariaDB) in various virtual storage configurations. The results of 36 experiments involving different numbers of virtual users (10, 50, and 100) showed that a hybrid configuration that used HDDs for the operating system and NVME for database storage provided the best performance. On SQL Server, SSD configurations show better results for smaller user loads. The results suggest that the combination of HDD and NVME is the optimal configuration for most databases in OLTP tasks, and it provides useful guidance in efficient storage investment decision-making. Further research is expected to be able to conduct tests.

An Enhanced Predictive Method for Large Droplet Breakage Based on the Discrete Particle Model

Abstract In high-speed flows, a single droplet undergoes fragmentation, yielding numerous child droplets. Conventional breakup models usually group these droplets into a single parcel, neglecting the post-breakup spatial distribution. To address this limitation, detailed numerical simulations have been conducted focusing on the bag and bag-stamen breakup modes of 200 µm- diameter droplet at Weber numbers of 15 and 30. The result shows that the largest length of the child droplets cloud can reach up to 29 relative to the original diameter. Importantly, if the grid size is less than 29 times the droplet diameter, traditional models that use a single parcel for child droplets could produce inaccurate results. To overcome this limitation, a disk-like breakup (DLB) model was introduced. With this model, multiple parcels replace the original droplet and are initialized on a virtual disk. Additionally, partitioned breakup modeling was employed for both bag and bag-stamen breakups. Calculations using the DLB model were compared with the TAB, KH-RT and ETAB models. The result indicates that the DLB model is capable of simulating the spatial distribution of the droplet cloud post-breakup, achieving better agreement with the detailed numerical simulations using the VOF method in this paper and experiments in the literature.

From SSDs Back to HDDs: Optimizing VDO to Support Inline Deduplication and Compression for HDDs as Primary Storage Media

Deduplication and compression are powerful techniques to reduce the ratio between the quantity of logical data stored and the physical amount of consumed storage. Deduplication can impose significant performance overheads, as duplicate detection for large systems induces random accesses to the backend storage. These random accesses have led to the concern that deduplication for primary storage and HDDs are not compatible. Most inline data reduction solutions are therefore optimized for SSDs and discourage their use for HDDs, even for sequential workloads. In this work, we show that these concerns are valid if and only if the lessons learned from deduplication research are not applied. We have therefore investigated data reduction solutions for primary storage based on the RedHat Virtual Disk Optimizer (VDO) and show that directly applying them can decrease sequential write performance for HDDs by 36×. We then show that slight modifications to VDO plus the integration of a very small SSD area significantly improve performance even beyond the performance without data reduction enabled, making HDDs more cost-efficient for a wide range of mostly sequential cloud workloads than SSDs. Additionally, these VDO optimizations do not require to maintain different code bases for HDDs and SSDs, and we therefore provide the first data reduction solution applicable to both storage media.

Peridynamics simulation of TBM cutting process in soft and hard composite strata with a simplified loading scheme

In this study, we address the complex geological conditions encountered during tunnel boring machine (TBM) excavation, particularly the challenges posed by soft and hard composite strata. To overcome limitations of conventional numerical methods for analyzing rock fracture in such strata, we employ Peridynamics to simulate rock fragmentation induced by disc cutters. We propose a virtual disc cutter loading scheme that enhances computational efficiency by replacing traditional contact models. Through numerical examples, we demonstrate the efficacy of this loading scheme in simulating rock fragmentation within soft and hard composite strata. With this method, we conduct numerical studies on kerfs-assisted rock fragmentation in such geological conditions, finding that kerfs can help mitigate differences in cutter forces between soft and hard rocks, thus showing potential for improving TBM performance. Our findings offer insights into optimizing TBM operations in challenging geological environments.

Decentralized Scheduling for Data-Parallel Tasks in the Cloud

For latency-sensitive data processing applications in the cloud, concurrent data-parallel tasks need to be scheduled and processed quickly. A data-parallel task usually consists of a set of sub-tasks, generating a set of flows that are collectively referred to as coflows . The state-of-the-art schedulers collect coflow information in the cloud to optimize coflow-level performance. However, most of the coflows, classified as small coflows because they consist of only short flows, have been largely overlooked. This paper presents OptaX , a decentralized network scheduling service that collaboratively schedules data-parallel tasks’ small coflows. OptaX adopts a cross-layer, COTS (commercial off-the-shelf) switch-compatible design that leverages the sendbuffer information in the kernel to adaptively optimize flow scheduling in the network. Specifically, OptaX (i) monitors the system calls (syscalls) in the hosts to obtain their sendbuffer footprints, and (ii) recognizes small coflows and assigns high priorities to their flows. OptaX transfers these flows in a FIFO manner by adjusting TCP’s two attributes: window size and round-trip time. We have implemented OptaX as a Linux kernel module. The evaluation shows that OptaX is at least 2.2 × faster than fair sharing and 1.2 × faster than only assigning small coflows with the highest priority. We further apply OptaX to improve the small I/O performance of Ursa , a distributed block storage system that provides virtual disks where small I/O is dominant. URSA with OptaX achieves significant improvement compared to the original URSA for small I/O latency.

Influence of scale effect on flow field offset for ships in confined waters

To investigate the flow field characteristics of full-scale ships advancing through confined waters, the international standard container ship (KRISO Container Ship) was considered as a research object in this study. Using the RANS equation, the volume of fluid method and the body force method were selected to investigate the hydrodynamic characteristics of a model-scale ship (the model-scale ratio λ=31.6) and a full-scale ship advancing through confined waters at low speed. A virtual disk was used in the full-scale model to determine the influence of the propeller on the ship’s flow field. First, the feasibility of the numerical calculations was verified. This proves the feasibility of the numerical and grid division methods. The self-propulsion point of the full-scale ship at Fr=0.108 is determined. The calculation cases of model-scale and full-scale ships (with or without virtual disks) at different water depths and distances between the ship and the shore were calculated, and the changes in the hull surface pressure, the flow field around the ship, and the wake fraction near the ship propeller disk in different calculation cases were determined and compared. The variations in the surge force, sway force, and yaw moment between the model- scale and full-scale ships were generally consistent. In very shallow water (H/T=1.3), the non-dimensional force and moment coefficients for model-scale ships increase more rapidly with decreasing distance from shore, suggesting that using model-scale ships to investigate the wall effect in very shallow water will result in predictions that are biased towards safety. By comparing full-scale ships with and without propellers, it was discovered that the surge force, sway force, and yaw moment were marginally greater in the propeller-equipped ship due to the suction effect, and the accompanying flow before and after the propeller was slightly smaller, with less asymmetry.

A Numerical Study on the Hydrodynamic Performance of a Tanker in Bow Sea Conditions Depending on Restraint Conditions

The importance of accurate ship performance estimation is increasing for efficient ship operation. Ship performance has been evaluated through model tests in the past, but there are limitations in terms of facilities and costs. With the spread of high-performance computers, the method of evaluating the performance of a ship by numerical analysis, especially computational fluid dynamics (CFD), has become common. There have been many numerical studies on added resistance under various wave conditions for many years, showing a high reliability. Meanwhile, most of the studies were conducted under conditions where the degree of freedom (DOF) of the ship was limited due to computational complexity. In this study, we tried to compare the added resistance performance and fluid dynamics of S-VLCC with 6 DOFs in the regular wave conditions. One of the methods for utilizing the 6 DOFs is the soft-mooring system, which allows springs to be attached to the bow and stern to recover the non-restoring force of the hull. The second method considers the free-running condition. The virtual disk is used for the self-propulsion of the ship, and the rudder can be rotated to maintain its course. The propeller rotation speed and rudder angle are controlled through PID control. The bow wave (ψ = 180°) and oblique wave (ψ = 150°, 120°) conditions were considered, and various regular wave conditions from short to long wavelengths were regarded. The effects of restraint conditions on the added resistance and motion response amplitude operator (RAO), according to each wave condition, were compared. As a result, there was a difference in the roll motion for each restraint condition, and the y-direction force and yaw moment generated on the hull were compared to analyze the cause. In addition, we observed the change in flow characteristics by comparing the streamlines around the hull and the nominal wake on the propeller plane.

UrsaX: Integrating Block I/O and Message Transfer for Ultrafast Block Storage on Supercomputers

It is increasingly important for the next-generation exascale supercomputers to extend its applications beyond traditional HPC (high-performance computing) scenarios, so as to achieve high social and economic benefit. Similar to AWS (Amazon Web Services) and Alibaba Cloud, cloud-style virtual HPC service is a promising application scenario on supercomputers, for which remote block storage is the key to provide tenants with supercomputers extremely-high storage performance. Unfortunately, the state-of-the-art block storage software systems (such as URSA and Ceph) cannot adapt to the advanced hardware features of supercomputers. This paper presents UrsaX, an efficient block storage service for our next-generation Tianhe exascale supercomputer that is equipped with the high-performance GLEX network and NVMe (Non-Volatile Memory Express) SSDs. UrsaXs virtual disks, which can be mounted like normal physical ones, enable not only traditional HPC applications but also supercomputeroblivious POSIX applications to enjoy the high performance of supercomputers. At the core of UrsaX is with a novel design of the efficient integration of on-disk block I/O and in-network message transfer on supercomputers. UrsaX utilizes the NVMe Fabrics kernel module to expand the NVMe standard on the supercomputer network, and separates metadata I/O and data I/O of blocks respectively being handled over the MP (Mini Packet) and RDMA (Remote Direct Memory Access) protocols. We thoroughly explore the design space for remote block storage on supercomputers including parallelism, scalability, fault tolerance, and consistency. We conduct extensive evaluation on a subset of our exascale supercomputer consisting of 44 storage machines (each with four NVMe SSDs). The result shows that UrsaX achieves local-storage-level I/O latency (tens of microseconds) while being able to linearly increase the aggregate performance (IOPS and throughput) as the system scale increases, an order of magnitude higher than the state-of-the-art block storage systems.

Numerical simulation of KVLCC2 self-propulsion with ducted propeller in head waves

In order to meet the Energy Efficiency Design Index (EEDI) requirements, consideration of reducing added power in waves is important for large tankers operating in ocean environments. In this study, the Reynolds-averaged Navier-Stokes (RANS) solver is employed in Computational Fluid Dynamics (CFD) method to simulate the self-propulsion of KVLCC2 model with a ducted KP458 propeller in head waves, especially for comparison with the non-ducted cases. Two methods are adopted for simulating the ducted propeller: the discretized propeller method and the improved body force ducted propeller method. The latter method incorporates an improved principle of momentum conservation to solve the advance speed of the ducted virtual disk precisely in real time, resulting in similar accuracy and higher efficiency compared to the former method. For some wavelengths, the ducted cases display higher propulsive efficiency and lower power than the non-ducted cases, especially under very short wavelength condition, where negative thrust deduction fraction is observed in the ducted case. With the increase of wave height, the effect of the duct becomes more pronounced, resulting in an increase in propulsive efficiency and a reduction in power, both of which can exceed 10%. Moreover, this research carefully analyzes the added values of self-propulsion factors in head waves, as well as flow fields, providing useful insights to inform the application of ducted propellers in ultra-large ocean-going tankers.

Application of virtual disk propulsion model for self-propelled surface ship in regular head wave

Application of virtual disk propulsion model for self-propelled surface ship in regular head wave

Differences in office-based personal space perception between British and Korean populations.

We sought to understand how the perception of personal space is influenced by different levels of social density, spatial density, and type of window-view in South Korean and United Kingdom workplaces. We employed virtual reality to simulate shared and single occupancy offices. We obtained personal space estimations using a virtual disc around the participant which could be extended and retracted, inside the simulation, to indicate perceived amount of personal space, and compared this measure to questionnaire-based estimations. We found that in both cultures participants experienced greater perceived personal space (1) when in a sparse rather than dense office and (2) having a view of the city outside the office. However, British, but not Korean, participants had significantly higher personal space estimations in single occupancy offices than in shared offices. These results suggest subtle cross-cultural differences in workplace experience, that could only be investigated using virtual reality.

THE IMPLEMENTATION OF CLOUD COMPUTING AS STRATEGIC TECHNOLOGY FOR SUSTAINABLE DEVELOPMENT USING REGRESSION ANALYSIS

As information technology has advanced, there has been a shift toward relying more and more on online cloud storage and computing services. There is no getting around the fact that recent times have seen a meteoric rise in interest in cloud computing. This technology is used by many different organisations as the central component of their information technology infrastructure. The use of cloud computing results in increased data processing efficiency across a variety of computer and storage systems that are available over the internet. The approaches have advanced as a direct result of the cutting-edge and forward-thinking computer procedures that are the foundation of the internet's core database and network architecture. In the 1990s, a new sort of cutting-edge computing known as grid computing came into being. 2005 saw the birth of two new computing paradigms: cloud computing and utility computing. Consolidating several virtual computing components into a single physical platform is one of the most distinguishing features of cloud computing services and infrastructure. These components include the central processing unit (CPU), the network, storage, and memory. A piece of software known as a hypervisor is responsible for isolating each virtual machine (VM) (used by Virtual box and VMware, for example). Using this strategy, one virtual disc or machine may be prevented from directly accessing the memory and programmes of another inside the same environment. This can be accomplished by using a firewall. Through the use of hardware abstraction, it is feasible to conceal the complexity of operating physical computer systems, while at the same time efficiently boosting the systems' processing capacity. Utilizing virtualization technology in the cloud comes with a number of benefits, including scalability and the capacity to support many tenants (one software programme serving many users at once). These properties are essential to cloud computing because they make sharing and pooling resources possible. Sharing and pooling resources provides a number of benefits, some of which include increased business value, more flexibility, and cost savings.

Assessment of the Relevance and Reliability of Reaction Time Tests Performed in Immersive Virtual Reality by Mixed Martial Arts Fighters.

Immersive virtual reality (VR) is increasingly applied in various areas of life. The potential of this technology has also been noticed in recreational physical activity and sports. It appears that a virtual environment can also be used in diagnosing certain psychomotor abilities. The main aim of this study consisted of assessing the relevance and reliability of VR-implemented tests of simple and complex reaction time (RT) performed by mixed martial arts (MMA) fighters. Thirty-two professional MMA fighters were tested. The original test developed in the virtual environment was applied for RT assessment. The fighters’ task consisted of reacting to the lighting up of a virtual disc situated in front of them by pushing a controller button. The relevance of the test task was estimated by juxtaposing the obtained results with the classic computer test used for measuring simple and complex reactions, while its reliability was assessed with the intraclass correlation procedure. Significant relationships found between the results of VR-implemented tests and computer-based tests confirmed the relevance of the new tool for the assessment of simple and complex RT. In the context of their reliability, RT tests in VR do not differ from tests conducted with the use of standard computer-based tools. VR technology enables the creation of tools that are useful in diagnosing psychomotor abilities. Reaction time tests performed by MMA fighters with the use of VR can be considered relevant, and their reliability is similar to the reliability obtained in computer-based tests.

Simulation of the interaction between ship and ducted propeller with a modified body force method

For ships with conventional propellers, the body force method is one of the main methods for self-propulsion research due to its high computational efficiency. However, when it comes to ducted propellers with complex internal flow fields, applicability of the body force method is still unknown. In this work, a modified body force method which can be applied to the ducted propeller is investigated. Specifically, the Reynolds-averaged Navier–Stokes (RANS) solver is adopted to simulate the interaction between a trawler and a ducted propeller. Before self-propulsion simulations, uncertainty analysis of ship resistance, ducted propeller thrust, and ducted propeller torque was carried out. As a comparison, the discretized propeller method and the body force methods are adopted in the simulations of self-propulsion. Because of the neglect of the duct, the errors of the conventional body force method exceed the allowable range. Therefore, the concept of the ducted virtual disk is proposed, in which only the propeller is replaced by the virtual disk. Especially, the advance speed coefficient and the open water curve of the virtual disk are modified, so that the open water result of the ducted virtual disk is consistent with that of the ducted propeller. The modified body force method has good accuracy and can roughly describe the wake fields when applied to self-propulsion simulation. Furthermore, the interaction between the ship and the ducted propeller can be well reflected, which is of great significance in rapidly predicting self-propulsion of ships with ducted propellers.

Digital forensic investigation methodology for Storage Space: Based on the NIST digital forensic process.

For forensic examiners, investigating the RAID systems of servers has been challenging, as the examiners must reconstruct multiple high-capacity disks to identify digital evidence. Software-based RAID systems' use has been released for personal use, so examiners should consider RAID systems even when they investigate personal computers. Although there is a high probability that the software-based RAID will become a target of crime, there has been little research into digital forensic methodology for software-based RAID, as exemplified by Storage Space. In this paper, we introduce details about the structure of Storage Space found through reverse engineering. Storage Space was analyzed by applying the digital forensic process of NIST. We explain how to reconstruct a virtual disk configured using Storage Space and develop an automated tool to do so. To evaluate our study and the tool developed, we created an experimental scenario and describe in detail the forensic procedure and technical methods for the analysis of Storage Space. Our research can be used as the basis of forensic investigations for Storage Space.

Application of the body force method in the rim driven thruster

The rim driven thruster (RDT) has become a popular ship propulsion system in recent years. Due to the complex structure of RDT, a great number of computational resources are required to study the interaction between RDT and hull by adopting the discretized propeller method. This research looks into a modified body force method which is suitable for the RDT. To simulate self-propulsion of a trawler with a rim driven thruster, the Reynolds-averaged Navier–Stokes (RANS) solver is used. In the modified body force method, three virtual disks are adopted to replace the propeller and rim rotors. Before correction, the interactions among the duct, the rim rotors and the propeller were studied. Through the analysis, it is found that the most suitable scheme is to take the open water curves of the propeller, of the “rotors + duct” and of the RDT as the references for modification. The ducted virtual disks open water curve is modified in open water simulations until the result is consistent with the RDT open water calculation results. When used to self-propulsion simulation, the modified body force method is accurate and can roughly characterize the flow fields. The modified body force method saves a huge number of grids when compared to the discretized propeller method. Furthermore, the interaction between the ship and the RDT can be accurately modeled, which is critical for quickly predicting self-propulsion in ships equipped with rim driven thrusters. Finally, the modified body force method in this work is named as the body force RDT method.

INFLUENCE OF LOCATION OF ONE AND MULTIPLE ANTENNAS ON CAPACITY OF C2C COMMUNICATION SYSTEMS

Due to the variety of existing and future wireless services, the number of antennas installed on a vehicle is constantly increasing. However, due to design limitations or the addition of more components of electrical equipment, the number of user-friendly antenna positions is reduced. To ensure stable data connections or even higher data rates with the remaining installation space, a possible solution is to use multiple antenna systems. This document discusses and evaluates 16 possible positions of antennas for communication between cars (C2C). The radiation pattern of all antennas is determined by the antenna synthesis maximization method, which takes into account real-world limitations such as space availability, transmission power, number and location of antennas. Channel bandwidth is used to compare different settings. This bandwidth is calculated using virtual disks based on typical application scenarios. The results of this study show which antenna positions and which combinations of antenna positions are most suitable for communication between C2C. Additional time and cost constraints, as well as an increase in the range of products for the automotive industry and a large number of degrees of freedom for the multi-purpose antenna necessitate the use of advanced modeling models and design strategies. Thus, this is the starting point for this work. Here is presented and used a technique that allows you to optimize single and multiple antenna systems. The main purpose of the proposed synthesis is to optimize the radiation profiles of antennas based on constraints specific to vehicles. For antenna design, this document identifies different scenarios based on typical C2C security scenarios. The simulation is carried out in a typical worst case in urban and rural areas or on highways.

Virtual Disks Performance Analysis Using Flexible I/O and Powerstat

Abstract: Cloud computing has experienced significant growth in the recent years owing to the various advantages it provides such as 24/7 availability, quick provisioning of resources, easy scalability to name a few. Virtualization is the backbone of cloud computing. Virtual Machines (VMs) are created and executed by a software called Virtual Machine Monitor (VMM) or the hypervisor. It separates compute environments from the actual physical infrastructure. A disk image file representing a single virtual machine is created on the hypervisor’s file system. In this paper, we analysed the runtime performance of multiple different disk image file formats. The analysis comprises of four different parameters of performance namely- bandwidth, latency, input-output operations performed per second (IOPS) and power consumption. The impact of the hypervisor’s block and file sizes is also analysed for the different file formats. The paper aims to act as a reference for the reader in choosing the most appropriate disk file image format for their use case based on the performance comparisons made between different disk image file formats on two different hypervisors – KVM and VirtualBox. Keywords: Virtualization, Virtual disk formats, Cloud computing, fio, KVM, virt-manager, powerstat, VirtualBox.

Study of added resistance and seakeeping of KVLCC2 in waves with and without propeller

Numerical simulation of a full-scale ship model, KVLCC2, has been conducted applying the Reynolds Averaged Navier-Stokes (RANS) approach using the STARCCM+ commercial computational fluid dynamics (CFD) software to calculate total resistance, seakeeping and Pitch Moments. Results are obtained for the speed of 15.5 Knots under different sea conditions (calm water, regular waves and irregular waves), The total resistance calculated for the KVLCC2 ship hull in calm water is in a good agreement with the results from experiments and the results for motion (heave and pitch) and added resistance in waves were compared to numerical and experimental findings from previous research with good agreement. In addition to wave excitations, the full-scale ship model was subjected to propeller excitations using the virtual disk model from the CFD software. The body force propeller method, which simplified the full propeller characteristic of the KVLCC2 into a resultant body force, is applied to the virtual disk model. Results are compared with results from the hull-only model. A comparison of the wake results with previous work is also presented.

Guaranteed Bang for the Buck: Modeling VDI Applications to Identify Storage Requirements

In the cloud environment, most services are provided by virtual machines (VMs). Identifying storage requirements of VMs is challenging, but it is essential for good user experiences while optimizing use of storage resources. Determining the storage configuration necessary to support and satisfy VMs first requires an accurate description of the VM configurations, and the problem is further exacerbated by the diversity and special characteristics of the VMs. In this paper, we study Virtual Desktop Infrastructure (VDI), a prevalent and complicated VM application, to identify and characterize storage requirements of VMs and determine how to meet such requirements with minimal storage resources and cost. We first create a model to describe the behavior of VDI, and we collect real VDI traces to populate this model. The model allows us to identify the storage requirements of VDI and determine the potential bottlenecks of a given storage configuration. Based on this information, we can tell what capacity and minimum capability a storage configuration needs in order to support and satisfy given VDI configurations. We show that our model can describe more fine-grained VM behavior varying with time and virtual disk types compared with the rules of thumb currently used in industry.