Block Storage Research Articles

Soviet era landscape change and the post-Soviet legacy in Latvia

The collectivisation of agriculture and the development and application of land improvement “melioration” programmes and technologies, as well as the construction of kolkhoz centres during the Soviet era in Latvia was extensive and has a legacy on the post-Soviet landscape and agricultural economy. A study of a number of rural municipalities in different landscape types, through the comparison of maps from the early 20th century with those from around 2000, and one example with maps from the 1960s and 1990s, together with field work, revealed the degree of change that had taken place. In particular, there was a significant increase in forest – despite the kolkhoz system being targeted at increasing agricultural outputs, a reduction in the number of farmsteads – in some places this was a result of land battles in the Second World war – and a concentration of residences in villages and widespread drainage of marshes, wetlands and wetter forest. Village centres with concentrations of blocks of flats, storage sheds and industrial units were developed. After 1991 and the restitution of land to the original owners or their descendants, large numbers of kolkhoz agricultural buildings, old estate buildings and some residential blocks became redundant and abandoned. Some of the farmland was also abandoned. The sampled areas show different amounts of landscape change and all showed large numbers of ruined buildings scattered around the area. The question of what to do with these, many of which are robbed of anything useful, vandalised and possibly causing pollution remains open, even after 25 or more years.

Fly Ash Composites, A Step toward Pond Ash Composites

The study demonstrated that ash composites made from polyurethane and fly ash are able to reduce leaching of coal ash inorganics to less than one-third of the U.S. Environmental Protection Agency\'s maximum containment limit even after being exposed to an accelerated water circulation system for 14 months. Even if these ash blocks are broken, the composite is safe. The concept of encapsulation of fly ash into ash composite by using a polar polymer to bind the fine inorganic particles, as nature has done in the original unburned coal, makes the ash composite safe. The ash composites have compression and flexure strength and surface hardness suitable for many engineering applications such as building products and infrastructure products that are more valuable than the use of ash in concrete. The application examples demonstrated include reusable ash storage blocks, utility pole crossarms, and building products such as chair railings, base boards, and decorative moldings. In addition, there are many more positive attributes of ash composites such as insect and fire resistance, low electrical and thermal conductivities, and low coefficient of thermal expansion. These properties need to be assessed further. This fly ash\--composite technology will be expanded to include pond ash that is very abundant in the United States and worldwide and has very limited use. Other applications such as electric poles, railroad ties, and highway sound barriers are the products for exploration.

Scheduling cooperative twin automated stacking cranes in automated container terminals

In the considered Automated Container Terminal, twin (i.e., identical non-passing) automated stacking cranes are configured for each block. The twin Automated Stacking Cranes (ASCs) collaborate to serve storage and retrieval requests from opposite ends of a storage block. Since the ASCs are unable to pass each other, there is a handshake area that serves as a temporary storage location so that one crane can start a request and leave it to the other crane to complete it. In this paper, four modes of crane interference are summarized, and a mixed integer programming model is established to minimize the makespan of all requests. For large scale problems, a genetic algorithm is designed. Numerical experiments show that the algorithm is efficient and competitive. A serial of experiments are carried out where it is shown that the method can produce optimum solutions.

Extensible persistence as a service for containers

Micro-services and containers are becoming the de-facto way of building software and deploying workloads in an agile manner. Following these paradigms leads eventually to replacing the old fashioned monolithic applications by compositions of single-purpose, independent services communicating with each other through light-weight mechanisms. These services are often deployed in containers which have proven to be a suitable runtime platform for micro-services. In the container landscape, there are different container frameworks enabling elastic horizontal scaling for the workloads that are designed as so-called 12-factor applications.11https://12factor.net/.These frameworks were built to accommodate stateless services and require that any state need to be maintained out-of-band of the platform. Support for stateful services in a scalable way is not well covered, particularly in scenarios where state is accessed from workloads in different deployment platforms. It is noteworthy that these workloads cover a wide spectrum of legacy software applications. In order to efficiently support these kinds of workloads, persistent storage such as filesystem or block storage is necessary to maintain the data and make it available for the containers. Managing different types of persistent storage across heterogeneous container orchestrators is a challenging task that people tried to resolve in a specific way for each storage backend or container orchestrator. In this paper, we present the Ubiquity framework, which provides seamless access to persistent storage across different container orchestrators (Cloud Foundry, OpenShift, Kubernetes, Docker and Mesos). Ubiquity is extensible to other container frameworks and different types of file and block storage systems, which can be managed independently of the container orchestrator. Ubiquity makes it easy to onboard stateful services in heterogeneous container environments and based on heterogeneous storage backends, extending the efficiency gains of containerization.

Optimal matching between CO2 sources in Jiangsu province and sinks in Subei‐Southern South Yellow Sea basin, China

AbstractAn understanding of CO2 sources, sinks, and their optimal matching relationships is helpful when making an initial assessment or making decisions regarding CO2 sequestration. One of the most populous and developed provinces in China, Jiangsu, is facing tremendous pressure to reduce CO2 emissions. This study assessed CO2 emissions from large, stationary CO2 sources and the CO2 geological storage capacity for the Jiangsu province, and studied their optimal geographical matching relationships. The results of the study show that major, large, stationary sources have a total of 730.75 Mt/year CO2 emissions, and the majority of them are located in southern Jiangsu. The Subei‐Southern South Yellow Sea basin, with a total storage capacity of 5.21 × 104 Mt, can be subdivided into 28 storage blocks based on the faults. Source‐sink geographical matching shows that the locations of the sources and the matched sinks are approximately translational. When the entire Subei‐Southern South Yellow basin was chosen as an option for CO2 sinks, the sinks that matched to the northern Jiangsu CO2 sources were mainly located in the onshore northern Subei basin. The northern sources tended to match the north sinks of the northern Subei basin. The CO2 from the southern Jiangsu should be stored in the southern Subei basin and the offshore Southern South Yellow basin. When only the offshore storage blocks are optional CO2 sinks, the CO2 sources in the northern and central Jiangsu mainly match the sinks in the northwestern Southern South Yellow basin. The CO2 sources from southern Jiangsu mainly match the sinks in the southern and eastern Southern South Yellow basin. © 2018 Society of Chemical Industry and John Wiley & Sons, Ltd.

Sampling Methodology to Maximize the Efficient Use of National Abattoir Surveillance: Using Archived Sera to Substantiate Freedom From Bluetongue Virus Infection in Ireland.

In recent years, there has been increasing recognition of the value of multiple data sources available to fulfill surveillance objectives, and the use of these has been applied to address many questions relating to animal health surveillance. In Ireland, we face a slightly different problem, namely, best use of an existing surveillance resource (serological samples collected over many years from cull cows at slaughter), which has been used to substantiate freedom from Brucella abortus following its successful eradication in 2009. In this study, we evaluate a sampling methodology to use this resource to substantiate freedom from bluetongue virus (BTV) infection. An examination of the degree to which cull cows were resident in the same herd throughout the midge biting season showed that, of 50,640 samples collected between 17 October and 23 December 2016, 80.2% were from animals resident in the same herd between 01 April 2016 and 2 months prior to their slaughter date, 74.1% for 1 month prior, 70.1% for 2 weeks prior, 66.4% for 1 week prior, and 56.4% up to 1 day prior to slaughter. An examination was made of the degree to which individual samples within the same 88-well frozen storage block came from geographically clustered herds, whether from a concentration of animals from the same herd in a single block, or from clustering around the slaughterhouse where the samples were taken. On the basis of these analyses, a sampling strategy was derived aimed at minimizing the number of storage blocks which needed to be thawed, whilst ensuring a large enough and representative sample, geographically stratified according to the bovine population of 51 squares, each 45 × 45 km, covering the entirety of Ireland. None of the 503 samples tested were positive for BTV, providing reassurance of national BTV freedom. More broadly, the study demonstrates the use of abattoir-based serological samples collected for one large scale surveillance programme in surveillance for other bovine infections.

Container-based bioinformatics with Pachyderm.

MotivationComputational biologists face many challenges related to data size, and they need to manage complicated analyses often including multiple stages and multiple tools, all of which must be deployed to modern infrastructures. To address these challenges and maintain reproducibility of results, researchers need (i) a reliable way to run processing stages in any computational environment, (ii) a well-defined way to orchestrate those processing stages and (iii) a data management layer that tracks data as it moves through the processing pipeline.ResultsPachyderm is an open-source workflow system and data management framework that fulfils these needs by creating a data pipelining and data versioning layer on top of projects from the container ecosystem, having Kubernetes as the backbone for container orchestration. We adapted Pachyderm and demonstrated its attractive properties in bioinformatics. A Helm Chart was created so that researchers can use Pachyderm in multiple scenarios. The Pachyderm File System was extended to support block storage. A wrapper for initiating Pachyderm on cloud-agnostic virtual infrastructures was created. The benefits of Pachyderm are illustrated via a large metabolomics workflow, demonstrating that Pachyderm enables efficient and sustainable data science workflows while maintaining reproducibility and scalability.Availability and implementationPachyderm is available from https://github.com/pachyderm/pachyderm. The Pachyderm Helm Chart is available from https://github.com/kubernetes/charts/tree/master/stable/pachyderm. Pachyderm is available out-of-the-box from the PhenoMeNal VRE (https://github.com/phnmnl/KubeNow-plugin) and general Kubernetes environments instantiated via KubeNow. The code of the workflow used for the analysis is available on GitHub (https://github.com/pharmbio/LC-MS-Pachyderm).Supplementary information Supplementary data are available at Bioinformatics online.

An exact solution approach for scheduling cooperative gantry cranes

We consider a scheduling problem for two gantry cranes moving on the same rails at a single storage block. Containers originating at the seaside have to be stored in the block and containers that are already stored in the storage area at the beginning of the planning horizon have to be delivered to the landside handover point within given time windows. Most commonly in seaport operations, the berthing time of vessels is to be minimized. Thus, the objective considered in this article is to minimize the makespan of seaside container processing while guaranteeing on-time processing of landside containers and while considering non-crossing constraints among cranes. We allow preemption of seaside container processing. This means that one crane may move a seaside container to an intermediate storage slot, and the other crane takes it to its designated position. This has previously been shown to be an effective method of reducing the makespan when compared to classical approaches. We present a dynamic programming (DP) algorithm and a related beam search heuristic. The DP method makes use of bounding techniques and applies dominance properties of optimal solutions. In computational tests, we show that the DP approach clearly outperforms CPLEX and that it is able to quickly solve instances with real-world yard settings. The beam search heuristic is shown to be capable of quickly improving solutions of heuristic approaches that have previously been introduced in the literature. This allows both algorithms to be applied in real-world online settings, where container data is revealed incrementally.

A self-organized resource provisioning for cloud block storage

Modern cloud deployments rely on multiple layers of microservices and a layer of one or more persistent data store systems. The latter has always received a lot of attention as it is the slowest part of the request of an online service. Its unpredictable performance due to workload interference, performance degradation, lack of control, and network partitions has made the cloud less attractive for some services, especially for the applications that require guaranteed throughput, latency, elasticity, and high availability. Motivated by those facts, we propose the Block Software Defined Storage (BSDS), a framework to automate the orchestration, deployment, and management of a storage system by separating the data layer from control. BSDS employs an SLA-aware (Service Level Agreement) and self-learning scheduler that treats the backend media as a black box and abstracts the resource allocation from the state of the storage cluster. Our proposed framework is a step toward the emergence of an intelligent cloud infrastructure that can adapt to unexpected failures, network traffic fluctuations, workload interference perturbations or even changes in the underlying infrastructure. We perform extensive simulations with workloads deduced from an enterprise block storage system and showcase that the proposed scheduler can provide guaranteed Quality of Service (QoS). We finally demonstrate a practical deployment of BSDS on the OpenStack platform.

Effects of postmortem time and storage fluid on the material properties of bovine liver parenchyma in tension.

In motor vehicle collisions (MVCs), liver injuries are one of the most frequently reported types of abdominal organ trauma. Although finite element models are utilized to evaluate the risk of sustaining an abdominal organ injury in MVCs, these models must be validated based on biomechanical data in order to accurately assess injury risk. Given that previous studies that have quantified the tensile failure properties of human liver parenchyma have been limited to testing at 48 h postmortem, it is currently unknown how the material properties change between time of death and 48 h postmortem. Therefore, the objective of this study was to quantify the effects of postmortem degradation on the tensile material properties of bovine liver parenchyma with increasing postmortem time when stored in DMEM or saline. A total of 148 uniaxial tension tests were successfully conducted on parenchyma samples of fourteen bovine livers acquired immediately after death. Liver tissue was submerged in DMEM or saline and kept cool during sample preparation and storage. Twelve livers were stored as large blocks of tissue, while two livers were stored as small blocks and slices. Tension tests were performed on multiple dog-bone samples from each liver at three time points: ~6 h, ~24 h, and ~48 h postmortem. The data were then analyzed using a Linear Mixed Effect Model to determine if there were significant changes in the failure stress, failure strain, and modulus with respect to postmortem time. The results of the current study showed that the failure strain of bovine liver parenchyma decreased significantly between 6 h and 48 h after death when stored as large blocks in saline and refrigerated. Conversely, neither the failure stress nor failure strain changed significantly with respect to postmortem time when stored as large blocks in DMEM. The modulus did not change significantly with respect to postmortem time for tissue stored as large blocks in either saline or DMEM. Cellular disruption increased with postmortem time for tissue stored as large blocks, with tissue stored in saline showing the greatest increase at each time point. In addition, preliminary results indicated that reducing the tissue storage size had a negative effect on the material properties and cellular architecture. Overall, this study illustrated that the effects of postmortem liver degradation varied with respect to the preservation fluid, storage time, and storage block size.

DESIGN AND VERIFICATION OF REMOTE SENSING IMAGE DATA CENTER STORAGE ARCHITECTURE BASED ON HADOOP

Abstract. The data center is a new concept of data processing and application proposed in recent years. It is a new method of processing technologies based on data, parallel computing, and compatibility with different hardware clusters. While optimizing the data storage management structure, it fully utilizes cluster resource computing nodes and improves the efficiency of data parallel application. This paper used mature Hadoop technology to build a large-scale distributed image management architecture for remote sensing imagery. Using MapReduce parallel processing technology, it called many computing nodes to process image storage blocks and pyramids in the background to improve the efficiency of image reading and application and sovled the need for concurrent multi-user high-speed access to remotely sensed data. It verified the rationality, reliability and superiority of the system design by testing the storage efficiency of different image data and multi-users and analyzing the distributed storage architecture to improve the application efficiency of remote sensing images through building an actual Hadoop service system.

Impulsive forces distribution along the sediment storage dam upstream face for different mud–rock flow unit weight

Because of the huge damage caused by mud-rock flow for the downstream life and property, engineering prevention must be given. It is one of fast and effective measures to build sediment storage dams in the formation zone to the circulation area. Due to the undercutting, scour and impact effect of mud-rock flows to sediment storage dam foundation or the unreasonable reconnaissance design, sediment storage dams possibly cause damage in the design period. However, the impulsive forces of mud-rock flow are the main reason to lead the engineering control structures (sediment storage dams, drainage grooves and block structure of pipe group) to damage. It is very important to study the law of mud-rock flow impulsive forces, and it is of great significance to prevent the damage of sediment storage dam and provide data support and technical support for the construction of sediment storage dam. First, the distribution rules of the maximum and mean value of the impulsive forces of mud-rock flow for the sediment storage dam upstream surface were studied for four mud-rock flow slurry unit weight as the experiment variable. The mud-rock flow impulsive forces value was collected by a numerical collection device that connected eight pressure sensors positioned in various locations, which received the mud-rock flow impact signal. Then, the distribution roles of the maximum and mean impulsive forces value imparted by water or water-rock flows were compared. The results indicate that (1) due to the randomness of particle impacts, the distribution law of the maximum impulsive forces is not obvious, and the maximum mud-rock flow impulsive forces of 99.277 kPa occur in A(1)B(3)C(7) (for a range of particle sizes of 2-4.5 cm); (2) the mud-rock flow impulsive forces mean value first increases and then decreases as the unit weight of the mud-rock flow increases; and (3) the mud-rock flow impulsive forces mean value gradually decreases along the height direction of the sediment storage dams' upstream surface and gradually decreases as the direction changes to the overflow section toward the dam abutments.

Information Intelligent Management System Based on Hadoop

In order to explore the information management, the cloud computing technology is applied to the field of geographic information system, and remote sensing data storage and management system based on Hadoop is studied and realized. The main function of this system includes that the remote sensing data storage module provides the remote sensing data download function for data administrator, supports HTTP protocol and FTP protocol multi-threaded distributed HTTP download. The parallel constructing algorithm of remote sensing image of Pyramid based on Map Reduce is realized by the module, and layered cutting and block storage of massive remote sensing data are carried out. The GDAL open source library suitable for fast read raster data is used and it provides data resource for remote sensing data parallel cutting. In addition, the Geo Web Cache open source tile map service middleware is adopted and HBase is introduced as the storage support of tiles, which can deal with a large number of users’ visit, including loading and drag of maps. The system test is carried out to verify the effectiveness and practicability of the method proposed. The test results can show that the remote sensing data storage and management system based on Hadoop can effectively handle remote sensing data and improve the user’s experience. It is concluded that the information management system has high effectiveness and good practicability.

Composite linear flow model for multi-fractured horizontal wells in tight sand reservoirs with the threshold pressure gradient

Multi-stage fracturing is currently the most effective method to exploit tight sand reservoirs. Various analytical models have been proposed to fast and accurately investigate the post-fracturing pressure- and rate-transient behavior, and hence, estimate the key parameters that affect well performance. However, these analytical models mainly consider the 2D flow, neglecting the fluids’ flow from the upper/lower reservoir when the vertical fractures partially penetrate the reservoir. Although for linear flow models, Olarewaju and Lee (1989) and Azari et al. (1990, 1991) have studied the effects of fracture height, they merely used a skin factor. Moreover, the reservoir heterogeneity is seldom included. This paper presents an analytical model for multi-fractured horizontal wells (MFHWs) in tight sand reservoirs, accounting for the upper/lower reservoir contributions, reservoir heterogeneity and threshold-pressure gradient (TPG).The model is extended from the “five-flow-region” model and subdivides the reservoir into seven parts including two upper/lower flow regions, two outer flow regions, two inner flow regions and a hydraulic fracture flow region. Reservoir heterogeneity along the horizontal wellbore is considered, thus, the effects of the fracture pattern in a heterogeneous reservoir are documented. Fracture interference is simulated by locating a virtual no-flow boundary between two adjacent fractures. The exact location of a no-flow boundary is determined based on the boundary's pressure. Thus, the no-flow boundary has a minimum pressure difference between its two sides during the well production, making the no-flow assumption reasonable. The experimentally observed TPG and the pressure drop within the horizontal wellbore are included.Modeling results are compared with those from the well-testing software KAPPA Ecrin, obtaining a good match in most flow regimes. Both the constant-rate and constant-pressure conditions are studied. Results suggest that the fracture penetration ratio dominates the early-mid time pressure responses and the start time of the boundary-dominated flow. For production responses, it determines the initial productivity and the production decline rate. The existence of the TPG results in a higher pressure drop and accelerates the production decline during the middle-late times. But this influence is marginal when the TPG is small (TPG<0.4psi/ft). Effects of other relative parameters, such as the formation permeability, fracture length, conductivity, fracture pattern, wellbore storage, flow-capacity ratio and storativity ratio for dual-porosity reservoir blocks are systematically investigated. Besides, some field data are analyzed and compared graphically, using type curve matching, and reliable results are obtained.Low CPU demands and the minimal data requirement of this model enable the operators to predict well-testing results under different fracture patterns in heterogeneous reservoirs with TPGs in a simple but effective way.

Opportunities for Lipid-Based Probes in the Field of Immunology.

Lipids perform a wide range of functions inside the cell, ranging from structural building block of membranes and energy storage to cell signaling. The mode of action of many signaling lipids has remained elusive due to their low abundance, high lipophilicity, and inherent instability. Various chemical biology approaches, such as photoaffinity or activity-based protein profiling methods, have been employed to shed light on the biological role of lipids and the lipid-protein interaction profile. In this review, we will summarize the recent developments in the field of chemical probes to study lipid biology, especially in immunology, and indicate potential avenues for future research.

A Survey on Secure Block Storage and Access Control Using Big Data Environment

Over past few years, the amount of data being collected continuous to grow more and more companies are building Big Data repositories to store , aggregate and extract meaning from this data and securing Big Data comes main challenge. This paper presents the comparison of different encryption based algorithms i.e. Key Management for Access Control , Attribute-Based Access Control, Attribute-Based Encryption (ABE), Key Policy Attribute-Based Encryption (KP-ABE), Cipher text -Policy Attribute-Based Encryption (CP-ABE) and cryptography for security and access control, its real time applications. This comparison results cannot provide flexibility and efficiency for data analysis. The future scope of this survey on big data can be discussed by using access control algorithm.

Dynamic multiple node failure recovery in distributed storage systems

Our daily lives are getting more and more dependent on data centers and distributed storage systems in general, whether at the business or at the personal level. With the advent of fog computing, personal mobile devices in a given geographical area may also comprise a very dynamic distributed storage system. These paradigm changes call for the urgent need of devising efficient and reliable failure recovery mechanisms in dynamic scenarios where failures become more likely and nodes join and leave the network more frequently. Redundancy schemes in distributed storage systems have become essential for providing reliability given the fact of frequent node failures. In this work, we address the problem of multiple failure recovery with dynamic scenarios using the fractional repetition code as a redundancy scheme. The fractional repetition (FR) code is a class of regenerating codes that concatenates a maximum distance separable code (MDS) with an inner fractional repetition code where data is split into several blocks then replicated and multiple replicas of each block are stored on various system nodes. We formulate the problem as an integer linear programming problem and extend it to account for three dynamic scenarios of newly arriving blocks, nodes, and variable priority blocks allocation. The contribution of this paper is four-fold: i. we generate an optimized block distribution scheme that minimizes the total system repair cost of all dependent and independent multiple node failure scenarios; ii. we address the practical scenario of having newly arriving blocks and allocate those blocks to existing nodes without any modification to the original on-node block distribution; iii. we consider new-comer nodes and generate an updated optimized block distribution; iv. we consider optimized storage and recovery of blocks with varying priority using variable fractional repetition codes. The four problems are modeled using incidence matrices and solved heuristically. We present a range of results for our proposed algorithms in several scenarios to assess the effectiveness of the solution approaches that are shown to generate results close to optimal.

Study on building energy - saving performance of diatomite materials

In order to study the application of phase change materials in the field of building energy saving, diatomite / fatty acid shaped phase change materials were prepared by vacuum impregnation method using modified diatomite as carrier. The structural composition and thermal properties of the shaped phase change materials were analyzed. The phase change material is directly mixed into the cement mortar by stirring. The phase change mortar, phase change mortar test block and phase change mortar heat storage plate are made. Its structural properties, mechanical properties, thermal properties and energy-saving effect was detected and analyzed. The diatomite was modified by roasting, acid leaching, roasting/acid leaching. X-ray diffraction (XRD), scanning electron microscopy (SEM) and BET experiments were used to test the composition and structure of modified diatomite. The results show that the modified diatomite prepared by roasting / acid leaching method has better performance. It has the characteristics of uniform surface pore distribution, complete structure and moderate surface roughness. The stereotyped phase change material has good thermal stability at 105°C. The mass loss rate of the deformed phase change material is 41.65%. Therefore, the stereotyped phase change material can play a good role in the process of environmental temperature changes in the heat.

A Split Architecture Approach to Terabyte-Scale Caching in a Protocol-Oblivious Forwarding Switch

Research has proven that in-network caching is an effective way of eliminating redundant network traffic. For a larger cache that scales up to terabytes, a network element must utilize block storage devices. Nevertheless, accessing block devices in packet forwarding paths could be a major performance bottleneck because storage devices are prone to be much slower than memory devices concerning bandwidth and latency. Software-defined networking (SDN) has entered into all aspects of network architecture by separating the control and forwarding plane to make it more programmable and application-aware. Protocol-oblivious forwarding (POF), which is an enhancement to current OpenFlow-based SDN forwarding architecture, enhances the network programmability further. In this paper, we proposed a novel split architecture to cope with the problem of speed mismatch between high-speed packet forwarding and low-speed block I/O operation over POF switches. The issues raised by this split architecture were first explored and could be summarized as packet dependency and protocol conversion. Then, we focused on solving these two problems and proposed an efficient and scalable design. Finally, we conducted extensive experiments to evaluate the split architecture along with the proposed approaches for packet dependency and protocol conversion.

Hfplayer

We introduce new methods to replay intensive block I/O workloads more accurately. These methods can be used to reproduce realistic workloads for benchmarking, performance validation, and tuning of a high-performance block storage device/system. In this article, we study several sources in the stock operating system that introduce uncertainty in the workload replay. Based on the remedies of these findings, we design and develop a new replay tool called hfplayer that replays intensive block I/O workloads in a similar unscaled environment with more accuracy. To replay a given workload trace in a scaled environment with faster storage or host server, the dependency between I/O requests becomes crucial since the timing and ordering of I/O requests is expected to change according to these dependencies. Therefore, we propose a heuristic way of speculating I/O dependencies in a block I/O trace. Using the generated dependency graph, hfplayer tries to propagate I/O related performance gains appropriately along the I/O dependency chains and mimics the original application behavior when it executes in a scaled environment with slower or faster storage system and servers. We evaluate hfplayer with a wide range of workloads using several accuracy metrics and find that it produces better accuracy when compared to other replay approaches.