Effects of micro-alloying elements and production process on microstructure, mechanical properties and precipitates of 600 MPa grade rebars were studied by using pilot test, metallographic observa- tion, tensile test,...Effects of micro-alloying elements and production process on microstructure, mechanical properties and precipitates of 600 MPa grade rebars were studied by using pilot test, metallographic observa- tion, tensile test, thermodynamic calculation and transmission electron microscopy. The results show that the tested steels are composed of ferrite and pearlite, in which the conterlt range of pearlite is 33%-45%. For vanadium micro-alloyed steel, interphase preeipitation Strengthening effect of V can be promoted and the yield strength of tested steels can be increased with increasing V content and de- creasing finishing rolling temperature. The temperature of terminated cooling should be more than 700 ℃ when the water cooling is used. When niobium is added to the steel, more coarse (Nb,V)C,N precipitates are generated at high temperature, so that the solid solubility of precipitated phases of vanadium is reduced and the precipitation strengthening effect of vanadium is weakened.展开更多
Cloud computing is an elastic computing model where users can lease computing and storage resources on demand from a remote infrastructure. It is gaining popularity due to its low cost, high reliability, and wide avai...Cloud computing is an elastic computing model where users can lease computing and storage resources on demand from a remote infrastructure. It is gaining popularity due to its low cost, high reliability, and wide availability. With the emergence of public cloud storage platforms like Amazon, Microsoft, and Google, individual applications and enterprise storage are being deployed on Clouds. However, a serious impediment to its wider deployment is the relative lack of effective data management services. Our experiments, as well as industry reports, have shown that the performance and service-level agreement (SLA) cannot be guaranteed when the data is served over public Clouds. The relatively slow access to persistent data and large variability in cloud storage I/O performance can significantly degrade the performance of data-intensive applications. This paper addresses the issue of I/O performance fluctuation over public cloud platforms and we propose a middleware called CloudMW between the Cloud storage and clients to provide the storage services with better performance and SLA satisfaction. Some technologies, including data virtualization, data chunking, caching, and replication, are integrated into CloudMW to achieve a more stable and predictable performance, and permit flexible sharing of storage among the virtual machines (VMs). Experimental results based on Amazon Web Services (AWS) show that CloudMW is able to improve the stability and help provide better SLAs and data sharing for cloud storage.展开更多
Using a Gleeble-1500D thermal-mechanical simulator,the hot-deformation behavior and critical strain in the dynamic recrystallization of SA508Gr.4N steel were investigated by compression tests from 1050 to 1250℃ with ...Using a Gleeble-1500D thermal-mechanical simulator,the hot-deformation behavior and critical strain in the dynamic recrystallization of SA508Gr.4N steel were investigated by compression tests from 1050 to 1250℃ with strain rates from 0.001 to 0.1 s^-1.Stress-strain curves were fitted by a nonlinear fitting method.Based on these tests,the flow stress constitutive equations of the work-hardening dynamical recovery period and dynamical recrystallization period Were established for SA508Gr.4N steel.The stress-strain curves of SA508Gr.4N steel predicted by the established models are in a good agreement with the experimental ones.Curves of ln θ -ε and --(a)(lnθ)/(a)ε-ε (where θ is the work-hardening rate and ε is true strain)were plotted from experimental data.A critical strain (εc)and a peak strain (εp)of dynamic recrystallization were obtained and exhibited a linear relationship,i.e.,εc =0.386εp.The predicted model of εc could be described by the equation of εc=1.604×10^-3Z^0.127.展开更多
The two-pass isothermal hot compression method was used to study the effect of different thermal deformation conditions on static recrystallization behavior in Ni-Cr-Mo series SA508Gr.4N low alloy steel with interval ...The two-pass isothermal hot compression method was used to study the effect of different thermal deformation conditions on static recrystallization behavior in Ni-Cr-Mo series SA508Gr.4N low alloy steel with interval holding time ranging from 1 to 300 s,temperature ranging from 950 to 1150℃,strain rate ranging from 0.01 to 1 s^(-1),true strains ranging from 0.1 to 0.2,and initial austenite grain size ranging from 175 to 552μm.It can be concluded that the static recrystallization volume fraction gradually increases with the increase in the deformation temperature,strain rate,strain and pass interval,and the decrease in the initial grain size,which is mainly due to the increase in the deformation energy storage and dislocations.Moreover,strain-induced grain boundary migration is the nucleation mechanism for static recrystallization of SA508Gr.4N low alloy steel.Based on the stress-strain curve,the predicted value obtained from the established static recrystallization kinetics model is in good consistence with the experimental value,and the static recrystallization thermal activation energy of SA508Gr.4N steel was calculated as 264,225.99 J/mol.展开更多
Due to its low latency,byte-addressable,non-volatile,and high density,persistent memory(PM)is expected to be used to design a high-performance storage system.However,PM also has disadvantages such as limited endurance...Due to its low latency,byte-addressable,non-volatile,and high density,persistent memory(PM)is expected to be used to design a high-performance storage system.However,PM also has disadvantages such as limited endurance,thereby proposing challenges to traditional index technologies such as B(+)tree.B(+)tree is originally designed for dynamic random access memory(DRAM)-based or disk-based systems and has a large write amplification problem.The high write amplification is detrimental to a PM-based system.This paper proposes WO-tree,a write-optimized B(+)tree for PM.WO-tree adopts an unordered write mechanism for the leaf nodes,and the unordered write mechanism can reduce a large number of write operations caused by maintaining the entry order in the leaf nodes.When the leaf node is split,WO-tree performs the cache line flushing operation after all write operations are completed,which can reduce frequent data flushing operations.WO-tree adopts a partial logging mechanism and it only writes the log for the leaf node.The inner node recognizes the data inconsistency by the read operation and the data can be recovered using the leaf node information,thereby significantly reducing the logging overhead.Furthermore,WO-tree adopts a lock-free search for inner nodes,which reduces the locking overhead for concurrency operation.We evaluate WO-tree using the Yahoo!Cloud Serving Benchmark(YCSB)workloads.Compared with traditional B(+)tree,wB-tree,and Fast-Fair,the number of cache line flushes caused by WO-tree insertion operations is reduced by 84.7%,22.2%,and 30.8%,respectively,and the execution time is reduced by 84.3%,27.3%,and 44.7%,respectively.展开更多
Electrical additive manufacturing can improve manufacturing efficiency and reduce the cost of 16MND5 reactor pres-sure vessel steel. Impact tests were conducted to compare the impact toughness of 16MND5 steels manufac...Electrical additive manufacturing can improve manufacturing efficiency and reduce the cost of 16MND5 reactor pres-sure vessel steel. Impact tests were conducted to compare the impact toughness of 16MND5 steels manufactured by the electrical additive manufacturing and conventional forging, respectively. It is found that the impact toughness of electrical additive manufacturing specimen was slightly higher than that of conventional forging specimen. The characterizations of microstructure show that there were large ferrites and carbides in electrical additive manufacturing specimen. The fracture mechanisms of electrical additive manufacturing specimen were that microvoids or microcracks were prone to nucleate at the large ferrite/bainite interface and large carbide/bainitic ferrite interface, where the stress concentration was high. In addi-tion, the block size and high-angle grain boundaries played a vital role in hindering crack propagation of electrical additive manufacturing specimen, helping to improve the impact energy and leading to a low ductile–brittle transition temperature. The results suggest that the electrical additive manufacturing technology was an effective method to enhance the impact toughness of 16MND5 steel.展开更多
Among redundant arrays of independent disks(RAID)-6 codes, maximum distance separable(MDS)based RAID-6 codes are popular because they have the optimal storage efficiency. Although vertical MDS codes exhibit better loa...Among redundant arrays of independent disks(RAID)-6 codes, maximum distance separable(MDS)based RAID-6 codes are popular because they have the optimal storage efficiency. Although vertical MDS codes exhibit better load balancing compared to horizontal MDS codes in partial stripes, an I/O unbalancing problem still exists in some vertical codes. To address this issue, we propose a novel efficient data layout, uniform P-code(UPC), to support highly balanced I/Os among P-coded disk arrays(i.e., PC). In UPC, the nonuniformly distributed information symbols in each parity chain of P-code are moved along their columns to other rows, thus enabling the parity chain to keep original parity relationships and tolerate double disk failures. The UPC scheme not only achieves optimal storage efficiency, computational complexity, and update complexity, but also supports better I/O balancing in the context of large-scale storage systems. We also conduct a performance study on reconstruction algorithms using an analytical model. Besides extensive theoretical analysis, comparative performance experiments are conducted by replaying real-world workloads under various configurations. Experimental results illustrate that our UPC scheme significantly outperforms the PC scheme in terms of average user response time. In particular, in the case of a 12-disk array, the UPC scheme can improve the access performance of the RAID-6 storage system by29.9% compared to the PC scheme.展开更多
The metadynamic recrystallization(MDRX)model is established,and the coefficients determined by multiple linear regression analysis are used to describe the microstructure evolution of SA508Gr.4N steel.The effects of c...The metadynamic recrystallization(MDRX)model is established,and the coefficients determined by multiple linear regression analysis are used to describe the microstructure evolution of SA508Gr.4N steel.The effects of compression temperature of 950–1150℃,strain rate of 0.001–0.1 s^(-1),pre-strain of 0.3–0.6,initial austenite grain size(IAGS)of 136–552 lm,and interval time of 1–300 s on the MDRX kinetics and microstructure evolution were analyzed,using twopass compression test method on Gleeble thermo-mechanical simulator.The results show that MDRX kinetics and austenite grain size are strongly dependent on compression temperature and strain rate,MDRX volume fraction increases with increasing compression temperature and strain rate,and the grain size decreases with increasing strain rate and decreasing compression temperature,while less affected by the pre-strain and IAGS.Meanwhile,the values predicted using MDRX model and the ones calculated from experiment are compared,and the results show that the proposed model can give a reasonable estimate of MDRX behavior for SA508Gr.4N steel.展开更多
Performance and energy consumption of a solid state disk(SSD) highly depend on file systems and I/O schedulers in operating systems. To find an optimal combination of a file system and an I/O scheduler for SSDs, we us...Performance and energy consumption of a solid state disk(SSD) highly depend on file systems and I/O schedulers in operating systems. To find an optimal combination of a file system and an I/O scheduler for SSDs, we use a metric called the aggregative indicator(AI), which is the ratio of SSD performance value(e.g., data transfer rate in MB/s or throughput in IOPS) to that of energy consumption for an SSD. This metric aims to evaluate SSD performance per energy consumption and to study the SSD which delivers high performance at low energy consumption in a combination of a file system and an I/O scheduler. We also propose a metric called Cemp to study the changes of energy consumption and mean performance for an Intel SSD(SSD-I) when it provides the largest AI, lowest power, and highest performance, respectively. Using Cemp, we attempt to find the combination of a file system and an I/O scheduler to make SSD-I deliver a smooth change in energy consumption. We employ Filebench as a workload generator to simulate a wide range of workloads(i.e., varmail, fileserver, and webserver), and explore optimal combinations of file systems and I/O schedulers(i.e., optimal values of AI) for tested SSDs under different workloads. Experimental results reveal that the proposed aggregative indicator is comprehensive for exploring the optimal combination of a file system and an I/O scheduler for SSDs, compared with an individual metric.展开更多
Sequential prefetching schemes are widely employed in storage servers to mask disk latency and improve system throughput. However, existing schemes cannot benefit parallel disk systems as expected due to the fact that...Sequential prefetching schemes are widely employed in storage servers to mask disk latency and improve system throughput. However, existing schemes cannot benefit parallel disk systems as expected due to the fact that they ignore the distinct internal characteristics of the parallel disk system, in particular, data striping. Moreover, their aggressive prefetching pattern suffers from premature evictions and prolonged request latencies. In this paper, we propose a strip-oriented asynchronous prefetching (SoAP) technique, which is dedicated to the parallel disk system. It settles the above-mentioned problems by providing multiple novel features, e.g., enhanced prediction accuracy, adaptive prefetching strength, physical data layout awareness, and timely prefetching. To validate SoAP, we implement a prototype by modifying the software redundant arrays of inexpensive disks (RAID) under Linux. Experimental results demonstrate that SoAP can consistently offer improved average response time and throughput to the parallel disk system under non-random workloads compared with STEP, SP, ASP, and Linux-like SEQPs.展开更多
基金supported by Natural Science Research Project of Anhui Province of China (KJ2016A091)Natural Science Foundation of Anhui Province (1708085ME116)Science and Technology Research Program of Anhui Province of China (1201a0201005)
文摘Effects of micro-alloying elements and production process on microstructure, mechanical properties and precipitates of 600 MPa grade rebars were studied by using pilot test, metallographic observa- tion, tensile test, thermodynamic calculation and transmission electron microscopy. The results show that the tested steels are composed of ferrite and pearlite, in which the conterlt range of pearlite is 33%-45%. For vanadium micro-alloyed steel, interphase preeipitation Strengthening effect of V can be promoted and the yield strength of tested steels can be increased with increasing V content and de- creasing finishing rolling temperature. The temperature of terminated cooling should be more than 700 ℃ when the water cooling is used. When niobium is added to the steel, more coarse (Nb,V)C,N precipitates are generated at high temperature, so that the solid solubility of precipitated phases of vanadium is reduced and the precipitation strengthening effect of vanadium is weakened.
基金Project supported by the National Basic Research Program (973) of China (No. 2011CB302303)the National High-Tech R&D Program (863) of China (No. 2009AA01A402)+3 种基金the National Natural Science Foundation of China (No. 60933002)the Chenguang Plan of Wuhan,China (No. 201050231073)the Innovation Plan of WNLOthe National Science Foundation of USA (Nos. CNS-0917157,CNS-0615376,and CNS-0541369)
文摘Cloud computing is an elastic computing model where users can lease computing and storage resources on demand from a remote infrastructure. It is gaining popularity due to its low cost, high reliability, and wide availability. With the emergence of public cloud storage platforms like Amazon, Microsoft, and Google, individual applications and enterprise storage are being deployed on Clouds. However, a serious impediment to its wider deployment is the relative lack of effective data management services. Our experiments, as well as industry reports, have shown that the performance and service-level agreement (SLA) cannot be guaranteed when the data is served over public Clouds. The relatively slow access to persistent data and large variability in cloud storage I/O performance can significantly degrade the performance of data-intensive applications. This paper addresses the issue of I/O performance fluctuation over public cloud platforms and we propose a middleware called CloudMW between the Cloud storage and clients to provide the storage services with better performance and SLA satisfaction. Some technologies, including data virtualization, data chunking, caching, and replication, are integrated into CloudMW to achieve a more stable and predictable performance, and permit flexible sharing of storage among the virtual machines (VMs). Experimental results based on Amazon Web Services (AWS) show that CloudMW is able to improve the stability and help provide better SLAs and data sharing for cloud storage.
文摘Using a Gleeble-1500D thermal-mechanical simulator,the hot-deformation behavior and critical strain in the dynamic recrystallization of SA508Gr.4N steel were investigated by compression tests from 1050 to 1250℃ with strain rates from 0.001 to 0.1 s^-1.Stress-strain curves were fitted by a nonlinear fitting method.Based on these tests,the flow stress constitutive equations of the work-hardening dynamical recovery period and dynamical recrystallization period Were established for SA508Gr.4N steel.The stress-strain curves of SA508Gr.4N steel predicted by the established models are in a good agreement with the experimental ones.Curves of ln θ -ε and --(a)(lnθ)/(a)ε-ε (where θ is the work-hardening rate and ε is true strain)were plotted from experimental data.A critical strain (εc)and a peak strain (εp)of dynamic recrystallization were obtained and exhibited a linear relationship,i.e.,εc =0.386εp.The predicted model of εc could be described by the equation of εc=1.604×10^-3Z^0.127.
基金This work was financially supported by the National Energy Application Technology Research and Engineering Demonstrative Project of China(NY201501)the National High Technology Research and Development Program of China(863 program.No.2012AA03A501)the National Key Research and Development Program of China(2016YFB0300203).
文摘The two-pass isothermal hot compression method was used to study the effect of different thermal deformation conditions on static recrystallization behavior in Ni-Cr-Mo series SA508Gr.4N low alloy steel with interval holding time ranging from 1 to 300 s,temperature ranging from 950 to 1150℃,strain rate ranging from 0.01 to 1 s^(-1),true strains ranging from 0.1 to 0.2,and initial austenite grain size ranging from 175 to 552μm.It can be concluded that the static recrystallization volume fraction gradually increases with the increase in the deformation temperature,strain rate,strain and pass interval,and the decrease in the initial grain size,which is mainly due to the increase in the deformation energy storage and dislocations.Moreover,strain-induced grain boundary migration is the nucleation mechanism for static recrystallization of SA508Gr.4N low alloy steel.Based on the stress-strain curve,the predicted value obtained from the established static recrystallization kinetics model is in good consistence with the experimental value,and the static recrystallization thermal activation energy of SA508Gr.4N steel was calculated as 264,225.99 J/mol.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.U1709220,U2001203,61821003,61872413,and 61902137in part by the National Key Research and Development Program of China under Grant No.2018YFB1003305in part by the Key-Area Research and Development Program of Guangdong Province of China under Grant No.2019B010107001.
文摘Due to its low latency,byte-addressable,non-volatile,and high density,persistent memory(PM)is expected to be used to design a high-performance storage system.However,PM also has disadvantages such as limited endurance,thereby proposing challenges to traditional index technologies such as B(+)tree.B(+)tree is originally designed for dynamic random access memory(DRAM)-based or disk-based systems and has a large write amplification problem.The high write amplification is detrimental to a PM-based system.This paper proposes WO-tree,a write-optimized B(+)tree for PM.WO-tree adopts an unordered write mechanism for the leaf nodes,and the unordered write mechanism can reduce a large number of write operations caused by maintaining the entry order in the leaf nodes.When the leaf node is split,WO-tree performs the cache line flushing operation after all write operations are completed,which can reduce frequent data flushing operations.WO-tree adopts a partial logging mechanism and it only writes the log for the leaf node.The inner node recognizes the data inconsistency by the read operation and the data can be recovered using the leaf node information,thereby significantly reducing the logging overhead.Furthermore,WO-tree adopts a lock-free search for inner nodes,which reduces the locking overhead for concurrency operation.We evaluate WO-tree using the Yahoo!Cloud Serving Benchmark(YCSB)workloads.Compared with traditional B(+)tree,wB-tree,and Fast-Fair,the number of cache line flushes caused by WO-tree insertion operations is reduced by 84.7%,22.2%,and 30.8%,respectively,and the execution time is reduced by 84.3%,27.3%,and 44.7%,respectively.
基金Project supported by the National Natural Science Foundation of China (Nos. 61472152, 614320{37, 61572209, and 61300047), the Fundamental Research Funds for the Central Universities, China (No. 2015QN069), the Director Fund of Wuhan National Laboratory for Optoelectronics (WNLO), and the MOE Key Laboratory of Data Storage System, China
基金This work was financially supported by the Nuclear Power Technology Innovation Center(HDLCXZX-2018-HD-027-03)Science and Technology on Reactor System Design Technology Laboratory(HT-KFKT-02-2017006).
文摘Electrical additive manufacturing can improve manufacturing efficiency and reduce the cost of 16MND5 reactor pres-sure vessel steel. Impact tests were conducted to compare the impact toughness of 16MND5 steels manufactured by the electrical additive manufacturing and conventional forging, respectively. It is found that the impact toughness of electrical additive manufacturing specimen was slightly higher than that of conventional forging specimen. The characterizations of microstructure show that there were large ferrites and carbides in electrical additive manufacturing specimen. The fracture mechanisms of electrical additive manufacturing specimen were that microvoids or microcracks were prone to nucleate at the large ferrite/bainite interface and large carbide/bainitic ferrite interface, where the stress concentration was high. In addi-tion, the block size and high-angle grain boundaries played a vital role in hindering crack propagation of electrical additive manufacturing specimen, helping to improve the impact energy and leading to a low ductile–brittle transition temperature. The results suggest that the electrical additive manufacturing technology was an effective method to enhance the impact toughness of 16MND5 steel.
基金supported by the National Basic Research Program(973)of China(No.2011CB302303)the National High-Tech R&D Program(863)of China(No.2013AA013203)
文摘Among redundant arrays of independent disks(RAID)-6 codes, maximum distance separable(MDS)based RAID-6 codes are popular because they have the optimal storage efficiency. Although vertical MDS codes exhibit better load balancing compared to horizontal MDS codes in partial stripes, an I/O unbalancing problem still exists in some vertical codes. To address this issue, we propose a novel efficient data layout, uniform P-code(UPC), to support highly balanced I/Os among P-coded disk arrays(i.e., PC). In UPC, the nonuniformly distributed information symbols in each parity chain of P-code are moved along their columns to other rows, thus enabling the parity chain to keep original parity relationships and tolerate double disk failures. The UPC scheme not only achieves optimal storage efficiency, computational complexity, and update complexity, but also supports better I/O balancing in the context of large-scale storage systems. We also conduct a performance study on reconstruction algorithms using an analytical model. Besides extensive theoretical analysis, comparative performance experiments are conducted by replaying real-world workloads under various configurations. Experimental results illustrate that our UPC scheme significantly outperforms the PC scheme in terms of average user response time. In particular, in the case of a 12-disk array, the UPC scheme can improve the access performance of the RAID-6 storage system by29.9% compared to the PC scheme.
基金This work was financially supported by the National Energy Application Technology Research and Engineering Demonstrative Project of China(NY201501)the National High Technology Research and Development Program of China(863 Program,No.2012AA03A501)the National Key Research and Development Program of China(2016YFB0300203).
文摘The metadynamic recrystallization(MDRX)model is established,and the coefficients determined by multiple linear regression analysis are used to describe the microstructure evolution of SA508Gr.4N steel.The effects of compression temperature of 950–1150℃,strain rate of 0.001–0.1 s^(-1),pre-strain of 0.3–0.6,initial austenite grain size(IAGS)of 136–552 lm,and interval time of 1–300 s on the MDRX kinetics and microstructure evolution were analyzed,using twopass compression test method on Gleeble thermo-mechanical simulator.The results show that MDRX kinetics and austenite grain size are strongly dependent on compression temperature and strain rate,MDRX volume fraction increases with increasing compression temperature and strain rate,and the grain size decreases with increasing strain rate and decreasing compression temperature,while less affected by the pre-strain and IAGS.Meanwhile,the values predicted using MDRX model and the ones calculated from experiment are compared,and the results show that the proposed model can give a reasonable estimate of MDRX behavior for SA508Gr.4N steel.
基金supported by the National Basic Research Program(973)of China(No.2011CB302303)the National Natural Science Foundation of China(No.60933002)+1 种基金the National High-Tech R&D Program(863)of China(No.2013AA013203)the U.S. National Science Foundation under Grants CCF0845257(CAREER),CNS-0917137(CSR),CNS-0757778(CSR),CCF-0742187(CPA),CNS-0831502(CyberTrust),CNS-0855251(CRI),OCI-0753305(CI-TEAM),DUE-0837341(CCLI),and DUE-0830831(SFS)
文摘Performance and energy consumption of a solid state disk(SSD) highly depend on file systems and I/O schedulers in operating systems. To find an optimal combination of a file system and an I/O scheduler for SSDs, we use a metric called the aggregative indicator(AI), which is the ratio of SSD performance value(e.g., data transfer rate in MB/s or throughput in IOPS) to that of energy consumption for an SSD. This metric aims to evaluate SSD performance per energy consumption and to study the SSD which delivers high performance at low energy consumption in a combination of a file system and an I/O scheduler. We also propose a metric called Cemp to study the changes of energy consumption and mean performance for an Intel SSD(SSD-I) when it provides the largest AI, lowest power, and highest performance, respectively. Using Cemp, we attempt to find the combination of a file system and an I/O scheduler to make SSD-I deliver a smooth change in energy consumption. We employ Filebench as a workload generator to simulate a wide range of workloads(i.e., varmail, fileserver, and webserver), and explore optimal combinations of file systems and I/O schedulers(i.e., optimal values of AI) for tested SSDs under different workloads. Experimental results reveal that the proposed aggregative indicator is comprehensive for exploring the optimal combination of a file system and an I/O scheduler for SSDs, compared with an individual metric.
基金supported by the National Basic Research Program(973) of China (No. 2011CB302303)the National Natural Science Foundation of China (No. 60933002)the Fundamental Research Funds for the Central Universities,China (Nos.2012QN100 and 2011TUS-136)
文摘Sequential prefetching schemes are widely employed in storage servers to mask disk latency and improve system throughput. However, existing schemes cannot benefit parallel disk systems as expected due to the fact that they ignore the distinct internal characteristics of the parallel disk system, in particular, data striping. Moreover, their aggressive prefetching pattern suffers from premature evictions and prolonged request latencies. In this paper, we propose a strip-oriented asynchronous prefetching (SoAP) technique, which is dedicated to the parallel disk system. It settles the above-mentioned problems by providing multiple novel features, e.g., enhanced prediction accuracy, adaptive prefetching strength, physical data layout awareness, and timely prefetching. To validate SoAP, we implement a prototype by modifying the software redundant arrays of inexpensive disks (RAID) under Linux. Experimental results demonstrate that SoAP can consistently offer improved average response time and throughput to the parallel disk system under non-random workloads compared with STEP, SP, ASP, and Linux-like SEQPs.