The Experts below are selected from a list of 28509 Experts worldwide ranked by ideXlab platform

Artem Starostin - One of the best experts on this subject based on the ideXlab platform.

  • The original publication is available at www.springerlink.com Formal Pervasive Verification of a Paging Mechanism
    2015
    Co-Authors: Eyad Alkassar, Norbert Schirmer, Artem Starostin
    Abstract:

    Abstract. Memory virtualization by means of demand paging is a crucial com-ponent of every Modern Operating System. The formal verification is challenging since reasoning about the page fault handler has to cover two concurrent com-putational sources: the processor and the hard disk. We accurately model the in-terleaved executions of devices and the page fault handler, which is written in a high-level programming language with inline assembler portions. We describe how to combine results from sequential Hoare logic style reasoning about the page fault handler on the low-level concurrent machine model. To the best of our knowledge this is the first example of pervasive formal verification of software communicating with devices.

  • Formal pervasive verification of a paging mechanism
    2008
    Co-Authors: Eyad Alkassar, Norbert Schirmer, Artem Starostin
    Abstract:

    Abstract. Memory virtualization by means of demand paging is a crucial com-ponent of every Modern Operating System. The formal verification is challenging since reasoning about the page fault handler has to cover two concurrent com-putational sources: the processor and the hard disk. We accurately model the in-terleaved executions of devices and the page fault handler, which is written in a high-level programming language with inline assembler portions. We describe how to combine results from sequential Hoare logic style reasoning about the page fault handler on the low-level concurrent machine model. To the best of our knowledge this is the first example of pervasive formal verification of software communicating with devices.

Hao Yang - One of the best experts on this subject based on the ideXlab platform.

  • memos revisiting hybrid memory management in Modern Operating System
    arXiv: Operating Systems, 2017
    Co-Authors: Lei Liu, Mengyao Xie, Hao Yang
    Abstract:

    The emerging hybrid DRAM-NVM architecture is challenging the existing memory management mechanism in Operating System. In this paper, we introduce memos, which can schedule memory resources over the entire memory hierarchy including cache, channels, main memory comprising DRAM and NVM simultaneously. Powered by our newly designed kernel-level monitoring module and page migration engine, memos can dynamically optimize the data placement at the memory hierarchy in terms of the on-line memory patterns, current resource utilization and feature of memory medium. Our experimental results show that memos can achieve high memory utilization, contributing to System throughput by 19.1% and QoS by 23.6% on average. Moreover, memos can reduce the NVM side memory latency by 3~83.3%, energy consumption by 25.1~99%, and benefit the NVM lifetime significantly (40X improvement on average).

  • rethinking memory management in Modern Operating System horizontal vertical or random
    IEEE Transactions on Computers, 2016
    Co-Authors: Lei Liu, Chen Ding, Hao Yang
    Abstract:

    On Modern multicore machines, the memory management typically combines address interleaving in hardware and random allocation in the Operating System (OS) to improve performance of both memory and cache. The conventional solutions, however, are increasingly strained as a wide variety of workloads run on complicated memory hierarchy and cause contention at multiple levels. We describe a new framework (named HVR) in OS memory management to support a flexible policy space for tackling diverse application needs, integrating vertical partitioning across layers, horizontal partitioning and random-interleaved allocation at a single layer. We exhaustively study the performance of these policies for over 2,000 workloads and correlate performance with application characteristics. Based on this correlation we derive several practical rules of memory allocation that we integrate into the unified HVR framework to guide resource partitioning and sharing for dynamic and diverse workloads. We implement our approach in Linux kernel 2.6.32 as a restructured page indexing System plus a series of kernel modules. Experimental results show that our framework consistently outperforms the unmodified Linux kernel, with up to 21 percent performance gains, and outperforms prior solutions at individual levels of the memory hierarchy.

Rui Jian - One of the best experts on this subject based on the ideXlab platform.

  • design and implementation of linux file System supporting multilingualism
    Computer Science, 2005
    Co-Authors: Rui Jian
    Abstract:

    Multilingualization of Modern Operating System is necessitated on the Internet. Since internationalization architecture complying to POSIX has less support for multilingual and distributed applications, Linux file System dirived from POSIX may lose data in storing some multilingual text. Based on Linux file System, a new File System called EXT2U is presented, which supports metadata encoded by UTF-16. Meanwhile, virtual fileSystem switch in Linux kernel is improved and a set of System calls using a data type special to UTF-16 are proposed. by means of EXT2U and new System calls, the ability to process multilingual information can be achieved easier in Linux.

Eyad Alkassar - One of the best experts on this subject based on the ideXlab platform.

  • The original publication is available at www.springerlink.com Formal Pervasive Verification of a Paging Mechanism
    2015
    Co-Authors: Eyad Alkassar, Norbert Schirmer, Artem Starostin
    Abstract:

    Abstract. Memory virtualization by means of demand paging is a crucial com-ponent of every Modern Operating System. The formal verification is challenging since reasoning about the page fault handler has to cover two concurrent com-putational sources: the processor and the hard disk. We accurately model the in-terleaved executions of devices and the page fault handler, which is written in a high-level programming language with inline assembler portions. We describe how to combine results from sequential Hoare logic style reasoning about the page fault handler on the low-level concurrent machine model. To the best of our knowledge this is the first example of pervasive formal verification of software communicating with devices.

  • Formal pervasive verification of a paging mechanism
    2008
    Co-Authors: Eyad Alkassar, Norbert Schirmer, Artem Starostin
    Abstract:

    Abstract. Memory virtualization by means of demand paging is a crucial com-ponent of every Modern Operating System. The formal verification is challenging since reasoning about the page fault handler has to cover two concurrent com-putational sources: the processor and the hard disk. We accurately model the in-terleaved executions of devices and the page fault handler, which is written in a high-level programming language with inline assembler portions. We describe how to combine results from sequential Hoare logic style reasoning about the page fault handler on the low-level concurrent machine model. To the best of our knowledge this is the first example of pervasive formal verification of software communicating with devices.

Lei Liu - One of the best experts on this subject based on the ideXlab platform.

  • memos revisiting hybrid memory management in Modern Operating System
    arXiv: Operating Systems, 2017
    Co-Authors: Lei Liu, Mengyao Xie, Hao Yang
    Abstract:

    The emerging hybrid DRAM-NVM architecture is challenging the existing memory management mechanism in Operating System. In this paper, we introduce memos, which can schedule memory resources over the entire memory hierarchy including cache, channels, main memory comprising DRAM and NVM simultaneously. Powered by our newly designed kernel-level monitoring module and page migration engine, memos can dynamically optimize the data placement at the memory hierarchy in terms of the on-line memory patterns, current resource utilization and feature of memory medium. Our experimental results show that memos can achieve high memory utilization, contributing to System throughput by 19.1% and QoS by 23.6% on average. Moreover, memos can reduce the NVM side memory latency by 3~83.3%, energy consumption by 25.1~99%, and benefit the NVM lifetime significantly (40X improvement on average).

  • rethinking memory management in Modern Operating System horizontal vertical or random
    IEEE Transactions on Computers, 2016
    Co-Authors: Lei Liu, Chen Ding, Hao Yang
    Abstract:

    On Modern multicore machines, the memory management typically combines address interleaving in hardware and random allocation in the Operating System (OS) to improve performance of both memory and cache. The conventional solutions, however, are increasingly strained as a wide variety of workloads run on complicated memory hierarchy and cause contention at multiple levels. We describe a new framework (named HVR) in OS memory management to support a flexible policy space for tackling diverse application needs, integrating vertical partitioning across layers, horizontal partitioning and random-interleaved allocation at a single layer. We exhaustively study the performance of these policies for over 2,000 workloads and correlate performance with application characteristics. Based on this correlation we derive several practical rules of memory allocation that we integrate into the unified HVR framework to guide resource partitioning and sharing for dynamic and diverse workloads. We implement our approach in Linux kernel 2.6.32 as a restructured page indexing System plus a series of kernel modules. Experimental results show that our framework consistently outperforms the unmodified Linux kernel, with up to 21 percent performance gains, and outperforms prior solutions at individual levels of the memory hierarchy.