Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems

Hitoshi Mitake, Tsung Han Lin, Yuki Kinebuchi, Hiromasa Shimada, Tatsuo Nakajima

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    7 Citations (Scopus)

    Abstract

    When a real-time OS (RTOS) and a symmetric multiprocessing general purpose OS (SMP GPOS) are executed on the same multicore processor, there is a possibility to cause the lock holder preemption (LHP) problem, which is a well known problem of the sources of the performance degradation on an SMP GPOS. The problem occurs when a kernel mode thread holding a lock in a SMP GPOS is preempted by other OSes if these OSes share the same physical core. The existing solution does not take into account real-time responsiveness so it is not suitable to use in embedded systems. The paper proposes two new techniques to avoid the LHP problem for ensuring both the real-time responsiveness of real-time OS and the high throughput of SMP GPOS. The new proposed techniques have been implemented on our virtualization layer called SPUMONE, and we measured the results showing that the proposed new techniques reduce the LHP problem without degrading the real-time responsiveness.

    Original languageEnglish
    Title of host publicationProceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA
    Pages270-279
    Number of pages10
    DOIs
    Publication statusPublished - 2012
    Event18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - Seoul
    Duration: 2012 Aug 192012 Aug 22

    Other

    Other18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012
    CitySeoul
    Period12/8/1912/8/22

    Fingerprint

    Embedded systems
    Program processors
    Throughput
    Degradation
    Virtualization

    Keywords

    • Embedded Systems
    • Lock Holder Preemption
    • Muticore Processor
    • Virtualization

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Hardware and Architecture
    • Computer Vision and Pattern Recognition

    Cite this

    Mitake, H., Lin, T. H., Kinebuchi, Y., Shimada, H., & Nakajima, T. (2012). Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems. In Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA (pp. 270-279). [6300159] https://doi.org/10.1109/RTCSA.2012.32

    Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems. / Mitake, Hitoshi; Lin, Tsung Han; Kinebuchi, Yuki; Shimada, Hiromasa; Nakajima, Tatsuo.

    Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA. 2012. p. 270-279 6300159.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Mitake, H, Lin, TH, Kinebuchi, Y, Shimada, H & Nakajima, T 2012, Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems. in Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA., 6300159, pp. 270-279, 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012, Seoul, 12/8/19. https://doi.org/10.1109/RTCSA.2012.32
    Mitake H, Lin TH, Kinebuchi Y, Shimada H, Nakajima T. Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems. In Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA. 2012. p. 270-279. 6300159 https://doi.org/10.1109/RTCSA.2012.32
    Mitake, Hitoshi ; Lin, Tsung Han ; Kinebuchi, Yuki ; Shimada, Hiromasa ; Nakajima, Tatsuo. / Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems. Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA. 2012. pp. 270-279
    @inproceedings{1eacfa61da2b4b9e97d221b7f130860f,
    title = "Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems",
    abstract = "When a real-time OS (RTOS) and a symmetric multiprocessing general purpose OS (SMP GPOS) are executed on the same multicore processor, there is a possibility to cause the lock holder preemption (LHP) problem, which is a well known problem of the sources of the performance degradation on an SMP GPOS. The problem occurs when a kernel mode thread holding a lock in a SMP GPOS is preempted by other OSes if these OSes share the same physical core. The existing solution does not take into account real-time responsiveness so it is not suitable to use in embedded systems. The paper proposes two new techniques to avoid the LHP problem for ensuring both the real-time responsiveness of real-time OS and the high throughput of SMP GPOS. The new proposed techniques have been implemented on our virtualization layer called SPUMONE, and we measured the results showing that the proposed new techniques reduce the LHP problem without degrading the real-time responsiveness.",
    keywords = "Embedded Systems, Lock Holder Preemption, Muticore Processor, Virtualization",
    author = "Hitoshi Mitake and Lin, {Tsung Han} and Yuki Kinebuchi and Hiromasa Shimada and Tatsuo Nakajima",
    year = "2012",
    doi = "10.1109/RTCSA.2012.32",
    language = "English",
    pages = "270--279",
    booktitle = "Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA",

    }

    TY - GEN

    T1 - Using virtual CPU migration to solve the lock holder preemption problem in a multicore processor-based virtualization layer for embedded systems

    AU - Mitake, Hitoshi

    AU - Lin, Tsung Han

    AU - Kinebuchi, Yuki

    AU - Shimada, Hiromasa

    AU - Nakajima, Tatsuo

    PY - 2012

    Y1 - 2012

    N2 - When a real-time OS (RTOS) and a symmetric multiprocessing general purpose OS (SMP GPOS) are executed on the same multicore processor, there is a possibility to cause the lock holder preemption (LHP) problem, which is a well known problem of the sources of the performance degradation on an SMP GPOS. The problem occurs when a kernel mode thread holding a lock in a SMP GPOS is preempted by other OSes if these OSes share the same physical core. The existing solution does not take into account real-time responsiveness so it is not suitable to use in embedded systems. The paper proposes two new techniques to avoid the LHP problem for ensuring both the real-time responsiveness of real-time OS and the high throughput of SMP GPOS. The new proposed techniques have been implemented on our virtualization layer called SPUMONE, and we measured the results showing that the proposed new techniques reduce the LHP problem without degrading the real-time responsiveness.

    AB - When a real-time OS (RTOS) and a symmetric multiprocessing general purpose OS (SMP GPOS) are executed on the same multicore processor, there is a possibility to cause the lock holder preemption (LHP) problem, which is a well known problem of the sources of the performance degradation on an SMP GPOS. The problem occurs when a kernel mode thread holding a lock in a SMP GPOS is preempted by other OSes if these OSes share the same physical core. The existing solution does not take into account real-time responsiveness so it is not suitable to use in embedded systems. The paper proposes two new techniques to avoid the LHP problem for ensuring both the real-time responsiveness of real-time OS and the high throughput of SMP GPOS. The new proposed techniques have been implemented on our virtualization layer called SPUMONE, and we measured the results showing that the proposed new techniques reduce the LHP problem without degrading the real-time responsiveness.

    KW - Embedded Systems

    KW - Lock Holder Preemption

    KW - Muticore Processor

    KW - Virtualization

    UR - http://www.scopus.com/inward/record.url?scp=84869026261&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84869026261&partnerID=8YFLogxK

    U2 - 10.1109/RTCSA.2012.32

    DO - 10.1109/RTCSA.2012.32

    M3 - Conference contribution

    SP - 270

    EP - 279

    BT - Proceedings - 18th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, RTCSA 2012 - 2nd Workshop on Cyber-Physical Systems, Networks, and Applications, CPSNA

    ER -