• DocumentCode
    3082660
  • Title

    A Fully Preemptive Multiprocessor Semaphore Protocol for Latency-Sensitive Real-Time Applications

  • Author

    Brandenburg, Bjorn B.

  • Author_Institution
    Max Planck Inst. for Software Syst. (MPI-SWS), Saarbrucken, Germany
  • fYear
    2013
  • fDate
    9-12 July 2013
  • Firstpage
    292
  • Lastpage
    302
  • Abstract
    Independence preservation, a property in real-time locking protocols that isolates latency-sensitive tasks from delays due to unrelated critical sections, is identified, formalized, and studied in detail. The key to independence preservation is to ensure that tasks remain fully preemptive at all times. For example, on uniprocessors, the classic priority inheritance protocol is independence-preserving. It is shown that, on multiprocessors, independence preservation is impossible if job migrations are disallowed. The O(m) independence-preserving protocol (OMIP), a new, asymptotically optimal binary sempahore protocol based on migratory priority inheritance, is proposed and analyzed. The OMIP is the first independence-preserving, real-time, suspension-based locking protocol for clustered job-level fixed-priority scheduling. It is shown to benefit latency-sensitive workloads, both analytically by means of schedulability experiments, and empirically using response-time measurements in LITMUSRT.
  • Keywords
    multiprocessing systems; processor scheduling; protocols; LITMUS; OMIP; asymptotic optimal binary sempahore protocol; clustered job-level fixed-priority scheduling; fully preemptive multiprocessor semaphore protocol; independence preservation; independence-preserving locking protocol; latency-sensitive real-time applications; latency-sensitive tasks; migratory priority inheritance; priority inheritance protocol; real-time locking protocol; real-time locking protocols; response-time measurements; suspension-based locking protocol; Boosting; Delays; Job shop scheduling; Processor scheduling; Protocols; Real-time systems; Spinning; blocking optimality; locking; low-latency locking; multiprocessor; priority inversion; real-time system; suspension-oblivious schedulability analysis; synchronization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Real-Time Systems (ECRTS), 2013 25th Euromicro Conference on
  • Conference_Location
    Paris
  • Type

    conf

  • DOI
    10.1109/ECRTS.2013.38
  • Filename
    6602109