Low-overhead Online Assessment of Timely Progress as a System Commodity

Weifan Chen; Ivan Izhbirdeev; Denis Hoornaert; Shahin Roozkhosh; Patrick Carpanedo; Sanskriti Sharma; Renato Mancuso

doi:10.4230/LIPIcs.ECRTS.2023.11

Publications Workload Profiling

Low-overhead Online Assessment of Timely Progress as a System Commodity

Weifan Chen, Ivan Izhbirdeev, Denis Hoornaert, Shahin Roozkhosh, Patrick Carpanedo, Sanskriti Sharma, Renato Mancuso

35th Euromicro Conference on Real-Time Systems (ECRTS 2023), July 2023, Vienna, Austria

Outstanding Paper AwardBest Presentation Award

Read the PDF Publisher page (DOI) Code and artifacts Cite

Figure 1 High-level overview of the proposed system design. The CFG of the target application is analyzed to produce a Timed Milestone Graph (TMG). Together with the online data produced by the Trace Unit (TU), a progress tracker assesses timely progress and reports to the OS. The OS can take corrective measures accordingly.

Abstract

The correctness of safety-critical systems depends on both their logical and temporal behavior. Control-flow integrity (CFI) is a well-established and understood technique to safeguard the logical flow of safety-critical applications. But unfortunately, no established methodologies exist for the complementary problem of detecting violations of control flow timeliness. Worse yet, the latter dimension, which we term Timely Progress Integrity (TPI), is increasingly more jeopardized as the complexity of our embedded systems continues to soar. As key resources of the memory hierarchy become shared by several CPUs and accelerators, they become hard-to-analyze performance bottlenecks. And the precise interplay between software and hardware components becomes hard to predict and reason about. How to restore control over timely progress integrity? We postulate that the first stepping stone toward TPI is to develop methodologies for Timely Progress Assessment (TPA). TPA refers to the ability of a system to live-monitor the positive/negative slack—with respect to a known reference—at key milestones throughout an application’s lifespan. In this paper, we propose one such methodology that goes under the name of Milestone-Based Timely Progress Assessment or MB-TPA, for short. Among the key design principles of MB-TPA is the ability to operate on black-box binary executables with near-zero time overhead and implementable on commercial platforms. To prove its feasibility and effectiveness, we propose and evaluate a full-stack implementation called Timely Progress Assessment with 0 Overhead (TPAw0v). We demonstrate its capability in providing live TPA for complex vision applications while introducing less than 0.6% time overhead for applications under test. Finally, we demonstrate one use case where TPA information is used to restore TPI in the presence of temporal interference over shared memory resources.

Code and hardware artifacts

RT-Bench Software Used or cited in this paper
An extensible framework that turns existing benchmarks into periodic real-time workloads.

Cite this paper

@inproceedings{LiveTPA_ECRTS23,
  title     = {{Low-overhead Online Assessment of Timely Progress as a System Commodity}},
  author    = {Chen, Weifan and Izhbirdeev, Ivan and Hoornaert, Denis and Roozkhosh, Shahin and Carpanedo, Patrick and Sharma, Sanskriti and Mancuso, Renato},
  booktitle = {35th Euromicro Conference on Real-Time Systems (ECRTS 2023)},
  year      = 2023,
  month     = jul,
  volume    = {262},
  pages     = {13:1--13:26},
  publisher = {Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik},
  address   = {Vienna, Austria},
  doi       = {10.4230/LIPIcs.ECRTS.2023.11},
  url       = {https://doi.org/10.4230/LIPIcs.ECRTS.2023.11},
  note      = {Outstanding Paper Award, Best Presentation Award}
}

Download .bib

TY - CONF
AU - Chen, Weifan
AU - Izhbirdeev, Ivan
AU - Hoornaert, Denis
AU - Roozkhosh, Shahin
AU - Carpanedo, Patrick
AU - Sharma, Sanskriti
AU - Mancuso, Renato
TI - Low-overhead Online Assessment of Timely Progress as a System Commodity
T2 - 35th Euromicro Conference on Real-Time Systems (ECRTS 2023)
PY - 2023
DA - 2023/07//
VL - 262
PB - Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik
CY - Vienna, Austria
SP - 13:1
EP - 13:26
DO - 10.4230/LIPIcs.ECRTS.2023.11
UR - https://doi.org/10.4230/LIPIcs.ECRTS.2023.11
AB - The correctness of safety-critical systems depends on both their logical and temporal behavior. Control-flow integrity (CFI) is a well-established and understood technique to safeguard the logical flow of safety-critical applications. But unfortunately, no established methodologies exist for the complementary problem of detecting violations of control flow timeliness. Worse yet, the latter dimension, which we term Timely Progress Integrity (TPI), is increasingly more jeopardized as the complexity of our embedded systems continues to soar. As key resources of the memory hierarchy become shared by several CPUs and accelerators, they become hard-to-analyze performance bottlenecks. And the precise interplay between software and hardware components becomes hard to predict and reason about. How to restore control over timely progress integrity? We postulate that the first stepping stone toward TPI is to develop methodologies for Timely Progress Assessment (TPA). TPA refers to the ability of a system to live-monitor the positive/negative slack—with respect to a known reference—at key milestones throughout an application’s lifespan. In this paper, we propose one such methodology that goes under the name of Milestone-Based Timely Progress Assessment or MB-TPA, for short. Among the key design principles of MB-TPA is the ability to operate on black-box binary executables with near-zero time overhead and implementable on commercial platforms. To prove its feasibility and effectiveness, we propose and evaluate a full-stack implementation called Timely Progress Assessment with 0 Overhead (TPAw0v). We demonstrate its capability in providing live TPA for complex vision applications while introducing less than 0.6% time overhead for applications under test. Finally, we demonstrate one use case where TPA information is used to restore TPI in the presence of temporal interference over shared memory resources.
ER -

Download .ris

%0 Conference Paper
%A Chen, Weifan
%A Izhbirdeev, Ivan
%A Hoornaert, Denis
%A Roozkhosh, Shahin
%A Carpanedo, Patrick
%A Sharma, Sanskriti
%A Mancuso, Renato
%T Low-overhead Online Assessment of Timely Progress as a System Commodity
%B 35th Euromicro Conference on Real-Time Systems (ECRTS 2023)
%D 2023
%V 262
%P 13:1-13:26
%I Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik
%C Vienna, Austria
%R 10.4230/LIPIcs.ECRTS.2023.11
%U https://doi.org/10.4230/LIPIcs.ECRTS.2023.11
%X The correctness of safety-critical systems depends on both their logical and temporal behavior. Control-flow integrity (CFI) is a well-established and understood technique to safeguard the logical flow of safety-critical applications. But unfortunately, no established methodologies exist for the complementary problem of detecting violations of control flow timeliness. Worse yet, the latter dimension, which we term Timely Progress Integrity (TPI), is increasingly more jeopardized as the complexity of our embedded systems continues to soar. As key resources of the memory hierarchy become shared by several CPUs and accelerators, they become hard-to-analyze performance bottlenecks. And the precise interplay between software and hardware components becomes hard to predict and reason about. How to restore control over timely progress integrity? We postulate that the first stepping stone toward TPI is to develop methodologies for Timely Progress Assessment (TPA). TPA refers to the ability of a system to live-monitor the positive/negative slack—with respect to a known reference—at key milestones throughout an application’s lifespan. In this paper, we propose one such methodology that goes under the name of Milestone-Based Timely Progress Assessment or MB-TPA, for short. Among the key design principles of MB-TPA is the ability to operate on black-box binary executables with near-zero time overhead and implementable on commercial platforms. To prove its feasibility and effectiveness, we propose and evaluate a full-stack implementation called Timely Progress Assessment with 0 Overhead (TPAw0v). We demonstrate its capability in providing live TPA for complex vision applications while introducing less than 0.6% time overhead for applications under test. Finally, we demonstrate one use case where TPA information is used to restore TPI in the presence of temporal interference over shared memory resources.

Download .enw

[
    {
        "id": "LiveTPA_ECRTS23",
        "type": "paper-conference",
        "title": "Low-overhead Online Assessment of Timely Progress as a System Commodity",
        "author": [
            {
                "family": "Chen",
                "given": "Weifan"
            },
            {
                "family": "Izhbirdeev",
                "given": "Ivan"
            },
            {
                "family": "Hoornaert",
                "given": "Denis"
            },
            {
                "family": "Roozkhosh",
                "given": "Shahin"
            },
            {
                "family": "Carpanedo",
                "given": "Patrick"
            },
            {
                "family": "Sharma",
                "given": "Sanskriti"
            },
            {
                "family": "Mancuso",
                "given": "Renato"
            }
        ],
        "container-title": "35th Euromicro Conference on Real-Time Systems (ECRTS 2023)",
        "issued": {
            "date-parts": [
                [
                    2023,
                    7
                ]
            ]
        },
        "volume": "262",
        "page": "13:1-13:26",
        "publisher": "Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik",
        "publisher-place": "Vienna, Austria",
        "DOI": "10.4230/LIPIcs.ECRTS.2023.11",
        "abstract": "The correctness of safety-critical systems depends on both their logical and temporal behavior. Control-flow integrity (CFI) is a well-established and understood technique to safeguard the logical flow of safety-critical applications. But unfortunately, no established methodologies exist for the complementary problem of detecting violations of control flow timeliness. Worse yet, the latter dimension, which we term Timely Progress Integrity (TPI), is increasingly more jeopardized as the complexity of our embedded systems continues to soar. As key resources of the memory hierarchy become shared by several CPUs and accelerators, they become hard-to-analyze performance bottlenecks. And the precise interplay between software and hardware components becomes hard to predict and reason about. How to restore control over timely progress integrity? We postulate that the first stepping stone toward TPI is to develop methodologies for Timely Progress Assessment (TPA). TPA refers to the ability of a system to live-monitor the positive/negative slack—with respect to a known reference—at key milestones throughout an application’s lifespan. In this paper, we propose one such methodology that goes under the name of Milestone-Based Timely Progress Assessment or MB-TPA, for short. Among the key design principles of MB-TPA is the ability to operate on black-box binary executables with near-zero time overhead and implementable on commercial platforms. To prove its feasibility and effectiveness, we propose and evaluate a full-stack implementation called Timely Progress Assessment with 0 Overhead (TPAw0v). We demonstrate its capability in providing live TPA for complex vision applications while introducing less than 0.6% time overhead for applications under test. Finally, we demonstrate one use case where TPA information is used to restore TPI in the presence of temporal interference over shared memory resources."
    }
]

Download .json

W. Chen, I. Izhbirdeev, D. Hoornaert, S. Roozkhosh, P. Carpanedo, S. Sharma, and R. Mancuso, “Low-overhead Online Assessment of Timely Progress as a System Commodity,” in 35th Euromicro Conference on Real-Time Systems (ECRTS 2023), vol. 262, pp. 13:1–13:26, Jul. 2023, doi: 10.4230/LIPIcs.ECRTS.2023.11.

Download .txt

Chen, W., Izhbirdeev, I., Hoornaert, D., Roozkhosh, S., Carpanedo, P., Sharma, S., & Mancuso, R. (2023). Low-overhead Online Assessment of Timely Progress as a System Commodity. In 35th Euromicro Conference on Real-Time Systems (ECRTS 2023) (pp. 13:1–13:26). Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik. https://doi.org/10.4230/LIPIcs.ECRTS.2023.11

Download .txt