+
Skip to content

FEO: Move S-CORE v1.0 features to a separate section of the feature description #1698

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 5, 2025
Merged

FEO: Move S-CORE v1.0 features to a separate section of the feature description #1698

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
160 changes: 100 additions & 60 deletions docs/features/frameworks/feo/index.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,7 @@ Executor and Agents
* The coordinating entity in the primary process is the "executor"
* The executor coordinates the invocation of the activities in the
order as described above
* As a central entity the executor is able to trace, record or monitor the
* As a central entity, the executor is able to trace and monitor the
system behavior as sequence of activity invocations (see below)
* The actual activity invocation is done by an "agent"
* The agent exists in each process belonging to an application
Expand All @@ -351,9 +351,82 @@ Executor and Agents
executes them in its local process on behalf of the executor


External state
Tracing
=======

* The framework can make use of the tracing API (feo::tracing) to trace
the program flow, mainly for debugging purposes.
* The tracing events generated by the tracing API can be recorded for later
inspection e.g. using a UI like Google Perfetto or Eclipse TraceCompass.


Performance
===========

The framework is designed to ensure deterministic execution order and
timing of activities, supporting safety-critical applications
in the automotive domain. In this domain the footprint of the framework is crucial especially
w.r.t impact of computation load and latency.


.. |example_task_chain| image:: _assets/example_task_chain.png

.. |example_task_chain_5_threads| image:: _assets/example_task_chain_5_threads.png

.. |example_task_chain_3_threads_optimized| image:: _assets/example_task_chain_3_threads_optimized.png

.. |example_task_chain_3_threads_dynamic| image:: _assets/example_task_chain_3_threads_dynamic.png


Error Handling
==============

Possible error cases during the different FEO life cycle states shall be handled as follows. For now, the
descriptions are focussed on the intended implementation for S-CORE v0.5. Potential adaptations for
S-CORE v1.0 have been noted down in the next Section.

* Independent of state
- If the primary process dies, the external lifecycle management shall kill all dependent processes.
- If a secondary process dies, the lifecycle management shall send a termination signal to the primary process.
The primary process shall call the shutdown function of all remaining activities in arbitrary sequence and
terminate itself.

* State: Lifecycle Manager creates all processes (primary & secondaries)
- If not all secondaries connect to the primary in time, the primary will terminate itself.
The startup functions shall not be triggered.

* State: Lifecycle Manager has created all processes (primary & secondaries), all secondaries have connected to the primary
- If an error occurs during the execution of a startup function, the primary process shall abort calling startup functions
and terminate itself. For all of the activities whose startup functions have already been called successfully,
the corresponding shutdown functions shall be executed in arbitrary sequence.
- During initialization (i.e. in the startup function of an activity), activities shall check for resource allocation
and report an error to the executor in case of failure.
- If a timeout occurs during startup, stepping or shutdown of an activity, the primary process shall shutdown
all successfully started activities in arbitrary sequence and terminate itself.
- If not all activities reach their initialized state within a certain period of time (startup timeout),
the primary process shall shutdown all successfully started activities in arbitrary sequence and terminate itself.

* State: Lifecycle Manager has created all processes (primary & secondaries), all secondaries have connected to the primary, all activities have been started up successfully
- If an activity fails in the step function, the primary process shall call shutdown for all activities in
arbitrary sequence and terminate itself.
- If activities do not meet their intermediate (time/memory/cpu-) budgets the issue shall be detected and handled
outside of FEO. (Resource supervision and quotas will be defined in a separate feature request, if needed.)

* State: Shutdown of activities
- If an activity fails in the shutdown function, the primary process shall shutdown all remaining activities
and terminate itself.


Extended features for S-CORE v1.0
=================================

The following features will not be implemented as part of S-CORE v0.5, but have been noted down as potential extensions
for v1.0. They shall be considered as drafts only.


External state
''''''''''''''

* Depending on the reprocessing scenario (see below) it might be necessary
to put the activities into a well defined state. This can either be done
by providing all the input to the activities which they need to get
Expand All @@ -369,9 +442,12 @@ External state
then potentially manipulate the state based on their inputs and then
store it back for the next task chain invocation


Recording
=========
'''''''''

* As a central entity, the executor is able to record the system behavior as sequence
of activity invocations.
* The framework can record all messages going over its communication topics
* For each message the recording includes:

Expand All @@ -394,7 +470,7 @@ Recording


Reprocessing
============
''''''''''''

* There are multiple possible reprocessing scenarios, for example:

Expand All @@ -417,39 +493,8 @@ Reprocessing
- Providing time via its time API as recorded


Tracing
=======

* The framework can make use of the tracing API (feo::tracing) to trace
the program flow, mainly for debugging purposes.
* The tracing events generated by the tracing API can be recorded for later
inspection e.g. using a UI like Google Perfetto or Eclipse TraceCompass.


Performance
===========

The framework is designed to ensure deterministic execution order and
timing of activities, supporting safety-critical applications
in the automotive domain. In this domain the footprint of the framework is crucial especially
w.r.t impact of computation load and latency.


.. |example_task_chain| image:: _assets/example_task_chain.png

.. |example_task_chain_5_threads| image:: _assets/example_task_chain_5_threads.png

.. |example_task_chain_3_threads_optimized| image:: _assets/example_task_chain_3_threads_optimized.png

.. |example_task_chain_3_threads_dynamic| image:: _assets/example_task_chain_3_threads_dynamic.png


Error Handling for S-CORE v0.5
==============================

Possible error cases during the different FEO life cycle states shall be handled as follows. For now, the
descriptions are focussed on the intended implementation for S-CORE v0.5. Potential adaptations for
S-CORE v1.0 have been noted down, but shall be considered as drafts only.
Extended Error Handling
'''''''''''''''''''''''

* Independent of state
- If the primary process dies, the external lifecycle management shall kill all dependent processes.
Expand All @@ -458,36 +503,31 @@ S-CORE v1.0 have been noted down, but shall be considered as drafts only.
terminate itself.

* State: Lifecycle Manager creates all processes (primary & secondaries)
- If not all secondaries connect to the primary in time,
- S-CORE v0.5: the primary will terminate itself. The startup functions shall not be triggered.
- S-CORE v1.0: the primary will not terminate, but report an error to the lifecycle/health management.
The startup functions shall not be triggered.
- If not all secondaries connect to the primary in time, the primary will not terminate, but report an error to the
lifecycle/health management. The startup functions shall not be triggered.

* State: Lifecycle Manager has created all processes (primary & secondaries), all secondaries have connected to the primary
- If an error occurs during the execution of a startup function,
- S-CORE v0.5: the primary process shall abort calling startup functions
and terminate itself. For all of the activities whose startup functions have already been called successfully,
the corresponding shutdown functions shall be executed in arbitrary sequence.
- S-CORE v1.0: in addition, the primary process shall report the issue to health management.
- If an error occurs during the execution of a startup function, the primary process shall abort calling startup
functions and terminate itself. For all of the activities whose startup functions have already been called successfully,
the corresponding shutdown functions shall be executed in arbitrary sequence.
In addition, the primary process shall report the issue to health management.
- During initialization (i.e. in the startup function of an activity), activities shall check for resource allocation
and report an error to the executor in case of failure.
- If a timeout occurs during startup, stepping or shutdown of an activity,
- S-CORE v0.5: the primary process shall shutdown all successfully started activities in arbitrary sequence
and terminate itself.
- S-CORE v1.0: In addition, the primary process shall report the issue to health management.
- If not all activities reach their initialized state within a certain period of time (startup timeout),
- S-CORE v0.5: the primary process shall shutdown all successfully
started activities in arbitrary sequence and terminate itself.
- S-CORE v1.0: In addition, the primary process shall report the issue to health management.
- If a timeout occurs during startup, stepping or shutdown of an activity, the primary process shall shutdown all
successfully started activities in arbitrary sequence and terminate itself.
In addition, the primary process shall report the issue to health management.
- If not all activities reach their initialized state within a certain period of time (startup timeout), the
primary process shall shutdown all successfully started activities in arbitrary sequence and terminate itself.
In addition, the primary process shall report the issue to health management.

* State: Lifecycle Manager has created all processes (primary & secondaries), all secondaries have connected to the primary, all activities have been started up successfully
- If an activity fails in the step function,
- S-CORE v0.5: the primary process shall call shutdown for all activities in arbitrary sequence and terminate itself.
- S-CORE v1.0: In addition, a logical waypoint error shall be reported to health management.
- If an activity fails in the step function, the primary process shall call shutdown for all activities in
arbitrary sequence and terminate itself.
In addition, a logical waypoint error shall be reported to health management.
- If activities do not meet their intermediate (time/memory/cpu-) budgets the issue shall be detected and handled
outside of FEO. (Resource supervision and quotas will be defined in a separate feature request, if needed.)

* State: Shutdown of activities
- If an activity fails in the shutdown function,
- S-CORE v0.5: the primary process shall shutdown all remaining activities and terminate itself.
- S-CORE v1.0: In addition, a logical waypoint error shall be reported to health management.
- If an activity fails in the shutdown function, the primary process shall shutdown all remaining activities and
terminate itself.
In addition, a logical waypoint error shall be reported to health management.
点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载