Cheddar: an open-source real-time scheduling tool/simulator
In few words
Cheddar is a GPL real-time scheduling tool/simulator. Cheddar
allows you to model software architectures of real-time systems and to
check their schedulability or other performance criteria.
As many schedulability analysis tools, schedulability can be assessed by
scheduling simulations or feasibility tests.
With Cheddar, the modeling of the system to verify can be made with
or with the Cheddar architecture design language.
Some experiments also exist with MARTE UML.
Finally, Cheddar hosts a domain specific language
inside its scheduling simulator that allows users to design new task models
or scheduling policies.
Cheddar can help you : to perform schedulability analysis,
to be used for educational purpose or to
quickly prototype new real-time scheduling policies or task models.
Cheddar is developed and maintened by a team composed of the
Lab-STICC laboratory UMR CNRS 6285,
from the University of Brest
The Cheddar project was started in 2002 by Frank Singhoff,
University of Brest. The full list of the contributors
can be reach there.
Since 2008, Ellidiss Technologies
also contributes to the development of
Cheddar and provides industrial support of it by their commertial tool called
The use of AADLInspector is the best way to performa
schedulability analysis of AADL models with the Cheddar toolset.
Cheddar is composed of two independent parts : an editor to
model the real-time system to be analyzed, and a framework to perform analysis.
The editor allows you to describe systems composed of cores, processors, cache units,
which own software components (e.g. tasks, shared resources, buffers).
Task component may communicate by messages or with buffers.
Cheddar includes its own ADL, namely Cheddar ADL for such modeling work.
However, Cheddar is also able to handle AADL models with an embedded AADL V1.0 parser
but also with
a full compliant AADL V2 parser thanks to its commercial version embedded into AADLInspector.
The framework, called "Cheddar Kernel", can be called alone (e.g. by a shell script)
or embedded in a toolset.
The framework is embedded in specific tool sets such as
AADLInspector and STOOD (Ellidiss Tech),
seems to include Cheddar also.
The framework includes many feasibility tests and simulation tools.
The main analysis tools of Cheddar are the following:
- Analysis by scheduling simulations:
- With preemptive and non preemptive scheduling policies.
- With uniprocessor and multiprocessor scheduling policies/
- Available uniprocessor policies : Rate Monotonic, Deadline Monotonic,
Least Laxity First, Earliest Deadline
First, POSIX queueing policies (SCHED_OTHERS,
SCHED_FIFO and SCHED_RR), Maximum Urgency First, Round-Robin and
several time sharing scheduling policies.
- Available multiprocessor policies : global version of above uniprocessor
policies, Proportionate Fair, EDZL, LLREF and a prototype (not ready to be used) of the RUN policy.
- With instruction cache entities and the several CRPD computation models.
- With different types of tasks : aperiodic task, periodic task, sporadic task, task activated
according to a poisson process or a user-defined policy.
- With shared resources : with FIFO, PCP, PIP, IPCP synchronization protocols.
- Several hierarchical schedulers such as : ARINC 653 scheduling, sporadic server, polling server,
- With task jitters and offsets.
- With various task dependency constraints.
- Sustainable scheduling simulation with cache unit with a dedicated CRPD model.
- Extract information from scheduling simulations, such as:
- Worst/best/average task response times, task missed deadlines.
- Number of preemption, number of context switches.
- Worst/best/average shared resource blocking time.
- Deadlock and priority inversion.
- Worst/average buffer utilization factor, message worst/average waiting time.
- Apply schedulability/feasibility tests on tasks, buffers and shared resources :
- Compute worst case task response times on periodic tasks set by methods similar
to Joseph and Pandia WCRT (for any deadline/period relationships,
for preemptive and non preemptive fixed priority scheduling, for preemptive and non preemptive
EDF/LLF policies, with or without jitter).
- Several methods to compute worst case response times with linear and
tree transactions : Tindell,
Audsley, WCDOPS+Plus and WCDOPS+_NIMP methods.
- Apply processor utilization feasibility tests.
- Compute bound on buffer size (when buffers are shared by periodic tasks).
- Worst case shared resource blocking time.
- Memory footprint of software entities.
- Shared resources support (both scheduling simulation and
blocking time analysis). Supported protocols : FIFO, PIP, OPCP, IPCP.
- Various means to compute CRPD to be used for worst case response time computation, scheduling simulation or task priority assignment: CRPD computed according to UCB, ECB, UCB-Union, UCB-union-Multiset, ECB-Union-Multiset, combined Multiset.
- Queueing system theory models to be applied on real-time system analysis : classicals
such as M/M/1 or M/D/1, but also other modeling periodic behaviors such as P/P/1 and M/P/1 queueing models.
- Features to automatically generate Cheddar architecture models according to UUNIFAST or
- PAES implementation, both sequential and concurrent, with also an example of use to cluster
tasks of Cheddar ADL models. PAES is an heuristic that we use to explose software design space with
competing objective functions. With PAES, we can design complex specific partitioning algorithms.
- Tools to express and perform analysis with task dependencies:
- Model task transactions (linear or tree) and compute worst case response times.
- Compute Scheduling simulations according to task precedencies.
- Compute Tindell Holistic end to end response time.
- Apply Chetto and Blazewicz algorithms on task deadlines.
- Task and resource priority assignments:
- Classical Rate Monotonic, Deadline Monotonic, Audsley task priority assignments.
- Task priority assignment according to CRPD.
- Shared resource ceiling priority assignement (for PCP like policies).
- Features to allow users to define and handle their own policies:
- User-defined scheduling policies (based on pipeline models or automaton models).
- USer-defined task model policies, to express and handle specific task activation policies.
- User-defined analysis on scheduling simulation, to look for specific properties on
scheduling simulation result.
- Partitionning algorithms for periodic task set :
- Best fit policy
- General Task fit policy
- Fist fit policy
- Small fit policy
- Next fit policy
The picture below is a screenshot of Cheddar : on the top of the picture, scheduling is
drawn according to the scheduling policy of each core and processor. On the bottom,
some task information is computed and displayed (response times, missed deadlines,
processor utilization factor, ...).
One position currently available:
- PhD position: Safe and Secure Real-Time Architecture for Dynamic Positioning
of maritime platform. In the Cheddar team, Lab-STICC, MOCS team, CNRS, UBO, Brest, France.
- Available on autumn 2018 for three years
- Dynamic positioning (DP) is a computer-controlled system to automatically maintain a vessel¿s position and heading by using its own propellers and thrusters. Position reference sensors, combined with wind sensors, motion sensors and gyrocompasses, provide information to the computer pertaining to the vessel¿s position and the magnitude and direction of environmental forces affecting its position. Due to the high costs for operation and maintenance in the offshore industry, many utility companies and marine owners are focusing on costs reduction for operation and maintenance.
To face reduce cost maintenance, the DP systems design require to work on architecture models and to proceed to the verification activities at the earliest stages of the development life-cycle. We propose in this PhD to focus on the criticality of a DP system and to investigate in the mitigation of the errors, while keeping real-time schedule of the system.
In this thesis, we propose to handle these issues through:
The validation of the proposals will be driven by failure scenarios provided by the industrial context defined by the D-ICE ENGINEERING and the Ellidiss Technologies companies. This project is also part of the joint work on safety/security models between the university of Sao Paulo/Brazil (USP) and the Lab-STICC/MOCS.
- a model-based analysis of the system based on the safety/security failures of Dynamic Positioning system in order to evaluate its criticality level
- optimization schemes of the Dynamic Positioning System architecture of the system in order to achieve a certain criticality level under performance constraints. For instance, hardware redundancy patterns can be applied on specific sub-system or component for this goal
- an analysis of the performance of the safe and secure designs proposed during the thesis, i.e. to verify that any functions of the systems are able to meet its temporal requirements.
- Contacts to apply:
Catherine Dezan (Associate Professor, Lab-STICC, UBO, Brest, Catherine.Dezan@univ-brest.fr tel:+33298016973),
Frank Singhoff (Professor, Lab-STICC, UBO, Brest, Frank.Singhoff@univ-brest.fr tel:+33298016211).
- To apply, please provide:
Your marks and rank for the Master degree
A motivation Letter,
Recommendations letter from teachers or internship advisor.
- Practical info:
PhD funded by a CIFRE contract between D-ICE engineering and Lab-STICC.
PhD Location: Brest (Lab-STICC/UBO) and Nantes (D-ICE engineering). Occasional visits to the different partners, both industrial (Ellidiss technologies) and academics (USP, Brazil)
- Deadline for the application: 10 july 2018
- 12/31/2017 : a new tutorial about Cheddar is available. this tutorial
shows how to use AADLInspector, the commercial version of Cheddar with AADL.
The tutorial is in French ... a english translation will come for the end of
- 11/04/2017 : the call for papers of the 2018 Ada-Europe conference is out.
here the call for papers. Feel free to contribute !
- 10/10/2017 : a new Cheddar's binary release is distributed (Release 3.1)
- 11/02/2015 : a new Cheddar's binary release is distributed (Release 3.0)
- 08/10/2011 : Announce of Ellidiss Technologies (Pierre Dissaux).
Ellidiss announces the availability of their new product: AADL Inspector.
AADL Inspector is a light-weight standalone analysis tool for textual AADL specifications
It includes a set of static rules checkers, Cheddar for schedulability analysis and Marzhin
for dynamic simulation.
Additional plug-ins can easily be added to fit corporate or project specific analysis requirements.
Please contact Ellidiss' technical support at firstname.lastname@example.org for further details about these
AADL Inspector is available for download at: http://www.ellidiss.com/downloads.asp
and comes with a temporary evaluation license.
- 07/01/2008 : a new Cheddar's release is distributed (Release 2.1)
- 02/12/2007 : a new Cheddar's release is distributed (Release 2.0)
- 01/12/2007 : create a SVN repository for Cheddar (http://beru.univ-brest.fr/svn/CHEDDAR)
- 12/07/2005 : provides solaris binaries
- 11/17/2005 : fix the install Makefile and the INSTALL file to the
linux distribution. The current linux archive contains these updated
- 11/11/2005 : the gtkada compiled libraries are now include in the linux binaries distribution.
- 11/01/2005 : annual Cheddar's release. Current release is now
- 09/11/2004 : new patch on 1.3 (see Last patch section). Current release is now
- 09/08/2004 : a new Cheddar's release is distributed (1.3p3)
- 09/25/2003 : new version of the User's guide.
- 09/09/2003 : new patch on 1.3 (see Last patch section). Current release is now
- 08/28/2003 : new patch on 1.3 (see Last patch section). Current release is now
- 08/26/2003 : a new Cheddar's release is distributed (1.3p0)
- 07/03/2003 : a remote cvs access is now available. If you plan to write
code with Cheddar, contact us to get an account on this cvs repository.
- 05/31/2003 : create a Cheddar users and developpers mailing list and
provide dayly built cvs snapshot.
- 11/21/2002 : release of a new patch, see FIXED_BUGS.txt file for list of fixed bugs.
Current version is now Cheddar-1.2p1.
- 10/21/2002 : improve installation Makefile and online User's guide.
Download Cheddar binaries (current version is Cheddar-3.1, release date :
the 10th of October 2017) :
Cheddar is a free software under the GNU General Public License.
You can get
the current stable Cheddar source code
Previous releases can be found
See the ChangesLog.pdf file to have history of modifications.
The file REQUESTED_FEATURES.pdf contains the
new features required by users and that we plan to implement in the next releases.
You can also get access
to the SVN repository of Cheddar.
To compile Cheddar on any computer, you can also use VirtualBox. You must download
in this case.
For compilation procedures with VirtualBox, please read
For compilation procedures, please read
Cheddar is written in Ada, with GNAT and GtkAda Adacore products.
Cheddar is known to run on Linux and
windows boxes, but should run on any Adacore supported platforms
see AdaCore web site for details).
For installation procedures, please read
There is no binary patch currently distributed as all fixed bug are
integrated in the current binary release.
file to have the detailed list of fixed bugs.
The list of
the bugs to be fixed can be read there (file BUGS_TO_FIX.pdf).
Current developments on Cheddar are about the following topics:
- Cache analysis support.
- Global multiprocessor scheduling.
- NoC support.
- PAES implementation.
Cheddar users and developers share information with
a mailing list hosted by the University of Brest.
To post to the list, send e-mail to email@example.com.
Warning : this is a private mailing-list (i.e. to post on this mailing-list, you have to subscribe to it).
To subscribe to the list : send a request to firstname.lastname@example.org
with the following text in the body of your e-mail:
SUBSCRIBE cheddar email@example.com
where firstname.lastname@example.org is your email address.
To unsubscribe to the list : send a request to email@example.com
with the following text in the body :
- The first publication about Cheddar :
Cheddar : a Flexible Real Time Scheduling Framework.
F. Singhoff, J. Legrand, L. Nana, L. Marcé.
ACM SIGAda Ada Letters,
volume 24, number 4, pages 1-8.
Edited by ACM Press, New York, USA.
- A tutorial about Cheddar, both in
Frank Singhoff. Lab-STICC technical report. September 2015.
A tutorial about Cheddar and AADL :
which shows how to use AADLInspector, the commercial version of Cheddar with AADL.
The tutorial exists
Cheddar Architecture Description Language reference guide.
C. Fotsing, F. Singhoff, A. Plantec, V. Gaudel,
S. Rubini, S. Li, H. N. Tran, L. Lemarchand, P. Dissaux, J Legrand.
January 2013. Lab-STICC technical.
A FAQ about several issues you may have when using Cheddar
- A text book on Ada and real-time scheduling analysis published
by Cambridge University press : Building Parallel,
and Real-Time Applications with Ada. J. W. McCormick, F. Singhoff, J. Hugues.
Cambridge University Press, UK, 365 pages, April 2011.
ISBN-13: 9780521197168. This book has several exercises on real-time
scheduling analysis with solutions computed by Cheddar. Exercises solutions of this
book are freely available from the Cambridge University Press website.
About how to use Cheddar with AADL :
Scheduling and Memory requirement analysis with AADL.
F. Singhoff, J. Legrand, L. Nana, and L. Marcé.
ACM SIGAda Ada Letters, volume 25, number 4, pages 1-10.
Edited by ACM Press, New York, USA,
You may also be interested by the list of AADL properties to use with Cheddar :
The Cheddar AADL Property sets (Release 2.x).
LISyC technical report number singhoff-03-07.
Cheddar Release 3.x User's Guide.
Christian Fotsing, Frank Singhoff. Lab-STICC technical report. July 2014.
- All the publications related to Cheddar :
can be downloaded here.
We distribute Cheddar with
a set of AADL and XML examples,
section also contains a set of contributions from Cheddar's users :
- The educational section: contains a set of real-time
scheduling courses built with the help of Cheddar.
- The examples of use section:
contains reports on performance
analysis realized with Cheddar and example of tool-chains developed by Cheddar's
Cheddar is developed and maintened by a team composed of members from the
Lab-STICC laboratory UMR CNRS 6285/Université de Bretagne
Occidentale and Ellidiss Technologies.
The current members of this project are
Pierre Dissaux (Ellidiss Technologies),
Jérôme Legrand (Ellidiss Technologies),
Alain Plantec (Lab-STICC/Université de Bretagne Occidentale),
Stéphane Rubini (Lab-STICC/Université de Bretagne Occidentale),
Jalil Boukhobza (Lab-STICC/Université de Bretagne Occidentale),
Laurent Lemarchand (Lab-STICC/Université de Bretagne Occidentale)
Nam Tran Hai (Lab-STICC/Université de Bretagne Occidentale)
and Frank Singhoff (Lab-STICC/Université de Bretagne Occidentale).
Phd Students working on Cheddar:
Ramha Bouaziz, Mourad Dridi and Blandine Djika.
Former Phd Students :
Hai Nam Tran,
The project has been funded by Ellidiss Technologies,
Conseil régional de Bretagne, UBO, Brest Métrople, BPI France,
Conseil département du Finistère, Thales TCS and EGIDE/Campus France PESSOA number 27380SA and 37932TF.
Researches on Cheddar are also performed in collaboration with the following partners:
The following people have also contributed to the project: see
Thanks to people who sent us bug reports and/or advices :
F. Rodrigues de la Rocha,
Su Young Lee,
and M. Zanconi, ...
To do a bug report, to find compilation instructions and developer documentations,
a work space is available for Cheddar software developers
on this wiki.
You can also report bugs and new tested platforms to
firstname.lastname@example.org (Warning : this is a private mailing-list. To post, you have
to subscribe to the mailing-list first).
Contact : Frank Singhoff mailto:email@example.com
Last update : The 31th of December, 2017