Simgrid

The "This one is 4 you" release. At last, this is the 4.0 release of SimGrid.

This is an important milestone for the SimGrid project, the culmination of
almost ten years of efforts, as described in this article: https://hal.science/hal-04909441

At the same time, this is also an incremental improvement over 3.36 as shown in the following changelog. We still have many
improvement ideas for the future and plan to keep the same release pace and plan: about 2 releases per year, and upgrade paths
that ensure your code will still compile, with warnings, for at least 3 releases. Please refer to the Release Notes in the
documentation for some of the envisioned future improvements.

SMPI:
- Allow automatic benchmarking with --cfg=smpi/host-speed:auto

S4U:
- Reduce the amount of static functions: deprecate Actor::create() functions in favor of Engine::add_actor()
- Introduce Actor::get_instance() so that you don't have to call the static Engine::get_instance() method
- Allow to turn disks on and off (it was limited to the kernel side until now). Tested in the activity livecycle tests.
- Turning off a host now turns off the disks attached to this host. Conversely, turning the host back on brings back
the disks online. Tested in teshsuite/src/host-on-off-disks.
- Deprecate Host::set_factor_cb for Host::set_cpu_factor_cb to give the concerned host as a callback parameter.

sthread:
- Implement pthread_exit() and pthread_cond_timedwait()
- Further restrict portability: Linux only, and now also GLIBC only.

Model-checker:
- Dependency on libevent was removed.
- Greatly improve the performances, and fix some bugs.

Platform API:
- The root netzone of every platform uses the full routing. It's created by default.
The ability to change the root zone does not increase the expressivity in any way, but it greatly complicates our code.
- Deprecate the create_*_zone() functions, add NetZone::add_netzone_*()
Methods are better than functions.
- Deprecate NetZone::set_parent(): it's now useless with the new API.
- Revamp the creation of Cluster NetZones (Fat-Tree, Torus, and Dragonfly) to explicitely pass all the parameters defining a network topology as arguments and to define leafs, loopbacks, and limiter links with callbacks.

Python:
- Add many missing bindings [Sergey Teryoshkin].
- Add MPI bindings [Jean-Noël Quintin].

Java:
- Reintroduce the bindings, on top of S4U.

Plugins:
- Chaos Monkey: Allow to restart the actors by pid at a given time.
- Chaos Monkey: Allow to restart disks.

C API:
- Deprecate some functions (we want to kill xbt_dict and xbt_dynar in the
future)
- sg_actor_get_properties() -> sg_actor_get_property_names()
- sg_host_get_properties() -> sg_host_get_property_names()
- sg_zone_get_properties() -> sg_zone_get_property_names()
- sg_zone_get_sons() -> sg_zone_get_childs()
- sg_zone_get_hosts() -> sg_zone_get_all_hosts()
- sg_actor_attach() now takes only 2 parameters (the props are removed)
- Introduce sg_zone_get_property_names()

Dependencies:
- If the compiler supports C++23, use the standard stacktraces instead of boost ones.

----------------------------------------------------------------------------

The Anne of Brittany release (she became a Duchess 536 years ago).

Intrusive changes:
- Timeout on communications do not interrupt the comm anymore.
This is for symmetry with the other activity kinds, which already had this behavior enabling polling activities.
The previous behavior is still available with Activity::wait_for_or_cancel()
- Remove the include/xbt/promise.hpp header, that was kinda internal.
- Remove the ill-inspired communication matching mechanism. If you need it, talk to us (and use the kernel version).

S4U:
- Starting Activities in a detached (a.k.a. fire-and-forget) mode is not limited to Comm and Mess anymore. Exec and
I/O can also benefit from that feature. This allows users to create a sequence of interdependent activities
(informally called a 'compound' activity and only wait for the completion of the last activity of the sequence.
- Add Engine::get_hosts_from_MPI_hostfile(const std::string& hostfile) to select a list of hosts within a loaded
platform from a text file. Each line of this text file comprises the name of a host (e.g., node-0) which can be
followed by a number of repetitions (e.g., node-0:2 will add node-0 twice to the created list of hosts). This
allows users to specify that more than one actor has to be started on a given host.
- Add Engine::get_all_netzones() to build a list of all the NetZones (including the root Zone) declared.
- Add Engine::papi_{start,stop,get_num_counters,get_counters}() to interact with PAPI.
- Enable to track task instances at runtime, and add Task::on_this_instance_completion_cb()
- Add SMPI_executable_start() to start a SMPI external binary instead of providing the code inline.
- C API: Add sg_actor_start_voidp() to start actors using a pthread-like prototype, taking a void* as parameter.

Kernel:
- Bugfix: non-recursive locks must deadlock when relocking by same actor.
- Make NetZoneImpl extendable.
- Implement asynchronous condvar acquisition. Not visible from the s4u API, but needed for the model-checker.
- (internals) cleanup the implementation of timeouts for activities, and other bits of activities.

Models:
- Introduce a 'raw' network model with overly simplistic equations, for non-TCP settings.

Model-checker:
- Enable the verification of SimGrid programs written in Python.
- Enable the verification of condition variables in both s4u and sthread.
- Introduce option 'model-check/cached-states-interval' to control how often the application state is cached using fork,
to speedup later restore when exploring other execution branches.
- Introduce option 'model-check/no-fork' to forbid the use of system forks to speed-up the exploration.
This is mandated for multithreaded applications, such as our Python bindings.
- Introduce option 'model-check/max-errors' continue the exploration after the first errors.
- Introduce option 'model-check/timeout-soft' to only search for a given amount of time
- Enable the use of guiding strategies with DPOR, ODPOR and SDPOR (not UDPOR yet).
- Allow to use mutexes and semaphores with UDPOR, that remains more experimental than the other explorations algorithms.
- Support iprobes in MC, not yet with UDPOR.
- Various bug fixes and performance optimizations all over the MC module.
- New guiding strategy: min_context_switch trying to minimize the context switches, inspired from the paper
"A randomized scheduler with probabilistic guarantees of finding bugs", by Musavathi et Al.
- Compute the transition dependencies without considering the context. That may reduce the dependency detection,
but it's much faster to compute so that should still be an optimization. The contextual gain of our dependency theorems
was near to zero (because our compute model is not optimized toward that goal).
- (internals) Reimplement the DPOR, ODPOR and SDPOR algorithms so that the code is closer to the pseudo-code of the
articles. The correction of our implementation is thus easier to check.
- Introduce a new option 'model-check/search-critical' to exhibit the critical transition when a failure is found.
Before that transition, at least one exploration is correct; After it, all explorations are faulty.
For now, the answer is approximate when a reduction algorithm is enabled.

sthread:
- Disable all verbose outputs when STHREAD_QUIET environment variable is defined
- Assume that unknown mutex types are similar to PLAIN ones (somehow true for ADAPTATIVE ones).
- Various fixes and other robustness improvements.

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG123: get_async for MessageQueue bugged
- FG117: Exec.set_tracing_category referenced in documentation but inexistant in Python

----------------------------------------------------------------------------

The "Thanks Giving up stateful model-checking" release. Stateless model checking remains.

S4U:
- New class ActivitySet to ease wait_any()/test_any()/wait_all()
- Deprecate {Comm,Io,Exec}::{wait_any,wait_all,test_any} and friends
- Simplify a bit the declaration of multi-zoned platforms from C++
- New function NetZone::add_route(host1, host2, links) when you don't need gateways
- Also add a variant with s4u::Link, when you don't want to specify the directions
on symmetric routes.
- Zone's gateways can now be controlled directly.
- Add NetZone::add_route(zone1, zone2, links) specifying the route between zones
- Introduce a Mailbox::get_async() with no payload parameter. You can use the new
Comm::get_payload() once the communication is over to retrieve the payload.
- Implement recursive mutexes. Simply pass true to the constructor to get one.
- Simplify the expression of horizontal scaling of Tasks.
- Each Task now consists of a dispatcher, a collector and one or more instances.
- The parallelism degree of each of these can be set.
- Several examples have been added or modified accordingly.
- Update s4u::create_DAG_from_json() to support wfformat 1.4.
- Introduce a new MessageQueue abstraction and associated Mess simulated object.
The behavior of a MessageQueue is similar to that of a Mailbox, but intended for
control messages that do not incur any simulated cost. Information is automagically
transported over thin air between producer and consumer. See examples/cpp/mess-wait
- New function: Mutex::get_owner()

S4U plugins:
- New: Add a JBOD (just a bunch of disks) concept. It's a sort of host with many disks.
- Revamp the battery plugin: rewrite completely the API, for a better usability.
The examples were updated accordingly.
The battery can now act as a simple connector (see battery-connector example).
- Revamp of the photovoltaic plugin: now called SolarPanel and complete rewrite of the API
- Add chiller plugin: enable the management of chillers consuming electrical energy
to compensate heat generated by hosts.
- Add a battery-chiller-solar example combining several plugins to evaluate the amount
of brown energy (from the electrical grid) and green energy (from the solar panel)
during a given computation.

SMPI:
- New SMPI_app_instance_join(): wait for the completion of a started MPI instance
- MPI_UNIVERSE_SIZE now initialized to the total amount of hosts in the platform
- Memory usage due to SMPI for non-MPI actors greatly reduced.
- New implemented calls: MPI_Isendrecv, MPI_Isendrecv_replace

sthread:
- Allow to use on valgrind-observed or gdb-observed processes.
- Install sthread on user's disk.
- Implement recursive pthreads.
- Implement pthread_barrier and pthread_cond (but conditional are not supported by the MC yet).
- Add some McMini codes to test sthread further (controlled with enable_testsuite_McMini).

Model checking:
- Remove stateful model-checking. This was not used, not really working, and very hard to fix.
Liveness properties cannot be verified anymore.
- More informative backtraces on assertion failure.
- Fix dependency bugs for mutex and other transitions
- Fix some reversible_race definitions, and also the rest of ODPOR.

Python:
- Make the host_load plugin available from Python. See examples/python/plugin-host-load
- Mailbox::get_async() does not return a pair anymore. Use comm.get_payload() instead.
- Comm::waitall/waitany/testany() are gone. Please use ActivitySet() instead.
- Comm::waitallfor() is gone too. Its semantic was unclear on timeout anyway.
- Io::waitany() and waitanyfor() are gone. Please use ActivitySet() instead.
- Do not export the values of enums. So you need to write e.g. SharingPolicy.LINEAR
while it should have been possible to write LINEAR alone before. This is the advised
behavior for modern C++ code.

C API:
- Introduce sg_activity_set_t and deprecate wait_all/wait_any/test_any for
Exec, Io and Comm.

Kernel:
- optimize an internal data structure (replace boost::circular_buffer_space_optimized by
std::deque to store pending and unmatched Comms in Mailboxes). It is actually a revert
to what was used a few years back. The boost structure had a lower memory footprint than
deques, but it appeared that their "space_optimized" character was generating a huge lot
of refcount changes on the stored Comms.

General:
- Fix errors with ns-3 v3.36+
- Many other small bug fixes, in particular in MC and sthread.

----------------------------------------------------------------------------

Save the planet, skip a release: 3.33 was due 6 months ago, so skip directly to 3.34.

General:
- SimGrid now requires a compiler with C++17 support for public headers too.
Sibling projects should upgrade their FindSimGrid.cmake
- Remove the MSG API: its EOL was scheduled for 2020.
- Remove the Java bindings: they were limited to the MSG interface.
- On Windows, you now need to install WSL2 as the native builds are now disabled.
It was not really working anyway.
- Support for 32bits architecture is not tested anymore on our CI infrastructure.
It may break in the future, but we think that nobody's using SimGrid on 32 bits.
- Remove the surf module. It was replaced by the kernel/models module, and that
refactoring took almost 10 years to properly complete.

S4U:
- Activity::set_remaining() is not public anymore. Use for example
Comm::set_payload_size() to change the size of the simulated data.
- New function: Engine::flatify_platform(), to get a fully detailed vision of the
configured platform.
- New Task abstraction: They are designed to represent dataflows, i.e, graphs of repeatable Activities.
See the examples under examples/cpp/task-* and the associated documentation.
- Full simDAG integration: Activity::start() actually starts only when all dependencies
are fulfilled. If it cannot be started right away, it will start as soon as it becomes
possible.
- Allow to set a concurrency limit on disks and hosts, as it was already the case for links.
- Rename Link::get_usage() to Link::get_load() for consistency with Host::
- Every signal now come with a static version that is invoked for every object of that class,
and an instance version that is invoked for this specific object only. For example,
s4u::Actor::on_suspend_cb() adds a callback that is invoked for the suspend of any actor while
s4u::Actor::on_this_suspend_cb() adds a callback for this specific actor only.
- Activity::on_suspended_cb() is renamed to Activity::on_suspend_cb(), and fired right before the suspend.
- Activity::on_resumed_cb() is renamed to Activity::on_resume_cb(), and fired right before the resume.
- Resource::on_state_change_cb() is renamed to Resource::on_onoff_cb() to distinguish from the
Activity::on_state_change_cb() that is related to the activity state machine, not on/off.
- Activity signals (veto, suspend, resume, completion) are now specialized by activity class.
That is, callbacks registered in Exec::on_suspend_cb will not be fired for Comms nor Ios.

New S4U plugins:
- Battery: Enable the management of batteries on hosts.
See the examples under examples/cpp/battery-* and the documentation in the Plugins page.
- Photovoltaic: Enable the management of photovoltaic panels on hosts.
See the examples under examples/cpp/photovoltaic-* and the documentation in the Plugins page.

Kernel:
- optimize an internal data structure (use a set instead of a list for ongoing activities),
leading to a potentially big performance gain, in particular with many detached comms.

MPI:
- New option smpi/barrier-collectives to add a barrier to some collectives
to detect dangerous code that /may/ work on some MPI implems.
- New function SMPI_app_instance_start() to easily start a MPI instance in your S4U simulation.

Models:
- Write the section of the manual about models, at least.
- WiFi: the total capacity of a link depends on the amount of flows on that link.
- Use the nonlinear callback feature of LMM to reflect this.
- Calibration values can be changed to match different MCS configurations
- See the example teshsuite/models/wifi_usage_decay/wifi_usage_decay.cpp
- See also "A Flow-Level Wi-Fi Model for Large Scale Network Simulation"
https://hal.archives-ouvertes.fr/hal-03777726
- Merge parameters network/bandwidth-factor and smpi/bw-factor that serve the same purpose.
- Same for the latency
- Rewrite the corresponding documentation.
- Allow to disable the TCP windowing modeling by setting network/TCP-gamma to 0.
- Finally kill the 'compound' host model. You can change the CPU or network model
with the default host model, as it should.
- Rename option "surf/precision" to "precision/timing" for clarity.
- Rename option "maxmin/precision" to "precision/work-amount" for clarity.
- New function: Engine::flatify_platform() to debug your platform.

sthread:
- Implement pthread_join in MC mode.
- Implement semaphore functions in sthread.
- Add an intricated way to verify the access to non-reentrant data structures
It requires code annotation, as shown in examples/sthread/stdobject/stdobject.cpp

Model checking:
- Stateless model-checking is now usable on any system, including Mac OSX and ARM processors.
- The stateless aspects of the MC are now enabled by default in all SimGrid builds.
Liveness and stateful aspects are still controlled by the enabling_model-checking
configuration option.
- Introducing ODPOR and SDPOR reduction strategies
- Introducing guiding heuristics, trying to find bugs faster than DFS in reduced state space.
- Synchronize the MBI tests with upstream.
- Show the full actor backtraces when replaying a MC trace (with model-check/replay)
and the status of all actors on deadlocks in MC mode.

XBT:
- simgrid::xbt::cmdline and simgrid::xbt::binary_name are gone.
Please use simgrid::s4u::Engine::get_cmdline() instead.

Documentation:
- New tutorial on simulating DAGs.
- New section in the user guide on the provided performance models.
- New section presenting some technical good practices for (potential) contributors.
- Add a section on errors and exceptions to the API documentation.
- Move the s4u examples to a section on their own to ease navigation.

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG18: Java bindings should be redone or removed
- FG!118: Wi-Fi callback mechanism
- FG!119: SMPI: add option to inject a barrier before every collective call
- GH383: Segfault when adding a disk after load_platform(xml)

----------------------------------------------------------------------------

SimGrid (3.32) October 3. 2022.

The Wiedervereinigung release. Germany was reunited 32 years ago.

General:
- SimGrid now requires a compiler with C++17 support to compile the lib.
Our public headers still allow the user code to be compiled in C++14.
- Support graphviz v3 and ns-3 v3.36 (older versions are still supported).
- Tested with clang (v11, v13, v14 and v16), gcc (v7 to v13) and IntelCC v2022.2

S4U:
- API evolutions:
- kill signal Comm::on_completion that was not working anyway.
- Expose signals Activity::on_suspend and Activity::on_resume
- New macro xbt_enforce(): similar to xbt_assert(), but throws an AssertionError
instead of calling abort().
- New: s4u::Exec::get_thread_count()
- Various cleanups around virtual machines:
- host_by_name() and friends now only return hosts. VMs are now excluded.
- It is now impossible to search a VM by name globally.
You can only search VM by name on a given PM, so either you know
the PM on which your VM runs and you can search by name, or you need
to manually iterate over all PMs to search this VM.
- The s4u::VirtualMachine constructor is now deprecated.
Please use s4u::Host::create_vm() instead.
- Rename s4u::VirtualMachine::on_creation() to on_vm_creation() to
avoid confusion with s4u:Host::on_creation() that is inherited.
Also s4u::VirtualMachine::on_destruction -> on_vm_destruction().
- Bug fixes:
- One-sided communications (Comm::sendto) can now be detached,
and should now be more resilient to network and host faults.

Python:
- Added the following bindings / examples:
- Comm (now 100% covers the C++ interface):
- Comm.dst_data_size, Comm.mailbox, Comm.sender, Comm.start_time, Comm.finish_time
- Comm.state_str [examples: examples/python/comm-failure/, examples/python/comm-host2host/]
- Comm.remaining [examples: examples/python/comm-host2host/, examples/python/comm-suspend/]
- Comm.set_payload_size [example: examples/python/comm-host2host/]
- Comm.set_rate [example: examples/python/comm-throttling/]
- Comm.sendto, Comm.sendto_init, Comm.sendto_async [example: examples/python/comm-host2host/]
- Comm.start, Comm.suspend, Comm.resume [example: examples/python/comm-host2host/]
- Comm.test_any [example: examples/python/comm-testany/]
- Comm.wait_until [example: examples/python/comm-waituntil/]
- Engine:
- Engine.host_by_name [example: examples/python/comm-host2host/]
- Engine.mailbox_by_name_or_create [example: examples/python/comm-pingpong/]
- Engine.set_config
- Mailbox: Mailbox.ready [example: examples/python/comm-ready/]
- Ptask [example: examples/python/exec-ptask/]:
- this_actor.exec_init
- this_actor.parallel_execute
- Exec.suspend
- Exec.wait_for
- Added an AssertionError exception that may be thrown in case of error.
For instance, creating two hosts with the same name will now throw this exception
instead of killing the interpreter.

SMPI:
- Implement MPI_File_get_type_extent(), MPI_File_s/get_atomicity() and
MPI_File_get_byte_offset()
- Intercept getpid() calls to return the simulated ones.
- Fix various bugs in MPI IO.

Platform description & visualization:
- More robust sanity checks for platforms, to reject forbidden topologies with
a proper error message.
- New platform example: supernode.cpp and supernode.py.
The Python version generates a nice graphical representation of the platform.
- Bug fixes around fat-tree topologies.
- Allow to dump the platform topology as a CSV file representing the graph edges
with platform_graph_export_csv() (similar to the DOT export).
- Fix graphicator for "cluster" topologies (e.g. fat-tree, dragonfly).

Models:
- Fix a bug when using ptasks with multicores (FG!111).

Model-Checker:
- First bits of sthread, that intercepts pthread operations at runtime.
The intend is to use it together with simgrid-mc, but it is TBD.
- Sync MBI generators with upstream changes.
- Various cosmetics, small bug fixes and inner refactorings

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG105: "Variable penalty should not be negative!" with in-flight messages and bandwidth profiles
- FG109: Application time reported by --cfg=smpi/display-timing:yes is wrong
- FG110: Wait_any does not trigger new model solve when host events occur
- FG111: Wrong execution time in rare cases when using multicore
- FG!98: Re-enable the tests for legacy stochastic profiles
- FG!109: Trigger new engine solve upon host events such as host on/off
- FG!116: SMPI/replay: Fix issue with recv of size =0

----------------------------------------------------------------------------

SimGrid (3.31) March 22. 2022.

The ненасильство release. We stand against war.

Against the agression by a sick system that forces peoples to take arms against each other.

MC:
- Rework the internals, for simpler and modern code. This shall unlock many future improvements.
- You can now define plugins onto the DFS explorer (previously called SafetyChecker), using the
declared signals. See CommunicationDeterminism for an example.
- Support mutex, semaphore and barrier in DPOR reduction
- Seems to work on Arm64 architectures too.
- Display a nice error message when ptrace is not usable.
- New test suite, imported from the MPI Bugs Initiative (MBI). Not all MBI generators are integrated yet.
- Remove the ISP test suite: it's not free software, and it's superseeded by MBI.

SMPI:
- fix for FG100 by ensuring small asynchronous messages never overtake larger
ones, conforming to the standard.
- replay: fix waitall behaviour to avoid forgetting requests and leaking
their handles.
- tracing: ensure that we dump the TI traces continuously during execution and
not just at the end, reducing memory cost and performance hit.
- Update OpenMPI collectives selection logic to match current one (4.1.2)
- Add a coherence check for collective operation order and root/MPI_Op
coherence. Potentially costly so not activated unless smpi:pendantic is set
or -analyze is given.

S4U:
- New signal: Engine::on_simulation_start_cb()
- Introduce a new execution mode with this_actor::thread_execute(). This simulate
the execution of a certain amount of flops by multiple threads ran by a host. Each
thread executes the same number of flops, given as argument. An example of this new
function can be found in examples/cpp/exec-threads.
- Reimplementation of barriers natively.
Previously, they were implemented on top of s4u::Mutex and s4u::ConditionVariable.
The new version should be faster (and can be used in the model-checker).
- Actor::get_restart_count(): Returns the number of reboots that this actor did.

MSG:
- MSG_barrier_destroy now expects a non-const msg_barrier parameter.

New plugin: the Chaos Monkey (killing actors at any time)
- Along with the new simgrid-monkey script, it tests whether your simulation
resists resource failures at any possible timestamp in your simulation.
- It is mostly intended to test the SimGrid core in extreme conditions,
but some users may find it interesting too.

Models:
- New solver for parallel task: BMF.
- More realistic sharing of heterogeneous resources compared to the fair
bottleneck solver used by ptask_L07.
- Implement the BMF (Bottleneck max fairness) fairness.
- Improved resource sharing for parallel tasks with sub-flows (parallel
communications between same source and destination inside the ptask).
- Parameters:
- "--cfg=host/model:ptask_L07 --cfg=host/solver:bmf": enable the ptask
model with BMF solver.
- "--cfg=bmf/max-iterations: <N>": maximum number of iterations performed
by BMF solver (default: 1000).
- "--cfg=bmf/precision: <N>": numerical precision used when computing
resource sharing (default: 1e-12).
- This model requires Eigen3 library. Make sure Eigen3 is installed to use BMF.

General:
- Modifications of the Profile mechanism, with some impact on users
- Addition of a new (S4U) method to init profiles from generic functions to improve versatility
- Fix initial behaviour of state_profiles
- Modify periodicity to behave like a period, and not like a loop delay

XBT:
- Drop xbt_dynar_shrink().

Python:
- Made the following bindings static (previously member functions):
- Actor: Actor.kill_all(), Actor.by_pid()
- Host: Host.by_name(), Host.current(), Host.on_creation_cb()
- Mailbox: Mailbox.by_name()
- Added the following bindings:
- this_actor.warning()
- Mailbox.put_init() [example: examples/python/comm-waitallfor/]
- Comm.detach() [example: examples/python/comm-waitallfor/]
- Comm.wait_for() [example: examples/python/comm-waitfor/]
- Comm.wait_any_for()
- Comm.wait_all_for() [example: examples/python/comm-waitallfor/]
- Mutex [example: examples/python/synchro-mutex/]
- Barrier [example: examples/python/synchro-barrier/]
- Semaphore [example: examples/python/synchro-semaphore/]

Build System:
- Remove target "make uninstall" which was incomplete and no longer maintained.

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG57: Mc SimGrid should test whether ptrace is usable
- FG87: Smpi scripts fail with spaces in paths
- FG100: [SMPI] Order of the message matching is not guaranteed
- FG101: LGPL 2.1 is deprecated license
- FG104: "make uninstall" not up-to-date
- GH151: Missing mutexes for DPOR.

----------------------------------------------------------------------------

SimGrid (3.30) January 30. 2022.

The Sunday Bloody Sunday release.

Main user-visible changes:
- The SimDag API for the simulation of the scheduling of Directed Acyclic
Graphs has been dropped. It was marked as deprecated for a couple of years.
We finally complete the implementation of what has been called SimDag++
internally, i.e., porting the different features of SimDag on top of S4U.
The new way to simulate the execution of dependent activities directly by
maestro (without any other actor) is details in the examples/cpp/dag-* series
of examples.
- The removal of SimDag led us to also remove the export to Jedule files that
was tightly coupled to SimDag. The instrumentation of DAG simulation is still
possible through the regular instrumentation API based on the Paje format.
- We also dropped the old and clumsy Lua bindings to create platforms in a
programmatic way. It can be done in C++ in a much cleaner way now, which
motivates this suppression.

S4U:
- Introduce on_X_cb() functions for all signals, to attach a new
callback to the signal X. The signal variables are now hidden and
only these functions should be used.
Rationale: this enables the usual deprecation scheme where functions
remain for 4 releases if we need to modify the signals, while the
current code with the signal variables directly visible prevents any
smooth transition.
- New function: Engine::run_until(date), to split the simulation.
- New signal: Activity::on_veto, to detect when an activity fails to start.
- Signal change: Comm::on_start(Comm&, bool) has been replaced by
Comm::on_send and Comm::recv. These two signals respectively correspond to
when the sending or receiving side of a Comm is ready. They are raised at
the same locations as the former Comm::on_start signal.
- New function: Engine::track_vetoed_activities() to interrupt run()
when an activity fails to start, and to keep track of such activities.
Please see the corresponding example for more info.
- New functions: s4u::Comm::{sendto_init, set_source, set_destination} to enable
the use of vetoers with direct host-to-host communications. Both source and
destination have to set for a comm to start. Each call to these setters check
if all vetoes are satisfied. When it is the case, the comm starts. A use case of
these functions is given in examples/cpp/dag-scheduling.
- New functions: {Exec, Io}::update_priority allow you to modify the priority of
these kinds of activities during their execution. Behavior is detailed in
examples/cpp/io-priority/.

SMPI:
- Dynamic costs for MPI operations: New API to allow users to dynamically
change injected costs for MPI_Recv, MPI_Send and MPI_Isend operations.
Alternative for smpi/or, smpi/os and smpi/ois configuration options.
- Fix some issues with the replay mechanism.

XBT:
- Function xbt::Extendable::get_data() is now templated with the type of the
pointee. Untyped function is deprecated. Use get_data<void>() if you still
want to retrieve void*.

Documentation:
- New section: "SimGrid MPI calibration of a Grid5000 cluster"
presenting how to properly calibrate MPI communications in SimGrid.
- Complete and reword the platform section, which is now completed.

Python:
- Thread contexts are used by default with Python bindings. Other kinds of
contexts revealed unstable, specially starting with pybind11 v2.8.0.

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG95: Wrong computation time for multicore execution after pstate change
- FG97: Wrong computation time for ptask+multicore+pstates
- FG98: SMPI offline simulation is inconsistent with the online simulation
(deadlocks / message truncation)
- FG99: Weird segfault when not sealing an host

----------------------------------------------------------------------------

The "Ask a stupid question" release.

We wish that every user ask one question about SimGrid to celebrate.
On Mattermost, Stack Overflow or using the issues tracker.

New modeling features:
- Non-linear resource sharing, modeling resources whose performance heavily degrades with contention:
- The total capacity may be updated dynamically through a callback
and depends mainly on the number of concurrent flows.
- Examples (both cpp and python): io-degradation, network-nonlinear, exec-cpu-nonlinear

- Dynamic factors: model variability in the speed of activities
- Each action can now have a factor that affects its progression.
This multiplicative factor is applied when updating the amount of work
remaining, thereby an activity with factor=0.5 only uses half of the
instantaneous power/bandwidth it is allocated and will appear twice
slower than what it actually consumes.
- This can be used to model a overhead (e.g., there is a 20 bytes
header in a 480 bytes TCP packet so the factor 0.9583) but the novelty
is this factor can now easily be adjusted depending on activity's and
resources characteristics.
- This existed for network (e.g., the effective bandwidth depends
on the message in SMPI piecewise-linear network model) but it is now
more general (the factor may depend on the source and destination and
thus account to different behaviors for intra-node communications and
extra-node communications) and is available for CPUs (e.g., if you
want to model an affinity as in the "Unrelated Machines" problem in
scheduling) and disks (e.g., if you want to model a stochastic
capacity) too.
- For that, resources can be provided with a callback that computes
the activity factor when creating the action.
- Example: examples/cpp/exec-cpu-factors
- The same mechanism is also available for the latency, which
allows to easily introduce complex variability patterns.

Python:
- Added support to programmatic platform creation in Python.
Example: examples/python/clusters-multicpu

S4U:
- Disk and Host now have a set_sharing_policy() too, for non-linear sharing.
This can only be set through the API, not through XML files.

SMPI:
- TI Tracing/Replay:
- Multiple fixes to ensure reproducibility of tracing
- scan/excan can now be replayed
- wait action now uses ranks and not pid, as the other ones.
- smpi/init and smpi/finalization-barrier are now valid for replays.
- exit() is now intercepted by SMPI to avoid premature shutdown of
simulation. First non 0 return codes is returned as simulation return
code.

Documentation:
* New section "Release Notes" documenting recent and current developments.
* New section "Modeling I/O: the realistic way" presenting how to properly model disks in SimGrid.
* Improvements in API Reference for C++ and Python interfaces.

ns-3 model:
- Make wifi creation compatible with ns-3 version 3.34 too.

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG77: Search feature of doc is broken (update sphinx theme version)
- FG78: Multiple fixes for SMPI replay:
- TI tracing of allotallv/w was outputting wrong values
- MPI_LOGICAL in fortran is actually 32 bits wide, and not 8.

----------------------------------------------------------------------------

The Victoriadagarna Release.

New features:
- C++ platform interface: Users can now describe their platform directly in C++.
This provides greatly flexibility and performance improvement for complex
platforms. Main features:
- Fat-Tree/DragonFly/Torus composing: allows you to create clusters of
"zones", instead of single hosts. This feature enables the description
of clusters with complex hosts, composed of several CPUs, GPUs, etc.
- StarZone: new zone with a Star-like topology. The routes are defined
as a set of links used to communicate from node to everybody (node<->ALL).
- Split-Duplex links: auxiliary method to create split-duplex links in
the platform, easing its utilisation. It automatically creates both UP
and DOWN links (similarly as done in XML).
- Please refer to the documentation and the examples included:
e.g. examples/cpp/clusters-multicpu/ and examples/platforms/*.cpp.
- New plugin: Producer-Consumer with monitor. Just requires to include the
include/simgrid/plugins/ProducerConsumer.hpp header to be used. See the
associated example (examples/cpp/plugin-prodcons).

S4U:
- New: s4u::Comm::wait_all_for() (like s4u::Comm::wait_all, but with a timeout),
s4u::Io::wait_any(), s4u::Io::wait_any_for().
- Methods test_all/test_any/wait_all/wait_any in s4u now take their vector
parameter by reference, instead of a pointer.
- Fixed a bug where Activity::wait_for() killed the activity on timeout.
Explicitly cancel the activity to get back to previous behavior.
- New: Link::set_concurrency_limit() to limit the amount of concurrent flows.

SMPI:
- The default SMPI compiler flags are no more taken from the environment.
They can be explicitly set through cmake parameters SMPI_C_FLAGS,
SMPI_CXX_FLAGS, or SMPI_Fortran_FLAGS.
- New options:
--cfg=smpi/finalization-barrier: which can be used to add
a barrier inside MPI_Finalize. This can help for some codes which cleanup
data attached to a process, but still used in other SMPI processes.
--cfg=smpi/errors-are-fatal: True by default, behaves like if MPI_ERRORS_RETURN
is active when set to false, to keep going after a small error
--cfg=smpi/pedantic: True by default. Do not report some harmless MPI errors
which may or may not be problematic in the end.
- Sampling:
- fix behaviour, as maximum iteration count could be ignored
- add SMPI_SAMPLE_LOCAL_TAG and SMPI_SAMPLE_GLOBAL_TAG macros, to allow user to
use sampling when the same kernel is called with a different set of parameters
which have an impact on the timing.
- realloc is now intercepted, to be coherent, as malloc/calloc/free were already.
It should now work with smpi/auto-shared-malloc-thresh.
- Improve error handling and reporting in multiple places
- Improve correctness checks on the MPI code.(MPI_Op and MPI_Datatype
validity checks, truncated messages are now an error, return errors
when explicitely deleted handles are reused, ...)
- RMA: multiple fixes and stability improvements.
- analysis (-analyze flag in smpirun):
- SMPI can now report buffer leaks as well as MPI handles leaks,
if code was compiled without SMPI_NO_OVERRIDE_MALLOC.
- if -trace-call-location is used when compiling, SMPI can report
origin of leaked handles/buffers
- group leaks by type/origin in output message if possible
- New implemented MPI calls: MPI_Comm_test_inter

Models:
- Changed internal implementation of bandwidth factors in network models.
Models affected: CM02, LV08 (default), SMPI, IB.
Configuration affected: "network/bandwidth-factors" and "smpi/bw-factors".
Bandwidth factors are applied to communications to describe that users
cannot use 100% of the available bandwidth. For example, the default network model,
LV08, applies a factor of 0.97 to the bandwidth. In older versions, this
behavior was implemented by limiting the bandwidth available in the LMM
system for this flow. This may give the false impression that there is
bandwidth available for other flows due to its underutilization, especially
for the dynamic bandwidth factors used in SMPI models.
To avoid this, we have modified the implementation so that each flow uses the
maximum physical bandwidth according to the LMM system.
However, the actual throughput of the flow seen by the user is defined by
the physical bandwidth multiplied by the bandwidth factor.
This change impacts on the simulation results for all network models on
which we have bandwidth factors configured.
*****************************************
*DO NOT MIX 3.28 RESULTS WITH OLDER ONES*
*****************************************
This change may impact on the timing of your simulation results.
Take care when comparing simulations from different SimGrid's
versions. Sorry for the inconvenience.
- Dynamic network factors: users can configure a callback to define
the network factors dynamically. This API is available at
simgrid::kernel::resource::NetworkModelIntf.
- Users have access to complete information about the current communication
to decide which factor to apply. This includes: message size, source and
destination hosts, links and zones traversed.
- Dynamic factors for both latency and bandwidth.
- For more details, see the example in (examples/cpp/network-factors).
- Plugin host_energy: the "watt_off" and "watt_per_state" host properties,
deprecated since version 3.24, are no longer supported. Instead, use
"wattage_off" and "wattage_per_state".

XBT:
- xbt_assert is not disabled anymore, even when built with enable_debug=off.

Documentation:
- New tutorial: Model-checking and formal assessment
- New sections: "Demystifying the routing" and "C++ platforms"
- Update and improve the part on visualization in MPI and Algo tutorials.
- Improve the section on routing: how to define it, how it's used internally
- Fix many issues, broken links and missing references in doxygen and Sphinx

LUA:
- Lua platform files are deprecated. Their support will be dropped after v3.31.

Simix:
- Legacy functions deprecated in this release: SIMIX_get_clock(), SIMIX_run().

Fixed bugs (FG.. -> FramaGit bugs; FG!.. -> FG merge requests)
(FG: issues on Framagit; GH: issues on GitHub)
- FG47: Complete and fix tests from teshuite/s4u/activity-lifecycle
- FG64: Configuring smpi/IB-penalty-factors
- FG67: Running computation concurrently with MPI_Iallreduce
- FG69: Tutorial misleading users of pre-v3.26 versions of SimGrid
- FG71: Segmentation fault on invalid gw_src/gw_dst
- GH322: Issue when an actor kills his host vm

----------------------------------------------------------------------------