batsim issueshttps://gitlab.inria.fr/batsim/batsim/-/issues2022-03-29T17:57:15+02:00https://gitlab.inria.fr/batsim/batsim/-/issues/140c++ platform working in simgrid but not batsim2022-03-29T17:57:15+02:00ANGELELLI Lucc++ platform working in simgrid but not batsim**Describe the bug**
I was trying to create c++ platforms, got it working on simgrid, but trying it on batsim failed. Following tests showed that i can't get any c++ platform working on batsim, but xml platforms work fine.
**Provide i...**Describe the bug**
I was trying to create c++ platforms, got it working on simgrid, but trying it on batsim failed. Following tests showed that i can't get any c++ platform working on batsim, but xml platforms work fine.
**Provide information so the bug can be reproduced**
Attached are the nix shells i'm using to compile and run, the platforms in c++, so and xml, and relevent other files.
[default.nix](/uploads/d6172ee015843b0f5aa5b13ee97f3345/default.nix)
[platform_compiling.nix](/uploads/e3bf77fbc4bb000c0bae0941840b91f2/platform_compiling.nix)
[tuto-env.nix](/uploads/c2c751ee04b70644b644fd9530d6fe15/tuto-env.nix)
[very_small_platform.cpp](/uploads/131a4fb7e9941e5b99c07b983b28c2ff/very_small_platform.cpp)
[very_small_platform.so](/uploads/36035257d8aa006f7149c212fbe58cd5/very_small_platform.so)
[very_small_platform.xml](/uploads/5d3efda17da3bdeb7bddcb5d4a7e0676/very_small_platform.xml)
[test_one_delay_job.json](/uploads/730c3ccd5e43a9fb9c387c7ccda776ff/test_one_delay_job.json)
[s4u-comm-wait.cpp](/uploads/99bfeb6a3b42ea4bd1c01b54eb7601ba/s4u-comm-wait.cpp)
I'm compiling the platform in platform_compiling.nix with :
> $CXX -shared -o very_small_platform.so $(pkg-config --libs --cflags simgrid) very_small_platform.cpp
I'm running simgrid with simgrid-template-s4u-master. I compiled s4u-comm-wait.cpp with:
> $CXX -o s4u-comm-wait $(pkg-config --libs --cflags simgrid) s4u-comm-wait.cpp
and ran :
> ./s4u-comm-wait ./very_small_platform.so
and
> ./s4u-comm-wait ./very_small_platform.xml
which gave very similar results (as expected, see logs).
Then I tried in batsim something similar. In the nix shell tuto-env.nix, I ran:
> batsim -p ./platforms/very_small_platform.xml -w ./workloads/test_one_delay_job.json
and
> batsim -p ./platforms/very_small_platform.so -w ./workloads/test_one_delay_job.json
With the xml platform, it ran as expected, but c++ platform crashed with an error
> ../src/xbt/config.cpp:255: [root/CRITICAL] Refusing to register the config element 'smpi/iprobe' twice.
As far as i can tell, i'm not using SMPI here.
**Logs**
- Running with simgrid
```
[nix-shell:~/proj/simgrid-template-s4u-master]$ ./s4u-comm-wait ./very_small_platform.so
[master_host:sender:(1) 0.000000] [s4u_comm_wait/INFO] sleep_start_time : 5.000000 , sleep_test_time : 0.000000
[Jupiter:receiver:(2) 0.000000] [s4u_comm_wait/INFO] sleep_start_time : 1.000000 , sleep_test_time : 0.100000
[Jupiter:receiver:(2) 1.000000] [s4u_comm_wait/INFO] Wait for my first message
[master_host:sender:(1) 5.000000] [s4u_comm_wait/INFO] Send 'Message 0' to 'receiver'
[master_host:sender:(1) 17.041445] [s4u_comm_wait/INFO] Send 'Message 1' to 'receiver'
[Jupiter:receiver:(2) 17.100000] [s4u_comm_wait/INFO] I got a 'Message 0'.
[master_host:sender:(1) 29.141445] [s4u_comm_wait/INFO] Send 'Message 2' to 'receiver'
[Jupiter:receiver:(2) 29.200000] [s4u_comm_wait/INFO] I got a 'Message 1'.
[master_host:sender:(1) 41.241445] [s4u_comm_wait/INFO] Send 'finalize' to 'receiver'
[Jupiter:receiver:(2) 41.300000] [s4u_comm_wait/INFO] I got a 'Message 2'.
[Jupiter:receiver:(2) 41.400000] [s4u_comm_wait/INFO] I got a 'finalize'.
[nix-shell:~/proj/simgrid-template-s4u-master]$ ./s4u-comm-wait ./very_small_platform.xml
[master_host:sender:(1) 0.000000] [s4u_comm_wait/INFO] sleep_start_time : 5.000000 , sleep_test_time : 0.000000
[Jupiter:receiver:(2) 0.000000] [s4u_comm_wait/INFO] sleep_start_time : 1.000000 , sleep_test_time : 0.100000
[Jupiter:receiver:(2) 1.000000] [s4u_comm_wait/INFO] Wait for my first message
[master_host:sender:(1) 5.000000] [s4u_comm_wait/INFO] Send 'Message 0' to 'receiver'
[master_host:sender:(1) 17.643478] [s4u_comm_wait/INFO] Send 'Message 1' to 'receiver'
[Jupiter:receiver:(2) 17.700000] [s4u_comm_wait/INFO] I got a 'Message 0'.
[master_host:sender:(1) 30.343478] [s4u_comm_wait/INFO] Send 'Message 2' to 'receiver'
[Jupiter:receiver:(2) 30.400000] [s4u_comm_wait/INFO] I got a 'Message 1'.
[master_host:sender:(1) 43.043478] [s4u_comm_wait/INFO] Send 'finalize' to 'receiver'
[Jupiter:receiver:(2) 43.100000] [s4u_comm_wait/INFO] I got a 'Message 2'.
[Jupiter:receiver:(2) 43.200000] [s4u_comm_wait/INFO] I got a 'finalize'.
```
- Running with batsim
```
[nix-shell:~/proj/Batsim]$ batsim -p ./platforms/very_small_platform.xml -w ./workloads/test_one_delay_job.json
[0.000000] [batsim/INFO] Workload 'w0' corresponds to workload file '/home/defryder/proj/Batsim/./workloads/test_one_delay_job.json'.
[0.000000] [batsim/INFO] Batsim version: 4.1.0
[0.000000] [workload/INFO] Loading JSON workload '/home/defryder/proj/Batsim/./workloads/test_one_delay_job.json'...
[0.000000] [workload/INFO] JSON workload parsed sucessfully. Read 1 jobs and 1 profiles.
[0.000000] [workload/INFO] Checking workload validity...
[0.000000] [workload/INFO] Workload seems to be valid.
[0.000000] [workload/INFO] Removing unreferenced profiles from memory...
[0.000000] [xbt_cfg/INFO] Configuration change: Set 'host/model' to 'ptask_L07'
[0.000000] [batsim/INFO] Checking whether SMPI is used or not...
[0.000000] [machines/INFO] Creating the machines from platform file './platforms/very_small_platform.xml'...
[0.000000] [xbt_cfg/INFO] Switching to the L07 model to handle parallel tasks.
[0.000000] [machines/INFO] Looking for master host 'master_host'
[0.000000] [machines/INFO] The machines have been created successfully. There are 1 computing machines.
[0.000000] [batsim/INFO] Batsim's export prefix is 'out'.
[0.000000] [batsim/INFO] The process 'workload_submitter_w0' has been created.
[0.000000] [batsim/INFO] The process 'server' has been created.
[master_host:Scheduler REQ-REP:(3) 0.000000] [network/INFO] Sending '{"now":0.000000,"events":[{"timestamp":0.000000,"type":"SIMULATION_BEGINS","data":{"nb_resources":1,"nb_compute_resources":1,"nb_storage_resources":0,"allow_compute_sharing":false,"allow_storage_sharing":true,"config":{"redis-enabled":false,"redis-hostname":"127.0.0.1","redis-port":6379,"redis-prefix":"default","profiles-forwarded-on-submission":false,"dynamic-jobs-enabled":false,"dynamic-jobs-acknowledged":false,"profile-reuse-enabled":false,"sched-config":"","forward-unknown-events":false},"compute_resources":[{"id":0,"name":"Jupiter","state":"idle","properties":{"role":""},"zone_properties":{}}],"storage_resources":[],"workloads":{"w0":"/home/defryder/proj/Batsim/./workloads/test_one_delay_job.json"},"profiles":{"w0":{"delay10":{"type":"delay","delay":10}}}}}]}'
^C
[master_host:Scheduler REQ-REP:(3) 0.000000] [ker_engine/INFO] CTRL-C pressed. The current status will be displayed before exit (disable that behavior with option 'debug/verbose-exit').
[master_host:Scheduler REQ-REP:(3) 0.000000] [ker_engine/INFO] 3 actors are still running, waiting for something.
[master_host:Scheduler REQ-REP:(3) 0.000000] [ker_engine/INFO] Legend of the following listing: "Actor <pid> (<name>@<host>): <status>"
[master_host:Scheduler REQ-REP:(3) 0.000000] [ker_engine/INFO] Actor 1 (workload_submitter_w0@master_host) simcall actor::CommIsendSimcall
[master_host:Scheduler REQ-REP:(3) 0.000000] [ker_engine/INFO] Actor 2 (server@master_host) simcall NONE
[master_host:Scheduler REQ-REP:(3) 0.000000] [ker_engine/INFO] Actor 3 (Scheduler REQ-REP@master_host) simcall NONE
Segmentation fault.
Segmentation fault (core dumped)
[nix-shell:~/proj/Batsim]$ batsim -p ./platforms/very_small_platform.so -w ./workloads/test_one_delay_job.json
[0.000000] [batsim/INFO] Workload 'w0' corresponds to workload file '/home/defryder/proj/Batsim/./workloads/test_one_delay_job.json'.
[0.000000] [batsim/INFO] Batsim version: 4.1.0
[0.000000] [workload/INFO] Loading JSON workload '/home/defryder/proj/Batsim/./workloads/test_one_delay_job.json'...
[0.000000] [workload/INFO] JSON workload parsed sucessfully. Read 1 jobs and 1 profiles.
[0.000000] [workload/INFO] Checking workload validity...
[0.000000] [workload/INFO] Workload seems to be valid.
[0.000000] [workload/INFO] Removing unreferenced profiles from memory...
[0.000000] [xbt_cfg/INFO] Configuration change: Set 'host/model' to 'ptask_L07'
[0.000000] [batsim/INFO] Checking whether SMPI is used or not...
[0.000000] [machines/INFO] Creating the machines from platform file './platforms/very_small_platform.so'...
[0.000000] ../src/xbt/config.cpp:255: [root/CRITICAL] Refusing to register the config element 'smpi/iprobe' twice.
Backtrace (displayed in actor maestro):
(backtrace not set -- did you install Boost.Stacktrace?)
Aborted (core dumped)
```
**Possible fixes**
(Share any insight you have about the bug.)https://gitlab.inria.fr/batsim/batsim/-/issues/130batsim_ci docker image has outdated SSL certificates2021-12-14T17:52:10+01:00Millian Poquetbatsim_ci docker image has outdated SSL certificatesOld certificates causes some CI operations to fail (e.g., downloading anything from framagit) and is therefore very annoying.
I tried to update the old `batsim_ci` Dockerfile but it led to compiling way too many things (glibc, gcc...). ...Old certificates causes some CI operations to fail (e.g., downloading anything from framagit) and is therefore very annoying.
I tried to update the old `batsim_ci` Dockerfile but it led to compiling way too many things (glibc, gcc...).
Generating this container via Nix would probably be better.Millian PoquetMillian Poquethttps://gitlab.inria.fr/batsim/batsim/-/issues/129Batsim sphinx documentation build fails on readthedocs2021-12-14T18:00:37+01:00Millian PoquetBatsim sphinx documentation build fails on readthedocsBatsim's sphinx documentation seems fine (`nix-build . -A sphinx_doc` works) but the build on readthedocs's CI is broken: https://readthedocs.org/projects/batsim/builds/Batsim's sphinx documentation seems fine (`nix-build . -A sphinx_doc` works) but the build on readthedocs's CI is broken: https://readthedocs.org/projects/batsim/builds/Millian PoquetMillian Poquethttps://gitlab.inria.fr/batsim/batsim/-/issues/128Batsim-4.1.0 docker container increased too much2021-12-14T18:08:01+01:00Millian PoquetBatsim-4.1.0 docker container increased too muchBatsim-4.1.0 seems to weigh 55 Mo, while Batsim-4.0.0 weighed less than 25 Mo (source: [dockerhub](https://hub.docker.com/repository/registry-1.docker.io/oarteam/batsim/tags?page=1&ordering=last_updated)).
Something probably went wrong ...Batsim-4.1.0 seems to weigh 55 Mo, while Batsim-4.0.0 weighed less than 25 Mo (source: [dockerhub](https://hub.docker.com/repository/registry-1.docker.io/oarteam/batsim/tags?page=1&ordering=last_updated)).
Something probably went wrong in NUR-Kapack's nix recipes, maybe SimGrid-3.29.0's python binding that is included in the closure while it should not.
@adfaure, can you investigate this? (you recently developed a tool for this purpose ;)FAURE Adrienadrien.faure@inria.frFAURE Adrienadrien.faure@inria.frhttps://gitlab.inria.fr/batsim/batsim/-/issues/126Forward most Batsim options to the decision process2022-01-20T05:16:56+01:00Millian PoquetForward most Batsim options to the decision processIt would be interesting that decision processes know what Batsim simulates and what constraints they should respect.
Whether energy is enabled and hosts can be shared should for example be forwarded, as proposed [there](https://github.co...It would be interesting that decision processes know what Batsim simulates and what constraints they should respect.
Whether energy is enabled and hosts can be shared should for example be forwarded, as proposed [there](https://github.com/oar-team/batsim/issues/54#issuecomment-893316441).
Quick fix proposal:
- [x] add batsim CLI arguments into `SimulationBegins`. \
This is not robust to Batsim CLI changes and in the long run we probably want to have a clean model of what decisions are allowed or not, \
but the possibility to read Batsim CLI arguments from the protocol can be useful per se.5.0.0https://gitlab.inria.fr/batsim/batsim/-/issues/124not an issue : make sure mattermost notifications work2021-07-06T10:36:11+02:00Millian Poquetnot an issue : make sure mattermost notifications workhttps://gitlab.inria.fr/batsim/batsim/-/issues/123Kill of sequence profiles: seq count in progress is hacky2022-01-20T05:23:45+01:00Millian PoquetKill of sequence profiles: seq count in progress is hacky- The information is put in the `task_index` : https://gitlab.inria.fr/batsim/batsim/-/blob/4f12a4b51ab38ff2936bc1116fa3f34a05f494e6/src/jobs_execution.cpp#L81
- But this is not how the `task_index` is defined.
A dedicated field seems c...- The information is put in the `task_index` : https://gitlab.inria.fr/batsim/batsim/-/blob/4f12a4b51ab38ff2936bc1116fa3f34a05f494e6/src/jobs_execution.cpp#L81
- But this is not how the `task_index` is defined.
A dedicated field seems cleaner and easier to use.5.0.0https://gitlab.inria.fr/batsim/batsim/-/issues/119Parallel task with mapping2022-01-20T05:37:09+01:00FAURE Adrienadrien.faure@inria.frParallel task with mappingI noticed that when using the parallel tasks profile one can provide a mapping into the description of the job (and not the profile).
The mapping is used by batsim to map the activities of the parallel task to the executors chosen by th...I noticed that when using the parallel tasks profile one can provide a mapping into the description of the job (and not the profile).
The mapping is used by batsim to map the activities of the parallel task to the executors chosen by the scheduler.
In the current implementation, if a mapping is provided with the job it changes the number of resources Batsim expects for the job.
This number becomes the total of different executors.
The `res` attribute needs to match the computation vector size (and the square root of the communication matrix).
The following workload illustrates the issue, Batsim expects the job 0 to have only 1 resource allocated, instead of 2 as specified by the `res` attribute.
In my [scheduler](https://gitlab.inria.fr/adfaure/sked-ptask/blob/master/src/benet.rs#L198), I have to loop through the whole mapping object and count the number of different executors in order to provide to Batsim the number it expects.
```json
{
"jobs": [
{
"id": "0",
"mapping": {
"0": "0",
"1": "0",
},
"profile": "ptask",
"res": 2,
"subtime": 0
}
],
"profiles": {
"ptask": {
"com": [ 0, 0, 0, 0],
"cpu": [ 0, 0 ],
"type": "parallel"
}
}
}
```
This not a big deal, but I wanted to write down this behavior.
If it is what we want, I think it is worth to be documented.
In the other case, we can use this thread to find how to improve this.https://gitlab.inria.fr/batsim/batsim/-/issues/118Incoherent documentation of csv output2021-05-20T16:13:33+02:00Raphaël BleuseIncoherent documentation of csv outputThe latest documentation and the code are out of sync (rev 38068329).
see:
- https://gitlab.inria.fr/batsim/batsim/blob/380683295787300ed9458668c0ab24e0b3f08b0b/src/export.cpp#L970
- https://gitlab.inria.fr/batsim/batsim/blob/38068329578...The latest documentation and the code are out of sync (rev 38068329).
see:
- https://gitlab.inria.fr/batsim/batsim/blob/380683295787300ed9458668c0ab24e0b3f08b0b/src/export.cpp#L970
- https://gitlab.inria.fr/batsim/batsim/blob/380683295787300ed9458668c0ab24e0b3f08b0b/docs/output-jobs.rst (or https://batsim.readthedocs.io/en/latest/output-jobs.html)https://gitlab.inria.fr/batsim/batsim/-/issues/116Reduce Batsim closure size2023-08-02T16:05:19+02:00Millian PoquetReduce Batsim closure size### Objective
Provide a lightweight Batsim image for non-Nixed (yet) users (cf. #115).
### Problem
Batsim's closure (built from CI) weights 136 Mo…
The batsim package itself is a bit heavy, but most of the weight comes from unneeded de...### Objective
Provide a lightweight Batsim image for non-Nixed (yet) users (cf. #115).
### Problem
Batsim's closure (built from CI) weights 136 Mo…
The batsim package itself is a bit heavy, but most of the weight comes from unneeded dependencies.
![tree](/uploads/faa7a10ff31d2789c622502dd492d9c6/tree.png)
### Code to reproduce
- Generate Batsim in store: `nix-build --arg doCoverage false -A batsim -o out`
- Generate data about package sizes: `nix-store -qR out | sed -E 's/(.*)/du -bs \1/' | bash | sed -E 's/[[:space:]]+/ /g' | sed -E 'sW/nix/store([^-]*)-(.*)W\2W' > batsize.dat`
- Run R with some packages: `nix-shell -p R -p rPackages.readr -p rPackages.treemap --command R`
- Run this code:
```r
library(readr)
library(treemap)
data = read_delim('./batsize.dat', ' ', col_names=c('bytes', 'package'))
png(filename="tree.png", width=1200, height=1200)
treemap(data, index="package", vSize="bytes", type="index", fontsize.labels=20)
dev.off()
```Millian PoquetMillian Poquethttps://gitlab.inria.fr/batsim/batsim/-/issues/115Package Batsim in some distros2022-01-20T05:43:40+01:00Millian PoquetPackage Batsim in some distrosWe only provide Nix packages for now. Packaging Batsim in some distros would reduce the entry cost of some users.
NixOS
=====
Everything is already packaged, we just have to put these packages in nixpkgs then to push batsim.
We could a...We only provide Nix packages for now. Packaging Batsim in some distros would reduce the entry cost of some users.
NixOS
=====
Everything is already packaged, we just have to put these packages in nixpkgs then to push batsim.
We could also just stay in kapack (slowly moving stuff to our NUR).
Archlinux: Mostly Done
======================
All deps are now available (either in classical repos or in AUR).
A PKGBUILD similar to this one should work, I'll publish it for next Batsim release.
```
# Maintainer: Millian Poquet <millian.poquet@gmail.com>
pkgname=batsim
pkgver=b0f59fd35a49aa331877b30d544a1e3afa4f86ff
pkgrel=1
pkgdesc='An infrastructure simulator that enables the study of resource management techniques.'
arch=('i686' 'x86_64')
url='https://framagit.org/batsim/batsim'
license=('LGPL-3.0')
source=('https://framagit.org/batsim/batsim/-/archive/b0f59fd35a49aa331877b30d544a1e3afa4f86ff/batsim-b0f59fd35a49aa331877b30d544a1e3afa4f86ff.tar.gz')
depends=('simgrid' 'boost' 'intervalset' 'rapidjson' 'pugixml' 'zeromq' 'redox-pkgconfig' 'docopt')
makedepends=('meson' 'ninja' 'pkgconf' 'gtest')
md5sums=('0e8057d057e3d616918b9a27742e490b')
build() {
cd "${srcdir}/${pkgname}-${pkgver}"
meson --prefix=/usr build
ninja -C build
}
check() {
cd "${srcdir}/${pkgname}-${pkgver}"
meson test -C build
}
package() {
cd "${srcdir}/${pkgname}-${pkgver}"
DESTDIR="${pkgdir}" meson install -C build
rm -rf build
}
```
- [x] boost
- [x] rapidjson
- [x] simgrid: AUR https://aur.archlinux.org/packages/simgrid/
- [x] redox: AUR https://aur.archlinux.org/packages/redox-pkgconfig/
- [x] hiredis
- [x] libev
- [x] libzmq: zeromq
- [x] docopt
- [x] intervalset: AUR https://aur.archlinux.org/packages/intervalset
- [x] pugixml
Debian: **NOPE**
================
Dependencies:
- [x] simgrid: https://packages.debian.org/sid/libsimgrid-dev (3.25 should be available soon)
- [x] boost
- [x] rapidjson: https://packages.debian.org/sid/rapidjson-dev
- [ ] redox: NOPE
- [x] hiredis: https://packages.debian.org/sid/libhiredis-dev
- [x] libev: https://packages.debian.org/sid/libev-dev
- [x] libzmq
- [x] docopt: https://packages.debian.org/sid/libdocopt-dev
- [ ] intervalset: TO DO?
- [x] pugixml: https://packages.debian.org/sid/libpugixml-devMillian PoquetMillian Poquethttps://gitlab.inria.fr/batsim/batsim/-/issues/113CI : cachix push seems broken2020-02-19T15:46:41+01:00Millian PoquetCI : cachix push seems brokenJobs rebuild some dependencies (gtest, batexpe...) each time, which should not happen.Jobs rebuild some dependencies (gtest, batexpe...) each time, which should not happen.https://gitlab.inria.fr/batsim/batsim/-/issues/112EXECUTE_JOB: mapping with non-smpi profiles2022-01-20T05:37:57+01:00Millian PoquetEXECUTE_JOB: mapping with non-smpi profilesThe `mapping` optional field of the `EXECUTE_JOB` event should work for various job profiles, but current protocol doc says that it only works for `smpi` ones.
I think the doc is wrong but it would be nice to test (and put under CI) suc...The `mapping` optional field of the `EXECUTE_JOB` event should work for various job profiles, but current protocol doc says that it only works for `smpi` ones.
I think the doc is wrong but it would be nice to test (and put under CI) such cases.https://gitlab.inria.fr/batsim/batsim/-/issues/108Kill a sequence of delays: crash with "Internal error"2020-07-29T18:05:27+02:00Millian PoquetKill a sequence of delays: crash with "Internal error"**Describe the bug**
Killing a sequence of delays can make Batsim crash with an "Internal error"
**Provide information so the bug can be reproduced**
- Grab a copy of Batsim 19b6386 (framagit, pytest branch)
- Replace `pytest.xfail(...**Describe the bug**
Killing a sequence of delays can make Batsim crash with an "Internal error"
**Provide information so the bug can be reproduced**
- Grab a copy of Batsim 19b6386 (framagit, pytest branch)
- Replace `pytest.xfail("something seems wrong with sequences")` by `pass` in `./test/test_kill.py`.
- Run `nix-build ./release.nix -A integration_tests`
- Two tests from `test_kill.py` should fail as expected.
Test report can be opened with `firefox ./result/pytest_report.html`
**Logs**
```
...
[master_host:Scheduler REQ-REP:(4) 0.000045] [network/INFO] Received '{"now":10.000045,"events":[{"timestamp":0.000045,"type":"EXECUTE_JOB","data":{"job_id":"d3e758!1","alloc":"0"}},{"timestamp":10.000045,"type":"KILL_JOB","data":{"job_ids":["d3e758!1"]}}]}'
[Bourassa:job_d3e758!1:(5) 0.000060] [jobs_execution/INFO] Sleeping the whole task length
[Bourassa:job_d3e758!1:(5) 10.000060] [jobs_execution/INFO] Sleeping done
[Bourassa:job_d3e758!1:(5) 10.000060] [jobs_execution/INFO] Sleeping the whole task length
[master_host:killer_process:(6) 10.000060] /tmp/nix-build-batsim-3.0.0.drv-2/batsim/src/jobs.cpp:136: [root/CRITICAL] Internal error
(backtrace not set -- did you install Boost.Stacktrace?)
/home/carni/proj/batsim/test/test-out/kill-after10s-killer-small-delaysequences-noredis/cmd/batsim.bash: line 1: 15623 Aborted (core dumped) batsim -p '/home/carni/proj/batsim/platforms/small_platform.xml' -w '/home/carni/proj/batsim/workloads/test_sequence_delay.json' -e '/home/carni/proj/batsim/test/test-out/kill-after10s-killer-small-delaysequences-noredis/batres' --forward-profiles-on-submission
```
[pytest.log](/uploads/4d8fc33c42294b6c664be0c04c0c7097/pytest.log)https://gitlab.inria.fr/batsim/batsim/-/issues/106Remove old documentation and make Sphinx documentation the official one2020-02-19T15:47:04+01:00MERCIER MichaelRemove old documentation and make Sphinx documentation the official oneThe new Sphinx documentation in `./docs` is now much more mature and up-to-date then the old doc in `./doc` but readme file is still pointing on the old documentation.
We need to update the readme, move interesting part of the old to th...The new Sphinx documentation in `./docs` is now much more mature and up-to-date then the old doc in `./doc` but readme file is still pointing on the old documentation.
We need to update the readme, move interesting part of the old to the new and remove it.https://gitlab.inria.fr/batsim/batsim/-/issues/102Add replay of machine failures2019-01-28T13:27:52+01:00MOMMESSIN ClementAdd replay of machine failuresThat would be great to have a mechanism to replay failures of machines during simulation.
This could be implemented in a similar way as for static submission of jobs using workload input files.
An example of input JSON file:
```
{
...That would be great to have a mechanism to replay failures of machines during simulation.
This could be implemented in a similar way as for static submission of jobs using workload input files.
An example of input JSON file:
```
{
failures: [
{"machine_id" : 0, "failure_start" : 0, "failure_end": 1000},
{"machine_name" : "Foo", "failure_start" : 100, "failure_end" : 5000},
}
```
With for each item in the list the name or id of the SG host and the time interval where the failure appears.https://gitlab.inria.fr/batsim/batsim/-/issues/100Job ids appear twice in REGISTER_JOB2022-01-20T06:18:01+01:00MOMMESSIN ClementJob ids appear twice in REGISTER_JOBAs discussed during last meeting, the id of a job appears twice in a `REGISTER_JOB` event:
- a `job_id` field in the `data` field of the event
- an `id` field in the job description (`data[job]`) of the event
Second point: the `id` fiel...As discussed during last meeting, the id of a job appears twice in a `REGISTER_JOB` event:
- a `job_id` field in the `data` field of the event
- an `id` field in the job description (`data[job]`) of the event
Second point: the `id` field is sometimes of the form `wload_name!id` and sometimes just `id`.
The discussion finished with "we should get rid of the `id` field in the job description", is that correct?5.0.0https://gitlab.inria.fr/batsim/batsim/-/issues/99Improve column names of _jobs.csv2018-12-11T14:25:25+01:00Millian PoquetImprove column names of _jobs.csvAs @mmercier said, some fields of _job.csv are misleading and should be improved, such as `allocated_processors`.As @mmercier said, some fields of _job.csv are misleading and should be improved, such as `allocated_processors`.Batsim 3.0https://gitlab.inria.fr/batsim/batsim/-/issues/98Expose SimGrid log options to Batsim CLI2018-11-30T14:34:02+01:00Millian PoquetExpose SimGrid log options to Batsim CLISimilarly to `--sg-cfg`, we should expose a `--sg-log` command-line option.Similarly to `--sg-cfg`, we should expose a `--sg-log` command-line option.https://gitlab.inria.fr/batsim/batsim/-/issues/96Tutorials should be on periodic CI2019-08-12T14:19:29+02:00Millian PoquetTutorials should be on periodic CIThere is now at least one Batsim tutorial on the doc.
The tutorials are however not run by a CI yet, which will be very embarrassing with future breaks.
I propose to use a nightly CI for the tutorials, as it is important to make sure ...There is now at least one Batsim tutorial on the doc.
The tutorials are however not run by a CI yet, which will be very embarrassing with future breaks.
I propose to use a nightly CI for the tutorials, as it is important to make sure kapack remains consistent with them.
Running the tutorials in some CI jobs would not be very hard, as all code blocks are separated from the documentation itself.