autosubmit issueshttps://earth.bsc.es/gitlab/es/autosubmit/-/issues2024-03-27T10:20:44+01:00https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1263Autosubmit v4 interoperability with Leonardo2024-03-27T10:20:44+01:00dbeltranAutosubmit v4 interoperability with LeonardoThis issue is to recollect problems that may happen with the Leonardo platform.
* [ ] 2FA should be resolved in https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1133.
* [ ] Logs rework !409, this needs to be revised with 2FA before me...This issue is to recollect problems that may happen with the Leonardo platform.
* [ ] 2FA should be resolved in https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1133.
* [ ] Logs rework !409, this needs to be revised with 2FA before merging it.
Right now, this issue is stopped due to Leonardo being offline.
cc @mcastrildbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1262Pkl file and distributed DDBB (job_data_xxxx.db) not synchronized2024-03-22T11:23:15+01:00Luiggi Tenorio KuPkl file and distributed DDBB (job_data_xxxx.db) not synchronized
Hello @dbeltran and @bdepaula,
### Autosubmit Version
v3.14.0
### Expid affected(If applicable)
`a6zk` and `a70a`
### Summary
As mentioned in https://earth.bsc.es/gitlab/es/autosubmit_api/-/issues/31#note_266663, experiments `a6zk...
Hello @dbeltran and @bdepaula,
### Autosubmit Version
v3.14.0
### Expid affected(If applicable)
`a6zk` and `a70a`
### Summary
As mentioned in https://earth.bsc.es/gitlab/es/autosubmit_api/-/issues/31#note_266663, experiments `a6zk` and `a70a` don't have any content inside their `job_data_xxxx.db` and according to the `AS_LOGS/xxxx_xxxx_run.log` it is running. It seems that it just affected these 2 experiments that were copied from another experiment, so I guess is not something related to the version v3.14 in particular.
This is a problem for newer versions of the API that only rely on having the `job_data_xxxx.db` database synchronized and not a snapshot of the pkl file in the removed `as_times.db`. Instead, the API will return 0 total and completed jobs.https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1261Behaviour when parent task is FAILED and children is not COMPLETED2024-03-21T14:59:12+01:00Miguel Castrillomiguel.castrillo@bsc.esBehaviour when parent task is FAILED and children is not COMPLETEDHello @dbeltran
We discussed this when these kinds of dependencies were implemented.
It would be desirable that when the children TASK is already RUNNING because it's enabled by a RUNNING dependency, if the parent is FAILED the childr...Hello @dbeltran
We discussed this when these kinds of dependencies were implemented.
It would be desirable that when the children TASK is already RUNNING because it's enabled by a RUNNING dependency, if the parent is FAILED the children is set to WAITING. But maybe this is not necessarily true for all the cases.
What's the current behavior @dbeltran ?Autosubmit 4.1dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1260[DestinE] Communication between two or more different workflows2024-03-21T09:20:56+01:00dbeltran[DestinE] Communication between two or more different workflowsDestinE phase 2
Cc, @mcastril ,
This issue should contain ideas and implementations about communicating between different workflows.
* Dependencies? Complex(like a workflow graph) or simple( Run workflow b when workflow A does the s...DestinE phase 2
Cc, @mcastril ,
This issue should contain ideas and implementations about communicating between different workflows.
* Dependencies? Complex(like a workflow graph) or simple( Run workflow b when workflow A does the signal)?
* Launch command should be `autosubmit launch launch_suite.yml` or `autosubmit launch a001,a002,a003,a004`?
* Signal should be file-based? How do you generate the signal?
---------------------
* How to set and read configured signals
Simple
a000
```yaml
JOBS:
SECTION_A:
FILE:
...
SUITE:
METHOD: "ON_COMPLETED"
```
The signal, setting would be:
* Similar to the "checkpoint" function, we add the function generate_workflow_signal to all cmds
* Users call to add this %WORKFLOW_SIGNAL% in the templates they want and code the logic themselves
-----------
Complex
launch_suite.yml located somewhere outside the experiments
Using ASconfigparser, read as_conf.experiment_data["JOBS"] and add it as as_conf.experiment_data["JOBS_%EXPID%] afterwards read the launch_suite.yml
```yaml
JOBS_A000:
DEPENDENCIES:
jobs_a000.section_a:
job_names: (list)...
or
DATE: ... [n:m], any, all
MEMBER: ...[n:m], any, all
CHUNK: ...[n:m], any, all
SPLIT: ...[n:m], any, all
FROM_STATUS: "COMPLETED" or "RUNNING"
jobs_a000.section_b: # equals to put everything to ALL
jobs_a001.section_a:
jobs_a002.section_a:
JOBS_A001:
...
```
-------------
`autosubmit launch` needs:
* A way of detecting which workflows can be created and run. (through reading the yaml )
* A way of setting the dependencies between jobs of different workflows ( through reading the yaml)
* A way of detecting that some workflow has failed jobs.
* What to do? Stop all related experiments?
* A way of stopping and retaking the launch from the previous status.
* A way of detecting finished workflows so they don't run again.
I am not sure if I missed something.dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1259Error when running inspect and using horizontal wrappers2024-03-21T10:37:41+01:00Leo Arriolaleo.arriola@bsc.esError when running inspect and using horizontal wrappers
Hello @dbeltran and @bdepaula,
### Autosubmit Version
v4.1.2
### Expid affected(If applicable)
The experiment is **a0yd** the one I was using for the ICON transfer jobs. The experiment didn't have wrappers before, and I tried to add...
Hello @dbeltran and @bdepaula,
### Autosubmit Version
v4.1.2
### Expid affected(If applicable)
The experiment is **a0yd** the one I was using for the ICON transfer jobs. The experiment didn't have wrappers before, and I tried to add them afterwards.
### Which task has issues? Where is the log(If applicable)
* **Full_name**: a0yd_19910301_fc0_{X}_TRANSFER
* **Log_Path:**
### Summary
I'm not sure if it's only one bug or there are more layers to it. The bug or weird Autosubmit behaviour first appears when running inspect. After taking a long while, which I don't know if it's usual (I'm running a job with 1828 jobs though) Autosubmit crashes and reports the following [error.txt](/uploads/713c5cebe77ab43c57dcdaa8fc8285d6/error.txt) This is part of the error that appears.
The thing is, it breaks Autosubmit and then doesn't show much in the `ASLOGS/20240321_093513_inspect.log` logs.
After running inspect, you can see that the files are actually still produced. Yesterday I tried running the experiment, but what happened was that Autosubmit failed to be able to submit the wrapper jobs, and as it was set to “flexible” it directly just submitted all the jobs it could...
### Steps to reproduce
- access the climateDT VM (using the shared account)
- load module autosubmit/4.1.2
- autosubmit inspect a0yd
- autosubmit run a0yd
### What is the current bug behavior?
It breaks and doesn't allow to run using the horizontal wrappers.
### What is the expected correct behavior?
It creates the jobs well during inspect, and then it can submit wrappers taking into account the already completed jobs, etc...
### Relevant logs and/or screenshots(if applicable)
[error.txt](/uploads/713c5cebe77ab43c57dcdaa8fc8285d6/error.txt)
### Any other relevant information(if applicable)
()dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1257Fix BSC EasyBuild due to numpy and matplotlib2024-03-15T12:23:03+01:00Bruno de Paula KinoshitaFix BSC EasyBuild due to numpy and matplotlibHello @dbeltran logging this just in case we have another issue like this in the future.
We have an EasyConfig for EasyBuild used within the BSC for Autosubmit:
```python
# File: autosubmit-4.1.2-foss-2021b-Python-3.9.6.eb
easyblock = ...Hello @dbeltran logging this just in case we have another issue like this in the future.
We have an EasyConfig for EasyBuild used within the BSC for Autosubmit:
```python
# File: autosubmit-4.1.2-foss-2021b-Python-3.9.6.eb
easyblock = "PythonPackage"
name = 'autosubmit'
version = '4.1.2'
homepage = 'http://autosubmit.readthedocs.org'
description = """A versatile tool for managing ESM on HPC platforms"""
toolchain = {'name': 'foss', 'version': '2021b'}
#sources = [SOURCELOWER_TAR_GZ]
#source_urls = ['https://pypi.python.org/packages/source/a/autosubmit']
sources = ['autosubmit-4.1.2.tar.gz']
python = 'Python'
pyver = '3.9.6'
pyshortver = '3.6'
versionsuffix = '-%s-%s' % (python, pyver)
dependencies = [
(python, pyver),
('libpng','1.6.37'),
]
#use_pip = True
# override extensions sanity check, default filter that imports a Python module doesn't work here
exts_filter = ('', "")
sanity_check_paths = {
'files': ['bin/autosubmit'],
'dirs': [],
}
#sanity_check_commands = [('autosubmit -v','')]
moduleclass = 'tools'
```
Rebuilding it today at the BSC fails as EasyBuild's `eb` seems to pick any numpy greater than 1.26, as in our version range specification. However, different than `pip` that ignores alpha/beta by default, EasyBuild finds the Numpy2 beta release and tries to use it.
@dbeltran found this issue as Matplotlib fails to install due to numpy2 breaking changes.Autosubmit 4.1dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1256Autosubmit v3.15 interoperability with MN52024-03-14T15:54:42+01:00Manuel G. MarcianiAutosubmit v3.15 interoperability with MN5This is the issue to comment about the utilization of Autosubmit 3.15 and MN5.This is the issue to comment about the utilization of Autosubmit 3.15 and MN5.3.15.0dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1255[bug] Bug with CHECK: on_submission with horizontal wrappers2024-03-21T14:34:22+01:00Bruno de Paula Kinoshita[bug] Bug with CHECK: on_submission with horizontal wrappers@dbeltran , just creating an issue as this was reported by @agayayav in the DestinE workflow repository.
Here's what I did to reproduce the bug with the `master` branch, and affects latest version 4.1.2:
```git
(autosubmit4) bdepaula@b...@dbeltran , just creating an issue as this was reported by @agayayav in the DestinE workflow repository.
Here's what I did to reproduce the bug with the `master` branch, and affects latest version 4.1.2:
```git
(autosubmit4) bdepaula@bsces107921:~/Development/python/workspace/autosubmit$ git log -n 1
commit 75464cc8728cf8f9b768fb47ff4d9e5f03663251 (HEAD -> master, upstream/master, upstream/HEAD)
Author: Daniel Beltran Mora <daniel.beltran@bsc.es>
Date: Mon Mar 11 15:01:27 2024 +0100
changelog
```
```yaml
# File: minimal.yml
CONFIG:
AUTOSUBMIT_VERSION: "4.1.2"
MAXWAITINGJOBS: 20
TOTALJOBS: 20
SAFETYSLEEPTIME: 10
RETRIALS: 0
MAIL:
NOTIFICATIONS: False
TO:
STORAGE:
TYPE: pkl
COPY_REMOTE_LOGS: true
DEFAULT:
EXPID: "a005"
HPCARCH: "local"
EXPERIMENT:
DATELIST: '20000101'
MEMBERS: fc0
CHUNKSIZEUNIT: month
CHUNKSIZE: '4'
NUMCHUNKS: '2'
CHUNKINI: ''
CALENDAR: standard
PROJECT:
PROJECT_TYPE: none
PROJECT_DESTINATION: ''
GIT:
PROJECT_ORIGIN: ''
PROJECT_BRANCH: ''
PROJECT_COMMIT: ''
PROJECT_SUBMODULES: ''
FETCH_SINGLE_BRANCH: true
SVN:
PROJECT_URL: ''
PROJECT_REVISION: ''
LOCAL:
PROJECT_PATH: ''
PROJECT_FILES:
FILE_PROJECT_CONF: ''
FILE_JOBS_CONF: ''
JOB_SCRIPTS_TYPE: ''
RERUN:
RERUN: false
RERUN_JOBLIST: ''
PLATFORMS:
MARENOSTRUM4:
TYPE: slurm
HOST: mn1.bsc.es
PROJECT: bsc32
USER: bruno
QUEUE: debug
SCRATCH_DIR: /gpfs/scratch
ADD_PROJECT_TO_HOST: false
MAX_WALLCLOCK: 48:00
TEMP_DIR: ''
MAX_PROCESSORS: 128
JOBS:
TRANSFER:
PLATFORM: MARENOSTRUM4
PROCESSORS: 1
CHECK: on_submission
FILE: test.sh
WRAPPERS:
WRAPPER:
TYPE: horizontal
JOBS_IN_WRAPPER: TRANSFER
```
The key in the config above appear to be the `CHECK: on_submission`, and the `WRAPPER`.
To see the error message (hidden in the console by default, written to the log):
```bash
$ autosubmit create -cw a005 -np && autosubmit -lc DEBUG inspect a005
Checking configuration files...
Expdef config file is correct
Platforms sections: OK
Jobs sections OK
wrappers OK
Autosubmit general sections OK
Configuration files OK
The Experiment name is: a005
Sleep: 10
Loading JobList
Load finished
Creating jobs...
Creating TRANSFER jobs
Adding dependencies to the graph..
Changes detected, calculating dependencies
Adding dependencies for TRANSFER jobs
Adding dependencies to the job..
Transitive reduction...
Looking for edgeless jobs...
Loading JobList
Load finished
Creating jobs...
Creating TRANSFER jobs
Adding dependencies to the graph..
Changes detected, calculating dependencies
Adding dependencies for TRANSFER jobs
Adding dependencies to the job..
Transitive reduction...
Looking for edgeless jobs...
Length of the jobs list: 1
Sleep: 10
Starting to generate cmd scripts
Generating cmd scripts only for selected jobs
[WARNING] Generating the auxiliary job_list used for the -CW flag.
[WARNING] Aux Job_list was generated successfully
Loading parameters...
Parameters load.
Checking scripts...
1 of 1 checked
Scripts OK
Updating FAILED jobs
Updating WAITING jobs
Setting job: a005_TRANSFER status to: READY (all parents completed)...
Update finished
Loading parameters...
Parameters load.
Number of jobs available: 20
Number of jobs ready: 1
Jobs ready for MARENOSTRUM4: 1
Traceback (most recent call last):
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 2382, in submit_ready_jobs
packages_to_submit = JobPackager(as_conf, platform, job_list, hold=hold).build_packages()
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/job/job_packager.py", line 468, in build_packages
built_packages_tmp = self._build_horizontal_packages(jobs, wrapper_limits, section,wrapper_info=current_info)
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/job/job_packager.py", line 536, in _build_horizontal_packages
package_jobs = horizontal_packager.build_horizontal_package()
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/job/job_packager.py", line 848, in build_horizontal_package
if job.total_processors == "":
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/job/job.py", line 782, in total_processors
return int(self.processors)
TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/bdepaula/Development/python/workspace/autosubmit/bin/autosubmit", line 57, in main
return_value = Autosubmit.parse_args()
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 693, in parse_args
return Autosubmit.inspect(args.expid, args.list, args.filter_chunks, args.filter_status,
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 1516, in inspect
Autosubmit.generate_scripts_andor_wrappers(
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 1607, in generate_scripts_andor_wrappers
Autosubmit.submit_ready_jobs(as_conf, job_list, platforms_to_test, packages_persistence, True,
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 2417, in submit_ready_jobs
raise AutosubmitCritical("This seems like a bug in the code, please contact AS developers", 7070, str(e))
log.log.AutosubmitCritical:
Trace: int() argument must be a string, a bytes-like object or a number, not 'NoneType'
[CRITICAL] This seems like a bug in the code, please contact AS developers [eCode=7070]
More info at https://autosubmit.readthedocs.io/en/master/troubleshooting/error-codes.html
```
Will link with the existing merge request.Autosubmit 4.1dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1254[enhancement] Check that the AS project path is a directory, not a file2024-03-12T11:02:37+01:00Bruno de Paula Kinoshita[enhancement] Check that the AS project path is a directory, not a fileI was testing a workflow today for Oriol, and accidentally pasted the location of a file. `autosubmit create` fails with:
```bash
(autosubmit4) bdepaula@bsces107921:~/Development/python/workspace/autosubmit$ autosubmit create a004
/home...I was testing a workflow today for Oriol, and accidentally pasted the location of a file. `autosubmit create` fails with:
```bash
(autosubmit4) bdepaula@bsces107921:~/Development/python/workspace/autosubmit$ autosubmit create a004
/home/bdepaula/mambaforge/envs/autosubmit4/bin/autosubmit:4: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
__import__('pkg_resources').require('autosubmit==4.1.2')
Autosubmit is running with 4.1.2
Preparing .lock file to avoid multiple instances with same expid.
Copying /home/bdepaula/autosubmit/project/test.sh into /home/bdepaula/autosubmit/a004/proj
cp: cannot stat '/home/bdepaula/autosubmit/project/test.sh/*': Not a directory
Traceback (most recent call last):
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 4925, in _copy_code
output = subprocess.check_output(
File "/home/bdepaula/mambaforge/envs/autosubmit4/lib/python3.8/subprocess.py", line 415, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
File "/home/bdepaula/mambaforge/envs/autosubmit4/lib/python3.8/subprocess.py", line 516, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command 'cp -R /home/bdepaula/autosubmit/project/test.sh/* /home/bdepaula/autosubmit/a004/proj/local_project' returned non-zero exit status 1.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 4627, in create
if not Autosubmit._copy_code(as_conf, expid, as_conf.experiment_data.get("PROJECT",{}).get("PROJECT_TYPE","none"), False):
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 4932, in _copy_code
raise AutosubmitCritical(
log.log.AutosubmitCritical:
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/bdepaula/Development/python/workspace/autosubmit/bin/autosubmit", line 57, in main
return_value = Autosubmit.parse_args()
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 703, in parse_args
return Autosubmit.create(args.expid, args.noplot, args.hide, args.output, args.group_by, args.expand,
File "/home/bdepaula/Development/python/workspace/autosubmit/autosubmit/autosubmit.py", line 4798, in create
raise AutosubmitCritical(e.message, e.code, e.trace)
log.log.AutosubmitCritical:
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/bdepaula/Development/python/workspace/autosubmit/bin/autosubmit", line 37, in exit_from_error
Log.debug(traceback.format_exc())
File "/home/bdepaula/mambaforge/envs/autosubmit4/lib/python3.8/site-packages/log/log.py", line 295, in debug
Log.log.log(Log.DEBUG, msg.format(*args))
IndexError: Replacement index 0 out of range for positional args tuple
[CRITICAL] Can not copy /home/bdepaula/autosubmit/project/test.sh into /home/bdepaula/autosubmit/a004/proj. Exiting... [eCode=7063]
More info at https://autosubmit.readthedocs.io/en/master/troubleshooting/error-codes.htm
```
We can improve it by simply checking if the `Path` object exists and is a directory, and failing with a nicer message to the user.https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1253Time limit failure after a failure of the platform2024-03-14T12:00:27+01:00Francesc Roura Adseriasfrancesc.roura@bsc.esTime limit failure after a failure of the platform
Hello @dbeltran and @bdepaula,
### Autosubmit Version
4.0.104 (taken from the minimal.yml, Jeisson to confirm)
### Expid affected(If applicable)
`a12l`
### Which task has issues? Where is the log(If applicable)
* **Full_name**: a1...
Hello @dbeltran and @bdepaula,
### Autosubmit Version
4.0.104 (taken from the minimal.yml, Jeisson to confirm)
### Expid affected(If applicable)
`a12l`
### Which task has issues? Where is the log(If applicable)
* **Full_name**: a12l_20091024_fc0_4_1_OPA
* **Log_Path:** /appl/AS/AUTOSUBMIT_DATA/a12l/tmp/LOG_a12l/a12l_20091024_fc0_4_1_OPA.20240311105238.err
*
### Summary
Job killed due to time limit after platform failure `[ERROR] Submission failed, this can be due a failure on the platform [eCode=6015]`
### Steps to reproduce
- apparently error from machine, not reproducible
### What is the current bug behavior?
After that error, autosubmit is checking config files again, but then the experiments that were already submitted do not run anymore, until they reach the wallclock limit, when they are set to failed.
### What is the expected correct behavior?
According to documentation, this comes from a failed submission, but apparently the jobs were already submitted. I expected an automatic solution from AS:
![Screenshot_from_2024-03-12_09-53-02](/uploads/bc17c4db06bc4fb7a61a401cf987bc53/Screenshot_from_2024-03-12_09-53-02.png)
### Relevant logs and/or screenshots(if applicable)
```
[ERROR] Trace: Jobs_id []
[ERROR] Submission failed, this can be due a failure on the platform [eCode=6015]
Storing failed job count...
Storing failed job count...done
Waiting 15 seconds before continue
Checking configuration files...
Platforms sections: OK
Jobs sections OK
Autosubmit general sections OK
```
and then
```
+ load_environment_gsv /projappl/project_465000454/ a0fe
+ set +xuve
The following modules were not unloaded:
(Use "module --force purge" to unload all):
1) ModuleLabel/label 6) craype-accel-host
2) lumi-tools/23.11 7) libfabric/1.15.2.0
3) init-lumi/0.2 8) craype-network-ofi
4) LUMI/23.09 9) xpmem/2.5.2-2.4_3.50__gd0f7936.shasta
5) craype-x86-milan 10) partition/C
The following sticky modules could not be reloaded:
1) lumi-tools
slurmstepd: error: *** JOB 6428756 ON nid002595 CANCELLED AT 2024-03-11T11:11:54 DUE TO TIME LIMIT ***
```
### Any other relevant information(if applicable)
Full report from @jjavier [here](https://earth.bsc.es/gitlab/digital-twins/de_340/workflow/-/issues/72#note_263331)
()https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1252Issue while setstatus2024-03-14T10:47:30+01:00Francesc Roura Adseriasfrancesc.roura@bsc.esIssue while setstatus
Hello @dbeltran and @bdepaula,
### Autosubmit Version
v4.1.0-beta-dev9
### Expid affected(If applicable)
a12q
### Which task has issues? Where is the log(If applicable)
The setstatus command
```
autosubmit setstatus a12q -fl "a12q...
Hello @dbeltran and @bdepaula,
### Autosubmit Version
v4.1.0-beta-dev9
### Expid affected(If applicable)
a12q
### Which task has issues? Where is the log(If applicable)
The setstatus command
```
autosubmit setstatus a12q -fl "a12q_20200101_fc0_1_1_DN a12q_REMOTE_SETUP a12q_20200101_fc0_1_2_DN a12q_20200101_fc0_1_3_DN a12q_20200101_fc0_1_4_DN a12q_20200101_fc0_1_5_DN a12q_20200101_fc0_1_6_DN a12q_20200101_fc0_1_7_DN a12q_20200101_fc0_1_8_DN a12q_20200101_fc0_1_9_DN a12q_20200101_fc0_1_10_DN a12q_20200101_fc0_1_11_DN a12q_20200101_fc0_1_12_DN a12q_20200101_fc0_1_13_DN a12q_20200101_fc0_1_14_DN a12q_20200101_fc0_1_15_DN a12q_20200101_fc0_2_1_DN a12q_20200101_fc0_2_2_DN a12q_20200101_fc0_2_3_DN a12q_20200101_fc0_2_4_DN a12q_20200101_fc0_2_5_DN a12q_20200101_fc0_2_6_DN a12q_20200101_fc0_2_7_DN a12q_20200101_fc0_2_8_DN a12q_20200101_fc0_2_9_DN a12q_20200101_fc0_2_10_DN a12q_20200101_fc0_2_11_DN a12q_20200101_fc0_2_12_DN a12q_20200101_fc0_2_13_DN a12q_20200101_fc0_2_14_DN a12q_20200101_fc0_2_15_DN a12q_20200101_fc0_3_1_DN a12q_20200101_fc0_3_2_DN a12q_20200101_fc0_3_3_DN a12q_20200101_fc0_3_4_DN a12q_20200101_fc0_3_5_DN a12q_20200101_fc0_3_6_DN a12q_20200101_fc0_3_7_DN a12q_20200101_fc0_3_8_DN a12q_20200101_fc0_3_9_DN a12q_20200101_fc0_3_10_DN a12q_20200101_fc0_3_11_DN a12q_20200101_fc0_3_12_DN a12q_20200101_fc0_3_13_DN a12q_20200101_fc0_3_14_DN a12q_20200101_fc0_3_15_DN a12q_LOCAL_SETUP a12q_SYNCHRONIZE a12q_20200101_fc0_1_1_OPA_AQUA_1 a12q_20200101_fc0_1_2_OPA_AQUA_1 a12q_20200101_fc0_1_3_OPA_AQUA_1 a12q_20200101_fc0_1_4_OPA_AQUA_1 a12q_20200101_fc0_1_5_OPA_AQUA_1 a12q_20200101_fc0_1_6_OPA_AQUA_1 a12q_20200101_fc0_1_7_OPA_AQUA_1 a12q_20200101_fc0_1_8_OPA_AQUA_1 a12q_20200101_fc0_1_9_OPA_AQUA_1 a12q_20200101_fc0_1_10_OPA_AQUA_1 a12q_20200101_fc0_1_11_OPA_AQUA_1 a12q_20200101_fc0_1_12_OPA_AQUA_1 a12q_20200101_fc0_1_13_OPA_AQUA_1 a12q_20200101_fc0_1_14_APP_AQUA a12q_20200101_fc0_1_14_OPA_AQUA_1 a12q_20200101_fc0_1_15_APP_AQUA a12q_20200101_fc0_1_15_OPA_AQUA_1 a12q_20200101_fc0_2_1_APP_AQUA a12q_20200101_fc0_2_1_OPA_AQUA_1 a12q_20200101_fc0_2_2_APP_AQUA a12q_20200101_fc0_2_2_OPA_AQUA_1 a12q_20200101_fc0_2_3_APP_AQUA a12q_20200101_fc0_2_3_OPA_AQUA_1 a12q_20200101_fc0_2_4_APP_AQUA a12q_20200101_fc0_2_4_OPA_AQUA_1 a12q_20200101_fc0_2_5_APP_AQUA a12q_20200101_fc0_2_5_OPA_AQUA_1 a12q_20200101_fc0_2_6_APP_AQUA a12q_20200101_fc0_2_6_OPA_AQUA_1 a12q_20200101_fc0_2_7_APP_AQUA a12q_20200101_fc0_2_7_OPA_AQUA_1 a12q_20200101_fc0_2_8_APP_AQUA a12q_20200101_fc0_2_8_OPA_AQUA_1 a12q_20200101_fc0_2_9_APP_AQUA a12q_20200101_fc0_2_9_OPA_AQUA_1 a12q_20200101_fc0_2_10_APP_AQUA a12q_20200101_fc0_2_10_OPA_AQUA_1 a12q_20200101_fc0_2_11_APP_AQUA a12q_20200101_fc0_2_11_OPA_AQUA_1 a12q_20200101_fc0_2_12_APP_AQUA a12q_20200101_fc0_2_12_OPA_AQUA_1 a12q_20200101_fc0_2_13_APP_AQUA a12q_20200101_fc0_2_13_OPA_AQUA_1 a12q_20200101_fc0_2_14_APP_AQUA a12q_20200101_fc0_2_14_OPA_AQUA_1 a12q_20200101_fc0_2_15_APP_AQUA a12q_20200101_fc0_2_15_OPA_AQUA_1 a12q_20200101_fc0_3_1_APP_AQUA a12q_20200101_fc0_3_1_OPA_AQUA_1 a12q_20200101_fc0_3_2_APP_AQUA a12q_20200101_fc0_3_2_OPA_AQUA_1 a12q_20200101_fc0_3_3_APP_AQUA a12q_20200101_fc0_3_3_OPA_AQUA_1 a12q_20200101_fc0_3_4_APP_AQUA a12q_20200101_fc0_3_4_OPA_AQUA_1 a12q_20200101_fc0_3_5_APP_AQUA a12q_20200101_fc0_3_5_OPA_AQUA_1 a12q_20200101_fc0_3_6_APP_AQUA a12q_20200101_fc0_3_6_OPA_AQUA_1 a12q_20200101_fc0_3_7_APP_AQUA a12q_20200101_fc0_3_7_OPA_AQUA_1 a12q_20200101_fc0_3_8_APP_AQUA a12q_20200101_fc0_3_8_OPA_AQUA_1 a12q_20200101_fc0_3_9_APP_AQUA a12q_20200101_fc0_3_9_OPA_AQUA_1 a12q_20200101_fc0_3_10_APP_AQUA a12q_20200101_fc0_3_10_OPA_AQUA_1 a12q_20200101_fc0_3_11_APP_AQUA a12q_20200101_fc0_3_11_OPA_AQUA_1 a12q_20200101_fc0_3_12_APP_AQUA a12q_20200101_fc0_3_12_OPA_AQUA_1 a12q_20200101_fc0_3_13_APP_AQUA a12q_20200101_fc0_3_13_OPA_AQUA_1 a12q_20200101_fc0_3_14_APP_AQUA a12q_20200101_fc0_3_14_OPA_AQUA_1 a12q_20200101_fc0_3_15_APP_AQUA a12q_20200101_fc0_3_15_OPA_AQUA_1" -t COMPLETED -s -nt -np
```
### Summary
While trying to change the status of multiple jobs, I get an error (so )
### Steps to reproduce
this is the command, from the GUI @ltenorio
```
autosubmit setstatus a12q -fl "a12q_20200101_fc0_1_1_DN a12q_REMOTE_SETUP a12q_20200101_fc0_1_2_DN a12q_20200101_fc0_1_3_DN a12q_20200101_fc0_1_4_DN a12q_20200101_fc0_1_5_DN a12q_20200101_fc0_1_6_DN a12q_20200101_fc0_1_7_DN a12q_20200101_fc0_1_8_DN a12q_20200101_fc0_1_9_DN a12q_20200101_fc0_1_10_DN a12q_20200101_fc0_1_11_DN a12q_20200101_fc0_1_12_DN a12q_20200101_fc0_1_13_DN a12q_20200101_fc0_1_14_DN a12q_20200101_fc0_1_15_DN a12q_20200101_fc0_2_1_DN a12q_20200101_fc0_2_2_DN a12q_20200101_fc0_2_3_DN a12q_20200101_fc0_2_4_DN a12q_20200101_fc0_2_5_DN a12q_20200101_fc0_2_6_DN a12q_20200101_fc0_2_7_DN a12q_20200101_fc0_2_8_DN a12q_20200101_fc0_2_9_DN a12q_20200101_fc0_2_10_DN a12q_20200101_fc0_2_11_DN a12q_20200101_fc0_2_12_DN a12q_20200101_fc0_2_13_DN a12q_20200101_fc0_2_14_DN a12q_20200101_fc0_2_15_DN a12q_20200101_fc0_3_1_DN a12q_20200101_fc0_3_2_DN a12q_20200101_fc0_3_3_DN a12q_20200101_fc0_3_4_DN a12q_20200101_fc0_3_5_DN a12q_20200101_fc0_3_6_DN a12q_20200101_fc0_3_7_DN a12q_20200101_fc0_3_8_DN a12q_20200101_fc0_3_9_DN a12q_20200101_fc0_3_10_DN a12q_20200101_fc0_3_11_DN a12q_20200101_fc0_3_12_DN a12q_20200101_fc0_3_13_DN a12q_20200101_fc0_3_14_DN a12q_20200101_fc0_3_15_DN a12q_LOCAL_SETUP a12q_SYNCHRONIZE a12q_20200101_fc0_1_1_OPA_AQUA_1 a12q_20200101_fc0_1_2_OPA_AQUA_1 a12q_20200101_fc0_1_3_OPA_AQUA_1 a12q_20200101_fc0_1_4_OPA_AQUA_1 a12q_20200101_fc0_1_5_OPA_AQUA_1 a12q_20200101_fc0_1_6_OPA_AQUA_1 a12q_20200101_fc0_1_7_OPA_AQUA_1 a12q_20200101_fc0_1_8_OPA_AQUA_1 a12q_20200101_fc0_1_9_OPA_AQUA_1 a12q_20200101_fc0_1_10_OPA_AQUA_1 a12q_20200101_fc0_1_11_OPA_AQUA_1 a12q_20200101_fc0_1_12_OPA_AQUA_1 a12q_20200101_fc0_1_13_OPA_AQUA_1 a12q_20200101_fc0_1_14_APP_AQUA a12q_20200101_fc0_1_14_OPA_AQUA_1 a12q_20200101_fc0_1_15_APP_AQUA a12q_20200101_fc0_1_15_OPA_AQUA_1 a12q_20200101_fc0_2_1_APP_AQUA a12q_20200101_fc0_2_1_OPA_AQUA_1 a12q_20200101_fc0_2_2_APP_AQUA a12q_20200101_fc0_2_2_OPA_AQUA_1 a12q_20200101_fc0_2_3_APP_AQUA a12q_20200101_fc0_2_3_OPA_AQUA_1 a12q_20200101_fc0_2_4_APP_AQUA a12q_20200101_fc0_2_4_OPA_AQUA_1 a12q_20200101_fc0_2_5_APP_AQUA a12q_20200101_fc0_2_5_OPA_AQUA_1 a12q_20200101_fc0_2_6_APP_AQUA a12q_20200101_fc0_2_6_OPA_AQUA_1 a12q_20200101_fc0_2_7_APP_AQUA a12q_20200101_fc0_2_7_OPA_AQUA_1 a12q_20200101_fc0_2_8_APP_AQUA a12q_20200101_fc0_2_8_OPA_AQUA_1 a12q_20200101_fc0_2_9_APP_AQUA a12q_20200101_fc0_2_9_OPA_AQUA_1 a12q_20200101_fc0_2_10_APP_AQUA a12q_20200101_fc0_2_10_OPA_AQUA_1 a12q_20200101_fc0_2_11_APP_AQUA a12q_20200101_fc0_2_11_OPA_AQUA_1 a12q_20200101_fc0_2_12_APP_AQUA a12q_20200101_fc0_2_12_OPA_AQUA_1 a12q_20200101_fc0_2_13_APP_AQUA a12q_20200101_fc0_2_13_OPA_AQUA_1 a12q_20200101_fc0_2_14_APP_AQUA a12q_20200101_fc0_2_14_OPA_AQUA_1 a12q_20200101_fc0_2_15_APP_AQUA a12q_20200101_fc0_2_15_OPA_AQUA_1 a12q_20200101_fc0_3_1_APP_AQUA a12q_20200101_fc0_3_1_OPA_AQUA_1 a12q_20200101_fc0_3_2_APP_AQUA a12q_20200101_fc0_3_2_OPA_AQUA_1 a12q_20200101_fc0_3_3_APP_AQUA a12q_20200101_fc0_3_3_OPA_AQUA_1 a12q_20200101_fc0_3_4_APP_AQUA a12q_20200101_fc0_3_4_OPA_AQUA_1 a12q_20200101_fc0_3_5_APP_AQUA a12q_20200101_fc0_3_5_OPA_AQUA_1 a12q_20200101_fc0_3_6_APP_AQUA a12q_20200101_fc0_3_6_OPA_AQUA_1 a12q_20200101_fc0_3_7_APP_AQUA a12q_20200101_fc0_3_7_OPA_AQUA_1 a12q_20200101_fc0_3_8_APP_AQUA a12q_20200101_fc0_3_8_OPA_AQUA_1 a12q_20200101_fc0_3_9_APP_AQUA a12q_20200101_fc0_3_9_OPA_AQUA_1 a12q_20200101_fc0_3_10_APP_AQUA a12q_20200101_fc0_3_10_OPA_AQUA_1 a12q_20200101_fc0_3_11_APP_AQUA a12q_20200101_fc0_3_11_OPA_AQUA_1 a12q_20200101_fc0_3_12_APP_AQUA a12q_20200101_fc0_3_12_OPA_AQUA_1 a12q_20200101_fc0_3_13_APP_AQUA a12q_20200101_fc0_3_13_OPA_AQUA_1 a12q_20200101_fc0_3_14_APP_AQUA a12q_20200101_fc0_3_14_OPA_AQUA_1 a12q_20200101_fc0_3_15_APP_AQUA a12q_20200101_fc0_3_15_OPA_AQUA_1" -t COMPLETED -s -nt -np
```
### What is the current bug behavior?
Error message, status not changed successfully
### What is the expected correct behavior?
Status changed successfully
### Relevant logs and/or screenshots(if applicable)
```
CHANGED: job: a12q_20200101_fc0_2_11_OPA_AQUA_1 status to: COMPLETED
CHANGED: job: a12q_20200101_fc0_2_7_OPA_AQUA_1 status to: COMPLETED
[ERROR] Trace: Unknown failure while saving the job_list
[CRITICAL] unsupported format string passed to NoneType.__format__ [eCode=6040]
More info at https://autosubmit.readthedocs.io/en/master/troubleshooting/error-codes.html
```
### Any other relevant information(if applicable)
()https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1251[enhancement] Allow recovery to update current running/ready jobs2024-03-14T10:25:34+01:00Bruno de Paula Kinoshita[enhancement] Allow recovery to update current running/ready jobsFrom Slack thread with @dbeltran and @mcastril , and from issue in DestinE from @kkeller.
From @dbeltran:
>So, we're missing an option in the recovery to update current waiting/ready jobs and ignore the other status.
We could modify A...From Slack thread with @dbeltran and @mcastril , and from issue in DestinE from @kkeller.
From @dbeltran:
>So, we're missing an option in the recovery to update current waiting/ready jobs and ignore the other status.
We could modify Autosubmit to allow `recovery` to be used when you have jobs running, without cancelling them. From @mcastril's comments:
- We have to consider how to map active jobs and workflow tasks, e.g. when job ids do not correspond to the ones in pkl, who can we know which ones are submitted, running...
- We have to find a solution that does not involve submitting jobs if we already have one running
- Maybe we could look at the scheduler output if there are active jobs, and see if all match the job ids in the DB, and update their statuses. If there's a mismatch, then users would have to force `-f`
We also need to verify if there was no other reason why this feature was coded like this.
(Tried to summarize the comments here, feel free to edit if I added anything wrongly :thumbsup: )Autosubmit 4.1https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1250Add -fst flag to setstatus?2024-03-14T10:18:42+01:00Aina Gayaaina.gayayavila@bsc.esAdd -fst flag to setstatus?Hello @dbeltran and @bdepaula,
Just a suggestion: for the DestinE I think it would be useful to have the possibility to **combine "fs" and "ft" in the setstatus command**. Similarly as `-ftc`, maybe `-fst` could accept "`JOBNAME, STATUS...Hello @dbeltran and @bdepaula,
Just a suggestion: for the DestinE I think it would be useful to have the possibility to **combine "fs" and "ft" in the setstatus command**. Similarly as `-ftc`, maybe `-fst` could accept "`JOBNAME, STATUS`" (I'm thinking in `APP, WAITING`) as input. When they needed to stop the applications part of the workflow, they suspended all the APPs jobs, without taking into account that some were already completed, just because it was the easiest thing for them in a "critical" time, and then they wanted to recover the completed jobs from the HPC but it was not possible because a SIM chunk was running (https://earth.bsc.es/gitlab/digital-twins/de_340/project_management/-/issues/632#note_263189).
With this option, they could easily just suspend the non-completed jobs.
Thanks!!
()Autosubmit 4.1https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1249[docs] Update information about restricting jobs in paralell2024-03-11T11:44:19+01:00Bruno de Paula Kinoshita[docs] Update information about restricting jobs in paralellThis is Slack chat with @otinto that also confirmed with @dbeltran;
We have this page with information about how to control the number of jobs waiting or running in parallel for an experiment: https://autosubmit.readthedocs.io/en/master...This is Slack chat with @otinto that also confirmed with @dbeltran;
We have this page with information about how to control the number of jobs waiting or running in parallel for an experiment: https://autosubmit.readthedocs.io/en/master/userguide/configure/develop_a_project.html#controlling-the-number-of-active-concurrent-tasks-in-an-experiment
Pre 4.1, users had to duplicate the platform to have a second identical platform but with a different limits for jobs.
From 4.1 onward, the JOB can have the same settings from the platform (right @dbeltran ?).
We need to add that to this page, check if the Variables page also needs to be updated, and add a note for pre 4.1 users.
Thanks @otinto & @dbeltran !Autosubmit 4.1https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1248[enhancement] Provide an easier way to write start date intervals2024-03-21T08:23:14+01:00Bruno de Paula Kinoshita[enhancement] Provide an easier way to write start date intervalsHello @dbeltran
This is from a question from @pabretonniere that I think other users could have too.
If a user wants to use tens or hundreds of start dates, writing each individual start date in the `DATELIST` YAML entry is probably a ...Hello @dbeltran
This is from a question from @pabretonniere that I think other users could have too.
If a user wants to use tens or hundreds of start dates, writing each individual start date in the `DATELIST` YAML entry is probably a bit annoying.
We could provide some syntactic sugar here, maybe offer something like `START/END`, or `START/END/STEP`. Cylc uses ISO8601 for dates and periods, and I think ecFlow follows that for dates (not the period part).
Maybe we could use something like that — an open standard, instead of having to come up with some syntax for that.
Cheershttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1246Autosubmit v4 interoperability with MN52024-03-14T15:54:42+01:00Bruno de Paula KinoshitaAutosubmit v4 interoperability with MN5Following @dbeltran's suggestion from today's meeting, this is a placeholder to collect issues related to MN5 and AS.Following @dbeltran's suggestion from today's meeting, this is a placeholder to collect issues related to MN5 and AS.Autosubmit 4.1dbeltrandbeltranhttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1244[docker] Fix the Dockerfile for latest code2024-03-06T17:26:49+01:00Bruno de Paula Kinoshita[docker] Fix the Dockerfile for latest codeHello @dbeltran , @mcastril
I was testing a build of Autosubmit using GitHub Actions, and added the exact line from the `dockerfiles/README.md`, that we sent to EDITO-Infra team around August last year.
The command failed on GitHub, a...Hello @dbeltran , @mcastril
I was testing a build of Autosubmit using GitHub Actions, and added the exact line from the `dockerfiles/README.md`, that we sent to EDITO-Infra team around August last year.
The command failed on GitHub, and when I tried locally I got the exact same error. Might be something easy, but we better fix it sooner rather than later (before we have an upcoming deadline for EDITO).
```bash
kinow@ranma:~/Development/python/workspace/autosubmit/dockerfiles$ docker build \
-t ${USER}/autosubmit:4.0.84-bullseye-slim \
-t ${USER}/autosubmit:latest \
.
[+] Building 28.0s (20/25) docker:default
=> [internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 6.59kB 0.0s
=> [internal] load metadata for docker.io/library/debian:bullseye-slim 2.1s
=> [internal] load metadata for docker.io/mambaorg/micromamba:1.4.9-bull 2.2s
=> [auth] mambaorg/micromamba:pull token for registry-1.docker.io 0.0s
=> [auth] library/debian:pull token for registry-1.docker.io 0.0s
=> [internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [internal] preparing inline document 0.0s
=> [micromamba 1/1] FROM docker.io/mambaorg/micromamba:1.4.9-bullseye-s 17.2s
=> => resolve docker.io/mambaorg/micromamba:1.4.9-bullseye-slim@sha256:1 0.0s
=> => sha256:2083d5e3acfffcaca91475053252e8f3816a55e4400 2.37kB / 2.37kB 0.0s
=> => sha256:389c26cacad934fc7dd8fcfd259f44791ce175a9cb4 5.74kB / 5.74kB 0.0s
=> => sha256:1b459e9c6968a32ae5a4321a1f14dfbb8e9f1cb57d8 2.36kB / 2.36kB 0.0s
=> => sha256:072e55e492c8f53448eed58aa077e344eccc7b4 115.22kB / 115.22kB 1.3s
=> => sha256:14726c8f78342865030f97a8d3492e2d1a68fbd2 31.42MB / 31.42MB 14.7s
=> => sha256:2712dc90660a8ae3d5fea88bd5afd6e1063a9a66668 5.70MB / 5.70MB 7.6s
=> => sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d 32B / 32B 8.1s
=> => sha256:3ff1700158b11b432c1646cdcb66e7c2170a58a17bf7ef0 524B / 524B 8.9s
=> => sha256:492af156d32e36bc874a7fda25517dd9cf7477f35b50939 285B / 285B 9.4s
=> => sha256:f44123b607d41a6ff5e3e2934fcb8f3b6121750c95 4.55kB / 4.55kB 10.1s
=> => sha256:bf9cfdb98097403328f35cda87e4956b1e9c748a5de09c 683B / 683B 10.7s
=> => sha256:87bcfcd4e3d942fd007f334bb07c32b0147ad0f5c5bb2f 641B / 641B 11.2s
=> => sha256:fc3edf513487fc003623af5b960c953f3f2e9ffd4a43aa 345B / 345B 11.5s
=> => extracting sha256:14726c8f78342865030f97a8d3492e2d1a68fbd22778f9a3 1.8s
=> => extracting sha256:072e55e492c8f53448eed58aa077e344eccc7b40c5ea9c70 0.0s
=> => extracting sha256:2712dc90660a8ae3d5fea88bd5afd6e1063a9a666685ca3b 0.2s
=> => extracting sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6 0.0s
=> => extracting sha256:3ff1700158b11b432c1646cdcb66e7c2170a58a17bf7ef0c 0.0s
=> => extracting sha256:492af156d32e36bc874a7fda25517dd9cf7477f35b509392 0.0s
=> => extracting sha256:f44123b607d41a6ff5e3e2934fcb8f3b6121750c954020a7 0.0s
=> => extracting sha256:bf9cfdb98097403328f35cda87e4956b1e9c748a5de09c16 0.0s
=> => extracting sha256:87bcfcd4e3d942fd007f334bb07c32b0147ad0f5c5bb2ff1 0.0s
=> => extracting sha256:fc3edf513487fc003623af5b960c953f3f2e9ffd4a43aaab 0.0s
=> [stage-1 1/17] FROM docker.io/library/debian:bullseye-slim@sha256:c 17.6s
=> => resolve docker.io/library/debian:bullseye-slim@sha256:c6d9e246479d 0.0s
=> => sha256:c6d9e246479d56687c1a579a7a0336956a5ce6f2bc2 1.85kB / 1.85kB 0.0s
=> => sha256:49caa2d0610fd478d9aa58fa9dd449d7d76a201bc502a00 529B / 529B 0.0s
=> => sha256:71f8bbcd77b8db961035cc16424629f1f7482fdf3fe 1.46kB / 1.46kB 0.0s
=> => sha256:5d0aeceef7eeb53c3f853fb229ea7fd13a5a56f4 31.42MB / 31.42MB 15.6s
=> => extracting sha256:5d0aeceef7eeb53c3f853fb229ea7fd13a5a56f4ba371ca4 1.7s
=> [stage-1 2/17] COPY --from=micromamba /bin/micromamba /bin/micromamb 0.1s
=> [stage-1 3/17] COPY --from=micromamba /usr/local/bin/_activate_curre 0.0s
=> [stage-1 4/17] COPY --from=micromamba /usr/local/bin/_dockerfile_she 0.0s
=> [stage-1 5/17] COPY --from=micromamba /usr/local/bin/_entrypoint.sh 0.0s
=> [stage-1 6/17] COPY --from=micromamba /usr/local/bin/_dockerfile_ini 0.0s
=> [stage-1 7/17] COPY --from=micromamba /usr/local/bin/_dockerfile_set 0.0s
=> [stage-1 8/17] RUN /usr/local/bin/_dockerfile_initialize_user_accoun 0.4s
=> [stage-1 9/17] RUN if grep -q '^ID=alpine$' /etc/os-release; then 0.4s
=> [stage-1 10/17] WORKDIR /app/autosubmit/ 0.1s
=> [stage-1 11/17] RUN mkdir -pv "/app/autosubmit//logs" && mkdir -p 0.3s
=> ERROR [stage-1 12/17] RUN apt update && apt install -y bash 6.2s
------
> [stage-1 12/17] RUN apt update && apt install -y bash=5.1-2+deb11u1 ca-certificates=20210119 curl=7.74.0-1.3+deb11u7 desktop-file-utils=0.26-1 dialog=1.3-20201126-1 graphviz=2.42.2-5 iputils-ping=3:20210202-1 less=551-2 net-tools=1.60+git20181103.0eebece-1 openssh-server=1:8.4p1-5+deb11u1 python3-tk=3.9.2-1 sqlite3=3.34.1-3 sudo=1.9.5p2-3+deb11u1 vim=2:8.2.2434-3+deb11u1 xdg-utils=1.1.3-4.1 && update-ca-certificates && apt-get clean && rm -rf /var/lib/apt/lists/*:
0.380
0.380 WARNING: apt does not have a stable CLI interface. Use with caution in scripts.
0.380
0.482 Get:1 http://deb.debian.org/debian bullseye InRelease [116 kB]
0.600 Get:2 http://deb.debian.org/debian-security bullseye-security InRelease [48.4 kB]
0.639 Get:3 http://deb.debian.org/debian bullseye-updates InRelease [44.1 kB]
0.713 Get:4 http://deb.debian.org/debian bullseye/main amd64 Packages [8068 kB]
3.204 Get:5 http://deb.debian.org/debian-security bullseye-security/main amd64 Packages [269 kB]
3.247 Get:6 http://deb.debian.org/debian bullseye-updates/main amd64 Packages [18.8 kB]
4.330 Fetched 8564 kB in 4s (2181 kB/s)
4.330 Reading package lists...
5.011 Building dependency tree...
5.152 Reading state information...
5.173 All packages are up to date.
5.183
5.183 WARNING: apt does not have a stable CLI interface. Use with caution in scripts.
5.183
5.190 Reading package lists...
5.823 Building dependency tree...
5.963 Reading state information...
6.111 E: Version '7.74.0-1.3+deb11u7' for 'curl' was not found
6.111 E: Version '1:8.4p1-5+deb11u1' for 'openssh-server' was not found
------
Dockerfile:96
--------------------
95 | # TODO: add something like xpdf=3.04+git20210103-3 if GUI/X is needed.
96 | >>> RUN apt update && \
97 | >>> apt install -y \
98 | >>> bash=5.1-2+deb11u1 \
99 | >>> ca-certificates=20210119 \
100 | >>> curl=7.74.0-1.3+deb11u7 \
101 | >>> desktop-file-utils=0.26-1 \
102 | >>> dialog=1.3-20201126-1 \
103 | >>> graphviz=2.42.2-5 \
104 | >>> iputils-ping=3:20210202-1 \
105 | >>> less=551-2 \
106 | >>> net-tools=1.60+git20181103.0eebece-1 \
107 | >>> openssh-server=1:8.4p1-5+deb11u1 \
108 | >>> python3-tk=3.9.2-1 \
109 | >>> sqlite3=3.34.1-3 \
110 | >>> sudo=1.9.5p2-3+deb11u1 \
111 | >>> vim=2:8.2.2434-3+deb11u1 \
112 | >>> xdg-utils=1.1.3-4.1 && \
113 | >>> update-ca-certificates && \
114 | >>> apt-get clean && \
115 | >>> rm -rf /var/lib/apt/lists/*
116 |
--------------------
ERROR: failed to solve: process "/usr/local/bin/_dockerfile_shell.sh apt update && apt install -y bash=5.1-2+deb11u1 ca-certificates=20210119 curl=7.74.0-1.3+deb11u7 desktop-file-utils=0.26-1 dialog=1.3-20201126-1 graphviz=2.42.2-5 iputils-ping=3:20210202-1 less=551-2 net-tools=1.60+git20181103.0eebece-1 openssh-server=1:8.4p1-5+deb11u1 python3-tk=3.9.2-1 sqlite3=3.34.1-3 sudo=1.9.5p2-3+deb11u1 vim=2:8.2.2434-3+deb11u1 xdg-utils=1.1.3-4.1 && update-ca-certificates && apt-get clean && rm -rf /var/lib/apt/lists/*" did not complete successfully: exit code: 100
```https://earth.bsc.es/gitlab/es/autosubmit/-/issues/1243[enhancement] Make autosubmit run detach by default, avoid needing nohup/nohu...2024-03-06T09:08:44+01:00Bruno de Paula Kinoshita[enhancement] Make autosubmit run detach by default, avoid needing nohup/nohup.logHello @dbeltran and @mcastril ,
At the moment users launch Autosubmit with `autosubmit run`, which blocks the terminal. The recommended way to launch it to the background is with `nohup`. It's in our documentation, and that's how most u...Hello @dbeltran and @mcastril ,
At the moment users launch Autosubmit with `autosubmit run`, which blocks the terminal. The recommended way to launch it to the background is with `nohup`. It's in our documentation, and that's how most users launch it.
Some issues with this approach are
a) only the user launching the command has access to the nohup.log (when a robot account is used, AS developers not using the account are "locked out" and cannot see that file, regardless of umask/acl/linux permissions)
b) when the user forgets to `nohup`, they need to kill the command and launch it again (even if it might be doable to send it to the background, it is probably safer to avoid it)
I suggest we copy the behavior of Cylc here, and `autosubmit run` automatically sends the command to the background, and the logs to a file in the AS log files. That should simplify operation a bit, and allow users to run it without having to use `nohup`.
Furthermore, we can also copy the `--no-detach` flag so that `autosubmit run --no-detach $expid` keeps the terminal blocked, if the user so desires.Bruno de Paula KinoshitaBruno de Paula Kinoshitahttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1242Autosubmit does not warn the user when using a valid extended header/tailer o...2024-03-05T16:40:20+01:00Pablo Goitiapablo.goitia@bsc.esAutosubmit does not warn the user when using a valid extended header/tailer on a "none" projectThis is just an issue to remember ourselves (@mgimenez and I) to add a message when a specific situation occurs using an extended header/tailer.
### Autosubmit Version
Any version of Autosubmit 4, but also Autosubmit 3.15 is susceptibl...This is just an issue to remember ourselves (@mgimenez and I) to add a message when a specific situation occurs using an extended header/tailer.
### Autosubmit Version
Any version of Autosubmit 4, but also Autosubmit 3.15 is susceptible to.
### Summary
When using an extended header or tailer, but the project is of type "none", Autosubmit should throw a message notifying that the script is valid but the project's type is not, and it must be changed (to "local", for example). This would be useful for cases in which someone is building an experiment from scratch but doesn't know about project types, like me (discovering the reason because the extended header was not being included in the cmd files of my experiment was a true headache :)
### Steps to reproduce
Just create a new experiment and add a custom header without changing the project type.
### What is the current behavior?
Autosubmit runs the experiment without warning the user.
### What is the expected correct behavior?
Autosubmit should warn about it. It is a small fix that would be useful both for beginners and experimented developers with little auto-modelling knowledge.Pablo Goitiapablo.goitia@bsc.esPablo Goitiapablo.goitia@bsc.eshttps://earth.bsc.es/gitlab/es/autosubmit/-/issues/1241Add possibility to set --gpus-per-node2024-03-07T10:18:27+01:00Aina Gayaaina.gayayavila@bsc.esAdd possibility to set --gpus-per-node
Hello @dbeltran and @bdepaula (it's me again),
### Autosubmit Version
4.0.104
Low priority, but I wanted to ask for the possibility to set --gpus-per-node under JOBS/PLATFORMS. We are setting it as a custom directive, but sometimes w...
Hello @dbeltran and @bdepaula (it's me again),
### Autosubmit Version
4.0.104
Low priority, but I wanted to ask for the possibility to set --gpus-per-node under JOBS/PLATFORMS. We are setting it as a custom directive, but sometimes we have issues (that we can overcome).
Thanks!!
()