bwHPC Wiki - Recent changes [en]

SDS@hd/SV Management

H Schumacher — Fri, 09 Oct 2026 11:46:19 GMT

added instructions for role changes

← Older revision		Revision as of 13:46, 9 October 2026
Line 63:		Line 63:
	* ...add and remove Users from allocations except themselves or the PI.		* ...add and remove Users from allocations except themselves or the PI.
	* ...change the roles of Users on project and allocation level (Project: User <-> PM; SV: None <-> Guest).		* ...change the roles of Users on project and allocation level (Project: User <-> PM; SV: None <-> Guest).
			*: → Go to the Users table, click the action item for the selected user and change the role.

	* ...enable/disable notifications for other Users.		* ...enable/disable notifications for other Users.

Running Calculations

A Flachmueller — Fri, 09 Oct 2026 10:31:24 GMT

How To Run Jobs Efficiently

← Older revision		Revision as of 12:31, 9 October 2026
Line 70:		Line 70:
	Running calculations on an HPC node consumes a lot of energy. To make the most of the available resources and keep cluster and energy use as efficient as possible please also see our advice for		Running calculations on an HPC node consumes a lot of energy. To make the most of the available resources and keep cluster and energy use as efficient as possible please also see our advice for

	→ '''[[Efficient Cluster Usage]]'''		→ '''[[Energy Efficient Cluster Usage]]'''

	To optimize the job efficiency, it is very helpful to check which resources a job has actually used.		To optimize the job efficiency, it is very helpful to check which resources a job has actually used.

SDS@hd/SV Management

H Schumacher — Fri, 09 Oct 2026 09:16:39 GMT

added information to storage place management

← Older revision		Revision as of 11:16, 9 October 2026
Line 244:		Line 244:
	== Storage Space Management ==		== Storage Space Management ==

	At the ~~moment~~ you can't see how much storage space is left. ~~We are working on including this information.~~		At the acllocation page at bwServices-Management, you can see how much storage space is left.

	To keep the data hot, you should regularly check the following points:		To keep the data hot, you should regularly check the following points:
	* Make sure that temporary data gets removed.		* Make sure that temporary data gets removed:
			** Delete temporary files, for example in the .cache folder. Other folders starting with a dot might contain temporary files as well, for example .local/share/Trash.
⚫	* Make sure that no data from finished projects is stored. You might want to archive those with one of the archiving services listed on the [https://wiki.bwhpc.de/e/Main_Page Main Page].
			** Use the cleaning commands by your used software (e.g. conda).
			** Delete folders with temporary data created by your used software (e.g. nextflow).
		⚫	* Make sure that no data from finished projects is stored. You might want to archive those with one of the archiving services listed at the [https://wiki.bwhpc.de/e/Main_Page Main Page].
	* If someone has left the storage project, make sure that the PI has access to the data and the data is still hot.		* If someone has left the storage project, make sure that the PI has access to the data and the data is still hot.

Helix/bwVisu/JupyterLab

H Schumacher — Thu, 08 Oct 2026 17:58:47 GMT

Find the kernel section korrigiert

← Older revision		Revision as of 19:58, 8 October 2026
(One intermediate revision by the same user not shown)
Line 104:		Line 104:
	==== Step 1: Create the kernel ====		==== Step 1: Create the kernel ====
	'''Using venv or Conda'''		'''Using venv or Conda'''

	For a '''venv''' or '''Conda''' environment, the environment has to be activated before creating the kernel.

	<ol>		<ol>
Line 111:		Line 109:
	<li>Install the ipykernel package:		<li>Install the ipykernel package:
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	# for venv or conda:
	pip install ipykernel		pip install ipykernel
		⚫	</syntaxhighlight>
	# for uv:
			</li>
⚫	~~uv add ipykernel~~</syntaxhighlight~~></li~~>
	<li>Register the virtual environment as custom kernel to Jupyter.		<li>Register the virtual environment as custom kernel to Jupyter.
	* If you are the only person using the environment:		* If you are the only person using the environment:
	<syntaxhighlight lang="bash">python3 -m ipykernel install --user --name=<kernel_name></syntaxhighlight>		<syntaxhighlight lang="bash">python3 -m ipykernel install --user --name=<kernel_name></syntaxhighlight>
⚫	The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.
	* If you installed the environment in a shared place and want to have the kernel there as well:		* If you installed the environment in a shared place and want to have the kernel there as well:
	<syntaxhighlight lang="bash">python3 -m ipykernel install --prefix <path_to_kernel_folder> --name=<kernel_name>		<syntaxhighlight lang="bash">python3 -m ipykernel install --prefix <path_to_kernel_folder> --name=<kernel_name>
Line 133:		Line 129:
	* If you are the only person using the environment:		* If you are the only person using the environment:
	<syntaxhighlight lang="bash">uv run ipython kernel install --user --env VIRTUAL_ENV $(pwd)/.venv --name=<kernel_name></syntaxhighlight>		<syntaxhighlight lang="bash">uv run ipython kernel install --user --env VIRTUAL_ENV $(pwd)/.venv --name=<kernel_name></syntaxhighlight>
	The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.
	* If you installed the environment in a shared place and want to have the kernel there as well:		* If you installed the environment in a shared place and want to have the kernel there as well:
	<syntaxhighlight lang="bash">uv run ipython kernel install --prefix <path_to_kernel_folder> --env VIRTUAL_ENV $(pwd)/.venv --name=<kernel_name>		<syntaxhighlight lang="bash">uv run ipython kernel install --prefix <path_to_kernel_folder> --env VIRTUAL_ENV $(pwd)/.venv --name=<kernel_name>
Line 142:		Line 137:
	==== Step 2: Find the kernel ====		==== Step 2: Find the kernel ====

			* Private kernel:
⚫	The kernel can ~~then~~ be found under <code>path_to_kernel_folder/share/jupyter/kernels/<kernel_name></code>. As long as the same <code>path_to_kernel_folder</code> is used, all kernels will be saved next to each other in "kernels".
		⚫	*: The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.
			* Shared kernel:
		⚫	*: The kernel can be found under <code>path_to_kernel_folder/share/jupyter/kernels/<kernel_name></code>. As long as the same <code>path_to_kernel_folder</code> is used, all kernels will be saved next to each other in "kernels".

Development/Python

H Schumacher — Thu, 08 Oct 2026 17:43:30 GMT

Ergänzungen und Korrekturen bei uv

← Older revision		Revision as of 19:43, 8 October 2026
Line 255:		Line 255:
	→ '''[https://docs.astral.sh/uv/concepts/projects/ projects]'''		→ '''[https://docs.astral.sh/uv/concepts/projects/ projects]'''
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
			# Initialize project within current folder
			uv init
			# or initialize project in subfolder <application-name>
	uv init <application_name>		uv init <application_name>
	# If you want to create a python package:		# or if you want to create a python package:
	uv init --package <application_name>		uv init --package <application_name>
	</syntaxhighlight>		</syntaxhighlight>
Line 262:		Line 265:
	When you have an existing project, you can create a virtual environment at .venv with a specific python version as follows:		When you have an existing project, you can create a virtual environment at .venv with a specific python version as follows:
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
			# create the virtual environment and save it in folder $UV_PROJECT_ENVIRONMENT (.venv by default)
			uv venv
			# or create it in folder <env_name>
			uv venv <env_name>
			# or create it and install a specific python version
	uv python list # get available versions		uv python list # get available versions
	uv venv --python 3.13		uv venv --python 3.13
			# or create it by adding your first package
			uv add <package>
	</syntaxhighlight>		</syntaxhighlight>
	~~A specific name or path can be given instead of "venv" as well.~~ If the python version is not available on the system, uv downloads it.		If the python version is not available on the system, uv downloads it. See here for details about the [https://docs.astral.sh/uv/pip/environments/#discovery-of-python-environments discovery of python environments].

	==== Usage ====		==== Usage ====
Line 277:		Line 287:
	'''Note:''' You should load all cluster modules before creation/activation of a virtual environment. Due to the way venv, and therefore also uv, recovers the original paths upon deactivation we recommend '''not to load/unload modules''' while a virtual environment is active.		'''Note:''' You should load all cluster modules before creation/activation of a virtual environment. Due to the way venv, and therefore also uv, recovers the original paths upon deactivation we recommend '''not to load/unload modules''' while a virtual environment is active.

			To add packages:
	If you activated the virtual environment, you can install packagages as usual. Otherwise, you need to add "uv" before the command to run it within the virtual environment:
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	uv add <package_name>		uv add <package_name>
Line 287:		Line 297:
	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
	uv run <file.py>		uv run <file.py>
			</syntaxhighlight>

			Syncing and locking happens automatically. To be explicit about it use the following commands
			<syntaxhighlight lang="bash">
			# To update the lock file (e.g. after changing the pyproject.toml by hand):
			uv lock
			# To upgrade all packages
			uv lock --upgrade
			# To sync the project e.g. after changing the current python version via the ".python-version" file.
	</syntaxhighlight>		</syntaxhighlight>

Helix/bwVisu/JupyterLab

H Schumacher — Thu, 08 Oct 2026 17:35:58 GMT

Added uv instructions

← Older revision		Revision as of 19:35, 8 October 2026
Line 65:		Line 65:
	</li>		</li>
	<li>Activate your environment:		<li>Activate your environment:
	<syntaxhighlight lang="bash">conda activate <~~myenv~~></syntaxhighlight></li>		<syntaxhighlight lang="bash">conda activate <env_name></syntaxhighlight></li>
	<li>Install your packages:		<li>Install your packages:
	<syntaxhighlight lang="bash">conda install <~~mypackage~~></syntaxhighlight></li>		<syntaxhighlight lang="bash">conda install <packagename></syntaxhighlight></li>
	<li> [[#Create_an_IPython_Kernel \| Create an IPython kernel]]</li>		<li> [[#Create_an_IPython_Kernel \| Create an IPython kernel]]</li>
	</ol>		</ol>
Line 76:		Line 76:
	Steps for creating a '''uv''' virtual environment:		Steps for creating a '''uv''' virtual environment:
	<ol style="list-style-type: decimal;">		<ol style="list-style-type: decimal;">
	<li>Open a terminal.</li>		<li>Open a terminal</li>
	<li>Create a new virtual environment:		<li>Create a new project and virtual environment:
	<syntaxhighlight lang="bash"~~>uv venv <env_parent_dir>/<env_name> --python <python version></syntaxhighlight~~>		<syntaxhighlight lang="bash">
			uv init <env_parent_dir>/<env_name>
			uv venv <env_parent_dir>/<env_name> --python <python version></syntaxhighlight>
	* <code>env_parent_dir</code> is the path to the folder where the virtual environment shall be created. Relative paths can be used.		* <code>env_parent_dir</code> is the path to the folder where the virtual environment shall be created. Relative paths can be used.
	* The <code>--python</code> option can be omitted if the default Python version should be used.		* The <code>--python <python_version></code> option can be omitted if the default Python version should be used.
	* Caution: If you want to share the environment with others, make sure to ~~already create it in the shared place.~~		* Caution: If you want to share the environment with others, make sure to
			** Set your $HOME to the shared place before creating the environment: <code>HOME=<env_name></code>
			** Create the environment directly in the shared place.
	</li>		</li>
	<li>Install packages into the environment:		<li>Install packages into the environment:
	<syntaxhighlight lang="bash">uv ~~pip install --python <env_parent_dir>/<env_name>/bin/python~~ <packagename></syntaxhighlight></li>		<syntaxhighlight lang="bash">uv add <packagename></syntaxhighlight></li>
	<li> [[#Create_an_IPython_Kernel \| Create an IPython kernel]]</li>		<li> [[#Create_an_IPython_Kernel \| Create an IPython kernel]]</li>
	</ol>		</ol>
Line 95:		Line 99:
	conda_kernels		conda_kernels

	=== Create a kernel from a ~~venv or Conda~~ virtual environment ===		=== Create a kernel from a virtual environment ===
			Please follow these instructions to create and find the kernel.

			==== Step 1: Create the kernel ====
			'''Using venv or Conda'''

	For a '''venv''' or '''Conda''' environment, the environment has to be activated before creating the kernel.		For a '''venv''' or '''Conda''' environment, the environment has to be activated before creating the kernel.
Line 102:		Line 110:
	<li>Activate the virtual environment.</li>		<li>Activate the virtual environment.</li>
	<li>Install the ipykernel package:		<li>Install the ipykernel package:
	<syntaxhighlight lang="bash"~~>pip install ipykernel</syntaxhighlight></li~~>		<syntaxhighlight lang="bash">
			# for venv or conda:
			pip install ipykernel
			# for uv:
			uv add ipykernel</syntaxhighlight></li>
	<li>Register the virtual environment as custom kernel to Jupyter.		<li>Register the virtual environment as custom kernel to Jupyter.
	* If you are the only person using the environment:		* If you are the only person using the environment:
Line 108:		Line 120:
	The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.		The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.
	* If you installed the environment in a shared place and want to have the kernel there as well:		* If you installed the environment in a shared place and want to have the kernel there as well:
	<syntaxhighlight lang="bash">python3 -m ipykernel install --prefix <path_to_kernel_folder> --name=<kernel_name~~></syntaxhighlight~~>		<syntaxhighlight lang="bash">python3 -m ipykernel install --prefix <path_to_kernel_folder> --name=<kernel_name>
			</syntaxhighlight>
⚫	The kernel can then be found under <code>path_to_kernel_folder/share/jupyter/kernels/<kernel_name></code>. As long as the same <code>path_to_kernel_folder</code> is used, all kernels will be saved next to each other in "kernels".
	</li>		</li>
	</ol>		</ol>

			'''Using uv'''
	=== Create a kernel from a uv virtual environment ===

	A kernel can also be created from a <code>uv</code> virtual environment. The environment does not have to be activated.

	<ol>		<ol>
	<li>Install the ~~<code>~~ipykernel~~</code>~~ package ~~into the <code>uv</code> environment~~:		<li>Install the ipykernel package:
	<syntaxhighlight lang="bash"~~>uv pip install --python <env_parent_dir>/<env_name>/bin/python ipykernel</syntaxhighlight></li~~>		<syntaxhighlight lang="bash">
			uv add ipykernel</syntaxhighlight></li>
	<li>Register the environment as a custom kernel ~~using <code>uv~~ ~~run</code>:~~		<li>Register the virtual environment as custom kernel to Jupyter.
	* If you are the only person using the environment:		* If you are the only person using the environment:
	<syntaxhighlight lang="bash">uv run ~~--directory~~ ~~<env_parent_dir>/<env_name>~~ ~~python~~ -m ~~ipykernel~~ ~~install~~ ~~--user~~ --name=<kernel_name></syntaxhighlight>		<syntaxhighlight lang="bash">uv run ipython kernel install --user --env VIRTUAL_ENV $(pwd)/.venv --name=<kernel_name></syntaxhighlight>
	The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.		The kernel can be found under <code>~/.local/share/jupyter/kernels/</code>.
	* If you installed the environment in a shared place and want to have the kernel there as well:		* If you installed the environment in a shared place and want to have the kernel there as well:
	<syntaxhighlight lang="bash">uv run ~~--directory <env_parent_dir>/<env_name> python -m~~ ~~ipykernel~~ install --prefix <path_to_kernel_folder> --name=<kernel_name~~></syntaxhighlight~~>		<syntaxhighlight lang="bash">uv run ipython kernel install --prefix <path_to_kernel_folder> --env VIRTUAL_ENV $(pwd)/.venv --name=<kernel_name>
			</syntaxhighlight>
	The kernel can then be found under <code>path_to_kernel_folder/share/jupyter/kernels/<kernel_name></code>. As long as the same <code>path_to_kernel_folder</code> is used, all kernels will be saved next to each other in "kernels".
	</li>		</li>
	</ol>		</ol>

			==== Step 2: Find the kernel ====

		⚫	The kernel can then be found under <code>path_to_kernel_folder/share/jupyter/kernels/<kernel_name></code>. As long as the same <code>path_to_kernel_folder</code> is used, all kernels will be saved next to each other in "kernels".


	=== Multi-Language Support ===		=== Multi-Language Support ===

Registration/bwForCluster/RV/Management

K Siegmund — Wed, 07 Oct 2026 15:16:34 GMT

← Older revision		Revision as of 17:16, 7 October 2026
Line 72:		Line 72:
	*: → We would appreciate a short note about the reason. Some examples: "We didn't need the cluster much", "The publication is still work in progress", "We'd appreciate some help for getting started with the cluster usage".		*: → We would appreciate a short note about the reason. Some examples: "We didn't need the cluster much", "The publication is still work in progress", "We'd appreciate some help for getting started with the cluster usage".
	* We have only preprints so far.		* We have only preprints so far.
			*: → Please report them, when when they are fully published. You can mention, that a certain number of publications is in preparation.
	*: → You can report them already.
	* The purpose and resource needs of the RV have changed.		* The purpose and resource needs of the RV have changed.
	*: → ~~While~~ ~~it won't change anything for you, we still appreciate it when~~ the ~~information get updated~~ via the RV extension form.		*: → Please update the resources via the RV extension form.
	* We forgot to acknowledge the cluster in most of the publications.		* We forgot to acknowledge the cluster in most of the publications.
	*: → That's unfortunate but please report them nevertheless. You can save us the hassle of checking in detail when you provide us with an additional confirmation that the cluster was indeed used. For example "Some acknowledgements are missing but I confirm that the cluster usage was relevant for the publications nevertheless".		*: → That's unfortunate but please report them nevertheless. You can save us the hassle of checking in detail when you provide us with an additional confirmation that the cluster was indeed used. For example "Some acknowledgements are missing but I confirm that the cluster usage was relevant for the publications nevertheless". Please make sure the cluster is properly cited in the next publications.
	* I fear that the RV gets deactivated before the extension application gets accepted.		* I fear that the RV gets deactivated before the extension application gets accepted.
	*: → Depending on the cluster the access will still be possible for a while even if the RV is over its due date. But no new members can join while the extension is pending.		*: → Depending on the cluster the access will still be possible for a while even if the RV is over its due date. But no new members can join while the extension is pending.

Help talk:Editor's Guide

K Siegmund — Wed, 07 Oct 2026 14:56:38 GMT

Created page with " Vorschlag: ---- Lifecycle Management & Verification Articles should not stay unverified for longer than half a year. The wiki editorial team will coordinate the effort of reviewing pages. Pages kept to retain historic information must have a tag <code><nowiki>{{History}}</nowiki></code> ---- Diskussion nächste Wiki-Vk Lifecycle Management und überprüfen von Seiten ~~~~"

New page

Vorschlag:
----
Lifecycle Management & Verification
Articles should not stay unverified for longer than half a year. The wiki editorial team will coordinate the effort of reviewing pages. Pages kept to retain historic information must have a tag <code><nowiki>{{History}}</nowiki></code>
----
Diskussion nächste Wiki-Vk Lifecycle Management und überprüfen von Seiten
[[User:K Siegmund|K Siegmund]] ([[User talk:K Siegmund|talk]]) 16:56, 7 October 2026 (CEST)

Help:Editor's Guide

K Siegmund — Wed, 07 Oct 2026 14:55:38 GMT

to talk page

← Older revision		Revision as of 16:55, 7 October 2026
Line 70:		Line 70:

	* Internal vs External Links: Whenever something is in the wiki, an internal link, e.g. <code>[[Registration]]</code> should be used. The single brackets are for external links only.		* Internal vs External Links: Whenever something is in the wiki, an internal link, e.g. <code>[[Registration]]</code> should be used. The single brackets are for external links only.

	== Lifecycle Management & Verification ==

	Articles should not stay unverified for longer than half a year. The wiki editorial team will coordinate the effort of reviewing pages. Pages kept to retain historic information must have a tag <code><nowiki>{{History}}</nowiki></code>

Slurm

K Siegmund — Wed, 07 Oct 2026 14:47:35 GMT

K Siegmund deleted page Slurm request Alex. Not needed right now

Batch Systems

A Flachmueller — Wed, 07 Oct 2026 14:08:45 GMT

← Older revision		Revision as of 16:08, 7 October 2026
(One intermediate revision by the same user not shown)
Line 7:		Line 7:
	More information can be found on the clusters' respective wikipages.		More information can be found on the clusters' respective wikipages.

	* [[BwUniCluster3.0/Running_Jobs#Running_Jobs\|bwUniCluster 3.0]]		* [[BwUniCluster3.0/Running_Jobs#Running_Jobs\|bwUniCluster 3.0 Slurm]]
	* [[BinAC2/Slurm\|BinAC2]]		* [[BinAC2/Slurm\|BinAC2 Slurm]]
	* [[Helix/Slurm\|Helix]]		* [[Helix/Slurm\|Helix Slurm]]
	* [[BwForCluster_JUSTUS_2_Slurm_HOWTO\|~~JUSTUS~~ 2]]		* JUSTUS 2 Slurm ([[BwForCluster_JUSTUS_2_Slurm_HOWTO\|basic (sbatch)]] / [[JUSTUS2/Jobscripts:_Running_Your_Calculations\|more (salloc)]])
	* [[NEMO2/Slurm\|NEMO2]]		* [[NEMO2/Slurm\|NEMO2]]

BwUniCluster3.0/Running Jobs

P Schuhmacher — Wed, 07 Oct 2026 12:41:43 GMT

Development Queues

← Older revision		Revision as of 14:41, 7 October 2026
Line 159:		Line 159:
	\| mem-per-cpu=2000mb		\| mem-per-cpu=2000mb
	\|		\|
	\| time=30, nodes=1, mem=380000mb, ntasks-per-node=96, (threads-per-core=2)		\| time=30, nodes=2, mem=380000mb, ntasks-per-node=96, (threads-per-core=2)
	\|-		\|-
	\| <code>dev_gpu_h100</code>		\| <code>dev_gpu_h100</code>

Login Node Policies

A Flachmueller — Wed, 07 Oct 2026 12:09:45 GMT

Overview page of login node policies to use as link in the E-Learning course

New page

The bwHPC cluster have policies regarding allowed and forbidden tasks on the login nodes. Heavy resource usage on the login nodes slows down cluster access and interactivity of the login nodes, so make sure to comply with the respective cluster policy!

==Clusters' Login Node Policies==
* [[BwUniCluster3.0/Login#Allowed_Activities_on_Login_Nodes|bwUniCluster3.0]]
* [[Helix/Login#Allowed_Activities_on_Login_Nodes|Helix]]
* [[BinAC2/Getting_Started#Batch_System_Basics|BinAC2]]
* [[JUSTUS2/Policy_Agreement|JUSTUS2]]
* [[NEMO2/Login#Allowed_Activities_on_Login_Nodes|NEMO2]]

Helix/Slurm

H Schumacher — Wed, 07 Oct 2026 10:22:35 GMT

small correction

← Older revision		Revision as of 12:22, 7 October 2026
Line 188:		Line 188:
	→ '''[[Helix/bwVisu \| bwVisu]]'''		→ '''[[Helix/bwVisu \| bwVisu]]'''

	Interactive jobs must NOT run on the login nodes, however resources for interactive jobs can be requested using ~~srun~~. The following example requests an interactive session on 1 core for 2 hours:		Interactive jobs must NOT run on the login nodes, however resources for interactive jobs can be requested using salloc. The following example requests an interactive session on 1 core for 2 hours:

	<syntaxhighlight lang="bash">salloc --partition=cpu-single --ntasks=1 --time=2:00:00 </syntaxhighlight>		<syntaxhighlight lang="bash">salloc --partition=cpu-single --ntasks=1 --time=2:00:00 </syntaxhighlight>

Batch Systems

A Flachmueller — Wed, 07 Oct 2026 09:39:50 GMT

Slurm HPC Workload Manager

← Older revision		Revision as of 11:39, 7 October 2026
Line 1:		Line 1:
	= Slurm HPC Workload Manager =		= Slurm HPC Workload Manager =
			Currently all bwHPC Clusters are using Slurm as Batch System and Resource Management System.
	== Specification ==		== Specification ==
	Slurm is an open source, fault-tolerant, and highly scalable cluster management and job scheduling system for large and small Linux clusters. Slurm requires no kernel modifications for its operation and is relatively self-contained. As a cluster workload manager, Slurm has three key functions. First, it allocates exclusive and/or non-exclusive access to resources (compute nodes) to users for some duration of time so they can perform work. Second, it provides a framework for starting, executing, and monitoring work (normally a parallel job) on the set of allocated nodes. Finally, it arbitrates contention for resources by managing a queue of pending work.		Slurm is an open source, fault-tolerant, and highly scalable cluster management and job scheduling system for large and small Linux clusters. Slurm requires no kernel modifications for its operation and is relatively self-contained. As a cluster workload manager, Slurm has three key functions. First, it allocates exclusive and/or non-exclusive access to resources (compute nodes) to users for some duration of time so they can perform work. Second, it provides a framework for starting, executing, and monitoring work (normally a parallel job) on the set of allocated nodes. Finally, it arbitrates contention for resources by managing a queue of pending work.

Slurm

A Flachmueller — Wed, 07 Oct 2026 09:36:46 GMT

A Flachmueller moved page Slurm to Batch Systems Other Batch Systems / Resource Management Systems may be adopted in the future

New page

= Slurm HPC Workload Manager =
== Specification ==
Slurm is an open source, fault-tolerant, and highly scalable cluster management and job scheduling system for large and small Linux clusters. Slurm requires no kernel modifications for its operation and is relatively self-contained. As a cluster workload manager, Slurm has three key functions. First, it allocates exclusive and/or non-exclusive access to resources (compute nodes) to users for some duration of time so they can perform work. Second, it provides a framework for starting, executing, and monitoring work (normally a parallel job) on the set of allocated nodes. Finally, it arbitrates contention for resources by managing a queue of pending work.

More information can be found on the clusters' respective wikipages.

* [[BwUniCluster3.0/Running_Jobs#Running_Jobs|bwUniCluster 3.0]]
* [[BinAC2/Slurm|BinAC2]]
* [[Helix/Slurm|Helix]]
* [[BwForCluster_JUSTUS_2_Slurm_HOWTO|JUSTUS 2]]
* [[NEMO2/Slurm|NEMO2]]

SDS@hd/Registration

H Schumacher — Wed, 07 Oct 2026 09:28:48 GMT

removed entitlement hint

← Older revision		Revision as of 11:28, 7 October 2026
Line 106:		Line 106:
	*: Yes, there is a Test-SV for this purpose. You can write to the support to get invited. Please keep in mind that data gets regularly deleted and users may be removed after some time.		*: Yes, there is a Test-SV for this purpose. You can write to the support to get invited. Please keep in mind that data gets regularly deleted and users may be removed after some time.
	* I can login with different institutions/IDs (edugain, ORCID, university ID, university clinics ID,...). Which one shall I choose?		* I can login with different institutions/IDs (edugain, ORCID, university ID, university clinics ID,...). Which one shall I choose?
	*: If you want to be able to start your own SVs, ~~use~~ the ID ~~were~~ ~~you~~ ~~can~~ ~~get~~ ~~the~~ ~~entitlement~~ ~~most~~ ~~conveniently~~. Otherwise it doesn't matter. But ORCID is the most unspecific option and therefore should only be chosen if the other options don't work.		*: If you want to be able to start your own SVs, you must login with the account at an institution that is part of the bwIDM network. Otherwise it doesn't matter. But ORCID is the most unspecific option and therefore should only be chosen if the other options don't work.
	* I own a SV with my ID at institution A. Can I connect my account from institution B to it?		* I own a SV with my ID at institution A. Can I connect my account from institution B to it?
	*: You can't connect different accounts. But you can join the SV with both accounts if necessary.		*: You can't connect different accounts. But you can join the SV with both accounts if necessary.

SDS@hd/SV Management

H Schumacher — Wed, 07 Oct 2026 08:42:16 GMT

improved instructions

← Older revision		Revision as of 10:42, 7 October 2026
Line 76:		Line 76:

	==== Adding users ====		==== Adding users ====
	PMs can add users to their projects and to any allocation within the project~~. To provide a user with access to an allocation, both of the following steps must be followed~~.		PMs can add users to their projects and to any allocation within the project.

			{\|style="background:#deffee; width:70%;"
			\|style="padding:5px; background:#cef2e0; text-align:left"\|
			[[Image:Attention.svg\|center\|25px]]
			\|style="padding:5px; background:#cef2e0; text-align:left"\|
			To provide a user with access to an allocation, <ins>'''both of the following steps must be followed'''</ins>.
			\|}
	<u>'''1.''' Adding users to a project:</u>		<u>'''1.''' Adding users to a project:</u>
	# On the project's page either the button on the top or next to the users list can be used for adding users.		# On the project's page either the button on the top or next to the users list can be used for adding users.
Line 93:		Line 99:

	An allocation can have multiple users. To add a new user:		An allocation can have multiple users. To add a new user:
	# Go to the page of the ~~allocation~~		# Go to the page of the project.
	# Go to the section ~~"Users~~ in ~~Allocation"~~ ~~and~~ ~~click "Add Users"~~		# Go to the section with the allocations table.
			# Go to the page of the allocation by clicking on the folder symbol under "Actions".
			# Go to the section "Users in Allocation" and click "Add Users".
	# Choose the users that shall be added from the list of project members.		# Choose the users that shall be added from the list of project members.
	#: If you don't see the user here, please make sure that you've added them to the project first.		#: If you don't see the user here, please make sure that you've added them to the project first.

	==== Yearly Project Extension ====		==== Yearly Project Extension ====

Help:Editor's Guide

K Siegmund — Tue, 06 Oct 2026 14:39:52 GMT

← Older revision		Revision as of 16:39, 6 October 2026
(One intermediate revision by the same user not shown)
Line 6:		Line 6:

	== General Principles ==		== General Principles ==

			=== Keep in Line General Wikipedia Rules as Applicable ===

			Many of Wikepedia's guidelines are very helpful for writing here as well, while some are specific to creating an encyclopedia.

			See e.g. https://en.wikipedia.org/wiki/Wikipedia:Writing_better_articles

	=== Think from the User's Perspective ===		=== Think from the User's Perspective ===

	; Goal-Oriented Writing~~: Always ask:~~		; Goal-Oriented Writing
	: ~~→~~''"What is the user trying to accomplish?"'' ~~Provide actionable commands, job submission scripts, and practical examples.~~		: Always ask: ''"What is the user trying to accomplish?"''
			: → Provide actionable commands, job submission scripts, and practical examples.

	; Avoid Technical Jargon Overload:		; Avoid Technical Jargon Overload
	: ~~→~~ Assume the user is an expert in their scientific domain (e.g., chemistry, physics), but potentially a beginner in HPC and Linux environments.		: Assume the user is an expert in their scientific domain (e.g., chemistry, physics), but potentially a beginner in HPC and Linux environments.
			: → prefer common words over jargon, and if unavoidable, link jargon words to the [[HPC_Glossary]]

	=== No Empty Placeholders ===		=== No Empty Placeholders ===

Help:Editor's Guide

K Siegmund — Tue, 06 Oct 2026 14:31:46 GMT

Created page with "Welcome to the '''wiki.bwhpc.de''' contributor guide. This document outlines structural rules, content principles, and syntax conventions to keep our HPC documentation '''accurate, maintainable, user-focused, and machine-readable''' across all bwHPC sites. == Editorial Meetings == Don't be an anonymous editor, join the meeting of bwHPC wiki editors. More information in our project gitlab page at https://gitlab.kit.edu/groups/kit/bwhpc-s5/-/wikis/Home/AP1.1/Redaktionste..."

New page

Welcome to the '''wiki.bwhpc.de''' contributor guide. This document outlines structural rules, content principles, and syntax conventions to keep our HPC documentation '''accurate, maintainable, user-focused, and machine-readable''' across all bwHPC sites.

== Editorial Meetings ==

Don't be an anonymous editor, join the meeting of bwHPC wiki editors. More information in our project gitlab page at https://gitlab.kit.edu/groups/kit/bwhpc-s5/-/wikis/Home/AP1.1/Redaktionsteam_bwHPC-Wiki

== General Principles ==

=== Think from the User's Perspective ===

; Goal-Oriented Writing: Always ask:
: →''"What is the user trying to accomplish?"'' Provide actionable commands, job submission scripts, and practical examples.

; Avoid Technical Jargon Overload:
: → Assume the user is an expert in their scientific domain (e.g., chemistry, physics), but potentially a beginner in HPC and Linux environments.

=== No Empty Placeholders ===

Do not publish empty pages or sections containing only headers with text like "TBD", "Work in Progress", or "Under Construction". If a page has no actionable information yet, keep it in a local draft or sandbox space until it provides immediate value.

But: Stubs are Welcome: Short pages or sections (stubs) that provide meaningful information are fine - our goal is to provide information not to create long texts.

=== Text Longevity ===

Avoid hardcoding very short-lived data that is bound to be outdated soon.

When documenting forseeably quickly aging things like a specific software version, explicitly state the version in your documentation so that outdated information does not become incorrect information when seen in the context of more recent versions.

=== Central vs. Local Scoping ===

<pre>
┌─────────────────────────────────────────────────────────────┐
│ Generic / Cross-Cluster Content │
│ (Slurm fundamentals, general module usage, scaling) │
└──────────────────────────────┬──────────────────────────────┘
│
┌──────────────────┴──────────────────┐
▼ ▼
┌───────────────────────┐ ┌───────────────────────┐
│ Cluster-Specific Page │ │ Cluster-Specific Page │
│ (e.g., /Justus2/...) │ │ (e.g., /Helix/...) │
└───────────────────────┘ └───────────────────────┘
</pre>

# Generic Content (Main Namespace):
#* Applies to all or most bwHPC clusters (e.g., workflow concepts, general environment module syntax).
#* Keep it independent of site-specific configurations.
# Cluster-Specific Content (Subfolders / Subpages):
#* Applies only to a specific cluster environment (e.g., local storage paths, specific hardware queues/partitions, cluster hostnames).
#* Rule: Always place cluster-bound content under its respective subfolder:
#** <code>Cluster_Name/Topic</code> (e.g., <code>Justus3/Storage</code>, <code>BinAC2/Partitions</code>).

== Syntax & Formatting ==

* Use the simpler Wiki Syntax whenever possible instead of reverting to HTML

* Keep Output Relevant: Do not paste raw console dumps or directory listings, but only document the command to list them on-cluster (examples are of course ok)
* Variable Syntax: Use standard angle brackets <code><placeholder></code> for user-defined parameters to clearly distinguish them from literal strings:
** <code>squeue -u <username></code>

* Use emphasis sparingly and on point. Writing something in bold is very often not as useful as you may think

* Internal vs External Links: Whenever something is in the wiki, an internal link, e.g. <code>[[Registration]]</code> should be used. The single brackets are for external links only.

== Lifecycle Management & Verification ==

Articles should not stay unverified for longer than half a year. The wiki editorial team will coordinate the effort of reviewing pages. Pages kept to retain historic information must have a tag <code><nowiki>{{History}}</nowiki></code>

Job Monitoring

F Bartusch — Tue, 06 Oct 2026 09:51:21 GMT

← Older revision		Revision as of 11:51, 6 October 2026
Line 2:		Line 2:

	* [[BwUniCluster3.0/Running_Jobs#Monitor_and_manage_jobs \| bwUniCluster]]		* [[BwUniCluster3.0/Running_Jobs#Monitor_and_manage_jobs \| bwUniCluster]]
	* [[BinAC2/Slurm#Detailed_job_information_:_scontrol_show_job \| BinAC]]		* [[BinAC2/Slurm#Detailed_job_information_:_scontrol_show_job \| BinAC 2]]
	* [[Helix/Slurm#Job_Monitoring \| Helix]]		* [[Helix/Slurm#Job_Monitoring \| Helix]]
	* [[JUSTUS2/Jobscripts:_Running_Your_Calculations#Monitoring_Your_Jobs \| JUSTUS]]		* [[JUSTUS2/Jobscripts:_Running_Your_Calculations#Monitoring_Your_Jobs \| JUSTUS]]

BwUniCluster3.0/Hardware and Architecture

S Braun — Tue, 06 Oct 2026 07:25:32 GMT

Compute nodes

← Older revision		Revision as of 09:25, 6 October 2026
Line 77:		Line 77:
	!scope="column"\| Number of nodes		!scope="column"\| Number of nodes
	\| 272		\| 272
	\| 80		\| 82
	\| 5		\| 5
	\| 19		\| 20
	\| 1		\| 1
	\| 15		\| 14
	\| 19		\| 19
	\| 2		\| 2

BinAC2/Software/Jupyterlab

I Tachakor — Mon, 05 Oct 2026 20:44:25 GMT

Add a new Kernel

← Older revision		Revision as of 22:44, 5 October 2026
Line 167:		Line 167:
	=== Add a new Kernel ===		=== Add a new Kernel ===

	We will show you how to create new kernels for Python and R.		We will show you how to create new kernels for Python and R. For Python, you can use either Conda or <code>uv</code>. For R, <code>uv</code> is not supported, so R kernels must be created using Conda.

	==== Python ====		==== Python ====


	<syntaxhighlight lang="bash">		<syntaxhighlight lang="bash">
Line 180:		Line 179:
	</syntaxhighlight>		</syntaxhighlight>

	The first command creates a new Conda environment called <syntaxhighlight inline>kernel_env</syntaxhighlight> and installs a specific Python ~~packages~~ , along with a few additional Python packages.		The first command creates a new Conda environment called <syntaxhighlight inline>kernel_env</syntaxhighlight> and installs a specific Python version, along with a few additional Python packages.
	It's important that you also install <syntaxhighlight inline>ipykernel</syntaxhighlight>, as we will need it later to create the JupyterLab kernel.		It's important that you also install <syntaxhighlight inline>ipykernel</syntaxhighlight>, as we will need it later to create the JupyterLab kernel.
	The second command activates the <syntaxhighlight inline>kernel_env</syntaxhighlight> Conda environment.		The second command activates the <syntaxhighlight inline>kernel_env</syntaxhighlight> Conda environment.
	The third command creates the new JupyterLab kernel.		The third command creates the new JupyterLab kernel.

			Alternatively, the same Python environment can be created and registered as a JupyterLab kernel using <code>uv</code>:

			<syntaxhighlight lang="bash">
			uv venv kernel_env --python 3.13
			uv pip install --python kernel_env/bin/python pandas numpy matplotlib ipykernel
			uv run --directory kernel_env python -m ipykernel install --user --name pandas --display-name="Python 3.13 (pandas)"
			# Installed kernelspec pandas in $HOME/.local/share/jupyter/kernels/pandas
			</syntaxhighlight>

			The first command creates a new <code>uv</code> virtual environment called <syntaxhighlight inline>kernel_env</syntaxhighlight> using Python 3.13.
			The second command installs the required Python packages, including <syntaxhighlight inline>ipykernel</syntaxhighlight>.
			The third command creates the new JupyterLab kernel.

			Unlike with Conda, the <code>uv</code> environment does not have to be activated. The <code>uv</code> commands directly use the Python interpreter from the environment.

	[[ File:Binac2_jupyterlab_new_kernel.png \| 800px \| center \| New Python kernel in JupyterLab]]		[[ File:Binac2_jupyterlab_new_kernel.png \| 800px \| center \| New Python kernel in JupyterLab]]
Line 206:		Line 220:
	In this session, you can install any R packages you need for your kernel.		In this session, you can install any R packages you need for your kernel.
	Finally, create the new kernel with the <syntaxhighlight inline>installspec</syntaxhighlight> command.		Finally, create the new kernel with the <syntaxhighlight inline>installspec</syntaxhighlight> command.

			<code>uv</code> does not provide an equivalent for creating and managing R environments. Therefore, the Conda-based procedure above should be used for R kernels.

	=== Remove a Kernel ===		=== Remove a Kernel ===

Helix/bwVisu/JupyterLab

I Tachakor — Mon, 05 Oct 2026 20:21:16 GMT

Create a kernel from a virtual environment

Show changes

BwUniCluster3.0/Jupyter

I Tachakor — Mon, 05 Oct 2026 19:46:17 GMT

Virtual environments

← Older revision		Revision as of 21:46, 5 October 2026
(One intermediate revision by the same user not shown)
Line 209:		Line 209:

	=== Creation of virtual environment ===		=== Creation of virtual environment ===

			A virtual environment can be created using the standard Python <code>venv</code> module:

	<pre>		<pre>
	python -m venv <myEnv>		python -m venv <myEnv>
	source <myEnv>/bin/activate		source <myEnv>/bin/activate
	pip install <packageName>		pip install <packageName>
	deactivate		deactivate
	</pre>		</pre>

	The additional packages are installed under <code><myEnv>/lib/python3.11/site-packages/</code>.		The additional packages are installed under <code><myEnv>/lib/python3.11/site-packages/</code>.

			Alternatively, a virtual environment can be created and managed using <code>uv</code>:

			<pre>
			uv venv <myEnv>
			uv add --directory <myEnv> <packageName>
			</pre>

	=== Usage of virtual environment ===		=== Usage of virtual environment ===

	In order to use ~~the~~ virtual environment, it has to be activated via <code>source <myEnv>/bin/activate</code>. <code>PYTHONPATH</code> is set accordingly. Deactivation of the venv is done via <code>deactivate</code>.		In order to use a virtual environment created with <code>venv</code>, it has to be activated via <code>source <myEnv>/bin/activate</code>. <code>PYTHONPATH</code> is set accordingly. Deactivation of the venv is done via <code>deactivate</code>.

		⚫	For environments managed by <code>uv</code>, activation is not required. Python and other commands can be executed using <code>uv run</code>, which automatically uses the environment managed by <code>uv</code>.

	=== Usage of virtual environment in JupyterLab ===		=== Usage of virtual environment in JupyterLab ===
Line 230:		Line 241:
	source <myEnv>/bin/activate		source <myEnv>/bin/activate
	python -m ipykernel install \		python -m ipykernel install \
	--user \		--user \
	--name myEnv \		--name myEnv \
	--display-name "Python (myEnv)"		--display-name "Python (myEnv)"
	</pre>		</pre>

Line 244:		Line 255:
	<pre>		<pre>
	uv run python -m ipykernel install \		uv run python -m ipykernel install \
	--user \		--user \
	--name myEnv \		--name myEnv \
	--display-name "Python (myEnv)"		--display-name "Python (myEnv)"
	</pre>		</pre>

	After installing the kernel (and possibly refreshing the browser window), a button named "Python (myEnv)" is available in JupyterLab. The kernel can also be selected from the drop-down menu.

	'''Attention'''		'''Attention'''
Line 257:		Line 266:
	uv add ipykernel		uv add ipykernel
	</pre>		</pre>

⚫	~~When~~ ~~using~~ <code>uv</code>, ~~the~~ ~~environment does~~ not ~~have~~ to be ~~activated~~ ~~with~~ ~~<code>source</code>~~ ~~before~~ ~~installing~~ ~~the kernel. The~~ <code>uv run</code> ~~command~~ automatically ~~runs Python from~~ the environment managed by <code>uv</code>.

	== Examples on Data processing, Machine Learning & Visualization ==		== Examples on Data processing, Machine Learning & Visualization ==

JUSTUS2/Software/Python

I Tachakor — Mon, 05 Oct 2026 19:17:58 GMT

← Older revision		Revision as of 21:17, 5 October 2026
(3 intermediate revisions by the same user not shown)
Line 5:		Line 5:
	* Don't use conda (see [[#Conda\|below]])		* Don't use conda (see [[#Conda\|below]])
	* Don't use the system python for computation intensive work		* Don't use the system python for computation intensive work
	* ~~<b>~~Do never ever activate a python environment, neither venv nor conda, in your .bashrc! This may break various things.~~</b>~~		* '''Do never ever activate a python environment, neither venv nor conda, in your .bashrc! This may break various things.'''

	* Use optimized numerical libraries (SciPy, NumPy) provided as [[Environment Modules\|environment modules]]		* Use optimized numerical libraries (SciPy, NumPy) provided as [[Environment Modules\|environment modules]]
Line 16:		Line 16:
	[[Image:Attention.svg\|center\|25px]]		[[Image:Attention.svg\|center\|25px]]
	\|style="padding:5px; background:#cef2e0; text-align:left"\|		\|style="padding:5px; background:#cef2e0; text-align:left"\|
	Always load the environment modules before activating your Python environments!		Always load the environment modules before activating your Python environments!
	\|}		\|}

Line 42:		Line 42:
	export CFLAGS="-O2 -march=native"		export CFLAGS="-O2 -march=native"
	export FFLAGS="-O2 -march=native"		export FFLAGS="-O2 -march=native"
	export CXXFLAGS="-02 -march=native"		export CXXFLAGS="-02 -march=native"
	pip install --no-binary some_package some_package==VERSION BUILD_OPTIONS		pip install --no-binary some_package some_package==VERSION BUILD_OPTIONS

Line 50:		Line 50:

	* legal: unclear license situation for research with the official Anaconda channel		* legal: unclear license situation for research with the official Anaconda channel
	* free conda-forge channel provides mostly unoptimized packages		* free conda-forge channel provides mostly unoptimized packages
	* conflicting libraries: Conda installs own versions of low-level libraries such as OpenMPI, that do not work well together with Slurm.		* conflicting libraries: Conda installs own versions of low-level libraries such as OpenMPI, that do not work well together with Slurm.

Line 57:		Line 57:
	* some packages are only available via conda		* some packages are only available via conda
	* simple installation for testing some software before doing an optimized build		* simple installation for testing some software before doing an optimized build

			=uv=

			In contrast to Conda, we recommend using [https://docs.astral.sh/uv/ uv] for managing Python environments and packages on JUSTUS2.

			There are several advantages to using <code>uv</code> on the cluster:

			* fast environment and package management
			* uses the standard Python packaging ecosystem and PyPI
			* creates isolated virtual environments without requiring Conda
			* supports reproducible environments through lock files
			* does not install its own low-level system libraries such as OpenMPI, avoiding potential conflicts with the cluster's environment
			* works well with the existing Python and [[Environment Modules\|environment modules]] infrastructure

			For instructions on how to use <code>uv</code> on bwHPC systems, see [https://wiki.bwhpc.de/e/Development/Python#uv Development/Python: uv].

BwUniCluster3.0/Jupyter

I Tachakor — Mon, 05 Oct 2026 18:54:42 GMT

Usage of virtual environment in JupyterLab

@@ Line 239: / Line 239: @@
 '''Attention'''
 The (Lmod) base module you used in the Creation of virtual environment step must be loaded to use the venv. However, to be on the safe side, you can also use the system Python (<code>/usr/bin/python3.11</code>) at creation time, which is available even without any <code>jupyter/{base,tensorflow}</code> module loaded.
 == Examples on Data processing, Machine Learning & Visualization ==

SDS@hd/Registration

H Schumacher — Mon, 05 Oct 2026 14:31:19 GMT

improved troubleshooting section

← Older revision		Revision as of 16:31, 5 October 2026
Line 102:		Line 102:

	== FAQ ==		== FAQ ==

⚫	* I should be able to create a project but I can't despite being an employee at an institution that is a [https://www.bwidm.de/hochschulen.php bwIDM member].
⚫	*: If you don't see the button for creating a new project, please go to your user profile by clicking on your user-id in the upper right corner. In your profile you should see a green checkmark for your PI-status. If there is a red cross instead, please contact your local it-service desk as described [[SDS@hd/Registration/Institutional_Membership \| here]].
	* Is there a Test-SV to do technical tests?		* Is there a Test-SV to do technical tests?
	*: Yes, there is a Test-SV for this purpose. You can write to the support to get invited. Please keep in mind that data gets regularly deleted and users may be removed after some time.		*: Yes, there is a Test-SV for this purpose. You can write to the support to get invited. Please keep in mind that data gets regularly deleted and users may be removed after some time.
Line 123:		Line 122:
	** Error message: You have no access to a Speichervorhaben of the Service SDS@hd. Please register a new Speichervorhaben or collaborate with an existing Project on https://management.bwservices.uni-heidelberg.de/		** Error message: You have no access to a Speichervorhaben of the Service SDS@hd. Please register a new Speichervorhaben or collaborate with an existing Project on https://management.bwservices.uni-heidelberg.de/
	** Solution: Check the following points:		** Solution: Check the following points:
	*** Are you a member of a bwServices-Project?		**# Are you a member of a bwServices-Project?
	*** Does this project have an SDS@hd allocation?		**# Does this project have an SDS@hd allocation?
	*** Are you a member of this allocation/SV?		**# Are you a member of this allocation/SV? Please make sure that you finished the second step under [[#a)_Get_invited_to_existing_SV \| Get invited to existing SV]] (if you're not the PI).
	*** Is the bwServices-Project still active? The project mustn't be in the review process.		**# Is the bwServices-Project still active? The project mustn't be in the review process.
	*** Is the allocation still active? The allocation mustn't be expired.		**# Is the allocation still active? The allocation mustn't be expired.
		⚫	* '''Issue:''' I should be able to create a project but I can't despite being an employee at an institution that is a [https://www.bwidm.de/hochschulen.php bwIDM member].
		⚫	** If you don't see the button for creating a new project, please go to your user profile by clicking on your user-id in the upper right corner. In your profile you should see a green checkmark for your PI-status. If there is a red cross instead, please contact your local it-service desk as described [[SDS@hd/Registration/Institutional_Membership \| here]].

SDS@hd/SV Management

H Schumacher — Mon, 05 Oct 2026 12:07:20 GMT

improved change request description and FAQ

← Older revision		Revision as of 14:07, 5 October 2026
Line 140:		Line 140:
	==== Adjust SV Attributes ====		==== Adjust SV Attributes ====

	To change the properties of your SV, you can hand in a Change Request.		To change the properties of your SV, you can hand in a ''Change Request''. You can find this option at the page of your SV at bwServices-Management.

	When you request a quota expansion for your SV at the SDS@hd service in order to store hot scientific data, we kindly ask you to answer the questions in the justification textfield for reasoning the extension. The questions are:		When you request a quota expansion for your SV at the SDS@hd service in order to store hot scientific data, we kindly ask you to answer the questions in the justification textfield for reasoning the extension. The questions are:
	<syntaxhighlight lang="text">Q1: Please explain why additional storage is needed.		<syntaxhighlight lang="text">Q1: Please explain why additional storage is needed.
Line 166:		Line 167:
	== FAQ ==		== FAQ ==

			* How can I ask for increased quota?
			*: Please do it via a change request as described in the section [[#Adjust_SV_Attributes \| Adjust SV Attributes]].
	* I changed a user's role in bwServices-Management but the user still has the previous access rights.		* I changed a user's role in bwServices-Management but the user still has the previous access rights.
	*: After 30 minutes the adjustment should be synced to all systems. If not, it helps when the member with the role change logs in to bwServices once to trigger an automatic update and then waits for 30 minutes.		*: After 30 minutes the adjustment should be synced to all systems. If not, it helps when the member with the role change logs in to bwServices once to trigger an automatic update and then waits for 30 minutes.
Line 175:		Line 178:
	*: Please [mailto:sds-hd-support@urz.uni-heidelberg.de submit a Ticket]		*: Please [mailto:sds-hd-support@urz.uni-heidelberg.de submit a Ticket]
	* How can the PI of a project be changed?		* How can the PI of a project be changed?
	*: This is currently not possible but will be possible in the future.		*: This is currently not possible but will be possible in the future. If it is really necessary to do it before the feature is officially implemented, you can contact the SDS@hd support.
			* My SV status is "approved". When does it get "active"?
			*: When the first SV member finishes the [[SDS@hd/Registration \| registration]] for SDS@hd.

SDS@hd/Registration/Institutional Membership

H Schumacher — Mon, 05 Oct 2026 11:53:33 GMT

added message draft

← Older revision		Revision as of 13:53, 5 October 2026
Line 9:		Line 9:
	* '''Ulm University'''		* '''Ulm University'''
	** Please contact the helpdesk. See https://www.uni-ulm.de/einrichtungen/kiz/service-katalog/beratung-schulung-hilfe/helpdesk/		** Please contact the helpdesk. See https://www.uni-ulm.de/einrichtungen/kiz/service-katalog/beratung-schulung-hilfe/helpdesk/

			You can use the following draft:
			<syntaxhighlight lang="text">Dear ...,

			I am an employee at <institution> and am therefore allowed to create storage projects at the research data storage SDS@hd (https://wiki.bwhpc.de/e/SDS@hd). But it seems as if the necessary attributes don't get transferred to the SDS@hd service. To be concrete, the following is needed:
			eduPersonScopedAffiliation needs to be "staff" or "employee".
			This is described for the 'SDS@hd Management Tool' at the bwIDM page: https://www.bwidm.de/dienste.php.

			Best regards,
			...
			</syntaxhighlight>

SDS@hd/Registration

H Schumacher — Mon, 05 Oct 2026 11:42:12 GMT

Added FAQ for missing PI-Status

← Older revision		Revision as of 13:42, 5 October 2026
Line 102:		Line 102:

	== FAQ ==		== FAQ ==
			* I should be able to create a project but I can't despite being an employee at an institution that is a [https://www.bwidm.de/hochschulen.php bwIDM member].
			*: If you don't see the button for creating a new project, please go to your user profile by clicking on your user-id in the upper right corner. In your profile you should see a green checkmark for your PI-status. If there is a red cross instead, please contact your local it-service desk as described [[SDS@hd/Registration/Institutional_Membership \| here]].
	* Is there a Test-SV to do technical tests?		* Is there a Test-SV to do technical tests?
	*: Yes, there is a Test-SV for this purpose. You can write to the support to get invited. Please keep in mind that data gets regularly deleted and users may be removed after some time.		*: Yes, there is a Test-SV for this purpose. You can write to the support to get invited. Please keep in mind that data gets regularly deleted and users may be removed after some time.

SDS@hd/Registration/Institutional Membership

H Schumacher — Mon, 05 Oct 2026 11:30:44 GMT

update

← Older revision		Revision as of 13:30, 5 October 2026
Line 1:		Line 1:
			== Confirm Employee Status at your Institution ==
	== Get SDS@hd Entitlement ==

			New projects and SVs can only be requested by bwIDM members with employee status. Usually, this information is transferred form your institution to SDS@h automatically. If any issues come up, please write to the support address of your institutional it- or hpc-service. You can find some addresses below. Please add the SDS@hd support in CC (sds-hd-support@urz.uni-heidelberg.de).
	New SVs can only be opened by bwIDM members who have the '''sds-hd-sv''' entitlement from their home university. This entitlement may have to be applied for individually at the home organisation. The criteria for awarding the entitlement to a user are entirely up to the respective home organization

			* '''Heidelberg University'''
	To see if you already have the needed entitlement, you can [[SDS@hd/Registration/Entitlement#Check_your_Entitlements\|''check your entitlements'']].
			** It's enough to directly write to the SDS@hd support.

			* '''Tübingen University'''
	If you need the entitlement, follow the instructions for your home university. <u>If none are provided, please contact your local service desk</u>.
			** Write to support@zdv.uni-tuebingen.de or hpcmaster@uni-tuebingen.de

	* '''~~Universität~~ ~~Freiburg~~'''		* '''Ulm University'''
	** Employees of the University of need to fill out this [https://uni-freiburg.de/forms-en/sds-hd-sv-entitlement/ '''form'''].
	* '''Universität Heidelberg'''
	** Employees of Heidelberg University receive this entitlement automatically. Students can't receive it.
	* '''Universität Mannheim'''
	** Employees of the University of Mannheim receive this entitlement automatically. Students can't receive it.
	* '''Universität Ulm'''
	** Please contact the helpdesk. See https://www.uni-ulm.de/einrichtungen/kiz/service-katalog/beratung-schulung-hilfe/helpdesk/		** Please contact the helpdesk. See https://www.uni-ulm.de/einrichtungen/kiz/service-katalog/beratung-schulung-hilfe/helpdesk/

	== Check your Entitlements ==

	# Log in to https://bwservices.uni-heidelberg.de
	# Go to "Index" -> "Personal Data"
	# Choose the "Shibboleth" tab
	# Search for the following entry: http://bwidm.de/entitlement/sds-hd-sv (this is an attribute and not a link)
	If you can find it, you already have the needed entitlement.

	<p style="text-align:right;">→ [[SDS@hd/Registration#b)_Apply_for_new_SV\| go forward with the SV application]]</p>

SDS@hd/Registration/Entitlement

H Schumacher — Mon, 05 Oct 2026 11:09:31 GMT

H Schumacher moved page SDS@hd/Registration/Entitlement to SDS@hd/Registration/Institutional Membership without leaving a redirect

New page

== Get SDS@hd Entitlement ==

New SVs can only be opened by bwIDM members who have the '''sds-hd-sv''' entitlement from their home university. This entitlement may have to be applied for individually at the home organisation. The criteria for awarding the entitlement to a user are entirely up to the respective home organization

To see if you already have the needed entitlement, you can [[SDS@hd/Registration/Entitlement#Check_your_Entitlements|''check your entitlements'']].

If you need the entitlement, follow the instructions for your home university. <u>If none are provided, please contact your local service desk</u>.

* '''Universität Freiburg'''
** Employees of the University of need to fill out this [https://uni-freiburg.de/forms-en/sds-hd-sv-entitlement/ '''form'''].
* '''Universität Heidelberg'''
** Employees of Heidelberg University receive this entitlement automatically. Students can't receive it.
* '''Universität Mannheim'''
** Employees of the University of Mannheim receive this entitlement automatically. Students can't receive it.
* '''Universität Ulm'''
** Please contact the helpdesk. See https://www.uni-ulm.de/einrichtungen/kiz/service-katalog/beratung-schulung-hilfe/helpdesk/

== Check your Entitlements ==

# Log in to https://bwservices.uni-heidelberg.de
# Go to "Index" -> "Personal Data"
# Choose the "Shibboleth" tab
# Search for the following entry: http://bwidm.de/entitlement/sds-hd-sv (this is an attribute and not a link)
If you can find it, you already have the needed entitlement.

<p style="text-align:right;">→ [[SDS@hd/Registration#b)_Apply_for_new_SV| go forward with the SV application]]</p>

SDS@hd/Access

H Schumacher — Mon, 05 Oct 2026 11:04:30 GMT

changed prerequisites and added hint to them in troubleshooting section

← Older revision		Revision as of 13:04, 5 October 2026
Line 5:		Line 5:
	== Prerequisites ==		== Prerequisites ==

	* ~~You~~ ~~need to be~~ [[SDS@hd/Registration\|~~registered~~]].		* The two [[SDS@hd/Registration\|registration]] steps are completed <span style="text-decoration: underline;">and</span> still valid.
			* Your IP address is within the [https://www.belwue.de BelWü] network which connects universities and other scientific institutions in Baden-Württemberg. If your computer is in your university network (e.g. at your office), you should be able to connect without restrictions. If it doesn't work or you are outside the BelWü network (e.g. at home), a VPN (virtual private network) connection to your university network must be established first. Please consult the VPN documentation of your university.
	* You need to be in the belwue-Network. This means you have to use the VPN Service of your HomeOrganization, if you want to access SDS@hd from outside the bwHPC-Clusters (e.g. via eduroam or from your personal notebook).
			*: Exception: If you registered via eduGAIN or ORCiD, you don't need to be part of a specific network.
			* If you encounter any issues, please have a look at the [[#Troubleshooting\|Troubleshooting]] section.

	== Needed Information, independent of the chosen tool ==		== Needed Information, independent of the chosen tool ==
Line 130:		Line 132:

	* '''Issue:''' The credentials aren't accepted		* '''Issue:''' The credentials aren't accepted
	*: Check if your credentials work in general by trying the ~~access via webbrowser:~~ [https://lsdf02-webdav.urz.uni-heidelberg.de/].		*: Check if your credentials work in general by trying the [https://lsdf02-webdav.urz.uni-heidelberg.de/ access via webbrowser].
	*: If this doesn't work:		*: If this doesn't work:
			*:: → Double check the [[#Prerequisites \| Prerequisites]]
	*:: → [[Registration/Login/Username\| Check your Username]]		*:: → [[Registration/Login/Username\| Check your Username]]
	*:: → [[Registration/bwForCluster/Helix#Troubleshooting_with_the_Help_of_bwServices \| Troubleshooting with bwServices]]		*:: → [[Registration/bwForCluster/Helix#Troubleshooting_with_the_Help_of_bwServices \| Troubleshooting with bwServices]]

← Older revision		Revision as of 11:51, 6 October 2026
Line 2:		Line 2:

	* [[BwUniCluster3.0/Running_Jobs#Monitor_and_manage_jobs \| bwUniCluster]]		* [[BwUniCluster3.0/Running_Jobs#Monitor_and_manage_jobs \| bwUniCluster]]
	* [[BinAC2/Slurm#Detailed_job_information_:_scontrol_show_job \| BinAC]]		* [[BinAC2/Slurm#Detailed_job_information_:_scontrol_show_job \| BinAC 2]]
	* [[Helix/Slurm#Job_Monitoring \| Helix]]		* [[Helix/Slurm#Job_Monitoring \| Helix]]
	* [[JUSTUS2/Jobscripts:_Running_Your_Calculations#Monitoring_Your_Jobs \| JUSTUS]]		* [[JUSTUS2/Jobscripts:_Running_Your_Calculations#Monitoring_Your_Jobs \| JUSTUS]]