Batch system

JEDI is accessed through a dedicated set of login nodes used to write and compile applications as well as to perform pre- and post-processing of simulation data. Access to the compute nodes in the system is controlled by the workload manager.

On JEDI the Slurm (Simple Linux Utility for Resource Management) Workload Manager, a free open-source resource manager and batch system, is employed. Slurm is a modern, extensible batch system that is widely deployed around the world on clusters of various sizes.

A Slurm installation consists of several programs and daemons. The slurmctld daemon is the central brain of the batch system responsible for monitoring the available resources and scheduling batch jobs. The slurmctld runs on an administrative node with a special setup to ensure availability in the case of hardware failures. Most user programs such as srun, sbatch, salloc and scontrol interact with the slurmctld. For the purpose of job accounting slurmctld communicates with the slurmdbd database daemon. Information from the accounting database can be queries using the sacct command. Slurm combines the functionality of the batch system and resource management. For this purpose Slurm provides the slurmd daemon which runs on the compute nodes and interacts with slurmctld. For the executing of user processes slurmstepd instances are spawned by slurmd to shepherd the user processes.

Slurm Partitions

In Slurm multiple nodes can be grouped into partitions which are sets of nodes with associated limits (for wall-clock time, job size, etc.). In practice these partitions can be used for example to signal need for resources that have certain hardware characteristics (normal, large memory, accelerated, etc.) or that are dedicated to specific workloads (large production jobs, small debugging jobs, visualization, etc.).

Hardware Overview

Type	Quantity	Description
Standard	48	288 cores, 480 GiB
Login	1	72 cores, 574 GiB

Available Partitions

Compute nodes are used exclusively by jobs of a single user; no node sharing between jobs is done. The smallest allocation unit is one node (288 cores). Users will be charged for the number of compute nodes multiplied with the wall-clock time used. On each node, a share of the available memory is reserved and not available for application usage.

The system has only one partition called all.

A limit regarding the maximum number of running jobs per user is enforced. The precise values are adjusted to optimize system utilization. In general, the limit for the number of running jobs is lower for nocont projects.

JEDI partitions

Partition	Resource	Value
all	max. wallclock time (normal / nocont)	6 h / 6 h
	default wallclock time	1 h
	min. / max. number of nodes	1 / 48
	node types	mem480 (480 GiB)

Internet Access

Due to security measures, we do not allow internet access on the compute nodes - please take this into consideration when running your jobs. Internet access is, however, allowed on the login nodes and on the devel partitions to facilitate development activities. If your production jobs require files available on the internet, consider downloading them first on the login nodes and using them from the jobs (some frameworks allow runs on “offline mode”). If this is not sufficient, and you need to run a “scraping” style workflow, please contact your Project Mentor or contact SC-Support at sc@fz-juelich.de for assistance.

Note

Although the internet access is allowed, only a few ports (as the usual HTTP/S 80/443) are open, while many other ports are blocked.

Allocations, Jobs and Job Steps

In Slurm a job is an allocation of selected resources for a specific amount of time. A job allocation can be requested using sbatch and salloc. Within a job multiple job steps can be executed using srun that use all or a subset of the allocated compute nodes. Job steps may execute at the same time if the resource allocation permits it.

Writing a Batch Script

Users submit batch applications (usually bash scripts) using the sbatch command. The script is executed on the first compute node in the allocation. To execute parallel MPI tasks users call srun within their script.

Note

mpiexec is not supported on JEDI and has to be replaced by srun.

The minimal template to be filled is

#!/bin/bash -x
#SBATCH --account=<budget account>
# budget account where contingent is taken from
#SBATCH --nodes=<no of nodes>
#SBATCH --ntasks=<no of tasks (MPI processes)>
# can be omitted if --nodes and --ntasks-per-node
# are given
#SBATCH --ntasks-per-node=<no of tasks per node>
# if keyword omitted: Max. 288 tasks per node
# (SMT enabled, see comment below)
#SBATCH --cpus-per-task=<no of threads per task>
# for OpenMP/hybrid jobs only
#SBATCH --output=<path of output file>
# if keyword omitted: Default is slurm-%j.out in
# the submission directory (%j is replaced by
# the job ID).
#SBATCH --error=<path of error file>
# if keyword omitted: Default is slurm-%j.out in
# the submission directory.
#SBATCH --time=<walltime>
#SBATCH --partition=all

# *** start of job script ***
# Note: The current working directory at this point is
# the directory where sbatch was executed.

export OMP_NUM_THREADS=${SLURM_CPUS_PER_TASK}
srun <executable>

Multiple srun calls can be placed in a single batch script. Options such as --account, --nodes, --ntasks and --ntasks-per-node are by default taken from the sbatch arguments but can be overwritten for each srun invocation.

Multiple srun calls can be placed in a single batch script. Options such as --account, --nodes, --ntasks and --ntasks-per-node are by default taken from the sbatch arguments but can be overwritten for each srun invocation.

The default partition on JEDI, which is used if --partition is omitted, is the all partition.

Job Script Examples

Note

For more information about the use of --cpus-per-task, SRUN_CPUS_PER_TASK and SBATCH_CPUS_PER_TASK after the update to Slurm version 23.02, please refer to the affinity documention found here: https://apps.fz-juelich.de/jsc/hps/jureca/affinity.html

Example 1: MPI application starting 1552 tasks on 4 nodes using 288 CPUs per node (no SMT) running for max. 15 minutes:

#!/bin/bash -x
#SBATCH --account=<budget>
#SBATCH --nodes=4
#SBATCH --ntasks=1552
#SBATCH --output=mpi-out.%j
#SBATCH --error=mpi-err.%j
#SBATCH --time=00:15:00
#SBATCH --partition=all

srun ./mpi-prog

The job script is submitted using:

$ sbatch <jobscript>

On success, sbatch writes the job ID to standard out.

Note

One can also define sbatch options on the command line, e.g.:

$ sbatch --nodes=4 --acount=<budget> --time=01:00:00 <jobscript>

Generic Resources, Features and Topology-aware Allocations

All nodes on JEDI are the same so there is no need to differentiate via Slurms generic resources or features mechanisms.

Note

The charged computing time is independent of the number of specified GPUs. Production workloads must use all available GPU resources per node.

Job Steps

The example below shows a job script where two different job steps are initiated within one job. In total 96 cores are allocated on two nodes where -n 288 causes that each job step uses 48 cores on one of the compute nodes. Additionally in this example the option --exclusive is passed to srun to ensure that distinct cores are allocated to each job step.:

#!/bin/bash -x
#SBATCH --account=<budget>
#SBATCH --nodes=2
#SBATCH --ntasks=576
#SBATCH --ntasks-per-node=288
#SBATCH --output=mpi-out.%j
#SBATCH --error=mpi-err.%j
#SBATCH --time=00:20:00

srun --exclusive -n 288 ./mpi-prog1 &
srun --exclusive -n 288 ./mpi-prog2 &

wait

Dependency Chains

Slurm supports dependency chains, i.e., collections of batch jobs with defined dependencies. Dependencies can be defined using the --dependency argument to sbatch:

sbatch --dependency=afterany:<jobid> <jobscript>

Slurm will guarantee that the new batch job (whose job ID is returned by sbatch) does not start before <jobid> terminates (successfully or not). It is possible to specify other types of dependencies, such as afterok which ensures that the new job will only start if <jobid> finished successfully.

Below an example script for the handling of job chains is provided. The script submits a chain of ${NO_OF_JOBS} jobs. A job will only start after successful completion of its predecessor. Please note that a job which exceeds its time-limit is not marked successful.:

#!/bin/bash -x
# submit a chain of jobs with dependency
# number of jobs to submit
NO_OF_JOBS=<no of jobs>
# define jobscript
JOB_SCRIPT=<jobscript>
echo "sbatch ${JOB_SCRIPT}"
JOBID=$(sbatch ${JOB_SCRIPT} 2>&1 | awk '{print $(NF)}')
I=0
while [ ${I} -le ${NO_OF_JOBS} ]; do
echo "sbatch --dependency=afterok:${JOBID} ${JOB_SCRIPT}"
JOBID=$(sbatch --dependency=afterok:${JOBID} ${JOB_SCRIPT} 2>&1 | awk '{print $(NF)}')
let I=${I}+1
done

Interactive Sessions

Interactive sessions can be allocated using the salloc command:

$ salloc --partition=<devel|dc-cpu-devel|...> --nodes=2 --account=<budget> --time=00:30:00

Once an allocation has been made salloc will start a shell on the login node (submission host). One can then execute srun from within the shell, e.g.:

$ srun --ntasks=4 --ntasks-per-node=2 --cpus-per-task=7 ./hybrid-prog

The interactive session is terminated by exiting the shell. In order to obtain a shell on the first allocated compute nodes one can start a remote shell from within the salloc session and connect it to a pseudo terminal using:

$ srun --cpu_bind=none --nodes=2 --pty /bin/bash -i

The option --cpu_bind=none is used to disable CPU binding for the spawned shell. In order to execute MPI application one uses srun again from the remote shell. To support X11 forwarding the --forward-x option to srun is available. X11 forwarding is required for users who want to use applications or tools with provide a GUI.

Below a transcript of an exemplary interactive session is shown. srun can be run within the allocation without delay (note that the first srun execution may take slightly longer due to the necessary node health checking performed upon the invocation of the very first srun command within the session).

[user1@jpblt-s01-01 ~]$ hostname
jpblt-s01-01.jupiter.internal
[user1@jpblt-s01-01 ~]$ salloc --nodes=2 --account=<budget>
salloc: Granted job allocation 72
salloc: Waiting for resource configuration
salloc: Nodes jpbot-001-[17-18] are ready for job
[user1@jpblt-s01-01 ~]$ hostname
jpblt-s01-01.jupiter.internal
[user1@jpblt-s01-01 ~]$ srun --ntasks 2 hostname
jpbot-001-18.jupiter.internal
jpbot-001-17.jupiter.internal
[user1@jpblt-s01-01 ~]$ srun --cpu-bind=none --nodes=1 --pty /bin/bash -i
[user1@jpbot-001-17 ~]$ hostname
jpbot-001-17.jupiter.internal
[user1@jpbot-001-17 ~]$ exit
[user1@jpblt-s01-01 ~]$ hostname
jpblt-s01-01.jupiter.internal
[user1@jpblt-s01-01 ~]$ exit
exit
salloc: Relinquishing job allocation 72
salloc: Job allocation 72 has been revoked.
[user1@jpblt-s01-01 ~]$ hostname
jpblt-s01-01.jupiter.internal

To support X11 forwarding the --forward-x option to srun is available.

Note

Your account will be charged per allocation whether the compute nodes are used or not. Batch submission is the preferred way to execute jobs.

Hold and Release Batch Jobs

Jobs that are in pending state (i.e., not yet running) can be put in hold using:

scontrol hold <jobid>

Jobs that are in hold are still reported as pending (PD) by squeue but the Reason shown by squeue or scontrol show job is changed to JobHeldUser:

The job can be released using:

$ scontrol release <jobid>

Slurm commands

Below a list of the most important Slurm user commands available on JEDI is given.

sbatch

is used to submit a batch script (which can be a bash, Perl or Python script)

The script will be executed on the first node in the allocation chosen by the scheduler. The working directory coincides with the working directory of the sbatch program. Within the script one or multiple srun commands can be used to create job steps and execute (MPI) parallel applications.

Note

mpiexec is not supported on JEDI. srun is the only supported method to spawn MPI applications.

salloc

is used to request an allocation

When the job is started, a shell (or other program specified on the command line) is started on the submission host (login node). From the shell srun can be used to interactively spawn parallel applications. The allocation is released when the user exits the shell.

srun

is mainly used to create a job step within an job

srun can be executed without arguments except the program to use the full allocation or with additional arguments to restrict the job step resources to a subset of the allocated processors.

squeue

allows to query the list of pending and running jobs

By default it reports the list of pending jobs sorted by priority and the list of running jobs sorted separately according to the job priority.

scancel

is used to cancel pending or running jobs or to send signals to processes in running jobs or job steps

Example: scancel <jobid>

scontrol

can be used to query information about compute nodes and running or recently completed jobs

Examples:

• scontrol show job <jobid> to show detailed information about pending, running or recently completed jobs

• scontrol update job <jobid> set ... to update a pending job

Note

For old jobs scontrol show job <jobid> will not work and sacct -j <jobid> should be used instead.

sacct

is used to retrieve accounting information for jobs and job steps

For older jobs sacct queries the accounting database.

Example: sacct -j <jobid>

sinfo

is used to retrieve information about the partitions and node states

sprio

can be used to query job priorities

smap

graphically shows the state of the partitions and nodes using a curses interface

We recommend Llview as an alternative which is supported on all JSC machines.

sattach

allows to attach to the standard input, output or error of a running job

sstat

allows to query information about a running job

Summary of sbatch and srun Options

The following table summarizes important sbatch and srun command options:

--account	Budget account where contingent is taken from.
--nodes	Number of compute nodes used by the job. Can be omitted if --ntasks and --ntasks-per-node is given.
--ntasks	Number of tasks (MPI processes). Can be omitted if --nnodes and --ntasks-per-node is given. 1
--ntasks-per-node	Number of tasks per compute nodes.
--cpus-per-task	Number of logical CPUs (hardware threads) per task. This option is only relevant for hybrid/OpenMP jobs.
--job-name	A name for the job
--output	Path to the job’s standard output. Slurm supports format strings containing replacement symbols such as %j (job ID). 2
--error	Path to the job’s standard error. Slurm supports format strings containing replacement symbols such as %j (job ID).
--time	Maximal wall-clock time of the job.
--partition	Partition to be used, e.g. batch or large. If omitted, batch is the default.
--mail-user	Define the mail address to receive mail notification.
--mail-type	Define when to send a mail notifications. 3
--pty (srun only)	Execute the first task in pseudo terminal mode.
--forward-x (srun)	Enable X11 forwarding on the first allocated node.
--disable-turbomode (sbatch)	Disable turbo mode of all CPUs of the allocated nodes.

1

If --ntasks is omitted the number of nodes can be specified as a range --nodes=<min no. of nodes>-<max no. of nodes> allowing the scheduler to start the job with fewer nodes than the maximum requested if this reduces wait time.

2

stdout and stderr can be combined by specifying the same file for the --output and --error option.

3

Valid types: BEGIN, END, FAIL, REQUEUE, ALL, TIME_LIMIT, TIME_LIMIT_90, TIME_LIMIT_80, TIME_LIMIT_50, ARRAY_TASKS to receive emails when events occur. Multiple type values may be specified in a comma separated list.

More information is available on the man pages of sbatch, srun and salloc which can be retrieved on the login nodes with the commands man sbatch, man srun and man salloc, respectively, or in the Slurm documentation.

CPU Limiting Options

Each JEDI node includes 4 Grace Hopper Superchips, as covered in the configuration details for JEDI. Each Superchip is comprised of a CPU and GPU, and each Superchip receives a fixed total power budget of 680 W.

By default, the CPU for each Superchip is limited to a power budget of 100 W, to maximise performance from the GPU, which for many applications will be delivering the bulk of compute performance. However, in some cases, where work is split between CPU and GPU, it may be advantageous to to rebalance the power budget between CPU and GPU.

JSC deploys a custom Slurm plugin, which provides the option --grace-power-cap=<cap-in-watts> (e.g. to set to 200 Watts use --grace-power-cap=200). This option is available for sbatch, srun and salloc commands, and can be set to values between 100 and 300, changing the CPU power limit to the corresponding number of Watts. The option operates on a per-node level, i.e. it limits all Grace CPUs on that node to the given value at once (including CPUs with job steps that may already be running).

Warning

Currently, setting this value to a number higher than 300 will silently fail and the CPU power limit will be set to the default of 100 W.

Note

If this option is used in srun commands, the value will not be reset at the end of that srun commands, i.e. if used in a batch script or salloc session with multiple job steps, subsequent jobs will use the same custom power limit.

It is important to understand that raising power limits on the CPU can diminish the amount of power available to the GPU, and there is not a 1-to-1 relationship between the power available, clock speeds and performance. If using this option, it is important to benchmark your specific use-case to understand what benefits (if any) you can extract from it, and in which situations this unacceptably degrades GPU performance.