Cluster Documentation: Difference between revisions

From ITTC Help
Jump to navigation Jump to search
No edit summary
 
(113 intermediate revisions by 6 users not shown)
Line 1: Line 1:
== Introduction ==
=Visit I2S New Cluster Documentation https://help.ittc.ku.edu/clusterdocs=
 
 
The Advanced Computing Facility (ACF) is located at the Information and Telecommunication Technology Center (ITTC) in Nichols Hall, and provides a 20-fold increase in power to support a diverse range of research. The facility houses high performance computing (HPC) resources and, thanks to a $4.6 million renovation grant from the NIH, has the capability of supporting over 24,000 processing cores. A unique feature of the ACF is a sophisticated computer-rack cooling system that shuttles heat from computing equipment into the Nichols Hall boiler room, resulting in an expected 15% reduction in building natural gas use. Additionally, when outdoor temperatures drop below 45 degrees, a "dry-cooler" will kick in, slashing electricity consumption by allowing cooling compressors to be powered down.
 
The ITTC Research Cluster is located in the ACF, and provides HPC resources to members of the center. The cluster uses the Slurm workload manager, which is an open source, fault-tolerant, and highly scalable cluster management and job scheduling system for Linux clusters. The cluster is composed of a variety of hardware types, with core counts ranging from 8 to 20 cores per node. In addition, there is specialized hardware including Nvidia graphics cards for GPU computing, Infiniband for low latency/high throughput parallel computing, and large memory systems with up to 512 GB of RAM.
 
== Job Submission Guide ==
=== PBS/Torque and Slurm ===
A translation for common PBS/Torque commands to Slurm commands can be found [https://slurm.schedmd.com/rosetta.pdf here]. This provides a quick guide for those who are familiar with PBS/Torque, but new to the Slurm scheduler.
 
=== Submitting Jobs ===
 
To submit jobs to the cluster, you can either write a script and submit it using sbatch:
<pre>
[username@login1 ~]$ sbatch script.sh
</pre>
 
Or, you can submit jobs interactively from the command line using srun:
<pre>
[username@login1 ~]$ srun echo Hello World!
</pre>
 
Job scripts use parameters (denoted by <code>#SBATCH</code>) in the script file to requested job resources, while interactive jobs request resources with command line parameters. When no resources are requested, a default set is automatically allocated for the job.
 
;This default resource set includes <b>:</b>
*The job's name is set the same as the script file name, or, if the job was started with srun, then the job name is the same as the first command (in the case of the example above, the name would be set to 'echo').<br/>
*The job is scheduled in the default intel queue.<br/>
*The job is allocated 1 core on 1 node with 2GB of memory.<br/>
*The job is allocated 1 day to run.<br/>
*The job redirects stdout and stderr to the same output file if the job is submitted with sbatch. If srun is used, then both will be printed to the screen.<br/>
*The job's output file name takes the form "slurm-<i>jobid</i>.out", and is created in the same directory as the job script.<br/>
 
==== <h3>srun</h3> ====
 
<code>srun</code> can be used to run any single task on a cluster node, but it is most useful for launching interactive GUI or bash sessions. Here is a srun example run on login1:
 
<pre>
[username@login1 ~]$ srun -p intel -N 1 -n 1 -c 4 --mem 4G --pty /bin/bash
[username@n097 ~]$
</pre>
 
;The options used in this example are all detailed below<b>:</b>:
:; -p        : Specifies a partition, or queue to create the job in. The current cluster partitions available are <code>intel</code>, <code>amd</code>, <code>bigm</code>, and <code>gpu</code>. For more information on the cluster queues, see [ this] page.
:; -N        : This sets the number of requested nodes for the interactive session.
:; -n        : Specifies the number of tasks or processes to run on each allocated node.
:; -c        : Sets the number of requested cpus per task
:; --mem    : This specifies the requested memory per node. Memory amounts can be given in Kilobytes (K), Megabytes (M), and Gigabytes (G).
:; --pty    : This option puts the srun session in pseudo-terminal mode. It is recommended to use this option if you are running an interactive shell session.
:; /bin/bash : The last option in a srun invocation is the program that srun will execute on the requested node. In this case, bash is specified to start an interactive shell session.
 
srun is used to submit both interactive and non-interactive jobs. When it is run directly on the command line as shown above, an interactive session is started on a cluster node. When it is used in a job submission script, it starts a non-interactive session.
 
==== <h3>sbatch</h3> ====
 
<code>sbatch</code> is used to submit jobs to the cluster using a script file. Below is an example job submission script:
 
<pre>
#!/bin/bash
#SBATCH -p intel
#SBATCH -N 1
#SBATCH -n 1
#SBATCH -c 1
#SBATCH --mem=1GB
#SBATCH -t 00:20:00
#SBATCH -J test_job
#SBATCH -o slurm-%j.out
echo "Job ${SLURM_JOB_ID} ran on ${HOSTNAME}"
</pre>
 
Example output:
 
<pre>
[username@login1 ~]$ sbatch test_job.sh
[username@login1 ~]$ cat slurm-47491.out
Job 47491 ran on n097
[username@login1 ~]$
</pre>
 
This script requests one node with one core, and 1GB of memory. <code>-J</code> is used to specify the job name that appears in the job queue, while <code>-o</code> specifies the log file name for the job. <code>%j</code> in the job output file name is replaced with the Slurm job id when the scheduler processes the script. The variable <code>SLURM_JOB_ID</code> used in the example output is an environment variable set by the Slurm scheduler for each job.
 
To run this example script, copy its contents into a file in your home directory (test_job.sh for example). Log in to either login1.ittc.ku.edu or login2.ittc.ku.edu with your ITTC credientials, and run the command <code>sbatch test_job.sh</code>. The job output log will be saved in the same directory as the job submission script, and should contain similar output to the example.
 
sbatch job scripts can run programs directly, as show above, but it is also possible to use srun within job submission scripts to run programs. Using srun in a job script allows for fine-grained resource control over parallel tasks run in a job script. An example is shown below:
 
<pre>
#!/bin/bash
#SBATCH -p intel
#SBATCH -N 1
#SBATCH -n 2
#SBATCH -c 1
#SBATCH --mem=2GB
#SBATCH -t 00:20:00
#SBATCH -J test_job
#SBATCH -o slurm-%j.out
 
srun -n 1 --mem=1G echo "Task 1 ran" &
srun -n 1 --mem=1G echo "Task 2 ran" &
 
wait
</pre>
 
When the sbatch script is submitted, both srun invocations will run at the same time, splitting the resources requested at the top of the script file. This method is useful for launching a small number of related jobs at once from the same script, but does not scale well with a large number of jobs. The Job Array section below goes into more depth on running large numbers of parallel jobs on the cluster.
 
When using srun within a job submission script, you need to specify what portion of the resources each srun invocation is allocated. If more resources are requested by srun than are made available by the <code>#SBATCH</code> parameters, then some jobs may wait to run, or attempt to share resources with already running jobs. In the example above, two tasks and 2GB of memory are requested. In the srun commands below the resource request, we specify how much memory and how many tasks are allocated to each job.
 
The sbatch options shown in these example scripts are just the tip on the iceberg in terms of what is available. For the full listing of sbatch parameters, see the official Slurm [https://slurm.schedmd.com/sbatch.html sbatch documentation]
 
;Here is a brief list of other common options that may be useful<b>:</b>:
:; -C                : Specifies a node constraint. This can be used to specify gpu nodes. See [ this ] example for more information on running gpu jobs.
:; -D                : Specifies the path to the log file destination directory. This can be an absolute path, or a relative path from the job submission script directory.
:; --cores-per-socket : Sets the requested number of cores per cpu socket.
:; --mem-per-cpu      : This specifies the memory allocated to each cpu in the interactive session. It has the same memory specification syntax as <code>--mem</code>.
:; --mail-type        : Sets when the user is to be mailed job notifications. NONE, BEGIN, END, FAIL, REQUEUE, TIME_LIMIT, TIME_LIMIT_90, TIME_LIMIT_80, and TIME_LIMIT_50 are all valid options
:; --mail-user        : specifies the user account to email when job notification emails are sent.
 
==== <h3>Job Arrays</h3> ====
Submitting a large number of cluster jobs at once has two general approaches. The first is to submit jobs to the scheduler using srun in a loop on the command line. The preferable, and more powerful approach uses job arrays to submit large blocks of jobs all at once with the sbatch command.
 
The <code>--array</code> parameter for sbatch allows the scheduler to queue up hundreds to thousands of jobs with the same resource requests. This method is much less taxing on the cluster scheduler, and simplifies the process of submitting a large number of jobs all at once. These arrays usually consist of the same program fed different parameters dictated by the job array indicies. An example job array script is shown below:
 
<pre>
#!/bin/bash
#SBATCH -p intel
#SBATCH -N 1
#SBATCH -n 1
#SBATCH -c 1
#SBATCH --mem=1G
#SBATCH -t 00:20:00
#SBATCH -J test_job
#SBATCH -o logs/%A_%a.out
#SBATCH --array=1-4
 
echo Job ${SLURM_ARRAY_TASK_ID} used $(awk "NR == ${SLURM_ARRAY_TASK_ID} {print \$0}" ${SLURM_SUBMIT_DIR}/parameters)
</pre>
 
In this example, the <code>%A</code> and <code>%a</code> symbols in the job log file path are replaced with the job array id and job array indicie respectively for each job in the array. The <code>--array</code> option specifies the creation of a job array which consists of four identical jobs with indices ranging from 1 to 4. Each job in the array is created with the same resource request at the top of the file, and will run the same bash command at the bottom of the script file. The <code>echo</code> command prints out the <code>SLURM_ARRAY_TASK_ID</code>  (or job array indicie) environment variable of each job, along with one line from a file called "parameters". The <code>awk</code> command within the <code>echo</code> selects one line in the parameters file with a line number that matches the job array indicie value. This technique can be used to feed in specific parameters to different jobs within a job array.
 
Another way of generating program parameters based on job array indices is through arithmetic. For example, if you wanted to define a minimum and maximum value a job needed to loop through, in your job script, you may include something like this:
 
<pre>
MAX=$(echo "${SLURM_ARRAY_TASK_ID} * 1000" | bc)
MIN=$(echo "$({SLURM_ARRAY_TASK_ID} - 1) * 1000" | bc)
 
for (( i=$MIN; i<$MAX; i++ )); do
  # Perform calculations...
done
</pre>
=== Cluster Partitions ===
Cluster partitions, or queues, are sets of nodes in the cluster grouped by their features. Currently, there are four partition in the ITTC cluster: intel, amd, bigm, and gpu. The intel and amd partitions are made up of nodes that contain exclusively intel and amd cpus respectively. The bigm queue is made up of nodes with RAM from 256 to 500GB, and the gpu partition contains nodes with Nvidia gpu co-processors. A specific partition can
==== Node Constraints ====
 
== GUI Access ==
 
 
===X11 forwarding===
Access to a GUI running on the cluster may be accomplished with X11 forwarding.  Data from the remote application is sent over ssh to an X server running locally.  Each additional ssh connection between the local machine and the cluster must be started with X11 forwarding enabled.  To request an interactive shell with X11 forwarding, you can run "srun.x11". The following steps assume that the local machine has an X server running.
 
1.  Login via ssh to login1 or login2.  Make sure your local ssh client has X11 forwarding enabled.  If you are using ssh on the command line, add the "-Y" flag to your ssh command. <br>
2.  Start an interactive session with X11 forwarding.  Be sure to request the number of cores, amount of memory, and walltime to complete your job.  Syntax: <br>
<pre>
srun.x11 -N 1 -n 2 --mem=4096mb -t 8:00:00
</pre>
 
===NoMachine===
 
NoMachine is a remote desktop application that is available for Linux, Windows, and OSX. NoMachine requires that you are connected to the KU or ITTC network; remote users will need to use the KU Anywhere VPN.
 
;Here is a step-by-step guide to setting up NoMachine<b>:</b>
 
<pdf height="575">File:NoMachineTutorial.pdf</pdf>
 
== Application Support ==
 
== Helpful Commands ==
The Slurm scheduler has a number of utilities for finding information on the status of your jobs. Below are listed a few of the most useful commands and options for quickly finding this information.
 
; Useful Slurm commands<b>:</b>:
:;squeue : Displays the short-form information for all currently running and queued jobs.
:;squeue -u username -l : Lists the long-form information about currently running jobs for a specific user.
:;sinfo : Displays information on which nodes are currently in use, and which are available to run on.
:;sinfo -T : Shows information on cluster node reservations, including reservation period, name, and reserved nodes.
:;sacct : Lists information on finished and currently running jobs, including job status and exit codes.
:;sview : If X11 forwarding is enabled, this command launches a graphical interface for viewing cluster information.
 
== Debugging ==
 
== Profiling ==

Latest revision as of 12:07, 11 August 2025

Visit I2S New Cluster Documentation https://help.ittc.ku.edu/clusterdocs

Retrieved from "https://help.ittc.ku.edu/index.php?title=Cluster_Documentation&oldid=1863"