Difference between revisions of "TALC Cluster"

From RCSWiki
Jump to navigation Jump to search
(Initial import)
 
 
(23 intermediate revisions by 4 users not shown)
Line 3: Line 3:
 
|title=Cybersecurity awareness at the U of C
 
|title=Cybersecurity awareness at the U of C
 
|message=Please note that there are typically about 950 phishing attempts targeting University of Calgary accounts each month. This is just a reminder to be careful about computer security issues, both at home and at the University. Please visit https://it.ucalgary.ca/it-security for more information, tips on secure computing, and how to report suspected security problems.}}
 
|message=Please note that there are typically about 950 phishing attempts targeting University of Calgary accounts each month. This is just a reminder to be careful about computer security issues, both at home and at the University. Please visit https://it.ucalgary.ca/it-security for more information, tips on secure computing, and how to report suspected security problems.}}
 
{{Message Box
 
|title=Need Help or have other ARC Related Questions?
 
|message=For all general RCS related issues, questions, or comments, please contact us at support@hpc.ucalgary.ca.
 
|icon=Support Icon.png}}
 
 
  
 
This guide gives an overview of the Teaching and Learning Cluster (TALC) at the University of Calgary and is intended to be read by new account holders getting started on TALC. This guide covers topics as the hardware and performance characteristics, available software, usage policies and how to log in and run jobs.  
 
This guide gives an overview of the Teaching and Learning Cluster (TALC) at the University of Calgary and is intended to be read by new account holders getting started on TALC. This guide covers topics as the hardware and performance characteristics, available software, usage policies and how to log in and run jobs.  
  
 
==Introduction==
 
==Introduction==
TALC is a cluster of computers created by Research Computing Services in response to requests for a central computing resource to support academic courses and workshops offered at the University of Calgary. It is a complement to the Advanced Research Computing (ARC) cluster that is used for research, rather than educational purposes. However, procedures for using TALC are very similar to those for ARC, so, what students learn about using TALC will have direct applicability to using ARC should they go on to use ARC for research work. At least for now, we also rely heavily on the ARC or external documentation, instead of repeating it here.
+
TALC is a cluster of computers created by Research Computing Services (RCS) in response to requests for a central computing resource to support academic courses and workshops offered at the University of Calgary. It is a complement to the Advanced Research Computing (ARC) cluster that is used for research, rather than educational purposes. The software environment in the TALC and ARC clusters is very similar and workflows between the two clusters are identical.  What students learn about using TALC will have direct applicability to using ARC should they go on to use ARC for research work.  
 +
 
 +
If you are the instructor for a course that could benefit from using TALC, please review this guide and the [[TALC Terms of Use]] and then contact us at support@hpc.ucalgary.ca to discuss your requirements. 
  
If you are the instructor for a course that could benefit from using TALC, please review this page and the TALC terms of use (which will be made available at https://rcs.ucalgary.ca/TALC_Terms_of_Use).  Then, write to support@hpc.ucalgary.ca  to discuss your requirements.  In order to ensure that software and accounts are in place and that your tutorial assistants have appropriate training, it is best to start this dicsussion several months prior to the start of the course.
+
Please note that in order to ensure that the appropriate software is available, student accounts are in place, and appropriate training has been provided for your teaching assistants, it is best to start this discussion several months prior to the start of the course.
  
If you are a student in a course for which TALC is being used, please review this guide for basic instructions in using the cluster.  Questions should first be directed to the tutorial assitants or instructor for your course.
+
If you are a student in a course using TALC, please review this guide for basic instructions in using the cluster.  Questions should first be directed to the teaching assistants or instructor for your course.
  
==Accounts==
+
===Obtaining an account===
TALC account requests are expected to be submitted by the instructor for the course involved, rather than from individual students.
+
TALC account requests are expected to be submitted by the course instructor rather than from individual students. You must have a University of Calgary IT account in order to use TALC. If you do not have a University of IT account or email address, please register for one at https://itregport.ucalgary.ca/. In order to ensure TALC is provisioned in time for a course start date, the instructor should submit the initial list of @ucalgary.ca accounts needed for the course 2 weeks before the start date.
  
Note that University of Calgary Information Technologies computing account credentials are used for TALC (the same as used for University of Calgary email accounts). If you don't have a University of Calgary email address, please register for one at https://itregport.ucalgary.ca/ ,
+
=== Getting Support ===
 +
{{Message Box
 +
|title=Need Help or have other TALC Related Questions?
 +
|message='''Students''', please send TALC-related questions to your course instructor or teaching assistants.<br />
 +
'''Course instructors and TAs''', please report system issues to support@hpc.ucalgary.ca.
 +
|icon=Support Icon.png}}
  
 
==Hardware==
 
==Hardware==
===Processors===
+
The TALC cluster is comprised of repurposed research clusters that are a few generations old. As a result, individual processor performance will not be comparable to the latest processors but should be sufficient for educational purposes and course work.   
Besides login and administrative servers, the TALC hardware consists of compute nodes where the bulk of the computations are performed.  These compute nodes were repurposed from older research computing clusters. As such, individual processor performance will not be comparable to modern computers, but, should be sufficient for coursesThere are two types of compute node in the TALC cluster, identified by a label called a partition:
+
{| class="wikitable"
 +
!Partition
 +
!Description
 +
!Nodes
 +
!CPU Cores, Model, and Year
 +
!Installed Memory
 +
!GPU
 +
!Network
 +
|-
 +
|gpu
 +
|GPU Compute
 +
|3
 +
|12 cores, 2x Intel Xeon Bronze 3204 CPU @ 1.90GHz (2019)
 +
|192 GB
 +
|5x NVIDIA Corporation TU104GL [Tesla T4]
 +
|40 Gbit/s InfiniBand
 +
|-
 +
|cpu16
 +
|General Purpose Compute
 +
|36
 +
|16 cores, 2x Eight-Core Intel Xeon CPU E5-2650 @ 2.00GHz (2012)
 +
|64 GB
 +
|N/A
 +
|40 Gbit/s InfiniBand
 +
|-
 +
|bigmem
 +
|General Purpose Compute
 +
|2
 +
|32 cores, 4x Intel(R) Xeon(R) CPU E7- 4830  @ 2.13GHz (2015)
 +
|1024 GB
 +
|N/A
 +
|40 Gbit/s InfiniBand
 +
|}
  
*cpu24 partition nodes: These are 24-core nodes, each with four sockets having 6-core AMD Istanbul processors running at 2.4 GHz. The 24 cores associated with one compute node share 256 GB of RAM, but, it is recommended that jobs request at most 255000 MB.  The cpu24 paritition nodes are connected with a high-speed InfiniBand network.
+
===Storage===
*cpu32-bigmem partition node: This is a single 32-core node with four 8-core Intel Xeon CPU E7- 4830 processors running at 2.13 GHz. These processors share 1 TB of memory of which you can request up to 1000000 MB.
+
{{Message Box
Storage
+
| title=No Backup Policy!
In addition to the compute nodes, TALC is connected to a disk storage system. There are two storage areas that are relevant when using TALC, the /home and /scratch file systems.  When you log in to TALC, your working directory is in the /home file system.  There is a quota of 500 GB for each user in /home.  The /scratch file system is used for large, job-oriented storage.
+
| message=You are responsible for your own backups.  Since accounts on TALC and related data are removed shortly after the associated course has finished, you should download anything you need to save to your own computer before the end of the course.
 +
}}
  
Associated with each job (calculation to be completed) a subdirectory of /scratch is created that can be referenced in job scripts as /scratch/${SLURM_JOB_ID}. You can use that directory for temporary files needed during the course of a job. Up to 30 TB of storage may be used, per user (total for all your jobs) in the /scratch file system. Deletion policy: data in /scratch associated with a given job will be deleted automatically, without exception, five days after the job finishes.
+
TALC is connected to a network disk storage system. This storage is split across the <code>/home</code> and <code>/scratch</code> file systems.
 +
====<code>/home</code>: Home file system====
 +
Each user has a directory under /home and is the default working directory when logging in to TALC. Each home directory has a per-user quota of 500 GB. This limit is fixed and cannot be increased.
  
'''Backup policy''': you are responsible for your own backupsSince accounts on TALC and related data are removed shortly after the associated course has finished, you should download anything you need to save to your own computer before the end of the course.
+
Note on file sharing: Due to security concerns, permissions set using <code>chmod</code> on your home directory to allow other users to read/write to your home directory will be automatically reverted by an automated system process unless an explicit exception is madeIf you need to share files with others on the TALC cluster, please write to support@hpc.ucalgary.ca to ask for such an exception.
  
===Software===
+
====<code>/scratch</code>: Scratch file system for large job-oriented storage====
Look for installed software under /global/software and through the module avail command. The configuration of the environment for using some of the installed software is facilitated through options of the module command.
+
Associated with each job, under the <code>/scratch</code> directory, a subdirectory is created that can be referenced in job scripts as <code>/scratch/${SLURM_JOB_ID}</code>. You can use that directory for temporary files needed during the course of a job. Up to 30 TB of storage may be used, per user (total for all your jobs) in the <code>/scratch</code> file system.
  
To list available enviornment modules, type:
+
Data in <code>/scratch</code> associated with a given job will be deleted automatically, without exception, five days after the job finishes.
  
module avail
+
== Software ==
 +
{{Message Box
 +
| title=Software Package Requests
 +
| message=Course instructors or teaching assistants should write to support@hpc.ucalgary.ca if additional software is required for their course.
 +
}}
  
To set up your environment to use one of the listed software packages, use the module load command. For example, to load a module for a particular version of Python 3 you can use:
+
All TALC nodes run a version of Rocky Linux. For your convenience, we have packaged commonly used software packages and dependencies as modules available under <code>/global/software</code>. If your software package is not available as a module, you may also try Anaconda which allows users to manage and install custom packages in an isolated environment.
  
module load python/anaconda-3.6-5.1.0
+
For a list of available packages that have been made available, please see [[ARC Software pages]].  
  
To remove the software from your environment, use
+
=== Modules ===
 +
The setup of the environment for using some of the installed software is through the <code>module</code> command.
  
module remove python/anaconda-3.6-5.1.0
+
Software packages bundled as a module will be available under <code>/global/software</code> and can be listed with the <code>module avail</code> command.
 +
<syntaxhighlight lang="bash">
 +
$ module avail
 +
</syntaxhighlight>
  
To see currently loaded modules, type:
+
To enable Python, load the Python module by running:
 +
<syntaxhighlight lang="bash">
 +
$ module load python/anaconda-3.6-5.1.0
 +
</syntaxhighlight>
  
module list
+
To unload the Python module, run:
 +
<syntaxhighlight lang="bash">
 +
$ module remove python/anaconda-3.6-5.1.0
 +
</syntaxhighlight>
  
Course instructors or assistants should write to support@hpc.ucalgary.ca if additional software needs to be installed.
+
To see currently loaded modules, run:
 +
<syntaxhighlight lang="bash">
 +
$ module list
 +
</syntaxhighlight>
  
 
==Using TALC==
 
==Using TALC==
 +
{{Message Box
 +
|title=Usage subject to [[TALC Terms of Use]]
 +
|message=Please review the [[TALC Terms of Use]] prior to using TALC.
 +
|icon=Support Icon.png}}
 +
 
===Logging in===
 
===Logging in===
To log in to TALC, connect to talc.ucalgary.ca using an ssh (secure shell) client. For more information about connecting and setting up your environment, the WestGrid QuickStart Guide for New Users may be helpful.  Note that connections are accepted only from on-campus IP addresses. You can connect from off-campus by using Virtual Private Network (VPN) software available from Information Techologies.
+
To log in to TALC, connect using SSH to talc.ucalgary.ca. Connections to TALC are accepted only from the University of Calgary network (on campus) or through the University of Calgary General VPN (off campus).
 +
 
 +
See [[Connecting to RCS HPC Systems]] for more information.
  
 
===Working interactively===
 
===Working interactively===
TALC uses the Linux operating system. The program that responds to your typed commands and allows you to run other programs is called the Linux shell. There are several different shells available, but, by default you will use one called bash. It is useful to have some knowledge of the shell and a variety of other command-line programs that you can use to manipulate files. If you are new to Linux systems, we recommend that you work through one of the many online tutorials that are available, such as the UNIX Tutorial for Beginners provided by the University of Surrey. The tutorial covers such fundamental topics, among others, as creating, renaming and deleting files and directories, how to produce a listing of your files and how to tell how much disk space you are using.   For a more comprehensive introduction to Linux, see The Linux Command Line.
+
<!-- original chunk -->
 +
TALC uses the Linux operating system. The program that responds to your typed commands and allows you to run other programs is called the Linux shell. There are several different shells available, but, by default you will use one called bash. It is useful to have some knowledge of the shell and a variety of other command-line programs that you can use to manipulate files. If you are new to Linux systems, we recommend that you work through one of the many online tutorials that are available, such as the [http://www.ee.surrey.ac.uk/Teaching/Unix/index.html UNIX Tutorial for Beginners (external link)] provided by the University of Surrey. The tutorial covers such fundamental topics, among others, as creating, renaming and deleting files and directories, how to produce a listing of your files and how to tell how much disk space you are using. For a more comprehensive introduction to Linux, see [http://linuxcommand.sourceforge.net/tlcl.php The Linux Command Line (external link)].
  
The TALC login node may be used for such tasks as editing files, compiling programs and running short tests while developing programs (under 15 minutes, say). Processors may also be reserved for interactive sessions using the salloc command specifying the resources needed through arguments on the salloc command line.
+
The TALC login node may be used for such tasks as editing files, compiling programs and running short tests while developing programs. CPU intensive workloads on the login node should be restricted to under 15 minutes as per [[General Cluster Guidelines and Policies|our cluster guidelines]]. For interactive workloads exceeding 15 minutes, use the '''[[Running_jobs#Interactive_jobs|salloc command]]''' to allocate an interactive session on a compute node.
 +
 
 +
The default <code>salloc</code> allocation is 1 CPU and 1 GB of memory. Adjust this by specifying <code>-n CPU#</code> and <code>--mem Megabytes</code>. You may request up to 5 hours of CPU time for interactive jobs.
 +
salloc --time 5:00:00 --partition cpu16
  
 
===Running non-interactive jobs (batch processing)===
 
===Running non-interactive jobs (batch processing)===
Production runs and longer test runs should be submitted as (non-interactive) batch jobs, in which commands to be executed are listed in a script (text file). Batch jobs scripts are submitted using the sbatch command, part of the Slurm job management and scheduling software. #SBATCH directive lines at the beginning of the script are used to specify the resources needed for the job (cores, memory, run time limit and any specialized hardware needed).
+
Production runs and longer test runs should be submitted as (non-interactive) batch jobs, in which commands to be executed are listed in a script (text file). Batch jobs scripts are submitted using the <code>sbatch</code> command, part of the Slurm job management and scheduling software. #SBATCH directive lines at the beginning of the script are used to specify the resources needed for the job (cores, memory, run time limit and any specialized hardware needed).
  
 
Most of the information on the Running Jobs page on the Compute Canada web site is also relevant for submitting and managing batch jobs and reserving processors for interactive work on TALC.  One major difference between running jobs on the TALC and Compute Canada clusters is in selecting the type of hardware that should be used for a job. On TALC, you choose the hardware to use primarily by specifying a partition, as described below.
 
Most of the information on the Running Jobs page on the Compute Canada web site is also relevant for submitting and managing batch jobs and reserving processors for interactive work on TALC.  One major difference between running jobs on the TALC and Compute Canada clusters is in selecting the type of hardware that should be used for a job. On TALC, you choose the hardware to use primarily by specifying a partition, as described below.
 +
 +
===Using JupyterHub on Talc===
 +
TALC has a Jupyterhub server which runs a Jupyter server on one of the TALC compute nodes and provides all the necessary encryption and plumbing to deliver the notebook to your computer.  To access this service you must have a TALC account. Point your browser at http://talc.ucalgary.ca and login with your usual UC account.  As of this writing, the job that runs the jupyter notebook is 1 cpu and 10GiB of memory on a cpu16 node.
  
 
===Selecting a partition===
 
===Selecting a partition===
The type of computer on which a job can or should be run is determined by characteristics of your software, such as whether it supports parallel processing and by simulation or data-dependent factors such as the amount of memory required.  If the program you are running uses MPI (Message Passing Interface) for parallel processing, which allows the memory usage to be distributed across multiple compute nodes, then, the memory required per MPI process is an important factor.  If you are running a serial code (that is, it is not able to use multiple CPU cores) or one that is parallelized with OpenMP or other thread-based techniques that restrict it to running on just a single compute node, then, the total memory required is the main factor to consider.
+
TALC currently has the following partitions available for use. The <code>gpu</code> and <code>cpu12</code> partitions are refer to the same nodes. The <code>cpu12</code> partition was created to only expose the CPUs on the GPU hardware for general purpose use. Each GPU node has 5 Tesla T4 GPUs installed, but you may only request one per job within the TALC environment.
 +
{| class="wikitable"
 +
!Partition
 +
!Description
 +
!Nodes
 +
!Cores
 +
!Memory
 +
!Memory Request Limit
 +
!Time Limit
 +
!GPU Request per Job
 +
!Network
 +
|-
 +
|gpu
 +
|GPU Compute
 +
|3
 +
|12 cores
 +
|192 GB
 +
|190 GB
 +
|24 hours
 +
|1x NVIDIA Corporation TU104GL [Tesla T4]
 +
|40 Gbit/s InfiniBand
 +
|-
 +
|cpu12
 +
|General Purpose Compute
 +
|3
 +
|12 cores
 +
|192 GB
 +
|190 GB
 +
|24 hours
 +
|None
 +
|40 Gbit/s InfiniBand
 +
|-
 +
|cpu16
 +
|General Purpose Compute
 +
|36
 +
|16 cores
 +
|64 GB
 +
|62 GB
 +
|24 hours
 +
|None
 +
|40 Gbit/s InfiniBand
 +
|-
 +
|bigmem
 +
|General Purpose Compute
 +
|2
 +
|32 cores
 +
|1024 GB
 +
|1022 GB
 +
|24 hours
 +
|None
 +
|40 Gbit/s InfiniBand
 +
|}
 +
There are some aspects to consider when selecting a partition including:
 +
* Resource requirements in terms of memory and CPU cores
 +
* Hardware specific requirements, such as GPU or CPU Instruction Set Extensions
 +
* Partition resource limits and potential wait time
 +
* Software support for parallel processing using Message Passing Interface (MPI), OpenMP, etc. For example, MPI for parallel processing can distribute memory across multiple nodes, so that per-node memory requirements could be lower. Whereas OpenMP or single process serial code that is restricted to one node would require a higher memory node.
  
Once you have decided what type of hardware best suits your calculations, you can select it on a job-by-job basis by including the partition keyword for an SBATCH directive in your batch job. The table below summarizes the characteristics of the various partitions.
+
Since resources that are requested are reserved for your job, please request only as much CPU and memory as your job requires to avoid reducing the cluster efficiency.  If you are unsure which partition to use or the specific resource requests that are appropriate for your jobs, please contact us at [mailto:support@hpc.ucalgary.ca support@hpc.ucalgary.ca] and we would be happy to work with you.
  
Partition Cores/node Memory limit (MB) Time limit (h)
+
=== Using a partition ===
cpu24 24 255000 24
 
cpu32-bigmem 32 1000000 24
 
For example, to select the cpu24 partition, include the following line in your batch job script:
 
  
#SBATCH --partition=cpu24
+
==== CPU only jobs ====
 +
To select the <code>cpu16</code> partition, include the following line in your batch job script:<syntaxhighlight lang="text">
 +
#SBATCH --partition=cpu16
 +
</syntaxhighlight>You may also start an interactive session with <code>salloc</code>:<syntaxhighlight lang="text">
 +
$ salloc --time 1:00:00 -p cpu16
 +
</syntaxhighlight>
  
===Time limits===
+
==== GPU jobs ====
Use a directive of the form
+
In TALC, you are limited to exactly 1 GPU per job. Jobs that request for 0 GPUs or 2 or more GPUs will not be scheduled.
  
#SBATCH --time=hh:mm:ss
+
To submit a job using the <code>gpu</code> partition with one GPU request, include the following to your batch job script:<syntaxhighlight lang="text">
 +
#SBATCH --partition=gpu
 +
#SBATCH --gpus-per-node=1
 +
</syntaxhighlight>
 +
 
 +
Like the previous example, you may also request interactive sessions with GPU nodes using <code>salloc</code>. Just specify the <code>gpu</code> partition and the number of GPUs required. <syntaxhighlight lang="text">
 +
$ salloc --time 1:00:00 -p gpu -n 1 --gpus-per-node 1
 +
</syntaxhighlight>You may verify that a GPU was assigned to your job or interactive session by running <code>nvidia-smi</code>. This command will show you the status of the GPU that was assigned to you.<syntaxhighlight lang="text">
 +
$ nvidia-smi
 +
+-----------------------------------------------------------------------------+
 +
| NVIDIA-SMI 450.80.02    Driver Version: 450.80.02    CUDA Version: 11.0    |
 +
|-------------------------------+----------------------+----------------------+
 +
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
 +
| Fan  Temp  Perf  Pwr:Usage/Cap|        Memory-Usage | GPU-Util  Compute M. |
 +
|                              |                      |              MIG M. |
 +
|===============================+======================+======================|
 +
|  0  Tesla T4            Off  | 00000000:3B:00.0 Off |                    0 |
 +
| N/A  36C    P0    14W /  70W |      0MiB / 15109MiB |      5%      Default |
 +
|                              |                      |                  N/A |
 +
+-------------------------------+----------------------+----------------------+
 +
                                                                             
 +
+-----------------------------------------------------------------------------+
 +
| Processes:                                                                  |
 +
|  GPU  GI  CI        PID  Type  Process name                  GPU Memory |
 +
|        ID  ID                                                  Usage      |
 +
|=============================================================================|
 +
|  No running processes found                                                |
 +
+-----------------------------------------------------------------------------+
 +
</syntaxhighlight>
 +
 
 +
==== Partition limitations ====
 +
In addition to the hardware limitations of the nodes within the partition, please be aware that there may also be policy limits imposed on your account for each partition. These limits restrict the number of cores, nodes, or GPUs that can be used at any given time. Since the limits are applied on a partition-by-partition basis, using resources in one partition should not affect the available resources you can use in another partition.
  
to tell the job scheduler the maximum time that your job might run. You can use the command
+
These limits can be listed by running:
 +
<syntaxhighlight lang="bash">
 +
$ sacctmgr show qos format=Name,MaxWall,MaxTRESPU%20,MaxSubmitJobs
 +
      Name    MaxWall            MaxTRESPU MaxSubmit
 +
---------- ----------- -------------------- ---------
 +
    normal  1-00:00:00                               
 +
  cpulimit                          cpu=48         
 +
gpucpulim+                          cpu=18         
 +
  gpulimit                cpu=2,gres/gpu=1               
 +
</syntaxhighlight>
  
  scontrol show partitions
+
=== Time limits ===
 +
Use the <code>--time</code> directive to tell the job scheduler the maximum time that your job might run. For example:
 +
#SBATCH --time=hh:mm:ss
  
to see the current configuration of the partitions including the maximum time limit you can specify for each partition, as given by the MaxTime field.  Alternatively, see the TIMELIMIT column in the output from
+
You can use <code>scontrol show partitions</code> or <code>sinfo</code> to see the current maximum time that a job can run.
 +
<syntaxhighlight lang="bash" highlight="6">
 +
$ scontrol show partitions
 +
PartitionName=cpu16
 +
  AllowGroups=ALL AllowAccounts=ALL AllowQos=ALL
 +
  AllocNodes=ALL Default=YES QoS=cpulimit
 +
  DefaultTime=NONE DisableRootJobs=NO ExclusiveUser=NO GraceTime=0 Hidden=NO
 +
  MaxNodes=UNLIMITED MaxTime=1-00:00:00 MinNodes=0 LLN=NO MaxCPUsPerNode=UNLIMITED
 +
  Nodes=n[1-36]
 +
  PriorityJobFactor=1 PriorityTier=1 RootOnly=NO ReqResv=NO OverSubscribe=NO
 +
  OverTimeLimit=NONE PreemptMode=OFF
 +
  State=UP TotalCPUs=576 TotalNodes=36 SelectTypeParameters=NONE
 +
  JobDefaults=(null)
 +
  DefMemPerNode=UNLIMITED MaxMemPerNode=UNLIMITED
  
sinfo
 
  
===Hardware resource limits===
 
There are limits on the number of cores, nodes and jobs one can use on TALC at any given time.  The limits are generally applied on a partition-by-partition basis, so, using resources in one partition should not affect the amount you can use in a different partition. To see the current limits you can run the command:
 
  
sacctmgr show qos format=name,maxwall,maxtrespu%20,MaxSubmitJobs
+
</syntaxhighlight>
  
==Support==
+
Alternatively, with <code>sinfo</code> under the <code>TIMELIMIT</code> column:
Please send TALC-related questions to your course instructor or tutorial assistants (who can relay reports of system problems to support@hpc.ucalgary.ca).
+
<syntaxhighlight lang="bash">
 +
$ sinfo
 +
PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
 +
cpu12        up 1-00:00:00      3  idle t[1-3]
 +
cpu16        up 1-00:00:00    36  idle n[1-36]
 +
bigmem      up 1-00:00:00      2  idle bigmem[1-2]
 +
gpu          up 1-00:00:00      3  idle t[1-3]
 +
 +
...
 +
</syntaxhighlight>
 +
[[Category:TALC]]
 +
[[Category:Guides]]

Latest revision as of 22:04, 6 January 2022

Security Icon.png

Cybersecurity awareness at the U of C

Please note that there are typically about 950 phishing attempts targeting University of Calgary accounts each month. This is just a reminder to be careful about computer security issues, both at home and at the University. Please visit https://it.ucalgary.ca/it-security for more information, tips on secure computing, and how to report suspected security problems.

This guide gives an overview of the Teaching and Learning Cluster (TALC) at the University of Calgary and is intended to be read by new account holders getting started on TALC. This guide covers topics as the hardware and performance characteristics, available software, usage policies and how to log in and run jobs.

Introduction

TALC is a cluster of computers created by Research Computing Services (RCS) in response to requests for a central computing resource to support academic courses and workshops offered at the University of Calgary. It is a complement to the Advanced Research Computing (ARC) cluster that is used for research, rather than educational purposes. The software environment in the TALC and ARC clusters is very similar and workflows between the two clusters are identical. What students learn about using TALC will have direct applicability to using ARC should they go on to use ARC for research work.

If you are the instructor for a course that could benefit from using TALC, please review this guide and the TALC Terms of Use and then contact us at support@hpc.ucalgary.ca to discuss your requirements.

Please note that in order to ensure that the appropriate software is available, student accounts are in place, and appropriate training has been provided for your teaching assistants, it is best to start this discussion several months prior to the start of the course.

If you are a student in a course using TALC, please review this guide for basic instructions in using the cluster. Questions should first be directed to the teaching assistants or instructor for your course.

Obtaining an account

TALC account requests are expected to be submitted by the course instructor rather than from individual students. You must have a University of Calgary IT account in order to use TALC. If you do not have a University of IT account or email address, please register for one at https://itregport.ucalgary.ca/. In order to ensure TALC is provisioned in time for a course start date, the instructor should submit the initial list of @ucalgary.ca accounts needed for the course 2 weeks before the start date.

Getting Support

Support Icon.png

Need Help or have other TALC Related Questions?

Students, please send TALC-related questions to your course instructor or teaching assistants.
Course instructors and TAs, please report system issues to support@hpc.ucalgary.ca.

Hardware

The TALC cluster is comprised of repurposed research clusters that are a few generations old. As a result, individual processor performance will not be comparable to the latest processors but should be sufficient for educational purposes and course work.

Partition Description Nodes CPU Cores, Model, and Year Installed Memory GPU Network
gpu GPU Compute 3 12 cores, 2x Intel Xeon Bronze 3204 CPU @ 1.90GHz (2019) 192 GB 5x NVIDIA Corporation TU104GL [Tesla T4] 40 Gbit/s InfiniBand
cpu16 General Purpose Compute 36 16 cores, 2x Eight-Core Intel Xeon CPU E5-2650 @ 2.00GHz (2012) 64 GB N/A 40 Gbit/s InfiniBand
bigmem General Purpose Compute 2 32 cores, 4x Intel(R) Xeon(R) CPU E7- 4830  @ 2.13GHz (2015) 1024 GB N/A 40 Gbit/s InfiniBand

Storage

Information Icon.png

No Backup Policy!

You are responsible for your own backups. Since accounts on TALC and related data are removed shortly after the associated course has finished, you should download anything you need to save to your own computer before the end of the course.

TALC is connected to a network disk storage system. This storage is split across the /home and /scratch file systems.

/home: Home file system

Each user has a directory under /home and is the default working directory when logging in to TALC. Each home directory has a per-user quota of 500 GB. This limit is fixed and cannot be increased.

Note on file sharing: Due to security concerns, permissions set using chmod on your home directory to allow other users to read/write to your home directory will be automatically reverted by an automated system process unless an explicit exception is made. If you need to share files with others on the TALC cluster, please write to support@hpc.ucalgary.ca to ask for such an exception.

/scratch: Scratch file system for large job-oriented storage

Associated with each job, under the /scratch directory, a subdirectory is created that can be referenced in job scripts as /scratch/${SLURM_JOB_ID}. You can use that directory for temporary files needed during the course of a job. Up to 30 TB of storage may be used, per user (total for all your jobs) in the /scratch file system.

Data in /scratch associated with a given job will be deleted automatically, without exception, five days after the job finishes.

Software

Information Icon.png

Software Package Requests

Course instructors or teaching assistants should write to support@hpc.ucalgary.ca if additional software is required for their course.

All TALC nodes run a version of Rocky Linux. For your convenience, we have packaged commonly used software packages and dependencies as modules available under /global/software. If your software package is not available as a module, you may also try Anaconda which allows users to manage and install custom packages in an isolated environment.

For a list of available packages that have been made available, please see ARC Software pages.

Modules

The setup of the environment for using some of the installed software is through the module command.

Software packages bundled as a module will be available under /global/software and can be listed with the module avail command.

$ module avail

To enable Python, load the Python module by running:

$ module load python/anaconda-3.6-5.1.0

To unload the Python module, run:

$ module remove python/anaconda-3.6-5.1.0

To see currently loaded modules, run:

$ module list

Using TALC

Support Icon.png

Usage subject to TALC Terms of Use

Please review the TALC Terms of Use prior to using TALC.

Logging in

To log in to TALC, connect using SSH to talc.ucalgary.ca. Connections to TALC are accepted only from the University of Calgary network (on campus) or through the University of Calgary General VPN (off campus).

See Connecting to RCS HPC Systems for more information.

Working interactively

TALC uses the Linux operating system. The program that responds to your typed commands and allows you to run other programs is called the Linux shell. There are several different shells available, but, by default you will use one called bash. It is useful to have some knowledge of the shell and a variety of other command-line programs that you can use to manipulate files. If you are new to Linux systems, we recommend that you work through one of the many online tutorials that are available, such as the UNIX Tutorial for Beginners (external link) provided by the University of Surrey. The tutorial covers such fundamental topics, among others, as creating, renaming and deleting files and directories, how to produce a listing of your files and how to tell how much disk space you are using. For a more comprehensive introduction to Linux, see The Linux Command Line (external link).

The TALC login node may be used for such tasks as editing files, compiling programs and running short tests while developing programs. CPU intensive workloads on the login node should be restricted to under 15 minutes as per our cluster guidelines. For interactive workloads exceeding 15 minutes, use the salloc command to allocate an interactive session on a compute node.

The default salloc allocation is 1 CPU and 1 GB of memory. Adjust this by specifying -n CPU# and --mem Megabytes. You may request up to 5 hours of CPU time for interactive jobs.

salloc --time 5:00:00 --partition cpu16

Running non-interactive jobs (batch processing)

Production runs and longer test runs should be submitted as (non-interactive) batch jobs, in which commands to be executed are listed in a script (text file). Batch jobs scripts are submitted using the sbatch command, part of the Slurm job management and scheduling software. #SBATCH directive lines at the beginning of the script are used to specify the resources needed for the job (cores, memory, run time limit and any specialized hardware needed).

Most of the information on the Running Jobs page on the Compute Canada web site is also relevant for submitting and managing batch jobs and reserving processors for interactive work on TALC. One major difference between running jobs on the TALC and Compute Canada clusters is in selecting the type of hardware that should be used for a job. On TALC, you choose the hardware to use primarily by specifying a partition, as described below.

Using JupyterHub on Talc

TALC has a Jupyterhub server which runs a Jupyter server on one of the TALC compute nodes and provides all the necessary encryption and plumbing to deliver the notebook to your computer. To access this service you must have a TALC account. Point your browser at http://talc.ucalgary.ca and login with your usual UC account. As of this writing, the job that runs the jupyter notebook is 1 cpu and 10GiB of memory on a cpu16 node.

Selecting a partition

TALC currently has the following partitions available for use. The gpu and cpu12 partitions are refer to the same nodes. The cpu12 partition was created to only expose the CPUs on the GPU hardware for general purpose use. Each GPU node has 5 Tesla T4 GPUs installed, but you may only request one per job within the TALC environment.

Partition Description Nodes Cores Memory Memory Request Limit Time Limit GPU Request per Job Network
gpu GPU Compute 3 12 cores 192 GB 190 GB 24 hours 1x NVIDIA Corporation TU104GL [Tesla T4] 40 Gbit/s InfiniBand
cpu12 General Purpose Compute 3 12 cores 192 GB 190 GB 24 hours None 40 Gbit/s InfiniBand
cpu16 General Purpose Compute 36 16 cores 64 GB 62 GB 24 hours None 40 Gbit/s InfiniBand
bigmem General Purpose Compute 2 32 cores 1024 GB 1022 GB 24 hours None 40 Gbit/s InfiniBand

There are some aspects to consider when selecting a partition including:

  • Resource requirements in terms of memory and CPU cores
  • Hardware specific requirements, such as GPU or CPU Instruction Set Extensions
  • Partition resource limits and potential wait time
  • Software support for parallel processing using Message Passing Interface (MPI), OpenMP, etc. For example, MPI for parallel processing can distribute memory across multiple nodes, so that per-node memory requirements could be lower. Whereas OpenMP or single process serial code that is restricted to one node would require a higher memory node.

Since resources that are requested are reserved for your job, please request only as much CPU and memory as your job requires to avoid reducing the cluster efficiency. If you are unsure which partition to use or the specific resource requests that are appropriate for your jobs, please contact us at support@hpc.ucalgary.ca and we would be happy to work with you.

Using a partition

CPU only jobs

To select the cpu16 partition, include the following line in your batch job script:

#SBATCH --partition=cpu16

You may also start an interactive session with salloc:

$ salloc --time 1:00:00 -p cpu16

GPU jobs

In TALC, you are limited to exactly 1 GPU per job. Jobs that request for 0 GPUs or 2 or more GPUs will not be scheduled.

To submit a job using the gpu partition with one GPU request, include the following to your batch job script:

#SBATCH --partition=gpu
#SBATCH --gpus-per-node=1

Like the previous example, you may also request interactive sessions with GPU nodes using salloc. Just specify the gpu partition and the number of GPUs required.

$ salloc --time 1:00:00 -p gpu -n 1 --gpus-per-node 1

You may verify that a GPU was assigned to your job or interactive session by running nvidia-smi. This command will show you the status of the GPU that was assigned to you.

$ nvidia-smi
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 450.80.02    Driver Version: 450.80.02    CUDA Version: 11.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla T4            Off  | 00000000:3B:00.0 Off |                    0 |
| N/A   36C    P0    14W /  70W |      0MiB / 15109MiB |      5%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

Partition limitations

In addition to the hardware limitations of the nodes within the partition, please be aware that there may also be policy limits imposed on your account for each partition. These limits restrict the number of cores, nodes, or GPUs that can be used at any given time. Since the limits are applied on a partition-by-partition basis, using resources in one partition should not affect the available resources you can use in another partition.

These limits can be listed by running:

$ sacctmgr show qos format=Name,MaxWall,MaxTRESPU%20,MaxSubmitJobs
      Name     MaxWall            MaxTRESPU MaxSubmit 
---------- ----------- -------------------- --------- 
    normal  1-00:00:00                                
  cpulimit                           cpu=48           
gpucpulim+                           cpu=18           
  gpulimit                 cpu=2,gres/gpu=1

Time limits

Use the --time directive to tell the job scheduler the maximum time that your job might run. For example:

#SBATCH --time=hh:mm:ss

You can use scontrol show partitions or sinfo to see the current maximum time that a job can run.

$ scontrol show partitions
PartitionName=cpu16
   AllowGroups=ALL AllowAccounts=ALL AllowQos=ALL
   AllocNodes=ALL Default=YES QoS=cpulimit
   DefaultTime=NONE DisableRootJobs=NO ExclusiveUser=NO GraceTime=0 Hidden=NO
   MaxNodes=UNLIMITED MaxTime=1-00:00:00 MinNodes=0 LLN=NO MaxCPUsPerNode=UNLIMITED
   Nodes=n[1-36]
   PriorityJobFactor=1 PriorityTier=1 RootOnly=NO ReqResv=NO OverSubscribe=NO
   OverTimeLimit=NONE PreemptMode=OFF
   State=UP TotalCPUs=576 TotalNodes=36 SelectTypeParameters=NONE
   JobDefaults=(null)
   DefMemPerNode=UNLIMITED MaxMemPerNode=UNLIMITED

Alternatively, with sinfo under the TIMELIMIT column:

$ sinfo
PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
cpu12        up 1-00:00:00      3   idle t[1-3]
cpu16        up 1-00:00:00     36   idle n[1-36]
bigmem       up 1-00:00:00      2   idle bigmem[1-2]
gpu          up 1-00:00:00      3   idle t[1-3]
 
...