Niagara Quickstart: Difference between revisions

Jump to navigation Jump to search
no edit summary
No edit summary
No edit summary
Line 9: Line 9:


<!--T:4-->
<!--T:4-->
Access to Niagara is via ssh (secure shell) only.  
Access to Niagara is via SSH (secure shell) only.  


<!--T:5-->
<!--T:5-->
To access Niagara, first open a terminal window (e.g. [[Connecting with MobaXTerm|MobaXTerm]] or [[Connecting with PuTTY|PuTTY]] on Windows), then ssh into the Niagara login nodes with your CC credentials:
To access Niagara, first open a terminal window (e.g. [[Connecting with PuTTY|PuTTY]] on Windows or [[Connecting with MobaXTerm|MobaXTerm]]), then SSH into the Niagara login nodes with your CC credentials:


<!--T:6-->
<!--T:6-->
Line 41: Line 41:


<!--T:16-->
<!--T:16-->
Niagara is replacing the General Purpose Cluster (GPC) and the Tightly Coupled Cluster (TCS) at SciNet.  The TCS was decommissioned last fall, and GPC will be decommissioned very soon: the compute nodes of the GPC will be decommissioned on April 21, 2018, while the storage attached to the GPC will be decommissioned on May 9, 2018.
Niagara replaces SciNet clusters
*TCS (Tightly Coupled Cluster) decommissioned last fall and
*GPC (General Purpose Cluster) whose compute nodes will be decommissioned on April 21, 2018 and storage space on May 9, 2018.


<!--T:17-->
<!--T:17-->
Active GPC Users got access to the new system, Niagara, on April 9, 2018.
Active GPC Users have access to Niagara since April 9, 2018.


<!--T:18-->
<!--T:18-->
Line 50: Line 52:


<!--T:19-->
<!--T:19-->
It is the user's responsibility to copy over data generated on the GPC after April 5th, 2018.
It is the user's responsibility to copy to Niagara any data generated on the GPC after April 5th, 2018.


<!--T:20-->
<!--T:20-->
Line 65: Line 67:
$ scp -r SCINETUSERNAME@gpc-logindm01:\$SCRATCH/abc $SCRATCH/abc
$ scp -r SCINETUSERNAME@gpc-logindm01:\$SCRATCH/abc $SCRATCH/abc
</source>
</source>
For many of you, CCUSERNAME and SCINETUSERNAME will be the same. Make sure you use the slash (\) before the first <tt>$SCRATCH</tt>; it causes the value of scratch on the remote node (i.e., here, gpc-logindm01) to be used. Note that the gpc-logindm01 will ask for your SciNet password.
For many of you, CCUSERNAME and SCINETUSERNAME will be the same. Make sure you use the backslash (\) before the first <tt>$SCRATCH</tt>; it causes the value of scratch on the remote node (i.e., here, gpc-logindm01) to be used. Note that the gpc-logindm01 will ask for your SciNet password.


<!--T:23-->
<!--T:23-->
Line 74: Line 76:
$ scp -r $SCRATCH/abc CCUSERNAME@nia-dm1:\$SCRATCH/abc
$ scp -r $SCRATCH/abc CCUSERNAME@nia-dm1:\$SCRATCH/abc
</source>
</source>
Again, pay attention to the slash in front of the last occurrence of <tt>$SCRATCH</tt>.
Again, pay attention to the backslash in front of the last occurrence of <tt>$SCRATCH</tt>.


<!--T:24-->
<!--T:24-->
Line 82: Line 84:


<!--T:26-->
<!--T:26-->
Those of you new to SciNet, but with 2018 RAC allocations on Niagara, will have your accounts created and ready for you to login.
Those who are new to SciNet, but have 2018 RAC allocations on Niagara, will have their accounts created and ready for them to login.


<!--T:27-->
<!--T:27-->
Line 123: Line 125:


<!--T:38-->
<!--T:38-->
Use the environment variables (HOME, SCRATCH, PROJECT) instead of the actual paths!  The paths may change in the future.
Use the environment variables (HOME, SCRATCH, PROJECT) instead of the actual paths since these may change in the future.


= Storage= <!--T:39-->
= Storage= <!--T:39-->
Line 134: Line 136:
! expiration time
! expiration time
! backed up
! backed up
! on login
! on login nodes
! on compute
! on compute nodes
|-
|-
| $HOME
| $HOME
Line 183: Line 185:
<li>Archive space is on [https://wiki.scinet.utoronto.ca/wiki/index.php/HPSS HPSS], which will be, but is not yet, attached to Niagara.</li>
<li>Archive space is on [https://wiki.scinet.utoronto.ca/wiki/index.php/HPSS HPSS], which will be, but is not yet, attached to Niagara.</li>
<li>Backup means a recent snapshot, not an achive of all data that ever was.</li>
<li>Backup means a recent snapshot, not an achive of all data that ever was.</li>
<li><p><code>$BBUFFER</code> stands for the Burst Buffer, a functionality that is still being set up.  This will be a faster parallel storage tier for temporary data.</p></li></ul>
<li><p><code>$BBUFFER</code> stands for the Burst Buffer, a functionality that is still being set up.  This parallel storage tier for temporary data will be the fastest</p></li></ul>


= Moving data = <!--T:42-->
= Moving data = <!--T:42-->


<!--T:43-->
<!--T:43-->
How users should move data onto and off of the Niagara system depends on how big that data is.
Use the scp or rsync commands to move data to either niagara.scinet.utoronto.ca or niagara.computecanada.ca. The transfer method depends on the size of the data you need to move.  


<!--T:44-->
<!--T:44-->
*To move amounts less than 10GB, you can go through the login nodes. These are the only Niagara login nodes visible from outside Niagara. You can use scp or rsync to niagara.scinet.utoronto.ca or niagara.computecanada.ca (there is no difference). Transfers done in this way will time out for amounts larger than about 10GB.
*To move less than 10GB, use login nodes, which are the only ones visible from outside Niagara. Transfers done in this way will time out if data is larger than about 10GB.


<!--T:45-->
<!--T:45-->
*To move amounts of data larger than 10GB, you should go through the datamover node. Datamover nodes are not reachable from the outside, so to do so, from a Niagara login node, first ssh into <code>nia-dm1</code> or <code>nia-dm2</code>, and initiate transfer from the datamovers.
*To move more  than 10GB, use datamover nodes, which are not reachable from the outside. To do so, from a Niagara login node, first ssh into <code>nia-dm1</code> or <code>nia-dm2</code> and initiate transfer from the datamovers. The other side of the transfer (e.g. your machine) must be reachable from the outside.
This means that the other side of the transfer (e.g. your machine) must be reachable from the outside.


<!--T:46-->
<!--T:46-->
If you do this often, consider using [[Globus]], a web-based tool for data transfer.
If you often move data, consider using [[Globus]], a web-based tool for data transfer.


<!--T:47-->
<!--T:47-->
You may also want to move data to [https://wiki.scinet.utoronto.ca/wiki/index.php/HPSS HPSS/Archive/Nearline], but this functionality will be implemented later. Storage space on HPSS is allocated through the annual [https://www.computecanada.ca/research-portal/accessing-resources/resource-allocation-competitions Compute Canada RAC allocation].
You may also want to move data to [https://wiki.scinet.utoronto.ca/wiki/index.php/HPSS HPSS/Archive/Nearline], but this functionality will be implemented at a later date. Storage space on HPSS is allocated through the annual [https://www.computecanada.ca/research-portal/accessing-resources/resource-allocation-competitions Compute Canada RAC allocation].


= Loading software modules = <!--T:48-->
= Loading software modules = <!--T:48-->
Line 252: Line 253:
<li><p>The same [[Modules|software stack available on Compute Canada's General Purpose clusters]] [https://docs.computecanada.ca/wiki/Graham Graham] and [https://docs.computecanada.ca/wiki/Cedar Cedar], compiled (for now) for a previous generation of CPUs:</p>
<li><p>The same [[Modules|software stack available on Compute Canada's General Purpose clusters]] [https://docs.computecanada.ca/wiki/Graham Graham] and [https://docs.computecanada.ca/wiki/Cedar Cedar], compiled (for now) for a previous generation of CPUs:</p>
<source lang="bash">module load CCEnv</source>
<source lang="bash">module load CCEnv</source>
<p>If you want the same default modules loaded as on Cedar and Graham, then afterwards also <code>module load StdEnv</code>.</p></li></ol>
<p>If you want the same default modules as those loaded on Cedar and Graham, also run <code>module load StdEnv</code>.</p></li></ol>


<!--T:55-->
<!--T:55-->
Line 284: Line 285:


<!--T:64-->
<!--T:64-->
Oddly named, the module subcommand spider is the search-and-advice facility for modules.
Oddly named, the module subcommand spider is the search-and-advise facility for modules.


<!--T:65-->
<!--T:65-->
Line 339: Line 340:


<!--T:68-->
<!--T:68-->
* Possibly, but you have to bring your own license for it.
* You may have to provide your own license.
* SciNet and Compute Canada have an extremely large and broad user base of thousands of users, so we cannot provide licenses for everyone's favorite software.
* SciNet and Compute Canada have an extremely large and broad user base of thousands of users, so we cannot provide licenses for everyone's favorite software.
* Thus, the only commercial software installed on Niagara is software that can benefit everyone: Compilers, math libraries and debuggers.
* Thus, the only commercial software installed on Niagara is software that can benefit everyone: compilers, math libraries and debuggers.
* That means no Matlab, Gaussian, IDL,  
* That means no Matlab, Gaussian, IDL,  
* Open source alternatives like Octave, Python, R are available.
* Open source alternatives like Octave, Python, R are available.
rsnt_translations
56,430

edits

Navigation menu