Commit 45900195 authored by Brandon's avatar Brandon

Merge branch 'brandon/remove-email-references' into 'master'

Brandon/remove email references

See merge request !225
parents 5c0b32e3 dcde60f5
......@@ -20,7 +20,7 @@ username, then "sharing" has occurred and all usernames associated
with the owner of the shared username will be disabled.
If a user is disabled due to account sharing, the PI or an authorized
project manager must send a memo to consult@nersc.gov explaining why
project manager must send a memo to accounts@nersc.gov explaining why
the sharing occurred and assuring that it will not occur again. NERSC
will then determine if the user should be re-enabled.
......
......@@ -96,5 +96,5 @@ This page is based on the "Valgrind Quick Start Page". For more
information about valgrind, please refer to
[http://valgrind.org/](http://valgrind.org/).
For questions on using Valgrind at NERSC contact the consultants
at consult@nersc.gov.
For questions on using Valgrind at NERSC
contact [NERSC Consulting](https://help.nersc.gov).
......@@ -120,13 +120,15 @@ files to be read via http.
```
chmod -R o+rx /project/projectdirs/<project_name>/<svn_repository_path>/<svn_repository_name>
```
A symlink will have to be created by NERSC staff in order for your svn repo to
be accessible via http. You can request for a symlink to be created by sending
an email to `consult@nersc.gov`. Please include the full path to the SVN repo
in your request to expedite the process. A NERSC staff member will have to
create a symlink in `/var/www/svn` and will have to point to the location of
the svn repo (i.e.,
`/project/projectdirs/<project_name>/<svn_repository_name>`).
A symlink will have to be created by NERSC staff in order for your svn
repo to be accessible via http. You can request for a symlink to be
created by [opening a ticket](https://help.nersc.gov). Please include
the full path to the SVN repo in your request to expedite the
process. A NERSC staff member will have to create a symlink in
`/var/www/svn` and will have to point to the location of the svn repo
(i.e., `/project/projectdirs/<project_name>/<svn_repository_name>`).
```
ln -s /project/projectdirs/<project>/<svn_location> /var/www/svn/<symlink_name>
```
......@@ -138,7 +140,8 @@ svn co https://portal.nersc.gov/svn/<project>
## Authenticated access to SVN
Setting the `REPO_PATH` variable may be necessary if it's not already set.
Setting the `REPO_PATH` variable may be necessary if it's not already
set.
bash:
```
......
......@@ -14,11 +14,11 @@ and is also being evaluated by several other projects. For more
information on Fireworks visit:
https://materialsproject.github.io/fireworks/index.html
Please contact consult@nersc.gov if you are interested in using
Fireworks. The following is a quick example for running at NERSC based
on the Fireworks tutorial. Note that you will need access to a
mongoDB - you can request one to be set up for you at NERSC using this
form.
Please open a ticket with [NERSC Consulting](https://help.nersc.gov)
if you are interested in using Fireworks. The following is a quick
example for running at NERSC based on the Fireworks tutorial. Note
that you will need access to a mongoDB - you can request one to be set
up for you at NERSC using this form.
## Terminology
......
......@@ -31,8 +31,9 @@ advantage of the system's available bandwidth but striping over too
many will cause unnecessary overhead and lead to a loss in
performance. NERSC has provided striping command shortcuts based on
file size to simplify optimization on both Edison and Cori. Users who
want more detail should read the sections below or contact the
consultants at consult@nersc.gov.
want more detail should read the sections below and open a ticket
with [NERSC Consulting](https://help.nersc.gov) if there are
additional questions.
Striping must be set on a file before is written. For example, one
could simultaneously create an empty file which will later be 10-100
......@@ -97,8 +98,9 @@ srun -n 10 ./a.out
### File per processing element
If files are larger than 100GB contact consult@nersc.gov otherwise use
the default settings.
If files are larger than 100GB open a ticket
with [NERSC Consulting](https://help.nersc.gov) otherwise use the
default settings.
## Burst Buffer
......
# CVMFS
# CVMFS
[CVMFS (CernVM-File System)](https://cvmfs.readthedocs.io/en/stable/)
is a software distribution service heavily used by High-Energy Physics (HEP) experiments to deliver software to multiple different computing systems worldwide.
It presents remote software pulled over http as a POSIX read-only filesystem in user space (normally using FUSE).
Access is performant and scalable due to multiple levels of caching such as a local file cache and squid web caches.
is a software distribution service heavily used by High-Energy Physics
(HEP) experiments to deliver software to multiple different computing
systems worldwide. It presents remote software pulled over http as a
POSIX read-only filesystem in user space (normally using FUSE).
Access is performant and scalable due to multiple levels of caching
such as a local file cache and squid web caches.
## NERSC Setup
At NERSC CVMFS is mounted on Cori and Edison compute nodes as an NFS mount via DVMFS (Cray's I/O forwarder for remote mounted filesystems that is also used for /project filesystems).
It is also mounted on Cori and Edison login nodes. The NFS servers themselves mount cvmfs using FUSE in the normal way and we have dedicated local squid caches.
We believe this setup to now be stable and perform well enough but users should please contact us if you see any problems,
or if you need a new repository that is not currently available, via the [online help desk](https://help.nersc.gov/) or email to consult@nersc.gov.
PDSF systems also provide CVMFS though via its 'normal' mechanism.
At NERSC CVMFS is mounted on Cori and Edison compute nodes as an NFS
mount via DVMFS (Cray's I/O forwarder for remote mounted filesystems
that is also used for /project filesystems). It is also mounted on
Cori and Edison login nodes. The NFS servers themselves mount cvmfs
using FUSE in the normal way and we have dedicated local squid caches.
We believe this setup to now be stable and perform well enough but
users should please contact us if you see any problems, or if you need
a new repository that is not currently available, via
the [online help desk](https://help.nersc.gov/). PDSF systems also
provide CVMFS though via its 'normal' mechanism.
## Using CVMFS at NERSC
From a normal user perspective however this custom setup mentioned above doesn't change that all our mounted repositories appear under /cvmfs
From a normal user perspective however this custom setup mentioned
above doesn't change that all our mounted repositories appear under
/cvmfs
cori$ ls /cvmfs
<various repositories>
CVMFS is also available on Cori and Edison compute nodes with or without shifter
If using [shifter](/development/shifter/how-to-use.md) you should specify the `--modules=cvmfs` flag to shifter to make that mount appear inside your container (unless you want to use your own
version of cvmfs inside the container).
CVMFS is also available on Cori and Edison compute nodes with or
without shifter
If using [shifter](/development/shifter/how-to-use.md) you should
specify the `--modules=cvmfs` flag to shifter to make that mount
appear inside your container (unless you want to use your own version
of cvmfs inside the container).
cori$ shifter --module=cvmfs
You can also load this module in your batch script and you should also add the cvmfs filesystem license `-L cvmfs` which would allow us to pause your jobs from running if the cvmfs mount was unavailable
You can also load this module in your batch script and you should also
add the cvmfs filesystem license `-L cvmfs` which would allow us to
pause your jobs from running if the cvmfs mount was unavailable
#!/bin/bash
#SBATCH --module=cvmfs
......
......@@ -21,8 +21,8 @@ deployment, accepts feedback, and tries to recycle successful
approaches into methods that other science teams can benefit
from. Below you will find links to current projects and details about
the building blocks available to NERSC users. If you would like to
participate, or if you have questions, please contact
consult@nersc.gov.
participate, or if you have questions, please open a ticket with
[NERSC Consulting](https://help.nersc.gov).
## Science Gateway Availability and Support
......@@ -102,8 +102,8 @@ deployment, accepts feedback, and tries to recycle successful
approaches into methods that other science teams can benefit
from. Below you will find links to current projects and details about
the building blocks available to NERSC users. If you would like to
participate, or if you have questions, please contact
consult@nersc.gov.
participate, or if you have questions, please open a ticket with
[NERSC Consulting](https://help.nersc.gov)
NERSC Resource | Path On NERSC Resource | URL on the Web
--- | --- | ---
......@@ -212,9 +212,7 @@ tape archives via a science gateway should only be reserved for
infrequent accesses from a data pool that is too large to be
practically kept on the "project" filesystem. If you need to serve
very large files very frequently via a science gateway, please
contact
[NERSC consulting](https://www.nersc.gov/users/getting-help/online-help-desk/) for
assistance.
contact [NERSC Consulting](https:help.nersc.gov) for assistance.
Retrieving data from HPSS via a science gateway can be very slow. If
files have not been accessed in some time they will have to be
......@@ -283,6 +281,7 @@ found at [https://newt.nersc.gov/api](https://newt.nersc.gov/api).
## Moving Beyond Simple Gateway Functions
If you are building a web gateway to your science at NERSC, please
contact us at consult@nersc.gov. We are interested in engagaing
directly with science teams so that you can build a gateway that meets
your specific needs.
contact us by opening a ticket
with [NERSC Consulting](https://help.nersc.gov). We are interested in
engagaing directly with science teams so that you can build a gateway
that meets your specific needs.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment