Difference between revisions of "Sds-hd hpc access"
m (→Copying data on data mover node) |
m (→Access to SDS@hd) |
||
| Line 13: | Line 13: | ||
== Direct access in compute jobs == |
== Direct access in compute jobs == |
||
| + | * Fetch a Kerberos ticket on any loginnode with command: kinit (use your SDS@hd service password) |
||
| − | * Login in to a datamover, i.e. "ssh data1" or "ssh data2" (passwordless) |
||
| − | * Fetch a Kerberos ticket with command: kinit (use your SDS@hd service password) |
||
* Prepare your jobscript to use the directory ''/mnt/sds-hd/<your-sv-acronym>'' |
* Prepare your jobscript to use the directory ''/mnt/sds-hd/<your-sv-acronym>'' |
||
* submit your job |
* submit your job |
||
| − | == Copying data |
+ | == Copying data from SDS@hd to a cluster workspace == |
| − | Certain workflows or I/O patterns may require the transfer of data from SDS@hd to a workspace on the cluster before submitting jobs. Data transfers are possible on |
+ | Certain workflows or I/O patterns may require the transfer of data from SDS@hd to a workspace on the cluster before submitting jobs. Data transfers are possible on all login nodes: |
| − | * |
+ | * Fetch a Kerberos ticket on any loginnode with command: kinit (use your SDS@hd service password) |
| − | * Fetch a Kerberos ticket with command: kinit (use your SDS@hd service password) |
||
* Find your SDS@hd directory in /mnt/sds-hd/ |
* Find your SDS@hd directory in /mnt/sds-hd/ |
||
* Copy data between your SDS@hd directory and your workspaces |
* Copy data between your SDS@hd directory and your workspaces |
||
* Destroy your Kerberos ticket with command: kdestroy |
* Destroy your Kerberos ticket with command: kdestroy |
||
| − | * Logout from data1 for further work on the cluster |
||
<br> |
<br> |
||
Revision as of 15:49, 22 August 2018
1 Access to SDS@hd
 |
| SDS@hd ScientificDataStorage © University Heidelberg |
It is possible to access your storage space on SDS@hd directly on the bwforCluster MLS&WISO. You can access your SDS@hd directory with a valid Kerberos ticket on all compute nodes except standard nodes. Kerberos tickets are obtained and prolongated on the data mover nodes data1 and data2. Before a Kerberos ticket expires, notification is sent by e-mail.
1.1 Direct access in compute jobs
- Fetch a Kerberos ticket on any loginnode with command: kinit (use your SDS@hd service password)
- Prepare your jobscript to use the directory /mnt/sds-hd/<your-sv-acronym>
- submit your job
1.2 Copying data from SDS@hd to a cluster workspace
Certain workflows or I/O patterns may require the transfer of data from SDS@hd to a workspace on the cluster before submitting jobs. Data transfers are possible on all login nodes:
- Fetch a Kerberos ticket on any loginnode with command: kinit (use your SDS@hd service password)
- Find your SDS@hd directory in /mnt/sds-hd/
- Copy data between your SDS@hd directory and your workspaces
- Destroy your Kerberos ticket with command: kdestroy
