| Inhalt | ||
|---|---|---|
|
...
During the migration phase the use of Rocky Linux 9 "clx" compute nodes will be was free of charge.
Current migration state: complete
nodes | CentOS 7 | Rocky Linux 9 | |
|---|---|---|---|
login | blogin[1-2] | blogin[31-8] | |
compute (384 GB RAM) | 256- | 688948 | |
compute (768 GB RAM) | - | 32 | 0 |
compute (1536 GB RAM) | - | 20 |
Latest news
date | subject |
|---|---|
2024-09-30 | migration of remaining nodes from CentOS 7 to Rocky Linux 9 |
2024-09-16 | generic login name “blogin” resolves to blogin[3-6] |
2024-08-14 | migration of blogin[3-6] |
2024-07-30 | migration of another 576 standard compute nodes to Rocky Linux 9 |
2024-07-03 | official start of the migration phase with 2 login and 112 compute nodes running Rocky Linux 9 |
...
CentOS 7 | Rocky Linux 9 | |
|---|---|---|
old partition name | new partition name | current job limits |
● | ● | 512 nodes, 12h 12 h wall time |
● | ● | 32 16 nodes, 1 h wall time |
● | ● | 50 nodes, 12 h wall time |
● | ● | 32 nodes, 48 h wall time |
● | ||
● | ||
● | ● | 1 node, 48 h wall time |
( ● available ● closed/not available yet )
Jobs submitted without a partition name are placed in the default partition. The old default was standard96, the new default is cpu-clx.
Software and environment modules
...
| Erweitern | ||
|---|---|---|
| ||
No, your ssh key remains valid. We have seen this kind of problem for Windows users with an outdated version of PuTTY. Updating to a more recent PuTTY (≥ 0.81) solved this problem. The same holds for WinSCP which needs to be up-to-date, too. |
| Erweitern | ||
|---|---|---|
| ||
This behaviour is observed for jobs submitted to the old CentOS 7 partitions (see the table above). Please make sure you submit such jobs on |