@@ -11,37 +11,43 @@ The hardware specification is documented on the page
...
@@ -11,37 +11,43 @@ The hardware specification is documented on the page
Please read the following information carefully and follow the provided instructions.
Please read the following information carefully and follow the provided instructions.
There is a last step to go in order to finalize the
We are in the
[process of becoming `Alpha Centauri` a Stand-Alone Cluster](#becoming-a-stand-alone-cluster). This
[process of becoming `Alpha Centauri` a Stand-Alone Cluster](#becoming-a-stand-alone-cluster). Planned now is the integration of the cluster into the Infiniband infrastructure
last step of the migration process is to include `Alpha Centauri` into the Infiniband infrastructure
of the new cluster [`Barnard`](barnard.md).
of the new cluster [`Barnard`](barnard.md).
!!! hint "Maintenance Work"
!!! hint "Maintenance Work"
On **June 10+11**, we will shut down and migrate `Alpha Centauri` to the Barnard Infiniband
On **June 4+5**, we will shut down and migrate `Alpha Centauri` to the Barnard Infiniband
infrastructure. As consequences,
infrastructure.
* BeeGFS will no longer be available,
* all `Barnard` filesystems (`/home`, `/software`, `/data/horse`, `/data/walrus`) can be
reached faster,
* the new Lustre filesystem `/data/octopus` will be dedicated to `Alpha` users.
We already have started migrating your data from `/beegfs` to `/data/octopus`.
As consequences,
* BeeGFS will no longer be available,
* all `Barnard` filesystems (`/home`, `/software`, `/data/horse`, `/data/walrus`) can be
used normally.
For your convenience, we already have started migrating your data from `/beegfs` to
`/data/horse/beegfs`. Starting with the downtime, we again synchronize these data.
!!! hint "User Action Required"
!!! hint "User Action Required"
The less we have to synchronize the faster the overall process. So clean-up
as much as possible as soon as possible.
Important for your work is:
* Do not add terabytes of data to `/beegfs` if you cannot "consume" it before June 4.
* After final successful data transfer to `/data/horse/beegfs` you then have to
move it to normal workspaces on `/data/horse`.
* Be prepared to adapt your workflows to the new paths.
Important for your work now is:
What happens afterward:
* On **May 3** we will mount BeeGFS read-only on Alpha Centauri and start the final sync
* complete deletion of all user data in `/beegfs`
from `/beegfs` to `/data/octopus` for your convenience.
* complete recabling of the storage nodes (BeeGFS hardware)
* Afterwards, the BeeGFS storage will be migrated:
* Software+Firmware updates
* complete deletion of all user data
* set-up of a new WEKA filesystem for high I/O demands on the same hardware
* complete recabling of their Infiniband connection
* Software+Firmware updates
* set-up of a new WEKA filesystem for high I/O demands (on the BeeGFS hardware)
* Do not add terabytes of data to /beegfs if you cannot "consume" it before May 5.
* Instead, you can already create workspaces for /data/octopus on login1.barnard and bring your data there for computations after May 6.
* If you have millions of files you might consider the removal of data.
In case of any question regarding this maintenance or required action, please do not hesitate to
In case of any question regarding this maintenance or required action, please do not hesitate to
contact the [HPC support team](../support/support.md).
contact the [HPC support team](../support/support.md).
