Fil des news

We have to make urgent hardware upgrades on a few fileservers. These need a reboot afterward, fileservers will be unavailable a few minutes, at most. Expect lags and delays during these upgrades.

impacted services: $HOME and /Xnfs shares (mostly everyone)

We are powering down half of each main cluster (E5, Lake, Cascade):

• Ease on cooling system on hot days,
• Energy saving (and cost)…

Powering up will occur “on-demand” (more than one day in PENDING state).

I'm putting down Infiniband network on Cascade cluster (including scratches) for maintenance and debugging purposes.

EDIT 10:15: everything Cascade back online (QM8700 ↔ QM8790…).

: /scratch/Cascade is 98% full, please cleanup, or I'll do it…

kind reminder about scratches usage → http://www.ens-lyon.fr/PSMN/Documentation/filesystems/scratch.html

We are “hot-“modifying the InfiniBand network of Cascade cluster. You may experience some temporarly access problems on Cascade scratches.

/scratch/Cascade is 99% full, hence performing as badly as possible (it's even not performing at all, for now). You should have cleanup while you can, because now, I'm in charge…: Erasing all files & directory older than 180 days (that's six months old) on /scratch/Cascade. Do NOT complain, documentation is crystal-clear (http://www.ens-lyon.fr/PSMN/Documentation/filesystems/scratch.html)

EDIT 17:00: due to a misconfiguration we cannot find, half of scratch nodes (Cascade and Cral) are not connected anymore.

/Xnfs/highenergy volume is back online. Go easy, a scan/rebuild is still ongoing…