OSCER users


Options: Use Classic View

Use Proportional Font
Show HTML Part by Default
Show All Mail Headers

Topic: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Henry Neeman <[log in to unmask]>
Thu, 11 May 2023 14:03:18 -0500
text/plain (50 lines)
OSCER users,

Schooner scheduled maintenance outage Wed May 17 8am-midnight
Central Time
(*after* Commencement)

(1) Upgrade firmware and drivers for our Ethernet switches
and some of our Ethernet cards.

(2) If time permits, update Slurm to the most recent stable
major version (# 22).

This will give us the ability to create a "burst buffer" for
applications that do large numbers of tiny reads.

Soon, we will deploy a burst buffer server, with 16 NVMe SSDs
(~40 TB usable), hopefully in production by May -- that'll
make I/O for such applications significantly faster.

We had intended to do this during the Apr 19 scheduled
maintenance outage, but the procedure for this item was
taking too long, so we had to delay this.

(3) If time permits, install Power Distribution Unit (PDU)
power strips in compute/GPU racks, which will increase
the power capacity for compute/GPU nodes, both OSCER-owned
and condominium.

We had intended to do this task during the Apr 19 scheduled
maintenance outage, but other maintenance items were
taking too long, so we had to delay some of this.

This scheduled maintenance outage will affect *ALL* OSCER

* Supercomputer

* OURcloud

* OURdisk

* OURRstore tape archive

* OneOklahoma Friction Free Network

We apologize for the inconvenience -- as always, our goal
is to make OSCER systems and services even better!

The OSCER Team ([log in to unmask])