Updated December 24, 2024:

Amarel on all campuses has been returned to service following regularly scheduled maintenance. Please report any issues you may experience. Thank you!

Amarel monthly maintenance

Our vision is to provide a better user environment, with rolling updates affecting one portion of the cluster at a time, instead of a whole system. We strive to perform maintenance in less active periods so that classes and grants are minimally affected.

In January 2021, in an effort to avoid long, intensive maintenance periods, OARC shifted to a regular monthly maintenance schedule.

We will continue this, with the tentative schedule listed below of maintenance spanning up to 2 days each month, starting on the 3rd Tuesday of the month. We may not need the full 2 days each month, but we’ll reserve that time in case it is needed. Otherwise, the cluster will be returned to service early, immediately after the planned maintenance is complete. When possible, we will skip a month’s maintenance window entirely.

Each maintenance period is expected to begin at about 08:00 ET on the first day and end by about 23:59 ET on the 2nd day.

Anticipated maintenance schedule (all dates subject to change):

2024

JAN 23 & 24 (one week later because of MLK Day and first day of Spring semester)

FEB 20 & 21

MAR 19 & 20

APR 16 & 17

MAY 21 & 22

JUN 18 & 19

JUL 16 & 17 (PEARC24 conference will be held 7/21-7/25)

AUG 20 & 21

SEP 17 & 18

OCT 15 & 16

NOV 12 & 13

DEC 17 & 18

2025

Jan 14 & 15

Feb 18 & 19

Mar 11 & 12

Apr 15 & 16

May 20 & 21

Jun 17 & 18

Jul 15 & 16

Aug 19 & 20

Sep 16 & 17

Oct 21 & 22

Nov 11 & 12

Dec 16 & 17

Maintenance is usually scheduled for weekdays because it often involves coordination with University facilities teams or external vendors. There may also be times when Amarel must be unavailable due to externally-scheduled data center facilities, power, or telecommunications maintenance. When this happens, we will do our best to avoid adding to a month’s downtime with our own maintenance work (e.g., by working in parallel or postponing some tasks).