We recently upgraded our cluster from RedHat 7 to RedHat 8, and we use
Amber 16/AmberTools 17. We recompiled Amber during the migration.
Ever since the upgrade, we noticed that Amber jobs take dramatically longer
than they used to.
The CPU times remain normal (in the example below, about 9 minutes), but
the wall time needed was about 70 minutes. This job ran on two CPUs, so it
should have completed in less than five minutes. It must have been
idle/waiting for something for more than an hour.
Disk access performance appears to be normal, and I haven't seen any
complaints from other users, so it seems to be Amber related.
What else can I look for to track down the cause?
Thanks!
| Final Performance Info:
| -----------------------------------------------------
| Average timings for last 100 steps:
| Elapsed(s) = 10.50 Per Step(ms) = 104.96
| ns/day = 0.82 seconds/ns = 104959.07
|
| Average timings for all steps:
| Elapsed(s) = 4266.15 Per Step(ms) = 213.31
| ns/day = 0.41 seconds/ns = 213307.37
| -----------------------------------------------------
| Setup CPU time: 0.02 seconds
| NonSetup CPU time: 536.49 seconds
| Total CPU time: 536.52 seconds 0.15 hours
| Setup wall time: 0 seconds
| NonSetup wall time: 4266 seconds
| Total wall time: 4266 seconds 1.19 hours
_______________________________________________________________________
Kevin Keane | Systems Architect | University of San Diego ITS |
kkeane.sandiego.edu
*Pronouns: he/him/his*Maher Hall, 162 |5998 Alcalá Park | San Diego, CA
92110-2492 | 619.260.6859 | Text: 760-721-8339
*REMEMBER! **No one from IT at USD will ever ask to confirm or supply your
password*.
These messages are an attempt to steal your username and password. Please
do not reply to, click the links within, or open the attachments of these
messages. Delete them!
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Thu Apr 29 2021 - 21:00:02 PDT
