[Mauiusers] Late Maui snapshot sums up active jobs badly
Lennart Karlsson
Lennart.Karlsson at nsc.liu.se
Thu Sep 15 02:10:36 MDT 2005
Using Maui version maui-3.2.6p14-snap.1125680408 and
Torque version 1.2.0p6, there seems to be a factor two
error in simple arithemetics.
In the demonstration below user 'mahul' should be able to run
his three queued one-processor jobs, because the limit is eight
and he is merely using four. But Maui thinks that he already
uses eight processors.
I can tell that Maui has the same factor two problem counting MAXPS,
although I will not clutter up this e-mail with a demonstration.
-- Lennart Karlsson <Lennart.Karlsson at nsc.liu.se>
National Supercomputer Centre in Linkoping, Sweden
http://www.nsc.liu.se
===============================================================================
=
Demonstration:
# diagnose -q
Diagnosing blocked jobs (policylevel SOFT partition ALL)
job 35095 violates active SOFT MAXPROC limit of 8 for user mahul (R: 1, U: 8)
job 35162 violates active SOFT MAXPROC limit of 8 for user isaev (R: 1, U: 8)
job 35166 violates active SOFT MAXPROC limit of 8 for user mahul (R: 1, U: 8)
job 35167 violates active SOFT MAXPROC limit of 8 for user mahul (R: 1, U: 8)
job 35192 violates active SOFT MAXPROC limit of 8 for user soleil (R: 1, U: 8)
job 35292 violates active SOFT MAXPROC limit of 8 for user salam (R: 1, U: 10)
job 35299 violates active SOFT MAXPROC limit of 8 for user salam (R: 1, U: 10)
# showq
ACTIVE JOBS--------------------
JOBNAME USERNAME STATE PROC REMAINING STARTTIME
35310 alena Running 1 00:17:59 Thu Sep 15 09:59:46
35147 frenoca Running 1 23:49:02 Mon Sep 12 15:50:49
35148 frenoca Running 1 23:49:02 Mon Sep 12 15:50:49
35151 frenoca Running 1 23:49:02 Mon Sep 12 15:50:49
35149 frenoca Running 1 1:00:01:59 Mon Sep 12 16:03:46
35150 frenoca Running 1 1:00:01:59 Mon Sep 12 16:03:46
35108 mabos Running 1 1:10:43:02 Wed Sep 14 08:44:49
35109 mabos Running 1 1:10:43:22 Wed Sep 14 08:45:09
35110 mabos Running 1 1:10:43:22 Wed Sep 14 08:45:09
35111 mabos Running 1 1:10:43:22 Wed Sep 14 08:45:09
35293 petja Running 1 2:01:10:35 Thu Sep 15 09:12:22
35294 petja Running 1 2:01:10:35 Thu Sep 15 09:12:22
35295 petja Running 1 2:01:10:58 Thu Sep 15 09:12:45
35296 petja Running 1 2:01:11:08 Thu Sep 15 09:12:55
34193 soleil Running 1 3:04:14:45 Sun Sep 11 13:56:32
35264 salam Running 5 3:04:27:09 Wed Sep 14 14:28:56
34669 isaev Running 1 3:11:44:27 Sun Sep 11 21:26:14
34670 isaev Running 1 3:11:45:54 Sun Sep 11 21:27:41
34671 isaev Running 1 3:11:47:53 Sun Sep 11 21:29:40
34674 soleil Running 1 3:11:59:57 Sun Sep 11 21:41:44
34676 soleil Running 1 3:12:11:20 Sun Sep 11 21:53:07
34672 isaev Running 1 3:18:27:41 Mon Sep 12 04:09:28
35193 mikun Running 8 5:18:38:27 Tue Sep 13 16:40:14
35224 draad Running 1 5:23:42:08 Wed Sep 14 09:43:55
35191 soleil Running 1 6:13:41:05 Wed Sep 14 23:22:52
35165 mahul Running 1 6:15:39:19 Tue Sep 13 17:41:06
35092 mahul Running 1 6:22:24:25 Mon Sep 12 08:26:12
35093 mahul Running 1 6:22:24:57 Mon Sep 12 08:26:44
35094 mahul Running 1 6:22:25:00 Mon Sep 12 08:26:47
35083 arkady Running 8 8:04:00:57 Thu Sep 15 05:02:45
35082 arkady Running 8 8:04:06:11 Thu Sep 15 05:07:59
35088 arkady Running 8 8:06:25:26 Thu Sep 15 07:27:14
32 Active Jobs 64 of 70 Processors Active (91.43%)
IDLE JOBS----------------------
JOBNAME USERNAME STATE PROC WCLIMIT QUEUETIME
35091 arkady Idle 8 8:08:59:59 Mon Sep 12 05:10:39
35084 arkady Idle 8 8:08:59:59 Mon Sep 12 05:10:39
2 Idle Jobs
BLOCKED JOBS----------------
JOBNAME USERNAME STATE PROC WCLIMIT QUEUETIME
35095 mahul Idle 1 10:00:00:00 Mon Sep 12 08:22:12
35162 isaev Idle 1 7:00:20:00 Mon Sep 12 18:35:13
35166 mahul Idle 1 10:00:00:00 Mon Sep 12 23:19:21
35167 mahul Idle 1 10:00:00:00 Mon Sep 12 23:19:33
35192 soleil Idle 1 7:00:20:00 Tue Sep 13 10:31:36
35292 salam Idle 1 6:06:00:00 Wed Sep 14 18:42:32
35299 salam Idle 1 6:06:00:00 Thu Sep 15 09:33:33
Total Jobs: 41 Active Jobs: 32 Idle Jobs: 2 Blocked Jobs: 7
#
More information about the mauiusers
mailing list