[Mauiusers] why use 'checknode' command always tell me the node is DOWN??

luo yi luoyi829 at hotmail.com
Fri Dec 8 01:11:34 MST 2006


i use 'checknode' to check the whole nodes.the result is that every nodes 
is  idle ,except two nodes --c1502 and c1506.but the pbs_mom is runing at 
c1502 and c1506. i use qmgr to show nodes info shows the nodes is free ,but 
use checknode it show the nodes down. and these two nodes can't be 
scheduled to run job. i am so puzzled .
I have restart the pbs_mom at c1502 and c1506 , pbs_server for several 
times ,but it did not change anymore.

[root at console bin]# qmgr
Max open servers: 4
Qmgr: p n c1502
#
# Create nodes and set their properties.
#
#
# Create and define node c1502
#
# create node c1502     # unsupported operation
set node c1502 state = free
set node c1502 properties = dpool
set node c1502 ntype = cluster
set node c1502 status = opsys=linux
set node c1502 status += uname=Linux c1502 2.6.9-5.ELsmp #1 SMP Wed Jan 5 
19:30:39 EST 2005 i686
set node c1502 status += sessions=? 0
set node c1502 status += nsessions=? 0
set node c1502 status += nusers=0
set node c1502 status += idletime=0
set node c1502 status += totmem=3066284kb
set node c1502 status += availmem=3040300kb
set node c1502 status += physmem=1034676kb
set node c1502 status += ncpus=2
set node c1502 status += loadave=0.00
set node c1502 status += message=ERROR: torque spool filesystem full
set node c1502 status += netload=3071813
set node c1502 status += state=free
set node c1502 status += jobs=? 0
set node c1502 status += rectime=1165565461

[root at console bin]# checknode c1502


checking node c1502

State:      Down  (in current state for 00:00:00)
Configured Resources: PROCS: 2  MEM: 1010M  SWAP: 2969M  DISK: 1M
Utilized   Resources: PROCS: 2
Dedicated  Resources: [NONE]
Opsys:         linux  Arch:      [NONE]
Speed:      1.00  Load:       0.000
Network:    [DEFAULT]
Features:   [dpool]
Attributes: [Batch]
Classes:    [dpool 2:2]

Total Time: 21:07:23:55  Up: 00:00:00 (0.00%)  Active: 00:00:00 (0.00%)

Reservations:
NOTE:  no reservations on node

Max open servers: 4
Qmgr: p n c1506
#
# Create nodes and set their properties.
#
#
# Create and define node c1506
#
# create node c1506     # unsupported operation
set node c1506 state = free
set node c1506 properties = dpool
set node c1506 ntype = cluster
set node c1506 status = opsys=linux
set node c1506 status += uname=Linux c1506 2.6.9-5.ELsmp #1 SMP Wed Jan 5 
19:30:39 EST 2005 i686
set node c1506 status += sessions=2864
set node c1506 status += nsessions=1
set node c1506 status += nusers=1
set node c1506 status += idletime=5985
set node c1506 status += totmem=3066284kb
set node c1506 status += availmem=2927328kb
set node c1506 status += physmem=1034676kb
set node c1506 status += ncpus=2
set node c1506 status += loadave=0.00
set node c1506 status += message=ERROR: torque spool filesystem full
set node c1506 status += netload=51812000
set node c1506 status += state=free
set node c1506 status += jobs=? 0
set node c1506 status += rectime=1165565680

[root at console bin]# checknode c1506


checking node c1506

State:      Down  (in current state for 00:00:00)
Configured Resources: PROCS: 2  MEM: 1010M  SWAP: 2858M  DISK: 1M
Utilized   Resources: PROCS: 2
Dedicated  Resources: [NONE]
Opsys:         linux  Arch:      [NONE]
Speed:      1.00  Load:       0.000
Network:    [DEFAULT]
Features:   [dpool]
Attributes: [Batch]
Classes:    [dpool 2:2]

Total Time: 9:17:05:10  Up: 00:00:00 (0.00%)  Active: 00:00:00 (0.00%)

Reservations:
NOTE:  no reservations on node

_________________________________________________________________
ÓëÁª»úµÄÅóÓѽøÐн»Á÷£¬ÇëʹÓà MSN Messenger:  http://messenger.msn.com/cn  



More information about the mauiusers mailing list