(Click to open topic with navigation)
Synopsis
mdiag -R [-v] [-V job] [resourcemanagerid]
Overview
The mdiag -R command is used to present information about configured resource managers. The information presented includes name, host, port, state, type, performance statistics and failure notifications.
Examples
Example 4-19:
> $ mdiag -R -v
diagnosing resource managers
RM[internal] State: --- Type: SSS ResourceType: COMPUTE
Max Fail/Iteration: 0
JobCounter: 6
Partition: SHARED
RM Performance: AvgTime=0.00s MaxTime=0.00s (55353 samples)
RM Languages: -
RM Sub-Languages: -
RM[torque] State: Active Type: PBS ResourceType: COMPUTE
Timeout: 30000.00 ms
Version: '4.2.4'
Job Submit URL: exec:///opt/torque-4.2/bin/qsub
Objects Reported: Nodes=1 (12 procs) Jobs=1
Nodes Reported: 1 (N/A)
Flags: executionServer
Partition: torque
Event Management: EPORT=15004 (last event: 00:03:07)
NOTE: SSS protocol enabled
Submit Command: /opt/torque-4.2/bin/qsub
DefaultClass: batch
Total Jobs Started: 1
RM Performance: AvgTime=0.00s MaxTime=35.00s (220097 samples)
RM Languages: PBS
RM Sub-Languages: PBS
RM[torque] Failures:
clusterquery (683 of 55349 failed)
-12days 'cannot connect to PBS server '' (pbs_errno=15033, 'Batch protocol error')'
NOTE: use 'mrmctl -f messages <RMID>' to clear stats/failures
RM[FLEXlm] State: Active Type: NATIVE ResourceType: LICENSE
Timeout: 30000.00 ms
Cluster Query URL: exec://$TOOLSDIR/flexlm/license.mon.flexLM.pl
Licenses Reported: 6 types (250 of 282 available)
Partition: SHARED
License Stats: Avg License Avail: 239.01 (978 iterations)
Iteration Summary: Idle: 396.42 Active: 150.92 Busy: -447.34
License biocol 50 of 50 available (Idle: 100.00% Active: 0.00%)
License cloudform 100 of 100 available (Idle: 100.00% Active: 0.00%)
License mathworks 8 of 25 available (Idle: 52.00% Active: 48.00%)
License verity 25 of 25 available (Idle: 100.00% Active: 0.00%)
Event Management: (event interface disabled)
RM Performance: AvgTime=0.00s MaxTime=0.61s (1307618 samples)
clusterquery: AvgTime=0.02s MaxTime=0.61s (9465 samples)
queuequery: AvgTime=0.00s MaxTime=0.00s (1 samples)
rminitialize: AvgTime=0.00s MaxTime=0.00s (1 samples)
getdata: AvgTime=0.17s MaxTime=0.60s (978 samples)
RM Languages: NATIVE
RM Sub-Languages: NATIVE
AM[mam] Type: MAM State: 'Active'
Host: localhost
Port: 7112
Timeout: 15
Thread Pool Size: 2
Charge Policy: DEBITALLWC
Validate Job Submission: TRUE
Create Failure Action: CANCEL,HOLD
Start Failure Action: CANCEL,HOLD
AM[mam] Failures:
Fri Jun 21 14:32:45 Create 'Failure registering job Create (1) with accounting manager -- server rejected request with status code 740 - Insufficient funds: There are no valid allocations to satisfy the quote'