[
Date Prev][
Date Next][
Thread Prev][
Thread Next][
Date Index][
Thread Index]
[
List Home]
[ptp-user] Problem with OpenPBS monitoring
|
Hello ,
Seeking for your help,I am facing issues while setup LLview monitoring in with OpenPBS scheduler.All required file for llview is getting created but its not showing any node information in llview_final.xml file.
I am attaching here with log file and llview final.xml for your reference.
Thanks in advance.
Regards
Rahul
LML Data Access Workflow Manager 1.0, starting at (Thu Jan 24 17:48:22 IST 2019)
LML Data Access Workflow Manager 1.0, ending at (Thu Jan 24 17:48:22 IST 2019)
<system
system_name="Cluster (loginnode1)"
system_cpucount=""
system_cpuspeed=" GHz"
system_cputype=""
system_type="cluster"
system_frames=""
system_perform=" PFLOPS"
system_mem="TB"
system_time="01/24/19 17:48:22"
LLview_prediction="precalc"
system_motd="?"
>
<classes
system_sysprio="-1"
system_maxnumtopdogs="-1"
ConfiguredClasses=""
/>
<node
node_name="node25"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node19"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node20"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node14"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node33"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node1"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node32"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node26"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node31"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node10"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node5"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node17"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node7"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node9"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node18"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node24"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node11"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node30"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node8"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node23"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node28"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node13"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node4"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node21"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node27"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node22"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node6"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node2"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node15"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node29"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node16"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node12"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<node
node_name="node3"
node_state="Idle"
node_arch="x86"
node_cpus="0"
node_maxtasks="0"
node_avail_classes=""
>
<mem
mem_total="24"
mem_avail="24"
mem_used="0"
mem_unit="mb"
/>
<cpu
cpu_total="0"
cpu_run="0"
cpu_avail="0"
gpu_total="0"
gpu_run="0"
gpu_avail="0"
/>
</node>
<usage
date="01/24/19 17:48:22"
nodes="396"
running="0"
alloc="0"
power_usage=""
usagestr="01/24/19 17:48:22,396,0,0"
startdate="01/24/19 16:00:00"
enddate="01/24/19 17:45:00"
numentries="8"
step="0.25"
nodeshist="0:0:792:0:0:396:0:396"
runninghist="0:0:0:0:0:0:0:0"
allochist="0:0:0:0:0:0:0:0"
numhist="0:0:2:0:0:1:0:1"
pwr_startdate="01/24/19 16:00:00"
pwr_enddate="01/24/19 17:45:00"
pwr_numentries="8"
pwr_step="0.25"
pwr_watthist="0:0:0:0:0:0:0:0"
pwr_numhist="0:0:2:0:0:1:0:1"
usagepwrstr="01/24/19 17:48:22,0.000000"
/>
</system>
execute_step: input file for step not found /home/apps/llview/da/temp/datastep___init__.xml ...
execute_step: --> generating empty /home/apps/llview/da/temp/datastep___init__.xml ...
execute_step: unlink output file from previous run /home/apps/llview/da/temp/datastep_getdata.xml ...
"Mom" => "",
"Port" => "",
"comment" => "",
"license" => "",
"pbs_version" => "",
"pcpus" => "",
"resources_assigned.accelerator_memory" => "",
"resources_assigned.mem" => "",
"resources_assigned.naccelerators" => "",
"resources_assigned.ncpus" => "",
"resources_assigned.netwins" => "",
"resources_assigned.vmem" => "",
"resources_available.arch" => "",
"resources_available.host" => "",
"resources_available.mem" => "",
"resources_available.ncpus" => "",
"resources_available.vnode" => "",
"resv_enable" => "",
"sharing" => "",
execute_step: output file not generated by step, renaming input file to /home/apps/llview/da/temp/datastep_getdata.xml ...
reading file: /home/apps/llview/da/temp/sysinfo_LML.xml ...
LML_file_obj: read XML in 0.0003 sec
LML_file_obj: parse XML in 0.0002 sec
reading file: /home/apps/llview/da/temp/jobs_LML.xml ...
LML_file_obj: read XML in 0.0004 sec
LML_file_obj: parse XML in 0.0001 sec
reading file: /home/apps/llview/da/temp/nodes_LML.xml ...
LML_file_obj: read XML in 0.0003 sec
LML_file_obj: parse XML in 0.0023 sec
scan system: type is Cluster
system_type=Cluster
objects: total #34
|-- 33 (node)
|-- 1 (system)
execute_step: unlink output file from previous run /home/apps/llview/da/temp/datastep_cppermfile.xml ...
execute_step: output file not generated by step, renaming input file to /home/apps/llview/da/temp/datastep_cppermfile.xml ...
/home/apps/llview/da/LML_color/LML_color_obj.pl
scan system: type is Cluster
LML_llview_generator_cluster: new main
system_time=01/24/19-17:48:22
execute_step: output file not generated by step, renaming input file to /home/apps/llview/da/temp/datastep_convertLLview.xml ...
infile = /home/apps/llview/da/temp/perm/LML_color.xml
outfile = /home/apps/llview/da/temp/perm/llview_usage.xml
dbdir = /home/apps/llview/da/temp/perm/db
dbname = torquedb
interval = 0.25
WF: /home/apps/llview/da/temp/perm/LML_color.xml
WF2: usagestr="01/24/19 17:48:22,396,0,0"
WF: power=0.000000 01/24/19 17:48:22=01/24/19 17:48:22
UsageDB: found 01/24/19 17:48:22 396 0 0 0.000000
WF: sec_to_date 1548331200 -> sec=0,min=30,hours=17,mday=24,mon=1,year=19 -> 01/24/19 17:30:00
WF: sec_to_date 1548332100 -> sec=0,min=45,hours=17,mday=24,mon=1,year=19 -> 01/24/19 17:45:00
WF: sec_to_date 1548331200 -> sec=0,min=30,hours=17,mday=24,mon=1,year=19 -> 01/24/19 17:30:00
WF: sec_to_date 1548332100 -> sec=0,min=45,hours=17,mday=24,mon=1,year=19 -> 01/24/19 17:45:00
execute_step: output file not generated by step, renaming input file to /home/apps/llview/da/temp/datastep_Usage.xml ...
execute_step: unlink output file from previous run /home/apps/llview/da/temp/datastep_cpLLviewFile.xml ...
execute_step: output file not generated by step, renaming input file to /home/apps/llview/da/temp/datastep_cpLLviewFile.xml ...