mirror of
https://github.com/ClusterCockpit/cc-backend
synced 2026-01-15 17:21:46 +01:00
Remove embedded tagger rules
This commit is contained in:
0
configs/tagger/README.md
Normal file
0
configs/tagger/README.md
Normal file
1
configs/tagger/apps/alf.txt
Normal file
1
configs/tagger/apps/alf.txt
Normal file
@@ -0,0 +1 @@
|
||||
alf
|
||||
7
configs/tagger/apps/caracal.txt
Normal file
7
configs/tagger/apps/caracal.txt
Normal file
@@ -0,0 +1,7 @@
|
||||
calc_rate
|
||||
qmdffgen
|
||||
dynamic
|
||||
evbopt
|
||||
explore
|
||||
black_box
|
||||
poly_qmdff
|
||||
3
configs/tagger/apps/chroma.txt
Normal file
3
configs/tagger/apps/chroma.txt
Normal file
@@ -0,0 +1,3 @@
|
||||
chroma
|
||||
qdp
|
||||
qmp
|
||||
1
configs/tagger/apps/cp2k.txt
Normal file
1
configs/tagger/apps/cp2k.txt
Normal file
@@ -0,0 +1 @@
|
||||
cp2k
|
||||
1
configs/tagger/apps/cpmd.txt
Normal file
1
configs/tagger/apps/cpmd.txt
Normal file
@@ -0,0 +1 @@
|
||||
cpmd
|
||||
1
configs/tagger/apps/flame.txt
Normal file
1
configs/tagger/apps/flame.txt
Normal file
@@ -0,0 +1 @@
|
||||
flame
|
||||
3
configs/tagger/apps/gromacs.txt
Normal file
3
configs/tagger/apps/gromacs.txt
Normal file
@@ -0,0 +1,3 @@
|
||||
gromacs
|
||||
gmx
|
||||
mdrun
|
||||
1
configs/tagger/apps/julia.txt
Normal file
1
configs/tagger/apps/julia.txt
Normal file
@@ -0,0 +1 @@
|
||||
julia
|
||||
1
configs/tagger/apps/lammps.txt
Normal file
1
configs/tagger/apps/lammps.txt
Normal file
@@ -0,0 +1 @@
|
||||
lmp
|
||||
1
configs/tagger/apps/matlab.txt
Normal file
1
configs/tagger/apps/matlab.txt
Normal file
@@ -0,0 +1 @@
|
||||
matlab
|
||||
1
configs/tagger/apps/openfoam.txt
Normal file
1
configs/tagger/apps/openfoam.txt
Normal file
@@ -0,0 +1 @@
|
||||
openfoam
|
||||
1
configs/tagger/apps/orca.txt
Normal file
1
configs/tagger/apps/orca.txt
Normal file
@@ -0,0 +1 @@
|
||||
orca
|
||||
4
configs/tagger/apps/python.txt
Normal file
4
configs/tagger/apps/python.txt
Normal file
@@ -0,0 +1,4 @@
|
||||
python
|
||||
pip
|
||||
anaconda
|
||||
conda
|
||||
2
configs/tagger/apps/starccm.txt
Normal file
2
configs/tagger/apps/starccm.txt
Normal file
@@ -0,0 +1,2 @@
|
||||
starccm+
|
||||
-podkey
|
||||
10
configs/tagger/apps/turbomole.txt
Normal file
10
configs/tagger/apps/turbomole.txt
Normal file
@@ -0,0 +1,10 @@
|
||||
dscf
|
||||
grad
|
||||
ridft
|
||||
rdgrad
|
||||
ricc2
|
||||
statpt
|
||||
aoforce
|
||||
escf
|
||||
egrad
|
||||
odft
|
||||
2
configs/tagger/apps/vasp.txt
Normal file
2
configs/tagger/apps/vasp.txt
Normal file
@@ -0,0 +1,2 @@
|
||||
vasp
|
||||
VASP
|
||||
26
configs/tagger/jobclasses/highload.json
Normal file
26
configs/tagger/jobclasses/highload.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"name": "Excessive CPU load",
|
||||
"tag": "excessiveload",
|
||||
"parameters": [
|
||||
"excessivecpuload_threshold_factor",
|
||||
"job_min_duration_seconds",
|
||||
"sampling_interval_seconds"
|
||||
],
|
||||
"metrics": ["cpu_load"],
|
||||
"requirements": [
|
||||
"job.shared == \"none\"",
|
||||
"job.duration > job_min_duration_seconds"
|
||||
],
|
||||
"variables": [
|
||||
{
|
||||
"name": "load_threshold",
|
||||
"expr": "cpu_load.limits.peak * excessivecpuload_threshold_factor"
|
||||
},
|
||||
{
|
||||
"name": "load_perc",
|
||||
"expr": "1.0 - (cpu_load.avg / cpu_load.limits.peak)"
|
||||
}
|
||||
],
|
||||
"rule": "cpu_load.avg > load_threshold",
|
||||
"hint": "This job was detected as excessiveload because the average cpu load {{.cpu_load.avg}} falls above the threshold {{.load_threshold}}."
|
||||
}
|
||||
22
configs/tagger/jobclasses/lowUtilization.json
Normal file
22
configs/tagger/jobclasses/lowUtilization.json
Normal file
@@ -0,0 +1,22 @@
|
||||
{
|
||||
"name": "Low ressource utilization",
|
||||
"tag": "lowutilization",
|
||||
"parameters": ["job_min_duration_seconds"],
|
||||
"metrics": ["flops_any", "mem_bw"],
|
||||
"requirements": [
|
||||
"job.shared == \"none\"",
|
||||
"job.duration > job_min_duration_seconds"
|
||||
],
|
||||
"variables": [
|
||||
{
|
||||
"name": "mem_bw_perc",
|
||||
"expr": "1.0 - (mem_bw.avg / mem_bw.limits.peak)"
|
||||
},
|
||||
{
|
||||
"name": "flops_any_perc",
|
||||
"expr": "1.0 - (flops_any.avg / flops_any.limits.peak)"
|
||||
}
|
||||
],
|
||||
"rule": "flops_any.avg < flops_any.limits.alert && mem_bw.avg < mem_bw.limits.alert",
|
||||
"hint": "This job was detected as low utilization because the average flop rate {{.flops_any.avg}} falls below the threshold {{.flops_any.limits.alert}}."
|
||||
}
|
||||
26
configs/tagger/jobclasses/lowload.json
Normal file
26
configs/tagger/jobclasses/lowload.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"name": "Low CPU load",
|
||||
"tag": "lowload",
|
||||
"parameters": [
|
||||
"lowcpuload_threshold_factor",
|
||||
"job_min_duration_seconds",
|
||||
"sampling_interval_seconds"
|
||||
],
|
||||
"metrics": ["cpu_load"],
|
||||
"requirements": [
|
||||
"job.shared == \"none\"",
|
||||
"job.duration > job_min_duration_seconds"
|
||||
],
|
||||
"variables": [
|
||||
{
|
||||
"name": "load_threshold",
|
||||
"expr": "job.numCores * lowcpuload_threshold_factor"
|
||||
},
|
||||
{
|
||||
"name": "load_perc",
|
||||
"expr": "1.0 - (cpu_load.avg / cpu_load.limits.peak)"
|
||||
}
|
||||
],
|
||||
"rule": "cpu_load.avg < cpu_load.limits.caution",
|
||||
"hint": "This job was detected as lowload because the average cpu load {{.cpu_load}} falls below the threshold {{.cpu_load.limits.caution}}."
|
||||
}
|
||||
14
configs/tagger/jobclasses/parameters.json
Normal file
14
configs/tagger/jobclasses/parameters.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"lowcpuload_threshold_factor": 0.9,
|
||||
"excessivecpuload_threshold_factor": 1.1,
|
||||
"highmemoryusage_threshold_factor": 0.9,
|
||||
"node_load_imbalance_threshold_factor": 0.1,
|
||||
"core_load_imbalance_threshold_factor": 0.1,
|
||||
"high_memory_load_threshold_factor": 0.9,
|
||||
"lowgpuload_threshold_factor": 0.7,
|
||||
"memory_leak_slope_threshold": 0.1,
|
||||
"job_min_duration_seconds": 600.0,
|
||||
"sampling_interval_seconds": 30.0,
|
||||
"cpu_load_pre_cutoff_samples": 11.0,
|
||||
"cpu_load_core_pre_cutoff_samples": 6.0
|
||||
}
|
||||
Reference in New Issue
Block a user