Casper Qstat Queue
Queue: htc
queue_type = Execution
total_jobs = 132
state_count = Transit:0 Queued:2 Held:0 Waiting:0 Running:126 Exiting:1 Beg
un:3
max_queued = [u:rberrios=500]
from_route_only = True
resources_max.mps = 0
resources_max.ncpus = 144
resources_max.ngpus = 0
resources_max.nvpus = 0
resources_min.mps = 0
default_chunk.Qlist = htc
resources_assigned.mem = 7877951488kb
resources_assigned.mpiprocs = 220
resources_assigned.ncpus = 702
resources_assigned.nodect = 128
max_run_res.mem = [u:PBS_GENERIC=7200gb]
max_run_res.ncpus = [u:PBS_GENERIC=720]
backfill_depth = 50
enabled = True
started = True
Queue: casper
queue_type = Route
total_jobs = 2
state_count = Transit:0 Queued:0 Held:0 Waiting:2 Running:0 Exiting:0 Begun
:0
max_queued = [u:rberrios=500]
resources_max.mem = 25tb
resources_max.ncpus = 7168
resources_max.walltime = 340:00:00
route_destinations = largememroute,htc,htc2,tdd,vis,np_largegpu,gpgpu,a100,h100,
l40
route_held_jobs = False
route_retry_time = 60
enabled = True
started = True
Queue: vis
queue_type = Execution
total_jobs = 6
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:6 Exiting:0 Begun
:0
from_route_only = False
resources_max.gpu_type = gp100
resources_max.mps = 0
resources_max.ngpus = 1
resources_max.nvpus = 0
resources_min.gpu_type = gp100
resources_min.mps = 0
resources_min.ngpus = 1
default_chunk.Qlist = gp100
resources_assigned.mem = 652gb
resources_assigned.mpiprocs = 0
resources_assigned.ncpus = 13
resources_assigned.nodect = 6
max_run_res.ngpus = [u:PBS_GENERIC=2]
backfill_depth = 50
enabled = True
started = True
Queue: largemem
queue_type = Execution
total_jobs = 5
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:5 Exiting:0 Begun
:0
max_queued = [u:PBS_GENERIC=5]
from_route_only = True
resources_max.ncpus = 64
resources_max.ngpus = 0
resources_max.nodect = 1
resources_max.nvpus = 0
resources_min.mem = 354gb
default_chunk.Qlist = largemem
resources_assigned.mem = 4772gb
resources_assigned.mpiprocs = 2
resources_assigned.ncpus = 68
resources_assigned.nodect = 6
max_run = [u:PBS_GENERIC=3]
backfill_depth = 20
enabled = True
started = True
Queue: gpgpu
queue_type = Execution
total_jobs = 20
state_count = Transit:0 Queued:0 Held:7 Waiting:0 Running:13 Exiting:0 Begu
n:0
from_route_only = True
resources_max.gpu_type = v100
resources_max.ngpus = 32
resources_max.nvpus = 0
resources_min.gpu_type = v100
resources_min.ngpus = 1
default_chunk.Qlist = v100
resources_assigned.mem = 1350gb
resources_assigned.mpiprocs = 4
resources_assigned.ncpus = 16
resources_assigned.nodect = 13
max_run_res.ngpus = [u:PBS_GENERIC=32]
backfill_depth = 50
enabled = True
started = True
Queue: rda
queue_type = Execution
total_jobs = 57
state_count = Transit:0 Queued:1 Held:0 Waiting:0 Running:56 Exiting:0 Begu
n:0
resources_max.mem = 360gb
resources_max.ncpus = 36
resources_max.ngpus = 0
resources_max.walltime = 168:00:00
acl_group_enable = True
acl_groups = csg,dss,ssg
default_chunk.Qlist = rda
resources_assigned.mem = 135296mb
resources_assigned.ncpus = 119
resources_assigned.nodect = 58
backfill_depth = 100
enabled = True
started = True
Queue: tdd
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
from_route_only = True
resources_max.gpu_type = v100
resources_max.ngpus = 10
resources_max.nvpus = 0
resources_max.walltime = 08:00:00
resources_min.gpu_type = v100
resources_min.ngpus = 1
acl_group_enable = True
acl_groups = naml0001,niow0001,niow0002,ntdd0002,ntdd0003,ntdd0004,ntdd0005,
nvst0001,p22100000,p86850054
default_chunk.Qlist = v100
resources_assigned.mem = 0gb
resources_assigned.mpiprocs = 0
resources_assigned.ncpus = 0
resources_assigned.nodect = 0
max_run_res.ngpus = [u:PBS_GENERIC=32]
backfill_depth = 50
enabled = True
started = True
Queue: largememroute
queue_type = Route
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
resources_max.ncpus = 64
resources_max.ngpus = 0
resources_max.nodect = 1
resources_max.nvpus = 0
resources_min.mem = 354gb
route_destinations = largemem
route_held_jobs = False
route_retry_time = 60
enabled = True
started = True
Queue: mixgpu
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
from_route_only = True
resources_max.gpu_type = mixgpu
resources_max.ngpus = 16
resources_max.nvpus = 0
resources_min.gpu_type = mixgpu
resources_min.ngpus = 1
enabled = True
started = False
Queue: np_largegpu
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
from_route_only = True
resources_max.gpu_type = v100
resources_max.ngpus = 64
resources_max.nvpus = 0
resources_min.gpu_type = v100
resources_min.ngpus = 33
default_chunk.Qlist = v100
max_run = [u:PBS_GENERIC=1]
backfill_depth = 50
enabled = True
started = True
Queue: jhublogin
queue_type = Execution
total_jobs = 321
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:321 Exiting:0 Beg
un:0
max_queued = [u:PBS_GENERIC=1]
from_route_only = False
resources_max.ngpus = 0
default_chunk.Qlist = jhublogin
resources_assigned.mem = 2356gb
resources_assigned.ncpus = 589
resources_assigned.nodect = 589
backfill_depth = 1000
enabled = True
started = True
Queue: repair
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
acl_user_enable = True
acl_users = csgteam,jbaker,jblaas,sghosh,stormyk,vanderwb
from_route_only = False
resources_default.walltime = 01:00:00
default_chunk.Qlist = repair
enabled = True
started = True
Queue: htc2
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
acl_user_enable = True
acl_users = aricw,csgteam,jblaas,jedwards,mickc,sghosh,ssgadmin,vanderwb
from_route_only = True
resources_max.ncpus = 252
resources_max.ngpus = 0
resources_max.nvpus = 0
default_chunk.Qlist = htc
max_run_res.mem = [u:PBS_GENERIC=4680gb]
max_run_res.ncpus = [u:PBS_GENERIC=468]
backfill_depth = 5000
enabled = True
started = True
Queue: system
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
acl_group_enable = True
acl_groups = csg,csgteam,ssg,sssg0001
resources_assigned.mem = 0gb
resources_assigned.mpiprocs = 0
resources_assigned.ncpus = 0
resources_assigned.nodect = 0
enabled = True
started = True
Queue: gpudev
queue_type = Route
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
resources_max.gpu_type = v100
resources_max.mem = 738gb
resources_max.ncpus = 36
resources_max.ngpus = 4
resources_max.walltime = 00:30:00
resources_min.gpu_type = v100
resources_min.ngpus = 1
acl_group_enable = True
acl_groups = csg,ncar,ssg
route_destinations = S3011784
route_lifetime = 30
enabled = True
started = True
Queue: cloudtest
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
acl_group_enable = True
acl_groups = csg,hsg,ssg
resources_available.cloud_instance_type = t3.medium
resources_available.cloud_max_jobs_check_per_queue = 10
resources_available.cloud_queue = True
resources_available.cloud_scenario = cloudtest
backfill_depth = 0
enabled = True
started = True
Queue: gpuworkshop
queue_type = Route
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
resources_max.gpu_type = v100
resources_max.mem = 100gb
resources_max.ncpus = 2
resources_max.ngpus = 2
resources_max.walltime = 01:30:00
resources_min.gpu_type = v100
resources_min.ngpus = 1
acl_group_enable = True
acl_groups = csg,ncar,ssg,ucis0004
route_destinations = R3786268
enabled = True
started = True
Queue: a100
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
from_route_only = True
resources_max.gpu_type = a100
resources_max.ngpus = 32
resources_min.gpu_type = a100
resources_min.ngpus = 1
default_chunk.Qlist = a100
resources_assigned.mem = 0gb
resources_assigned.mpiprocs = 0
resources_assigned.ncpus = 0
resources_assigned.nodect = 0
max_run_res.ngpus = [u:PBS_GENERIC=32]
enabled = True
started = True
Queue: h100
queue_type = Execution
total_jobs = 2
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:2 Exiting:0 Begun
:0
from_route_only = True
resources_max.gpu_type = h100
resources_max.ngpus = 8
resources_min.gpu_type = h100
resources_min.ngpus = 1
default_chunk.Qlist = h100
resources_assigned.mem = 300gb
resources_assigned.mpiprocs = 0
resources_assigned.ncpus = 64
resources_assigned.nodect = 2
max_run_res.ngpus = [u:PBS_GENERIC=8]
enabled = True
started = True
Queue: l40
queue_type = Execution
total_jobs = 1
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:1 Exiting:0 Begun
:0
from_route_only = True
resources_max.gpu_type = l40
resources_max.ngpus = 36
resources_min.gpu_type = l40
resources_min.ngpus = 1
default_chunk.Qlist = l40
resources_assigned.mem = 60gb
resources_assigned.mpiprocs = 0
resources_assigned.ncpus = 1
resources_assigned.nodect = 1
max_run_res.ngpus = [u:PBS_GENERIC=36]
enabled = True
started = True
Queue: tutorial
queue_type = Route
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
default_chunk.mem = 100gb
route_destinations = R2696279
enabled = True
started = True
Queue: S3011784
queue_type = Execution
total_jobs = 0
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:0 Exiting:0 Begun
:0
acl_user_enable = True
acl_users = root@casper-pbs.hpc.ucar.edu
resources_max.gpu_type = v100
resources_max.mem = 738gb
resources_max.ncpus = 36
resources_max.ngpus = 4
acl_group_enable = True
acl_groups = csg,ncar,ssg
resources_available.gpu_type = v100
resources_available.mem = 738gb
resources_available.ncpus = 36
resources_available.ngpus = 4
enabled = True
started = False
partition = pbs-default