Follows the PBS Pro Design Document Guidelines.
This is to enhance the "node ramp down" feature, by introducing a new option "-k <select>" ("k" for "keep") to the pbs command "pbs_release_nodes". This will allow users or admins to retain some of the sister nodes/vnodes which satisfy the "select" argument, while performing node ramp down operation.
pbs_release_nodes [-j <job ID>] <vnode> [<vnode> [<vnode>] ...]
pbs_release_nodes [-j <job ID>] -a
pbs_release_nodes [-j <job ID>] -k <select statement>
pbs_release_nodes --version
$ qsub -l select=4:model=abc:ncpus=5+3:model=abc:bigmem=true:ncpus=1+2:model=def:ncpus=32 job.scr
120.pbssrv
Now grepping for assigned vnodes we may see :
$ qstat -f 120| egrep exec_vnode
exec_vnode = (nd_abc_1:ncpus=5)+(nd_abc_2:ncpus=5)+(nd_abc_3[0]:ncpus=5)+(nd_abc_3[1]:ncpus=5)+(nd_abc_4_bm:ncpus=1)+(nd_abc_5_bm:ncpus=1)+(nd_abc_6_bm:ncpus=1)+(nd_def_1:ncpus=32)+(nd_def_2:ncpus=32)
Here the first chunk "(nd_abc_1:ncpus=5)" represents the mother superior node while each of the remaining others represent a sister node.
and node statuses as :
$ pbsnodes -av
nd_abc_1
Mom = nd_abc_1.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.model = abc
resources_available.ncpus = 5
resources_assigned.ncpus = 5nd_abc_2
Mom = nd_abc_2.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.model = abc
resources_available.ncpus = 5
resources_assigned.ncpus = 5nd_abc_3[0]
Mom = nd_abc_3.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.model = abc
resources_available.ncpus = 5
resources_assigned.ncpus = 5nd_abc_3[1]
Mom = nd_abc_3.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.model = abc
resources_available.ncpus = 5
resources_assigned.ncpus = 5nd_abc_4_bm
Mom = nd_abc_4_bm.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.bigmem = True
resources_available.model = abc
resources_available.ncpus = 1
resources_assigned.ncpus = 1nd_abc_5_bm
Mom = nd_abc_5_bm.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.bigmem = True
resources_available.model = abc
resources_available.ncpus = 1
resources_assigned.ncpus = 1nd_abc_6_bm
Mom = nd_abc_6_bm.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.bigmem = True
resources_available.model = abc
resources_available.ncpus = 1
resources_assigned.ncpus = 1nd_def_1
Mom = nd_def_1.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.model = def
resources_available.ncpus = 32
resources_assigned.ncpus = 32nd_def_2
Mom = nd_def_2.pbspro.com
state = job-busy
jobs = 120.pbssrv/0
resources_available.model = def
resources_available.ncpus = 32
resources_assigned.ncpus = 32
Now if we do a pbs_release_nodes with the new "-k" option having a select argument which is a sub statement of select string used in qsub -l :
$ pbs_release_nodes -j 120 -k select=model=abc:ncpus=5+2:model=abc:bigmem=true:ncpus=1
will release the nodes (nd_abc_3[0]:ncpus=5)+(nd_abc_3[1]:ncpus=5)+(nd_abc_6_bm:ncpus=1)+(nd_def_1:ncpus=32)+(nd_def_2:ncpus=32) from the job while retaining the nodes (nd_abc_1:ncpus=5)+(nd_abc_2:ncpus=5)+(nd_abc_4_bm:ncpus=1)+(nd_abc_5_bm:ncpus=1).
The new phase of the job will have below vnodes associated with it
$ qstat -f 120| egrep exec_vnode
exec_vnode = (nd_abc_1:ncpus=5)+(nd_abc_2:ncpus=5)+(nd_abc_4_bm:ncpus=1)+(nd_abc_5_bm:ncpus=1)
The same result in the previous example can be achieved by using the below shorter select string where the resource list is partial one with respect to the original select supplied to qsub.
$ pbs_release_nodes -j 120 -k select=model=abc+2:bigmem=true
pbs_release_nodes: <sub select string>
pbs_release_nodes: -a and -k options cannot be used together
pbs_release_nodes: cannot supply node list with -k option
pbs_release_nodes: only a "select=" string is valid in -k option
pbs_release_nodes: Unknown resource: <undefined res name>
pbs_release_nodes: Server returned error 15010 for job
Project Documentation Main Page