Mahmood Naderan
2016-10-07 20:37:20 UTC
Hi,
I am confusing the nodect variable in Qmgr with the proc numbers defined in the server_priv/nodes.
Currently, I have
cluster np=15
compute-0-1 np=32
compute-0-2 np=32
compute-0-3 np=32
and
Qmgr: print queue @cluster
create queue default
set queue default queue_type = Execution
set queue default resources_max.nodect = 111
set queue default resources_default.nodes = 4
set queue default resources_available.nodect = 111
set queue default keep_completed = 120
set queue default enabled = True
set queue default started = True
Qmgr: list queue @cluster
Queue default
queue_type = Execution
total_jobs = 10
state_count = Transit:0 Queued:4 Held:0 Waiting:0 Running:4 Exiting:0
resources_max.nodect = 111
resources_default.nodes = 4
mtime = Fri Oct 7 23:57:44 2016
resources_available.nodect = 111
resources_assigned.nodect = 4
keep_completed = 120
enabled = True
started = True
I am confused with resources_max.nodect/resources_default.nodes/resources_available.nodect/resources_assigned.nodect = 4
111 is the sum of the cores (3*32+15).
Are these values correct?
Regards,
Mahmood
I am confusing the nodect variable in Qmgr with the proc numbers defined in the server_priv/nodes.
Currently, I have
cluster np=15
compute-0-1 np=32
compute-0-2 np=32
compute-0-3 np=32
and
Qmgr: print queue @cluster
create queue default
set queue default queue_type = Execution
set queue default resources_max.nodect = 111
set queue default resources_default.nodes = 4
set queue default resources_available.nodect = 111
set queue default keep_completed = 120
set queue default enabled = True
set queue default started = True
Qmgr: list queue @cluster
Queue default
queue_type = Execution
total_jobs = 10
state_count = Transit:0 Queued:4 Held:0 Waiting:0 Running:4 Exiting:0
resources_max.nodect = 111
resources_default.nodes = 4
mtime = Fri Oct 7 23:57:44 2016
resources_available.nodect = 111
resources_assigned.nodect = 4
keep_completed = 120
enabled = True
started = True
I am confused with resources_max.nodect/resources_default.nodes/resources_available.nodect/resources_assigned.nodect = 4
111 is the sum of the cores (3*32+15).
Are these values correct?
Regards,
Mahmood