ricardobarroslourenco / CCprimer

Compute Canada for geoscientists in a rush
https://ricardobarroslourenco.github.io/CCprimer/
Other
2 stars 0 forks source link

Queueing strategies #12

Open ricardobarroslourenco opened 9 months ago

ricardobarroslourenco commented 9 months ago

Include partition stats:


[lourenco@gra-login3 ~]$ partition-stats 

Node type |                     Max walltime                            
          |   3 hr   |  12 hr  |  24 hr  |  72 hr  |  168 hr |  672 hr |
----------|-------------------------------------------------------------
       Number of Queued Jobs by partition Type (by node:by core)        
----------|-------------------------------------------------------------
Regular   |    0:245 |   1:342 | 153:667 |  54:659 |  69:372 |   0:0   |
Large Mem |    0:401 |  88:948 |   3:252 |   2:10  |   1:133 |   0:0   |
GPU       |    0:1   |   0:2   |   0:76  |   8:162 |  33:11  |   0:0   |
----------|-------------------------------------------------------------
      Number of Running Jobs by partition Type (by node:by core)        
----------|-------------------------------------------------------------
Regular   |    1:8   |  23:84  |  40:1301|  55:886 |  58:1887|   0:0   |
Large Mem |    0:1   |   1:50  |   1:108 |   8:14  |   1:21  |   0:0   |
GPU       |    0:10  |   0:23  |   2:38  |  29:80  |   5:15  |   0:0   |
----------|-------------------------------------------------------------
        Number of Idle nodes by partition Type (by node:by core)        
----------|-------------------------------------------------------------
Regular   |    0:0   |   0:0   |   0:0   |   0:0   |   0:0   |   0:0   |
Large Mem |    0:0   |   0:0   |   0:0   |   0:0   |   0:0   |   0:0   |
GPU       |   43:38  |  29:24  |  24:24  |  21:15  |  15:13  |   0:0   |
----------|-------------------------------------------------------------
       Total Number of nodes by partition Type (by node:by core)        
----------|-------------------------------------------------------------
Regular   | 1074:632 |1074:632 |1044:612 | 753:381 | 371:170 |   0:0   |
Large Mem |   27:19  |  27:19  |  24:16  |  20:4   |   5:4   |   0:0   |
GPU       |  214:136 | 194:116 | 182:110 | 139:81  |  42:39  |   0:0   |
----------|-------------------------------------------------------------

[lourenco@gra-login3 ~]$ 

And a comment on how to get around scheduling queues, when the CPU queue is huge...