[one-users] Help need understanding the scheduler

[Shi Jin]

Thank you.

> So in this case. I do not really understand why host 2 with priority 1
> is after host 1 with priority 0.98. It seems it is a bug.
> Could you send as the RANK expression for VM 138 and the outout of
> onehost show for hosts 0, 1 and 2. So we can reproduce this error.

For VM 138, I used
RANK=-FREECPU
The output of onehost show for the 3 hosts are:
oneadmin at onefrontend64:~$ onehost show 0
HOST 0 INFORMATION
ID                    : 0
NAME                  : node1
STATE                 : MONITORED
IM_MAD                : im_kvm
VM_MAD                : vmm_kvm
TM_MAD                : tm_ssh

HOST SHARES
MAX MEM               : 33005972
USED MEM (REAL)       : 32605476
USED MEM (ALLOCATED)  : 7864320
MAX CPU               : 1600
USED CPU (REAL)       : 86
USED CPU (ALLOCATED)  : 375
RUNNING VMS           : 8

MONITORING INFORMATION
ARCH=x86_64
CPUSPEED=1596
FREECPU=1513.6
FREEMEMORY=22476240
HOSTNAME=node1
HYPERVISOR=kvm
MODELNAME=Intel(R) Xeon(R) CPU           X5570  @ 2.93GHz
NETRX=5421702
NETTX=492
TOTALCPU=1600
TOTALMEMORY=33005972
USEDCPU=86.4000000000001
USEDMEMORY=32605476
oneadmin at onefrontend64:~$ onehost show 1
HOST 1 INFORMATION
ID                    : 1
NAME                  : node2
STATE                 : MONITORED
IM_MAD                : im_kvm
VM_MAD                : vmm_kvm
TM_MAD                : tm_ssh

HOST SHARES
MAX MEM               : 33005972
USED MEM (REAL)       : 14841036
USED MEM (ALLOCATED)  : 3145728
MAX CPU               : 1600
USED CPU (REAL)       : 44
USED CPU (ALLOCATED)  : 150
RUNNING VMS           : 4

MONITORING INFORMATION
ARCH=x86_64
CPUSPEED=1596
FREECPU=1555.2
FREEMEMORY=28004332
HOSTNAME=node2
HYPERVISOR=kvm
MODELNAME=Intel(R) Xeon(R) CPU           X5570  @ 2.93GHz
NETRX=135006148
NETTX=492
TOTALCPU=1600
TOTALMEMORY=33005972
USEDCPU=44.8
USEDMEMORY=14841036
oneadmin at onefrontend64:~$ onehost show 2
HOST 2 INFORMATION
ID                    : 2
NAME                  : node3
STATE                 : MONITORED
IM_MAD                : im_kvm
VM_MAD                : vmm_kvm
TM_MAD                : tm_ssh

HOST SHARES
MAX MEM               : 33005964
USED MEM (REAL)       : 18188228
USED MEM (ALLOCATED)  : 1048576
MAX CPU               : 1600
USED CPU (REAL)       : 19
USED CPU (ALLOCATED)  : 50
RUNNING VMS           : 1

MONITORING INFORMATION
ARCH=x86_64
CPUSPEED=1596
FREECPU=1580.8
FREEMEMORY=29569136
HOSTNAME=node3
HYPERVISOR=kvm
MODELNAME=Intel(R) Xeon(R) CPU           X5570  @ 2.93GHz
NETRX=136062812
NETTX=492
TOTALCPU=1600
TOTALMEMORY=33005964
USEDCPU=19.2
USEDMEMORY=18188228

Also, in the table from the log file
Virtual Machine: 138
       0.983083        1
       1       2
       0.946115        0
Are they already sorted by the priority? Maybe there is something
wrong with PRI=1.
At the time of deploying VM 138, there was no VM running on HID=2.

Please let me know if you need more information to debug this.
Thanks a lot.

-- 
Shi Jin, Ph.D.