[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [HTCondor-users] Duplicated nodes on master?



Hello,

I figure it out:

I have two network interfaces (one for my external network IP 200.xxxxx and another for the condor network 192.168xxxxx). Condor is creating nodes for both interfaces.

How can I limit condor to NOT use the interface eth0 with IP 200.xxxxx?

Thank you!


------------------------------------------------------------------------------------------------------------------------
Prof. Dr. Roberto Fernandes Tavares Neto
Departamento de Engenharia de ProduÃÃo / Industrial Engineering Department
Universidade Federal de SÃo Carlos
tavares@xxxxxxxxxxxxx   tel +55 16 3351-9532
http://www.dep.ufscar.br/tavares
------------------------------------------------------------------------------------------------------------------------

On Tue, Dec 5, 2017 at 11:33 AM, Edier Zapata <edalzap@xxxxxxxxx> wrote:
Hi Roberto,
Âtry this:
condor_status -af:h Name OpSys Arch Memory Cpus
You will get the full name for each slot, operating system, architecture, memory and cores (CPUs)
The another way is check the Collector's log (/var/log/condor/CollectorLog) and the StartdLog (same path)

Bye

On Tue, Dec 5, 2017 at 6:30 AM, Roberto Tavares <tavares@xxxxxxxxxxxxx> wrote:
Hello,


I've configured HTCondor into to machines, Node0 (COLLECTOR, MASTER, NEGOTIATOR, SCHEDD, STARTD) and Node1 (MASTER, STARTD).

The communication seems to be fine, I can use all nodes. However, At some point I'm getting duplicated nodes on Node0. condor_status gives me:

$ condor_status
NameÂÂÂÂÂÂÂÂÂÂÂÂÂÂ OpSysÂÂÂÂÂ ArchÂÂ StateÂÂÂÂ Activity LoadAv MemÂÂ ActvtyTime

slot1@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:21
slot2@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:23
slot3@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:24
slot4@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:24
slot5@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:26
slot6@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:27
slot7@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:27
slot8@Node1 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 1992Â 0+00:00:21
slot1@Node0 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 3943Â 0+00:00:01
slot1@Node0 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.260 3943Â 0+00:00:01
slot2@Node0 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.240 3943Â 0+00:00:03
slot2@Node0 LINUXÂÂÂÂÂ X86_64 Unclaimed IdleÂÂÂÂÂ 0.000 3943Â 0+00:00:02
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ Total Owner Claimed Unclaimed Matched Preempting Backfill

ÂÂÂÂÂÂÂ X86_64/LINUXÂÂÂ 12ÂÂÂÂ 0ÂÂÂÂÂÂ 0ÂÂÂÂÂÂÂ 12ÂÂÂÂÂÂ 0ÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂÂÂ 0

ÂÂÂÂÂÂÂÂÂÂÂÂÂÂ TotalÂÂÂ 12ÂÂÂÂ 0ÂÂÂÂÂÂ 0ÂÂÂÂÂÂÂ 12ÂÂÂÂÂÂ 0ÂÂÂÂÂÂÂÂÂ 0ÂÂÂÂÂÂÂ 0

In my config file for Node0, I have:

$ cat /etc/condor/condor_config |grep NUM_CPUS
NUM_CPUS=2

How can I trace how I got 2 solt1@Node0 and 2 slot2@Node0?

I'm running condor_8.4.12-409562-ubuntu14_amd64

Thank you!!!

Roberto

_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxx.edu with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/



--


_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@cs.wisc.edu with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/