Re: [HTCondor-users] GPUs_MONITOR resource usage

["Baumeier, B." <B.Baumeier@xxxxxx>]

For what it's worth, for me it's not as high but about 8%. Which seems still a bit more than it should.

-----Original Message-----
From: HTCondor-users [mailto:htcondor-users-bounces@xxxxxxxxxxx] On Behalf Of Bert DeKnuydt
Sent: Thursday, January 10, 2019 8:50 AM
To: htcondor-users@xxxxxxxxxxx
Subject: Re: [HTCondor-users] GPUs_MONITOR resource usage



On 2019/01/09 22:04, Alexander Antoniades wrote:
> I killed the process and cpu usage is the same.
> 
> USERÂ Â Â ÂPID %CPU %MEMÂ Â VSZÂ ÂRSS TTYÂ Â Â STAT STARTÂ ÂTIME 
> COMMAND condor Â26313 67.1 0.0 26460 6772 ?    S  15:39 
> 14:44 GPUs_MONITOR
> 

Hi all,

I'm afraid I have to report the same here.

One GPU, old test machine, condor started less than one day ago.

-----------------
[root@maredsous ~]# ps -ef | grep condor
condor   21117     1  0 Jan09 ?        00:00:00 /usr/sbin/condor_master -f
root     21118 21117  0 Jan09 ?        00:00:11 condor_procd -A /var/run/condor/procd_pipe -L /var/log/condor/ProcLog -R 1000000 -S 60 -C 900
condor   21119 21117  0 Jan09 ?        00:00:00 condor_shared_port -f -p 9618
condor   21120 21117  0 Jan09 ?        00:00:09 condor_startd -f
condor   21169 21120  6 Jan09 ?        01:16:30 GPUs_MONITOR

[root@maredsous ~]# systemctl status condor â condor.service - Condor Distributed High-Throughput-Computing
    Loaded: loaded (/usr/lib/systemd/system/condor.service; enabled; vendor preset: disabled)
    Active: active (running) since Wed 2019-01-09 13:10:55 CET; 19h ago
  Main PID: 21117 (condor_master)
    Status: "All daemons are responding"
     Tasks: 5 (limit: 32767)
    Memory: 20.4M
    CGroup: /system.slice/condor.service
            ââ21117 /usr/sbin/condor_master -f
            ââ21118 condor_procd -A /var/run/condor/procd_pipe -L /var/log/condor/ProcLog -R 1000000 -S 60 -C 900
            ââ21119 condor_shared_port -f -p 9618
            ââ21120 condor_startd -f
            ââ21169 GPUs_MONITOR
------------------

This is 8.8.0 CentOS rpm, installed on Fedora 29.
Works perfectly for the rest.

strace reports it is mainly in

nanosleep({tv_sec=0, tv_nsec=100000000}

which is to be expected.  For the rest I see zillions (well, 4200 per second more or less), of these

ioctl(0, _IOC(_IOC_READ|_IOC_WRITE, 0x46, 0x2a, 0x20), 0x7ffe74c56e10) = 0

Don't know what this exactly is doing.

Greetings, Bert.
_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx 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/