Results 1 to 5 of 5
  1. #1

    High load process, how do I find out what it was?

    My server evidently had a really high load, I installed prm and it killed the offending process here is what I found in /usr/local/prm/killed

    USER: xfs
    PID : 3688
    CMD : xfs
    CPU%: 98 (limit: 40)
    MEM%: 0 (limit: 20)
    PROCS: 1 (limit: 25)

    Is there a way to find out what this was?
    Also inside of the log:
    /usr/local/prm/prm_log

    here is what I find:

    Jul 25 22:45:08 my-server prm(18226): process 3688 exceeded resource limits, killed.
    Jul 25 22:45:08 my-server prm(18226): check /usr/local/prm/killed/3688 for process specific information.
    Jul 25 22:48:00 my-server prm(20549): system load (0) below check requirment; aborting.
    Jul 25 22:52:00 my-server prm(20997): system load (0) below check requirment; aborting.
    Jul 25 22:56:01 my-server prm(21126): system load (0) below check requirment; aborting.
    Jul 25 23:00:00 my-server prm(21250): system load (0) below check requirment; aborting.
    Jul 25 23:04:01 my-server prm(21709): system load (0) below check requirment; aborting.
    Jul 25 23:07:15 my-server prm(21937): system load (0) below check requirment; aborting.
    Jul 25 23:07:32 my-server prm(21977): system load (0) below check requirment; aborting.
    Jul 25 23:08:00 my-server prm(22012): system load (0) below check requirment; aborting.
    Jul 25 23:12:00 my-server prm(22461): system load (0) below check requirment; aborting.
    Jul 25 23:16:00 my-server prm(22601): system load (0) below check requirment; aborting.
    Jul 25 23:20:00 my-server prm(28876): system load (0) below check requirment; aborting.
    Jul 25 23:24:00 my-server prm(29509): system load (0) below check requirment; aborting.
    Jul 25 23:28:00 my-server prm(29655): system load (0) below check requirment; aborting.
    Jul 25 23:32:00 my-server prm(30114): system load (0) below check requirment; aborting.
    Jul 25 23:36:00 my-server prm(30242): system load (0) below check requirment; aborting.
    Jul 25 23:40:00 my-server prm(30434): system load (0) below check requirment; aborting.
    Jul 25 23:44:00 my-server prm(30847): system load (0) below check requirment; aborting.
    Jul 25 23:48:00 my-server prm(30991): system load (0) below check requirment; aborting.
    Jul 25 23:52:00 my-server prm(31432): system load (0) below check requirment; aborting.
    Jul 25 23:56:01 my-server prm(31560): system load (0) below check requirment; aborting.
    Jul 26 00:00:00 my-server prm(31700): system load (0) below check requirment; aborting.
    Jul 26 00:04:00 my-server prm(32172): system load (0) below check requirment; aborting.
    Jul 26 00:08:00 my-server prm(32305): system load (0) below check requirment; aborting.
    Jul 26 00:12:00 my-server prm(392): system load (0) below check requirment; aborting.
    Jul 26 00:16:00 my-server prm(529): system load (0) below check requirment; aborting.
    Jul 26 00:20:00 my-server prm(658): system load (0) below check requirment; aborting.
    Jul 26 00:24:00 my-server prm(1079): system load (0) below check requirment; aborting.
    Jul 26 00:28:01 my-server prm(1213): system load (0) below check requirment; aborting.
    Jul 26 00:32:00 my-server prm(1664): system load (0) below check requirment; aborting.
    Jul 26 00:36:01 my-server prm(1794): system load (0) below check requirment; aborting.
    Jul 26 00:40:00 my-server prm(1991): system load (0) below check requirment; aborting.
    Jul 26 00:44:00 my-server prm(2396): system load (0) below check requirment; aborting.
    Jul 26 00:48:00 my-server prm(2540): system load (0) below check requirment; aborting.
    Jul 26 00:52:00 my-server prm(2983): system load (0) below check requirment; aborting.

    This goes on and on for a bit

    my-server is the hostname, but not the real one of course.

    I also installed HotsaNIC before I installed prm, take a look at that here and you can see the load drop off:
    www.reanns.com/hotsanic
    Look at system/load

    Thanks for any advice in advance..

  2. #2
    Join Date
    Jul 2002
    Location
    Manchester, UK
    Posts
    774
    that process is some sort of low-level process to do with the XFS filesystem. It is not a vital process unless you are actually using the XFS filesystem on any of your disks.

  3. #3
    any reason why it was sucking up 98% of the cpu?

    Edit:
    How can I tell if I am using the xfs filesystem?

  4. #4
    Join Date
    Jul 2002
    Location
    Manchester, UK
    Posts
    774
    If you're not sure if you're using xfs, you won't be. It's a very specialised filesystem. To double check, just do "cat /etc/fstab", look down the 3rd column and see if any of them say "xfs".

    I have no idea why it would be using 98% of the CPU, but any program has bugs, it probably got into an infinite loop or something. It was probably a one-off.

  5. #5
    Seems I am not using xfs according to this table here:
    LABEL=/ / ext3 defaults,usrquota,grpquota 1 1
    LABEL=/boot /boot ext3 defaults 1 2
    none /dev/pts devpts gid=5,mode=620 0 0
    none /proc proc defaults 0 0
    none /dev/shm tmpfs defaults 0 0
    /dev/hda2 swap swap defaults 0 0
    /dev/fd0 /mnt/floppy auto noauto,owner,kudzu 0 0
    Edit: that table didnt really format the way it looked in ssh, but you get the picture..


    Thanks for all the help probonic.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •