FAQ
I have a DRBL server, basically an nfs fileserver, which I am
rebuilding. I want to put the high i/o directories on a separate raid
array for performance. Currently everything is under / in one raid
array.

How can I tell which directories, obviously other than /home, are
getting high reads and/or writes? Any tools to measure i/o per
directory?

Thanks

--
Robert Arkiletian
Eric Hamber Secondary, Vancouver, Canada

Search Discussions

  • Joseph L. Casale at Aug 22, 2011 at 6:48 am

    I have a DRBL server, basically an nfs fileserver, which I am rebuilding. I want to
    put the high i/o directories on a separate raid array for performance. Currently
    everything is under / in one raid array.

    How can I tell which directories, obviously other than /home, are getting high
    reads and/or writes? Any tools to measure i/o per directory?
    Well there certainly might be better ways, but if iotop for example indicates a
    process is producing high file IO, lsof -p <pid> will show which file.

    Hth,
    jlc
  • Lisandro Grullon at Aug 22, 2011 at 7:36 am
    Dear List,
    I have been getting system crash, syslog is reporting the following in stdout...please advise.

    Message from syslogd at saturn at Aug 21 03:38:08 ...
    kernel: Northbridge Error, node 0

    Message from syslogd at saturn at Aug 21 03:38:08 ...
    kernel:ECC/ChipKill ECC error.

    Message from syslogd at saturn at Aug 21 15:23:47 ...
    kernel: Northbridge Error, node 0

    Message from syslogd at saturn at Aug 21 15:23:47 ...
    kernel:ECC/ChipKill ECC error.

    CentOS mailing list
    CentOS at centos.org
    http://lists.centos.org/mailman/listinfo/centos
    -------------- next part --------------
    An HTML attachment was scrubbed...
    URL: http://lists.centos.org/pipermail/centos/attachments/20110822/5d833946/attachment.html
  • Peter Kjellström at Aug 22, 2011 at 9:36 am

    On Monday, August 22, 2011 01:36:11 PM Lisandro Grullon wrote:
    Dear List,
    I have been getting system crash, syslog is reporting the following in
    stdout...please advise.
    Sure, please don't use "reply" when starting a new thread.
    Message from syslogd at saturn at Aug 21 03:38:08 ...
    kernel: Northbridge Error, node 0
    As for this, most likely one or several bad DIMMs (or possibly bad MB).

    /Peter
    Message from syslogd at saturn at Aug 21 03:38:08 ...
    kernel:ECC/ChipKill ECC error.

    Message from syslogd at saturn at Aug 21 15:23:47 ...
    kernel: Northbridge Error, node 0

    Message from syslogd at saturn at Aug 21 15:23:47 ...
    kernel:ECC/ChipKill ECC error.
    -------------- next part --------------
    A non-text attachment was scrubbed...
    Name: not available
    Type: application/pgp-signature
    Size: 198 bytes
    Desc: This is a digitally signed message part.
    Url : http://lists.centos.org/pipermail/centos/attachments/20110822/0281adbb/attachment.bin
  • Lisandro Grullon at Aug 22, 2011 at 9:43 am
    Thank you peter for the input...I don't think its the motherboard as I
    have 5 of these boxes and they all experiencing the same problem
    (running the latest bios). I tried switching the RAM around and did
    manual timing at 667 in the BIOS, hope this fixes the problem. Kingston
    won't be too happy if I tell them that there memory is not working in my
    systems specially when we talking about 512GB of memory. Let's see what
    happens, I will report back as I monitor this situation.
    Peter Kjellstr?m<cap at nsc.liu.se> 8/22/2011 9:36 AM >>>
    On Monday, August 22, 2011 01:36:11 PM Lisandro Grullon wrote:
    Dear List,
    I have been getting system crash, syslog is reporting the following in
    stdout...please advise.
    Sure, please don't use "reply" when starting a new thread.
    Message from syslogd at saturn at Aug 21 03:38:08 ...
    kernel: Northbridge Error, node 0
    As for this, most likely one or several bad DIMMs (or possibly bad
    MB).

    /Peter
    Message from syslogd at saturn at Aug 21 03:38:08 ...
    kernel:ECC/ChipKill ECC error.

    Message from syslogd at saturn at Aug 21 15:23:47 ...
    kernel: Northbridge Error, node 0

    Message from syslogd at saturn at Aug 21 15:23:47 ...
    kernel:ECC/ChipKill ECC error.
    -------------- next part --------------
    An HTML attachment was scrubbed...
    URL: http://lists.centos.org/pipermail/centos/attachments/20110822/9fc3871f/attachment.html

Related Discussions

Discussion Navigation
viewthread | post
Discussion Overview
groupcentos @
categoriescentos
postedAug 20, '11 at 1:47p
activeAug 22, '11 at 9:43a
posts5
users4
websitecentos.org
irc#centos

People

Translate

site design / logo © 2022 Grokbase