[2 days left] What’s wrong with your cloud strategy? Learn why multicloud solutions matter with Nimble Storage.Register Now


RedHat Linux 9 - Trouble with AMD

Posted on 2004-10-25
Medium Priority
Last Modified: 2013-12-16
I have a cluster of Linux machines running RedHat 9 (2.4.20)
All machines have their amd service configured so as all machines can access the others disks.
My problem is that at times the amd process takes up >50% cpu on ALL machines!!!
Does anyone have a clue?
Question by:shayb022800
Welcome to Experts Exchange

Add your voice to the tech community where 5M+ people just like you are talking about what matters.

  • Help others & share knowledge
  • Earn cash & points
  • Learn & ask questions
  • 2
  • 2
LVL 38

Expert Comment

ID: 12404799

   amd is the automount daemon. As my experience, amd doesn't work well under multiple heavy data transfer through (/net).
So for the NFS server with frequenty data access, you better use hard mount (specify in /etc/fstab or mount in /etc/rc.d/rc.local ) so you can specify the mount option to tune the NFS performance.

   Cross NFS mounting is the CPU and network killer. Besides it is the trouble maker even though it is convenient by use of amd or autofs.

   Tuning NFS/amd/autofs is the job for Unix systems adminstrators..... ^_^

Good luck,


Author Comment

ID: 12407766
Hi Wesly,
Thanks for the reply. Althogh I personally am not a Unix Sys Admin, all you have said above is known to me. And yet, my Unix Sys Admins have trouble locating and solving the problem of AMD taking > 50% of the CPU.
If I am not mistaken once the mount is established (automatically) minimal resources are needed as long as the mount is active.
So again what could be the problem? what should I ask my Sys Admins to check/do?
LVL 38

Accepted Solution

wesly_chen earned 500 total points
ID: 12408094
Ok, amd will unmount the unactive mount point after it idles for 5 minutes (or 10 minutes ?).
Change the setting to make it short (say 2 or 3 miuntes) So it will release the CPU resources quickly.

My suggestion is that you shouldn't use amd.net (mount /net) and make a list of necessary nfs shared directory and hostname.
So it can cut short of un-necessary mount points. Also, use options "async", "soft", and "noatime" on nfs client.

I perfer autofs instead of amd. Besides, autofs4 support /net on Linux, too. I got rid of amd (I want to use /net) after I used

Good luck,


Author Comment

ID: 12408172
I will pass this info to our sys admins and let you know how it goes.

Featured Post


Modern healthcare requires a modern cloud. View this brief video to understand how the Concerto Cloud for Healthcare can help your organization.

Question has a verified solution.

If you are experiencing a similar issue, please ask a related question

Using 'screen' for session sharing, The Simple Edition Step 1: user starts session with command: screen Step 2: other user (logged in with same user account) connects with command: screen -x Done. Both users are connected to the same CLI sessio…
Linux users are sometimes dumbfounded by the severe lack of documentation on a topic. Sometimes, the documentation is copious, but other times, you end up with some obscure "it varies depending on your distribution" over and over when searching for …
Learn how to find files with the shell using the find and locate commands. Use locate to find a needle in a haystack.: With locate, check if the file still exists.: Use find to get the actual location of the file.:
Get a first impression of how PRTG looks and learn how it works.   This video is a short introduction to PRTG, as an initial overview or as a quick start for new PRTG users.
Suggested Courses
Course of the Month13 days, 16 hours left to enroll

656 members asked questions and received personalized solutions in the past 7 days.

Join the community of 500,000 technology professionals and ask your questions.

Join & Ask a Question