Unix & Linux Stack Exchange is a question and answer site for users of Linux, FreeBSD and other Un*x-like operating systems. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I usually use Nethogs to see the network bandwidth per process. However, Nethogs won't see the PID of the processes generating some NFS traffic, and as a result they are aggregated over one single line with ? as PID:

enter image description here

Why does that happen and is there any way to circumvent it so that I can see NFS bandwith per PID?

I use NFSv3 on Ubuntu 12.04 (client).

share|improve this question
up vote 5 down vote accepted

NFS is a file system, as per its name. User processes that open/read/seek/write/close files on an NFS-mounted directory don't know that it's an NFS file system because the kernel makes NFS look like any other file system.

So, a user process that reads an NFS-mounted file will generate a read(2) system call that ends up causing some kernel code to run. All NFS traffic will come from the Linux/Unix kernel itself, not from a user-level process. Hence the "?" as a PID.

share|improve this answer
    
Very interesting, thanks! – Franck Dernoncourt Jul 10 '14 at 18:00

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.