@Guy,
Basically, I was adding my own header (instead of radiotap) in kernel and processing it in userland with my own code. Basically I wrote my own pcap for that.
Since, I did not get the performance, Now I have added extra fields in radiotap.
But I still see high CPU usage.
Its interesting that you point out there are more errors during mmap calls.
Is this anything to do with allignment of frames ? [I am having 37 byte radiotap header, which is not very good number I suppose]
Shall I see how the frame is added so that these errors don't occur.
@Dave : I am running this code on a Netgear router running OpenWrt, so I am not sure if there is profiler that can help me out.
You have raised a valid point, but is there any better tool to use/write for this ?
I want to know if this processor usage will effect the router performance ?
Or is it fine if the processor takes 40% or more for proper functioning of router ?
its clocked at 600 Mhz, so I suppose its a beefy hardware ...
-Abhinav
On Mon, Nov 12, 2012 at 9:01 AM, David Laight
<David.Laight@xxxxxxxxxx> wrote:
> hi,
> I just checked the two mechanism :
> (1) Using mmap to fetch packets from kernel to userspace
> (2) Using recvfrom() call to fetch packets
>
> I see top reports
> (1) 34% memory 20% cpu usage
> (2) 21% memory 7% cpu usage !
It is worth remembering that the cpu usage reported by top isn't
worth the paper it is printed on for many workloads.
IIRC it is based on the cpu state when the timer interrupt fires.
processes that are scheduled very often, and run for short periods
tend to get mis-counted.
Since the Linux scheduler doesn't get a high-res timestamp everytime
it does a process switch, about the only way to measure idle time
is to put a very low priority process into a counting loop.
Unfortunately the scheduler might make it difficult to make the
processes priority low enough.
David