Distribution of time spent in major page faults script

[Frank Ch. Eigler]

William Cohen <wcohen@redhat.com> writes:

> [...]

So I understand correctly, these are essentially faults that need to
be paged in from program or data files on disk, right?  I'm working on
a script that deals with the opposite - pages being evicted by swapd.

If so, some of the number seem hard to believe:

>      32 |                                                     0
>      64 |                                                     1
>     128 |@@                                                  14
>     256 |@@@                                                 18
>     512 |@@@@@@@                                             38
>    1024 |@@@@@@@@@@                                          52
> [...]

I don't know if a disk can possibly read a page in less than a
millisecond or few.  The other peaks around 4096-16384 seem plausible.


- FChE