This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: Distribution of time spent in major page faults script
- From: fche at redhat dot com (Frank Ch. Eigler)
- To: William Cohen <wcohen at redhat dot com>
- Cc: systemTAP <systemtap at sources dot redhat dot com>
- Date: 02 May 2007 14:36:23 -0400
- Subject: Re: Distribution of time spent in major page faults script
- References: <463894DE.4060401@redhat.com>
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