Re: [PATCH RT-TESTS] cyclictest: histogram overflow instance tracking

[John Kacur <jkacur@redhat.com>]

----- Original Message -----
> Hello Frank,
> 
> I apologize I didn't have a chance to review your proposed
> modifications to my patch.
> 
> I had looked at your proposal to introduce a '-g' option (for lack of
> a better letter) instead of piggy-backing on the '-h' option, and I
> completely agree with that approach.
> 
> It would be very handy to specify, for example, '-h 50 -g 1000' to
> capture and print the 1000 outliers beyond 50 us to get a good sense
> of any patterns hidden in the outliers.
> 
> If John has already accepted my proposed patches, do you want to
> propose your changes on top of that as a separate patch now?

Please pull the git tree, have a look at what I put in, and then think about
Frank's suggestions. Make sure you are "proactive" - (oh God, thinking about 
a Simpson's episode now), and see what you can do with it, instead of just
waiting for Frank to tell you his opinions.

Thanks!

> 
> Thanks for your review, and your excellent suggestion to make this
> feature even more useful.
> 
> --
> Bhavesh Davda
> 
> ----- Original Message -----
> > From: "Frank Rowand" <frank.rowand@am.sony.com>
> > To: "Bhavesh Davda" <bhavesh@vmware.com>, "John Kacur"
> > <jkacur@redhat.com>
> > Cc: linux-rt-users@vger.kernel.org
> > Sent: Tuesday, November 13, 2012 3:41:20 PM
> > Subject: Re: [PATCH RT-TESTS] cyclictest: histogram overflow
> > instance tracking
> > 
> > On 10/25/12 14:36, Frank Rowand wrote:
> > > On 10/16/12 10:02, Bhavesh Davda wrote:
> > >> From: Bhavesh Davda <bhavesh@vmware.com>
> > >>
> > >> Add feature to cyclictest histogram mode to track cycle counts
> > >> every time a
> > >> sample overflows the histogram limit. This should help identify
> > >> if
> > >> there is a
> > >> timing pattern to jitters in cyclictest runs.
> > >>
> > >> Example output (with -h 10):
> > >>  ...
> > >>  Histogram Overflows: 00001 00007 00000 00009 00004 00007 00000
> > >>  00001
> > >>  Histogram Overflow at cycle number:
> > >>  Thread 0: 09964
> > >>  Thread 1: 00000 00004 00006 00008 00010 09962 11594
> > >>  Thread 2:
> > >>  Thread 3: 01169 04698 06782 09033 10299 11561 21517 28734 29532
> > >>  Thread 4: 11574 11580 11583 11586
> > >>  Thread 5: 00020 09448 13954 14954 18954 20587 24973
> > >>  Thread 6:
> > >>  Thread 7: 18950
> > >>  ...
> > >>
> > >> Signed-off-by: Bhavesh Davda <bhavesh@vmware.com>
> > > 
> > > My comments up to "--" are not meant to be part of the header of
> > > the
> > > following patch.
> > > 
> > > I am including the following patch as my review of the patch I am
> > > replying to.  If the following patch is incorporated into the
> > > reviewed patch, then you can add my:
> > > 
> > >   Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
> > >   Tested-by: Frank Rowand <frank.rowand@am.sony.com>
> > > 
> > > to the combined patch.
> > 
> > < snip >
> > 
> > Bhavesh,
> > 
> > I never saw I reply to my suggestions.  Unfortunately John took my
> > reviewed-by for your white space patch and applied it to your
> > "cyclictest: histogram overflow instance tracking" patch, without
> > my suggestions, and released it in v0.85 rt-tests.
> > 
> > So...., any thoughts about the suggestions in the email that
> > this one is responding to?  And also any thoughts about my
> > second email in the series (I'll forward that one again to
> > you).
> > 
> > -Frank
> > 
> > 
>