From phk at phk.freebsd.dk  Tue Oct 13 10:06:36 2026
From: phk at phk.freebsd.dk (Poul-Henning Kamp)
Date: Tue, 13 Oct 2026 10:06:36 +0000
Subject: GCOV take 2 preview
Message-ID: <6ace02ac.28cee.63794a9d@critter.freebsd.dk>

I gave up fixing our current code-coverage setup:  Too much have
shifted under our feet since that was written.

Instead I started over with LLVM's coverage support, and I now
have the first preliminary output:

	https://phk.freebsd.dk/misc/gcov2/

The Vtest2 and Vmod numbers look suspiciously low, but dont panic
that, until I have had a chance to make sure everything is counted.

LLVM's coverage support counts differently than GCC's coverage
support, so the numbers have shifted and changed in and between
files, but I trust both to basically get it right - just differently.

Sparklines are still TBD.  When I see what the jump looks like,
I may decide to restart the sparkline history.

The bad news is that I need LLVM patches to run this.

Somebody hacked "continuous coverage" into LLVM, which is just
a strange way to say the counters are mmap(2)'ed so they also
saved when processes die in interesting ways.

That is only supported on Apple, because it depends on a
a weird linker option only they have, and to be honest,
because whoever did it, didn't give shit about anybody else.

I managed to come up with a small, and circumstances considered,
quite elegant patch for FreeBSD[1], but I have no idea if that
will ever be upstreamed to FreeBSD, much less LLVM.

So to run the "new" gcov, I need a jail or VM with a patched
FreeBSD source tree, which is a bit of a bother.

Poul-Henning

[1] See:

https://lists.freebsd.org/archives/freebsd-current/2026-October/010937.html

The patch almost certainly also works in Linux, but it may be necessary
to get rid of a lot of Linux specific code in that area first.

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.

From phk at phk.freebsd.dk  Wed Oct 14 09:16:58 2026
From: phk at phk.freebsd.dk (Poul-Henning Kamp)
Date: Wed, 14 Oct 2026 09:16:58 +0000
Subject: GCOV take 2 preview
Message-ID: <6acf488a.28cad.4b728ce6@critter.freebsd.dk>

Poul-Henning Kamp writes:

> I gave up fixing our current code-coverage setup:  Too much have
> shifted under our feet since that was written.
>
> Instead I started over with LLVM's coverage support, and I now
> have the first preliminary output:
>
> 	https://phk.freebsd.dk/misc/gcov2/

Now also with:

* sparklines
* all executables counted

Still missing:

* Coverage without root-privs (ie: no jailing)
* Whatever else is still missing
* Distill the history file (currently 450MB+)

-- 
Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe    
Never attribute to malice what can adequately be explained by incompetence.