Re: [LAU] Valgrind

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: <linux-audio-user@...>
Date: Friday, November 5, 2010 - 3:54 pm

--nextPart12278281.ZGqMtOXxko
Content-Type: Text/Plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

On Friday 05 November 2010 13:53:56 Darrin Thompson wrote:

I did manage to run jackd (with the firewire backend) inside valgrind --
tool=3Dcallgrind. Its not suitable to get any audio output but it gives som=
e=20
numbers and showed me the main processing time is spent in the locks for=20
phase-locked-loop of the streaming-clock... Might be biased because the=20
streaming clocks of pc and device where running completely different becaus=
e of=20
the valgrind overhead. But experiments without valgrind and without the loc=
ks=20
gave reason that really a lot of time is spent waiting there. Unfortunately=
=20
the locks are needed as it will crash without them...

But its possible and does give some numbers and hints. The overhead of the=
=20
memcheck tool is lower then the overhead of callgrind btw.

Have fun,

Arnold

--nextPart12278281.ZGqMtOXxko
Content-Type: application/pgp-signature; name=signature.asc
Content-Description: This is a digitally signed message part.

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)

iEYEABECAAYFAkzUKKIACgkQuYLL1cDjHx28oQCfU6DMNywiazMVz5wuHavR7gu8
gz8An0lsZhzV6Lc34nlmGLfhNLxWMySl
=/wi9
-----END PGP SIGNATURE-----

--nextPart12278281.ZGqMtOXxko--

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[LAU] Valgrind, Darrin Thompson, (Fri Nov 5, 12:54 pm)
Re: [LAU] Valgrind, Olivier Guilyardi, (Fri Nov 5, 4:46 pm)
Re: [LAU] Valgrind, Arnold Krille, (Fri Nov 5, 3:54 pm)
Re: [LAU] Valgrind, Robin Gareus, (Fri Nov 5, 12:59 pm)