Date: Sun, 19 Aug 2007 10:39:22 +0200 From: Pawel Jakub Dawidek <pjd@FreeBSD.org> To: freebsd-arch@FreeBSD.org Subject: Re: Lockless uidinfo. Message-ID: <20070819083922.GC11792@garage.freebsd.pl> In-Reply-To: <20070818230917.GI6498@garage.freebsd.pl> References: <20070818120056.GA6498@garage.freebsd.pl> <20070818220756.GH6498@garage.freebsd.pl> <20070818230917.GI6498@garage.freebsd.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
--s9fJI615cBHmzTOP
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable
On Sun, Aug 19, 2007 at 01:09:17AM +0200, Pawel Jakub Dawidek wrote:
> Ok, after implementing atomic_fetchadd_long() on amd64, we get additional
> 6% of performance improvement:
>=20
> x ./uidinfo_lockfree.txt (atomic_cmpset_long loop)
> + ./uidinfo_waitfree.txt (atomic_fetchadd_long)
> +------------------------------------------------------------------------=
------+
> | =
+|
> | =
+|
> |x xx xx =
+ ++|
> | |__MA___| =
|AM|
> +------------------------------------------------------------------------=
------+
> N Min Max Median Avg Stdd=
ev
> x 5 1561566 1575987 1568964 1569767 5853.13=
99
> + 5 1662362 1665936 1665810 1664881.8 1541.26=
93
> Difference at 95.0% confidence
> 95114.8 +/- 6241.96
> 6.05917% +/- 0.397636%
> (Student's t, pooled s =3D 4279.88)
One more thing - comparsion between waitfree method and when chgsbsize()
is a no-op:
x ./uidinfo_waitfree.txt (atomic_fetchadd_long)
+ ./uidinfo_none.txt (no chgsbsize)
+--------------------------------------------------------------------------=
----+
|x xx + + + + =
+|
| |AM| |_______M_A________| =
|
+--------------------------------------------------------------------------=
----+
N Min Max Median Avg Stddev
x 5 1662362 1665936 1665810 1664881.8 1541.2693
+ 5 1718287 1744448 1726343 1728176.6 10271.936
Difference at 95.0% confidence
63294.8 +/- 10711.8
3.80176% +/- 0.643395%
(Student's t, pooled s =3D 7344.66)
This small speed up is of course because of atomics in waitfree case, but it
shows that we can't do much better than waitfree version, as ideal case is =
only
3.8% faster, at least for this benchmark.
This was for eight processes and this is for one:
x ./uidinfo_up_waitfree.txt (atomic_fetchadd_long)
+ ./uidinfo_up_none.txt (no chgsbsize)
+--------------------------------------------------------------------------=
----+
|x x x x x + +=
+++|
| |______________M_____A_____________________| |_=
AM_||
+--------------------------------------------------------------------------=
----+
N Min Max Median Avg Stddev
x 5 419799 431017 422877 424180.2 4265.4168
+ 5 433705 434955 434696 434509.6 519.68
Difference at 95.0% confidence
10329.4 +/- 4431.34
2.43514% +/- 1.04468%
(Student's t, pooled s =3D 3038.41)
This means that something else slows that eight processes case a bit, but i=
t's
not uidinfo.
Ok, I need to stop, I need to stop right now!
--=20
Pawel Jakub Dawidek http://www.wheel.pl
pjd@FreeBSD.org http://www.FreeBSD.org
FreeBSD committer Am I Evil? Yes, I Am!
--s9fJI615cBHmzTOP
Content-Type: application/pgp-signature
Content-Disposition: inline
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.4 (FreeBSD)
iD8DBQFGyAG6ForvXbEpPzQRApYVAJ4oNRlFeOzCQHM6N1WtncBklkaQywCggSaK
Afv4wV9jNZHRESumApJeqNg=
=0DHg
-----END PGP SIGNATURE-----
--s9fJI615cBHmzTOP--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20070819083922.GC11792>