Date: Tue, 27 Dec 2011 17:27:57 +0100 From: Marius Strobl <marius@alchemy.franken.de> To: Doug Barton <dougb@FreeBSD.org> Cc: svn-src-head@FreeBSD.org, svn-src-all@FreeBSD.org, src-committers@FreeBSD.org Subject: Re: svn commit: r228857 - in head/usr.bin: . csup Message-ID: <20111227162757.GW90831@alchemy.franken.de> In-Reply-To: <4EF8DC5B.9070404@FreeBSD.org> References: <201112241216.pBOCGd1H012696@svn.freebsd.org> <4EF645D2.8080407@FreeBSD.org> <20111226102820.GT90831@alchemy.franken.de> <4EF8DC5B.9070404@FreeBSD.org>
index | next in thread | previous in thread | raw e-mail
On Mon, Dec 26, 2011 at 12:43:07PM -0800, Doug Barton wrote:
> On 12/26/2011 02:28, Marius Strobl wrote:
> > On Sat, Dec 24, 2011 at 01:36:18PM -0800, Doug Barton wrote:
> >> On 12/24/2011 04:16, Marius Strobl wrote:
> >>> On FreeBSD just use the MD5 implementation of libmd rather than that of
> >>> libcrypto so we don't need to relinquish csup when world is built without
> >>> OpenSSL.
> >>
> >> Did you benchmark this at all? I agree that keeping csup available
> >> absent openssl is a good goal, but csup is a prototypical "tool that
> >> does the same thing many thousands of times" so even tiny regressions
> >> could add up to a large cost in wall clock time.
> >
> > Well, in a real world test updating the same base on an amd64 machine
> > connected to the Internet
>
> Adding a network connection to the test is almost certainly going to
> obscure the results beyond utility. The appropriate way to test this
> would be to create a binary out of the md5 routine in csup, and link it
> alternately with libcrypto and libmd. Then for each version run it
> against the src tree (or ports, either way) 10 times. Discard the first
> and last, and then plot the results with ministat.
marius@flak:/home/marius > ministat -w 76 libmd libcrypto
x libmd
+ libcrypto
+----------------------------------------------------------------------------+
| + |
| + |
|x x + |
|xxx ++ |
|xxx ++ +|
||A| |A_| |
+----------------------------------------------------------------------------+
N Min Max Median Avg Stddev
x 8 244.08 246.16 245.18 245.01375 0.78758106
+ 8 302.36 307.12 302.92 303.26875 1.5784028
Difference at 95.0% confidence
58.255 +/- 1.33776
23.7762% +/- 0.545992%
(Student's t, pooled s = 1.24732)
Looks like the MD5 implementation of libcrypto is the counterpart of
SCHED_ULE and only pays out on real big stuff. At least this result
is consistent with the real world test of csup.
Marius
home |
help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20111227162757.GW90831>