Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 11 Mar 1998 18:30:10 -0800
From:      "Jordan K. Hubbard" <jkh@FreeBSD.ORG>
To:        Amancio Hasty <hasty@rah.star-gate.com>
Cc:        jkh@FreeBSD.ORG, current@FreeBSD.ORG
Subject:   Re: my worldstone 
Message-ID:  <1834.889669810@time.cdrom.com>
In-Reply-To: Your message of "Wed, 11 Mar 1998 17:47:33 PST." <199803120147.RAA01017@rah.star-gate.com> 

next in thread | previous in thread | raw e-mail | index | archive | help
> Honest, I have no use for profiled libraries they really should
> not be built by default -- thats akeen to asking to build your
> libraries with -g -- perhaps we should add that as default .

I know, but the real problem here is that people are still comparing
this "worldstone" figure in the same way they'd compare dhrystones or
xstones or whatever and ultimately people are going to be making
hardware decisions based on those numbers.  It's no use saying now
foolish such a practice is, it's simply inevitable - *people like
numbers*. :-)

So, if we're going to be tossing around numbers in a highly
comparative fashion (and say what you like but any posting that says
"2 hours?  Huh.  I get 1hr 10 minutes!" is attempting to compare
numbers) we need to level the playing field since the last thing
anybody needs is to go chasing after that extra illusive half-hour
only to be told later that the half hour speedup had nothing to do
with the hardware, it had to do with a smaller build set. :-)

Whether the profiled libraries are useful or not is almost irrelevant;
statistics compare numbers, not usefulness. ;-)

So, in the spirit of getting specific, I'd like to suggest the
following set of prototype ground rules to anyone daring to post their
"worldstone rating" here:

Before beginning a make world test, the following conditions must be
met:

1. /usr/obj must be empty (no "clean" pass to add minutes to time).

2. /usr/obj *must* be mounted async (too few mount it sync and it does
   bestow a large advantage).

3. /usr/src must reside on a physically different disk (unless ccd
   is in use, in which case this should be noted).  I know that's hard
   for some folks, but if you're running off a single drive then your
   numbers just won't be competetive.

4. -pipe must be added to CFLAGS in /etc/make.conf.  *no other build
   optimizations or omissions can be done!*  Same goes for additions -
   no kerberos bits enabled.

5. Source tree must be -current to within 7 days of the other people
   comparing numbers.  No point in compiling old bits just before
   perl5 entered the tree, or whatever, since that obviously skews the
   numbers.

And in posting your worldstone rating:

1. List number of CPUs, memory configuration and motherboard.

2. List types of drives involved in holding /usr/src and /usr/obj for
   this test.

3. List type of disk controller used.

Anything on this list I'm forgetting?

					Jordan

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1834.889669810>