pbzip2 isn't faster

[Eric A. Borisch]

On Fri, Apr 4, 2014 at 9:13 AM, René J.V. <rjvbertin at gmail.com> wrote:

>  On Friday April 04 2014 08:35:19 Eric A. Borisch wrote:
>
>
>
> > Here's an example with a locally compiled (and therefore run through
> pbzip2
>
> > as that is how I have MP set) MacPorts archive.
>
>
>
> Hmmm, how have you configured things?
>

I have a (manually installed, linked against system libs) pbzip2 in
/usr/local/bin/pbzip2. I configure macports (on install) with './configure
BZIP2=/usr/local/bin/pbzip2'


> > real 0m12.084s
>
> > user 0m45.713s
>
> > sys 0m0.534s
>
>
>
> > real 0m37.223s
>
> > user 0m36.872s
>
> > sys 0m0.343s
>
>
>
> > Note the user time is up (no free lunch; there is some overhead) but real
>
> > or "wall" time is down by a factor of 3. (I have a 4 core 2007 machine.)
>
>
>
> Depends on how it's measured; it could also reflect the number of CPUs
> used (i.e. correspond to the CPU%, 300% if you're indeed using 3 cores with
> complete efficiency) :)
>
>  R
>

I failed to include the fact for you that the CPUs were pegged. Granted, I
have some background tasks, but pbzip2 was 380%+ in activity monitor. It
doesn't scale completely linearly -- as you can see on pbzip2's web page --
but 3x is nothing to shake a stick at.

 - Eric
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.macosforge.org/pipermail/macports-users/attachments/20140404/d411252e/attachment.html>