On Wed, 19 Sep 2007, Casper.Dik at Sun.COM wrote:
>
>> Casper.Dik at Sun.COM wrote:
>>>> Optimizing bunzip is not worth the time/effort IMHO. Because it's a
>>>> CPU resource hog and only provides a couple of percentage points
>>>> reduction in the compressed file size compared to gzip. By far a
>>>> better solution is to ship .gz install files.
>>>
>>> +1 I've measured it and it's somewhere between 5-8%.
>> [snip]
>>
>> Are you talking about 5-8% performance improvement by bumping the
>> compiler optimizer to a higher level ? If "yes" - would you sponsor a
>> small patch for this ?
>
>
> No, I've measured the difference between gzip and bzip2 compressed
> "wos" archives. (Just checked again and it seems to be 7.5 percent so
> my memory was correct)
Was that with gzip -9 (aka --best)?
Is the source available for pkgadd, pfinstall etc?
> To bzcat vs zcat all files costs the following amount of time:
>
> (zcat is limited in I/O and was run concurrently with bzcat on a 2 CPU
> 2.2MHz Opteron system)
> time zcat .... > /dev/null
> 77.91u 3.97s 1:58.24 69.2%
>
>
> time bzcat ... > /dev/null
> 723.85u 7.13s 12:59.07 93.8%
>
> We're talking nearly a factor 10 of CPU time on a relatively fast system.
>
Yep.
Al Hopper Logical Approach Inc, Plano, TX. al at logical-approach.com
Voice: 972.379.2133 Fax: 972.379.2134 Timezone: US CDT
OpenSolaris Governing Board (OGB) Member - Apr 2005 to Mar 2007
http://www.opensolaris.org/os/community/ogb/ogb_2005-2007/
