Re: [gentoo-user] Gentoo speed comparison to other distros

[Mark David Dumlao]

On 03/14/2013 09:28 PM, Alan McKinnon wrote:
> On 14/03/2013 14:12, Pandu Poluan wrote:
>> On Mar 14, 2013 4:14 PM, "William Kenworthy" <billk@×××××××××.au
>> <mailto:billk@×××××××××.au>> wrote:
>>> Did this few years back for an online magazine sponsored by a local
>>> linux sysadmin company who wanted to see the difference between generic
>>> debian and optimised (not necessarily gentoo, but thats what I used.)
>>>
>>> Difference in times was ~10% across the board for graphics manipulations
>>> (gimp scripts), spreadsheet tasks (gnumeric) and the like.
>>>
>>> The "kicker" - simple optimisations gained far, far more than generic
>>> compiler settings.  e.g., initially, the gnumeric versions were slightly
>>> different, with some wild times across the tasks.  Make em the same
>>> version (and cuedos to the gnumeric maintainer for jumping in and
>>> helping diagnose/fix the problem - newer version on gentoo was heaps
>>> slower :) and there was little difference.
>>>
>>> Shared libs like glibc didnt make a huge difference, but being smart
>>> about how/what a "particular" task was handled gained more.  If a debian
>>> app was compiled with similar options as to gentoo, little difference
>>> between them in performance which considering shared libs etc wasn't
>>> what I expected.
>>>
>>> The intel compilers are/were said to be a lot better than gcc, not sure
>>> if the gap is still there (supposedly 20% better again)
>>>
>>> Its how long is a piece of string kind of question if considered OS
>>> wide, but pick a narrow task and optimise away with smart programmers
>>> and you will do well on almost anything.
>>>
>>> Big advantage of gentoo - configurability, version control (what version
>>> is installed and changing it at short notice) and general flexibility.
>>>
>> This.
>>
>> Why I prefer Gentoo over other distros: Full control.
>>
>> I mean, I can (and do) leverage "-march=native". And I certainly have an
>> overly long USE flags... but it's the sheet satisfaction of knowing that
>> my system is MY system that made me stick with Gentoo...
>>
>> It's eminently satisfying -- a geekgasm, if you will -- to know that
>> one's kernel is lean and customized, all the toolchains have been tuned,
>> and there are no useless things being installed...
>>
>> In regards to performance, the benefits might not be groundbreaking, but
>> it's there, and when your server is being relentlessly hammered by
>> requests, Gentoo seems to have additional breathing space where other
>> distros choke...
>
> Gentoo excels as a -dev system where your devs need to test things in
> different environments.
>
> A classic case is different pythons. We have many Centos 4 machines in
> production that run python-2.4, the developers naturally run something
> bleeding edge like 2.7 or 3.3 on their laptops.
>
> Many many times they need to know if their bespoke code runs properly on
> Centos, or PyPy or whatever other valid environment difference could
> happen in the real world.
>
> Tweak USE, tweak the masking and let emerge world do it's thing. Now the
> dev can do valid tests. If the dev machines are VMs, snapshot them just
> before starting this and you have the best possible solution for my money.
>
> Or, try remove LDAP, NIS and PAM support for auth from a RHEL machine to
> test if it works without those things in place.
> RHEL? Impossible.
> Gentoo? Trivially easy.
"Trivially easy", of course, means an emerge -euDNtv world && emerge
-ctv && revdep-rebuild -i && revdep-rebuild ... ehehehe

I dunno, it might actually be easier to setup the said distros in a VM.
And if those configurations don't work, you shouldn't have to support
them, eh? ;)