Phoronix Test Suite

classic Classic list List threaded Threaded
30 messages Options
12
Reply | Threaded
Open this post in threaded view
|

Phoronix Test Suite

Ektor Wetterström
I know http://bulk.fefe.de/scalability/ is wrong / outdated /
non-scientific / whatever... But what about this? Phoronix has more
credibility imho...

http://www.phoronix.com/scan.php?page=article&item=linux_bsd_opensolaris&num=1

Best Regards,
Ektor

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Tomas Bodzar-4
I'm missing info about how much and where is real crypto and security
techniques used in those systems. Oh wait....it's Phoronix. Now it's
clear. "I have better toy then you" benchmark type :-)

On Wed, Jun 23, 2010 at 12:36 PM, Ektor WetterstrC6m <[hidden email]>
wrote:
> I know http://bulk.fefe.de/scalability/ is wrong / outdated /
> non-scientific / whatever... But what about this? Phoronix has more
> credibility imho...
>
>
http://www.phoronix.com/scan.php?page=article&item=linux_bsd_opensolaris&num=
1
>
> Best Regards,
> Ektor
>
>



--
bIf youbre good at something, never do it for free.bB bThe Joker

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Siju George
In reply to this post by Ektor Wetterström
On Wed, Jun 23, 2010 at 4:06 PM, Ektor Wetterstrvm <[hidden email]> wrote:
> I know http://bulk.fefe.de/scalability/ is wrong / outdated /
> non-scientific / whatever... But what about this? Phoronix has more
> credibility imho...
>
>
http://www.phoronix.com/scan.php?page=article&item=linux_bsd_opensolaris&num=
1
>

So those who want to run those zip/unzip etc etc programs with that
margin of advantage should use freebsd ot fedora.

I just wonder how this guy can bench mark for such trivial stuff and
put it on the *BIG* website!!

I would like to see what happens when a complex filtering situation
comes up and how linux iptables tackles it and how pf in freebsd
tackels it and what is the perfomance there :-)

--Siju

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Nick Holland
In reply to this post by Ektor Wetterström
On 06/23/10 06:36, Ektor Wetterstrvm wrote:
> I know http://bullshit.fefe.de/ is wrong / outdated /
> non-scientific / whatever... But what about this? Phoronix has more
> credibility imho...
>
> [benchmarks]

facinating number of posts like this recently, all from gmail users
we've never seen before...

What I want to see is a comparison of critical bug and security
problems, or percentage of subsystems that Just Work, or man page
accuracy.  (or maybe packet filtering rates)

Nick.

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

E.T-3
In reply to this post by Ektor Wetterström
Hi

Very good performance putty :)

On Wed, 23 Jun 2010 12:36:38 +0200, Ektor WetterstrC6m <[hidden email]>
wrote:
> I know http://bulk.fefe.de/scalability/ is wrong / outdated /
> non-scientific / whatever... But what about this? Phoronix has more
> credibility imho...
>
>
http://www.phoronix.com/scan.php?page=article&item=linux_bsd_opensolaris&num=1
>
> Best Regards,
> Ektor

--
@plus

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Tomas Bodzar-4
In reply to this post by Nick Holland
On Wed, Jun 23, 2010 at 1:01 PM, Nick Holland
<[hidden email]> wrote:
> On 06/23/10 06:36, Ektor Wetterstrvm wrote:
>> I know http://bullshit.fefe.de/ is wrong / outdated /
>> non-scientific / whatever... But what about this? Phoronix has more
>> credibility imho...
>>
>> [benchmarks]
>
> facinating number of posts like this recently, all from gmail users
> we've never seen before...

I think that it shows some level of disillusion with those systems so
people are moving to another. Eg. there was a lot of people during
last weeks which tried OpenBSD on SPARC platform and eg. OpenSolaris
forum is mostly death when comparing with activity during last year
and so on.

>
> What I want to see is a comparison of critical bug and security
> problems, or percentage of subsystems that Just Work, or man page
> accuracy. B (or maybe packet filtering rates)

They care about users and not about quality or number of bugs. It's
still that same philosophy that bugs are normal and people are content
about it so why to care.

>
> Nick.
>
>



--
bIf youbre good at something, never do it for free.bB bThe Joker

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Joachim Schipper-2
In reply to this post by Ektor Wetterström
On Wed, Jun 23, 2010 at 12:36:38PM +0200, Ektor Wetterstrvm wrote:
> I know http://bulk.fefe.de/scalability/ is wrong / outdated /
> non-scientific / whatever... But what about this? Phoronix has more
> credibility imho...
>
> http://www.phoronix.com/scan.php?page=article&item=linux_bsd_opensolaris&num=1

Rather uncritical, really. Their PostMark benchmark gives a 386x
performance advantage (Fedora 12/OpenBSD) and they don't think to
investigate what is happening there (ext4 is apparently good at these
tests)? A similar thing comes up in the Sudokut benchmark - Fedora takes
nearly five times as long as Debian?  Really?

                Joachim

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Ektor Wetterström
In reply to this post by Nick Holland
On Wed, Jun 23, 2010 at 1:01 PM, Nick Holland
<[hidden email]> wrote:

> On 06/23/10 06:36, Ektor Wetterstrvm wrote:
>> I know http://bullshit.fefe.de/ is wrong / outdated /
>> non-scientific / whatever... But what about this? Phoronix has more
>> credibility imho...
>>
>> [benchmarks]
>
> facinating number of posts like this recently, all from gmail users
> we've never seen before...
>
> What I want to see is a comparison of critical bug and security
> problems, or percentage of subsystems that Just Work, or man page
> accuracy.  (or maybe packet filtering rates)

I agree, but you should admit that OpenBSD is clearly a looser in
regard to "pure performances" (e.g. I/O, compression, encryption,
etc.)

> Nick.

Bye,
Ektor

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Kevin Chadwick-2
> I agree, but you should admit that OpenBSD is clearly a looser in
> regard to "pure performances" (e.g. I/O, compression, encryption,
> etc.)
>
> > Nick.
>
> Bye,
> Ektor
>

They should have also ran tests on multiple hardware, single core and
32bit.

32 bit, out performs 64bit on OpenBSD, atleast in my experience
(my hardware).

And as was mentioned with the firewalls earlier. Run real world tests,
where speed matters, and then we may care. Firewalling is one task,
where speed really matters. You can always use multiple systems behind
PF to increase speed too and still keep the security and stability and
management time savings.

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Bret S. Lambert-2
In reply to this post by Ektor Wetterström
> I agree, but you should admit that OpenBSD is clearly a looser in
> regard to "pure performances" (e.g. I/O, compression, encryption,
> etc.)

Yes, if my goal is to have ZOMG AWEZUMZ benchmarks, clearly OpenBSD
is a douchebag.

But if I want a system that doesn't make me want to initiate a mass-
casualty event, I'm afraid it's a clear winner.


For those unable to read between the lines of the above:

Internet troll is, once again, on the Internet

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Tomas Bodzar-4
In reply to this post by Ektor Wetterström
On Wed, Jun 23, 2010 at 1:20 PM, Ektor WetterstrC6m <[hidden email]>
wrote:

> On Wed, Jun 23, 2010 at 1:01 PM, Nick Holland
> <[hidden email]> wrote:
>> On 06/23/10 06:36, Ektor Wetterstrvm wrote:
>>> I know http://bullshit.fefe.de/ is wrong / outdated /
>>> non-scientific / whatever... But what about this? Phoronix has more
>>> credibility imho...
>>>
>>> [benchmarks]
>>
>> facinating number of posts like this recently, all from gmail users
>> we've never seen before...
>>
>> What I want to see is a comparison of critical bug and security
>> problems, or percentage of subsystems that Just Work, or man page
>> accuracy. B (or maybe packet filtering rates)
>
> I agree, but you should admit that OpenBSD is clearly a looser in
> regard to "pure performances" (e.g. I/O, compression, encryption,
> etc.)

Says who? Can't see difference during work with Ubuntu 10.04 or
OpenBSD 4.7 on desktop. Everything has same speed either  GUI or eg.
copy of files to/from USB flash disk. For better I/O you need to buy
better disk, components and so on and not those cheap horrors.
Compression or decompression...... if it's something small then I
can't see difference if it's something big I'm running it in
background so I can do another job. I don't need to take a look at
list of compressed files scrolling in terminal. Where they tested
practical use of encryption, its implementation, cost, documentation
and so on in those tests?????

And how better pure performance can save eg. some private data if it's
available on buggy platform where anyone can stole them? Yes, he can
stole them quicker :D


>
>> Nick.
>
> Bye,
> Ektor
>
>



--
bIf youbre good at something, never do it for free.bB bThe Joker

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Adam M. Dutko
In reply to this post by Nick Holland
<crickets chirping>

.... yawn ....

</crickets chirping>

Continues working...

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Rod Whitworth-3
In reply to this post by Nick Holland
On Wed, 23 Jun 2010 07:01:44 -0400, Nick Holland wrote:

>On 06/23/10 06:36, Ektor Wetterstrvm wrote:
>> I know http://bullshit.fefe.de/ is wrong / outdated /
>> non-scientific / whatever... But what about this? Phoronix has more
>> credibility imho...
>>
>> [benchmarks]
>
>facinating number of posts like this recently, all from gmail users
>we've never seen before...
>
>What I want to see is a comparison of critical bug and security
>problems, or percentage of subsystems that Just Work, or man page
>accuracy.  (or maybe packet filtering rates)
>
>Nick.
>

++1
*** NOTE *** Please DO NOT CC me. I <am> subscribed to the list.
Mail to the sender address that does not originate at the list server is tarpitted. The reply-to: address is provided for those who feel compelled to reply off list. Thankyou.

Rod/
---
This life is not the real thing.
It is not even in Beta.
If it was, then OpenBSD would already have a man page for it.

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Rod Whitworth-3
In reply to this post by Ektor Wetterström
On Wed, 23 Jun 2010 13:20:34 +0200, Ektor Wetterstrvm wrote:

>Bye,
Promise?

*** NOTE *** Please DO NOT CC me. I <am> subscribed to the list.
Mail to the sender address that does not originate at the list server is tarpitted. The reply-to: address is provided for those who feel compelled to reply off list. Thankyou.

Rod/
---
This life is not the real thing.
It is not even in Beta.
If it was, then OpenBSD would already have a man page for it.

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Ektor Wetterström
On Wed, Jun 23, 2010 at 1:57 PM, Rod Whitworth <[hidden email]> wrote:
> On Wed, 23 Jun 2010 13:20:34 +0200, Ektor Wetterstrvm wrote:
>
>>Bye,
> Promise?

Sure, this is my last mail on the topic. I only wanted to know Your
opinions about these types of benchmarks...

By the way, I like OpenBSD and I really appreciate its strong points
but, unlike You, I have no problems in admitting its weaknesses (I see
to much zealotry here)...

Regards,
Ektor

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Adam M. Dutko
> By the way, I like OpenBSD and I really appreciate its strong points
> but, unlike You, I have no problems in admitting its weaknesses (I see
> to much zealotry here)...


Not that I have a lot of room to talk because I haven't submitted a patch
yet...  However, I think the general belief is that submitting patches with
the identification of a weakness is the best way to get peoples attention
and to start a meaningful discussion.  Otherwise, I imagine submitting a bug
with specifics or paying for a feature fix would also work?  Am I wrong
folks?

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Reyk Floeter-2
On Wed, Jun 23, 2010 at 08:39:20AM -0400, Adam M. Dutko wrote:
> Not that I have a lot of room to talk because I haven't submitted a patch
> yet...
>

this statement is weird, in some way.

reyk

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Adam M. Dutko
> this statement is weird, in some way.


I concur.  I'll shutup.  :-)

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Neal Hogan
In reply to this post by Reyk Floeter-2
On Wed, Jun 23, 2010 at 7:57 AM, Reyk Floeter <[hidden email]> wrote:
>
> this statement is weird, in some way.
>

that statement is self-referential . . . so, I agree, it's a bit "weird" ;-)

> reyk

Reply | Threaded
Open this post in threaded view
|

Re: Phoronix Test Suite

Kevin Chadwick-2
In reply to this post by Ektor Wetterström
On Wed, 23 Jun 2010 14:29:24 +0200
Ektor WetterstrC6m <[hidden email]> wrote:


> (I see to much zealotry here)...

It is not zealotry at all. Just a want to be straight and get things
correct. Questions which turn out, to be next to meaningless in the
real world, can annoy.

If I knew what tests the link contained beforehand, I wouldn't have even
looked at it.

> I have no problems in admitting its weaknesses

What are the unsurpassable real world weaknesses in OpenBSD, that you
know of?

12