Quantcast

Network performance comparison of DragonflyBSD, FreeBSD and Linux

classic Classic list List threaded Threaded
6 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Network performance comparison of DragonflyBSD, FreeBSD and Linux

Miroslav Lachman
There is some comparison of DragonflyBSD, FreeBSD and two versions of
Linux in specific network benchmark - HTTP/1.1 short lived connections.
FreeBSD is the worst in this test.

https://www.dragonflydigest.com/2017/03/06/19425.html

https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png
https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png
https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png

https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf

Miroslav Lachman
_______________________________________________
[hidden email] mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "[hidden email]"
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Network performance comparison of DragonflyBSD, FreeBSD and Linux

Slawa Olhovchenkov
On Tue, Mar 07, 2017 at 02:14:44AM +0100, Miroslav Lachman wrote:

> There is some comparison of DragonflyBSD, FreeBSD and two versions of
> Linux in specific network benchmark - HTTP/1.1 short lived connections.
> FreeBSD is the worst in this test.
>
> https://www.dragonflydigest.com/2017/03/06/19425.html
>
> https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png
> https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png
> https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png
>
> https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf

Is this you test?
I mean some congestion in file/page access layer on FreeBSD, can you
re-test w/ about 1000 different files?
I.e. every client request

http://server/X_K.bin~1
http://server/X_K.bin~2
....
http://server/X_K.bin~1000

not just http://server/X_K.bin
_______________________________________________
[hidden email] mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "[hidden email]"
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Network performance comparison of DragonflyBSD, FreeBSD and Linux

Miroslav Lachman
Slawa Olhovchenkov wrote on 2017/03/07 08:10:

> On Tue, Mar 07, 2017 at 02:14:44AM +0100, Miroslav Lachman wrote:
>
>> There is some comparison of DragonflyBSD, FreeBSD and two versions of
>> Linux in specific network benchmark - HTTP/1.1 short lived connections.
>> FreeBSD is the worst in this test.
>>
>> https://www.dragonflydigest.com/2017/03/06/19425.html
>>
>> https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png
>> https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png
>> https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png
>>
>> https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf
>
> Is this you test?

No, it is not mine test. I just found it on the internet.

> I mean some congestion in file/page access layer on FreeBSD, can you
> re-test w/ about 1000 different files?
> I.e. every client request
>
> http://server/X_K.bin~1
> http://server/X_K.bin~2
> ....
> http://server/X_K.bin~1000
>
> not just http://server/X_K.bin

_______________________________________________
[hidden email] mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "[hidden email]"
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Network performance comparison of DragonflyBSD, FreeBSD and Linux

O. Hartmann-5
In reply to this post by Miroslav Lachman
Am Tue, 7 Mar 2017 02:14:44 +0100
Miroslav Lachman <[hidden email]> schrieb:

> There is some comparison of DragonflyBSD, FreeBSD and two versions of
> Linux in specific network benchmark - HTTP/1.1 short lived connections.
> FreeBSD is the worst in this test.
>
> https://www.dragonflydigest.com/2017/03/06/19425.html
>
> https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png
> https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png
> https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png
>
> https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf
>
> Miroslav Lachman
> _______________________________________________
> [hidden email] mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-performance
> To unsubscribe, send any mail to "[hidden email]"
Thank you so much for this finding.

It is interesting that with a generic kernel, the "performance" is roughly the half of
what Linux and DFBSD would give.

I miss performance benchmarks, it seems, that over the past couple of years this habit
has become quite unusual for FreeBSD.

Oliver

--
O. Hartmann

Ich widerspreche der Nutzung oder Übermittlung meiner Daten für
Werbezwecke oder für die Markt- oder Meinungsforschung (§ 28 Abs. 4 BDSG).

attachment0 (321 bytes) Download Attachment
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Network performance comparison of DragonflyBSD, FreeBSD and Linux

Matthias Gamsjager
Maybe someone should retest and see where the problem.
It doesn't help in saying the test sucks or is done wrong.



On 9 March 2017 at 20:26, O. Hartmann <[hidden email]> wrote:

> Am Tue, 7 Mar 2017 02:14:44 +0100
> Miroslav Lachman <[hidden email]> schrieb:
>
> > There is some comparison of DragonflyBSD, FreeBSD and two versions of
> > Linux in specific network benchmark - HTTP/1.1 short lived connections.
> > FreeBSD is the worst in this test.
> >
> > https://www.dragonflydigest.com/2017/03/06/19425.html
> >
> > https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png
> > https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png
> > https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png
> >
> > https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf
> >
> > Miroslav Lachman
> > _______________________________________________
> > [hidden email] mailing list
> > https://lists.freebsd.org/mailman/listinfo/freebsd-performance
> > To unsubscribe, send any mail to "freebsd-performance-
> [hidden email]"
>
> Thank you so much for this finding.
>
> It is interesting that with a generic kernel, the "performance" is roughly
> the half of
> what Linux and DFBSD would give.
>
> I miss performance benchmarks, it seems, that over the past couple of
> years this habit
> has become quite unusual for FreeBSD.
>
> Oliver
>
> --
> O. Hartmann
>
> Ich widerspreche der Nutzung oder Übermittlung meiner Daten für
> Werbezwecke oder für die Markt- oder Meinungsforschung (§ 28 Abs. 4 BDSG).
>
_______________________________________________
[hidden email] mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "[hidden email]"
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Network performance comparison of DragonflyBSD, FreeBSD and Linux

George Neville-Neil
In reply to this post by Miroslav Lachman


On 7 Mar 2017, at 18:12, Miroslav Lachman wrote:

> Slawa Olhovchenkov wrote on 2017/03/07 08:10:
>> On Tue, Mar 07, 2017 at 02:14:44AM +0100, Miroslav Lachman wrote:
>>
>>> There is some comparison of DragonflyBSD, FreeBSD and two versions
>>> of
>>> Linux in specific network benchmark - HTTP/1.1 short lived
>>> connections.
>>> FreeBSD is the worst in this test.
>>>
>>> https://www.dragonflydigest.com/2017/03/06/19425.html
>>>
>>> https://leaf.dragonflybsd.org/~sephe/perfcomp/1K.png
>>> https://leaf.dragonflybsd.org/~sephe/perfcomp/8K.png
>>> https://leaf.dragonflybsd.org/~sephe/perfcomp/16K.png
>>>
>>> https://leaf.dragonflybsd.org/~sephe/perf_cmp.pdf
>>
>> Is this you test?
>
> No, it is not mine test. I just found it on the internet.
>

The work was presented at the latest AsiaBSDCon and several of us are
working the sephe@, who is a FreeBSD committer on improving the
benchmark's fidelity as well as addressing the issues that are
highlighted.

Look for P05C: 10 Years with DragonFlyBSD network stack

https://2017.asiabsdcon.org/program.html.en#

Best,
George
_______________________________________________
[hidden email] mailing list
https://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "[hidden email]"
Loading...