Re: FreeBSD vs Ubuntu - Discuss...

[Francisco Reyes-2]

Moving to chat instead of performance.

>> This was discussed in detail in slashdot.. starting with the fact that most
>> likely debug switches were not turned off for FreeBSD.
>
> "All of the FreeBSD and Ubuntu options were left at their defaults."
>
> My question is why is FreeBSD's disk i/o performance so bad?

As I mentioned... this was discussed actively in slashdot. You will  find
there many good comments on this.

> Not just in the benchmarks with debugging on, but in real world usage
> where it actually matters.

Are you saying this from actual experience or from reading other people's
comments? If it is from actual experience and XYZ version of Linux does a
particular job better then I don't see why you should not consider using
what works best.

As someone who has had to use Redhat for over a year because that is what
this job uses... I would trade some performance for not having to deal with
all the peculiarities in Linux distros.

Also, as  mentioned in the slashdot article discussion, some of the reasons
Linux may do better on some operations are a tradeoff between
stability/security and speed.

http://linux.slashdot.org/comments.pl?sid=1384455

>From having to use Linux I have found some instances where FreeBSD may no  
not be up to par (ie Java), but overall I would much rather use FreeBSD if I
had a choice. "Features" like the OOM killer are, in my opinion, extremely
poorly designed and likely worst executed.
_______________________________________________
freebsd-chat@... mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-chat
To unsubscribe, send any mail to "freebsd-chat-unsubscribe@..."

[Rick Nekus]

"...Pick any colour you want, as long as its BLACK..." -its not always the car, its invariably the DRIVER !!!

Obviously, as long that *IX works in your "real" world, then thats all that matters.

 

 Be situationally bound, NOT existentially.

 

:)

 

> From: lists@...
> To: freebsd@...
> Date: Tue, 29 Sep 2009 12:42:13 -0400
> CC: freebsd-chat@...
> Subject: Re: FreeBSD vs Ubuntu - Discuss...
>
> Moving to chat instead of performance.
>
> >> This was discussed in detail in slashdot.. starting with the fact that most
> >> likely debug switches were not turned off for FreeBSD.
> >
> > "All of the FreeBSD and Ubuntu options were left at their defaults."
> >
> > My question is why is FreeBSD's disk i/o performance so bad?
>
> As I mentioned... this was discussed actively in slashdot. You will find
> there many good comments on this.
>
> > Not just in the benchmarks with debugging on, but in real world usage
> > where it actually matters.
>
> Are you saying this from actual experience or from reading other people's
> comments? If it is from actual experience and XYZ version of Linux does a
> particular job better then I don't see why you should not consider using
> what works best.
>
> As someone who has had to use Redhat for over a year because that is what
> this job uses... I would trade some performance for not having to deal with
> all the peculiarities in Linux distros.
>
> Also, as mentioned in the slashdot article discussion, some of the reasons
> Linux may do better on some operations are a tradeoff between
> stability/security and speed.
>
> http://linux.slashdot.org/comments.pl?sid=1384455
>
> >From having to use Linux I have found some instances where FreeBSD may no
> not be up to par (ie Java), but overall I would much rather use FreeBSD if I
> had a choice. "Features" like the OOM killer are, in my opinion, extremely
> poorly designed and likely worst executed.
> _______________________________________________
> freebsd-chat@... mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-chat
> To unsubscribe, send any mail to "freebsd-chat-unsubscribe@..."

     
_________________________________________________________________
Windows Live helps you keep up with all your friends, in one place.
http://go.microsoft.com/?linkid=9660826_______________________________________________
freebsd-chat@... mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-chat
To unsubscribe, send any mail to "freebsd-chat-unsubscribe@..."

[soralx]

> Moving to chat instead of performance.
>
> >> This was discussed in detail in slashdot.. starting with the fact that
> >> most likely debug switches were not turned off for FreeBSD.
> >
> > "All of the FreeBSD and Ubuntu options were left at their defaults."
> >
> > My question is why is FreeBSD's disk i/o performance so bad?
>
> As I mentioned... this was discussed actively in slashdot. You will  find
> there many good comments on this.

Debug switches? Irrelevant, as 7.2 performed just as poorly (if not worse)
in the threaded random writes test. One would think that the unrealistically
poor [disk?] I/O performance bench data in FreeBSD was just a glitch, but
using the OS everyday as a workstation, I actually notice that there could
be some truth in those numbers. At least for ATA, when there's some disk I/O
going on, file write operations that normally take milliseconds, may take
tens of seconds or a minute! For example, loading the root disk with some
serious concurrent I/O (portupgrade, find, tar xz, etc) makes opera
unusable: the web browser normally saves "sessions" file everytime there's
a change (e.g., a tab closed, or a page scrolled), and usually the write
operation is unnoticeable, but with heavy disk I/O, one could wait for tens
of seconds before, say, a page gets scrolled following keyboard input.

I thinks that stream [memory benchmark] may also be demonstrating a
weakness in FreeBSD, though I have doubts on this one.

---
[SorAlx]  ridin' VN2000 Classic LT
_______________________________________________
freebsd-chat@... mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-chat
To unsubscribe, send any mail to "freebsd-chat-unsubscribe@..."