raid vs network performance

kony wrote in news:r57bm3d6pfbnqn90uu680pc1jpcr0hke8f@4ax.com
> On 16 Dec 2007 16:04:55 GMT, Arno Wagner <me.TakeThisOut@privacy.net>
> wrote:
>
>
> > > > > > Slower ones (RTL), make maybe 25MB/s.
> > > >
> > > > > RT8169 can fairly easily do 40MB/s.
> > > >
> > > > Depends very much on the board and the other components
> > > > in use. I have seen speeds as low as 240Mbit/s and that
> > > > was with UDP streaming, not TCP.
> >
> >
> > > ... Then it's not RT8169 that is the bottleneck and the
> > > comment about 25MB/s is just invalid.
> >
> >
> > 240Mbit/s = 25 MB/s
>
> And? It doesn't change that I have systems with RT8169
> which achieve more than 25MB/s.
>
>
>
> >
> > > I have, maybe half a dozen systems using these RT8169
> > > cards, they are not at all limited to the low throughput the
> > > OP is seeing, BUT, on any I bothered to benchmark, I did
> > > ensure better jumbo frame TCP/IP settings.
> >
> > There are different chip generations and the combination
> > of mainboard and chip also matters.
>
> Some, certainly with a few Via chipsets which had poor PCI
> bandwidth that was choking data flow to the NIC. As for
> pure chipset - NIC interactions, it is very rare and even
> more often attributable to an OS problem rather than
> mainboard problem.
>
>
>
> >
> > > Also, at some point realtek limited jumbo frame support to
> > > around 7K instead of 9K, so that limit is worth
> > > consideration but in real world use, 7K is not going to
> > > bottleneck anywhere near this value reported... maybe if it
> > > were a 80486 system or Pentium 1.
> >
> > If you can use Jumbo-frames. Depends.
>
> Most can at least use 4K frames if not 7-9K. The majority
> of networking equipment will pass more than 1.5K.
>
>
> > > > Yes, and PCI busses of that aera can often not reach more
> > > > than 70-80MB/s.
> >
> >
> > > Not true, the vast majority did reach peak throughtput, with
> > > exception of some Via and early skt 370 Sis chipsets.
> >
> > So? Then I must have consitently bought the wrong hardware....
>
> Many of us did buy a chipset or two that had this problem,
> but by midway into the Pentium 3 era, it was mostly reserved
> to Via chipsets as Sis had then covercome it. Intel had
> great PCI throughput much further back, I can't put my
> finger on exactly when it was more than 80MB/s but certainly
> by the 440LX/P2 era, and probably before that.
>
> > > I can say that any and all systems I have used Realtek 8169
> > > based PCI cards on, did not have any substantil bottleneck
> > > based on that card. What I really mean is, this is a cheap
> > > card and used when other things are budget constained too,
> > > that it can easily, always reach over 30Mb/s when there is
> >
> > I assume you mean 30MB/s?
>
> Yes, I mistyped 30MB/s.
>
>
> > > IOW, if the drive can do in excess of 50MB/s, which
> > > benchmarks show it can, then it's 50MB/s over the PCI bus to
> > > memory, then back again to the PCI NIC. While the PCI bus
> > > can achieve 100Mb/s, it can't do much more without at least
> >
> > Again, woujd that be 100MB/s?

> Yep, but wouldn't that have been obvious by my prior statements?

Actually it just casts some doubt on whether you are just another babble-head, just like the babblebot.

Who is the undisputed king of spelling errors and typos btw.

Oh, and you're likely to end up in babblebot's killfile now too.
 >> Stay informed about: raid vs network performance 

Arno Wagner wrote in news:5sm3agF1a32q2U2@mid.individual.net
> In comp.sys.ibm.pc.hardware.storage kony <spam.DeleteThis@spam.com> wrote:
> > On 16 Dec 2007 16:04:55 GMT, Arno Wagner <me.DeleteThis@privacy.net>
> > wrote:
>
>
> > > > > > > Slower ones (RTL), make maybe 25MB/s.
> > > > >
> > > > > > RT8169 can fairly easily do 40MB/s.
> > > > >
> > > > > Depends very much on the board and the other components
> > > > > in use. I have seen speeds as low as 240Mbit/s and that
> > > > > was with UDP streaming, not TCP.
> > >
> > >
> > > > ... Then it's not RT8169 that is the bottleneck and the
> > > > comment about 25MB/s is just invalid.
> > >
> > >
> > > 240Mbit/s = 25 MB/s
>
> > And? It doesn't change that I have systems with RT8169
> > which achieve more than 25MB/s.
>
> So? And I have ones that do not. And we both do not know
> what NIC the OP has.

Good for you, Arnie, that should shut him up.

>
> Arno
 >> Stay informed about: raid vs network performance 

Eric Gisin wrote in news:13m3ilrkdtndfd2@corp.supernews.com
> I doubt Promise makes a hardware RAID card.

Then silly you.

> PCI is a mistake too.

Even sillier you.

>
> You will get better results from Intel's soft RAID on the ICH8/9R,
> which has a GB/s path to system RAM, compared to PCI's 120MB/s.
>
> "3dO" <noaddress.TakeThisOut@nomail.com> wrote in message news:gDh8j.95897$KC6.81361@fe07.news.easynews.com...
> > ok, this is a long one but i really am clueless on this one
> >
> > two week ago i set up a "fileserver", as i'm a visual nut and not a
> > server nut i went for a simple xp pro machine with a raidcontroller:
> > asus p5k-vm with intel c2d e4300 - 1GB ram, promise fasttrak tx4310 PCI
> > raid controller, 4 samsung spinpoint t166 500GB (raid5) and 1 samsung
> > spinpoint t166 160GB as systemdisk.
> >
> > when i work with a 4.01GB video dvd image i get the following transferrates:
> >
> > localWRITE: copy from systemdisk to raid5 array : 28.9MB/s sustained
> > localREAD : copy from raid5 array to systemdisk : 49.4MB/s sustained
> > netWRITE: copy from network to raid5 array : 14.7MB/s
> > netREAD : copy from raid5 array to network : 24.5MB/s
 >> Stay informed about: raid vs network performance 

On Tue, 18 Dec 2007 23:47:11 +0100, "Folkert Rienstra"
<see_reply-to DeleteThis @myweb.nl> wrote:

>Eric Gisin wrote in news:13m3ilrkdtndfd2@corp.supernews.com
>> I doubt Promise makes a hardware RAID card.
>
>Then silly you.
>
>> PCI is a mistake too.
>
>Even sillier you.
>



No, if one is spending a lot of money these days on a
hardware RAID card, and the drives for it, it'd be a bit
foolish to run that on a 32bit, 33MHz PCI bus.

Even motherboard integrated SATA RAID betters that for
*free*. While I don't like depending on any certain
motherboard chipset for data storage, todays drives have now
made PCI insufficient for maximum performance... not just
from the drives in an isolated benchmark, but also
considering the odds there are other PCI devices in use
concurrently at least some of the time. Years ago, these
devices may have been lower bandwidth, but today's (for
example) Creative Labs sound cards or gigabit NICs leave a
lot of competition for bandwidth.
 >> Stay informed about: raid vs network performance 

On Tue, 18 Dec 2007 23:32:06 +0100, "Folkert Rienstra"
<see_reply-to RemoveThis @myweb.nl> wrote:


>> Yep, but wouldn't that have been obvious by my prior statements?
>
>Actually it just casts some doubt on whether you are just another babble-head, just like the babblebot.
>
>Who is the undisputed king of spelling errors and typos btw.

I confess, I do make a lot of typing errors.
If it bothers you too much, just ploke me.


>
>Oh, and you're likely to end up in babblebot's killfile now too.

Boo hoo?

Somehow I'll get by.
 >> Stay informed about: raid vs network performance 

In comp.sys.ibm.pc.hardware.storage kony <spam RemoveThis @spam.com> wrote:
> On Tue, 18 Dec 2007 23:32:06 +0100, "Folkert Rienstra"
> <see_reply-to RemoveThis @myweb.nl> wrote:


>>> Yep, but wouldn't that have been obvious by my prior statements?
>>
>>Actually it just casts some doubt on whether you are just another babble-head, just like the babblebot.
>>
>>Who is the undisputed king of spelling errors and typos btw.

> I confess, I do make a lot of typing errors.
> If it bothers you too much, just ploke me.


>>
>>Oh, and you're likely to end up in babblebot's killfile now too.

> Boo hoo?

> Somehow I'll get by.

Hehe, Folkert still does not get it. Why ever would I killfile you?
We may disagree, but that is not an issue.

Arno
 >> Stay informed about: raid vs network performance 

kony wrote:
> On Tue, 18 Dec 2007 23:47:11 +0100, "Folkert Rienstra"
> <see_reply-to.TakeThisOut@myweb.nl> wrote:
>
>
>>Eric Gisin wrote in news:13m3ilrkdtndfd2@corp.supernews.com
>>
>>>I doubt Promise makes a hardware RAID card.
>>
>>Then silly you.
>>
>>
>>> PCI is a mistake too.
>>
>>Even sillier you.
>>
>
>
>
>
> No, if one is spending a lot of money these days on a
> hardware RAID card, and the drives for it, it'd be a bit
> foolish to run that on a 32bit, 33MHz PCI bus.
>

There are other "flavors" of PCI.

> Even motherboard integrated SATA RAID betters that for
> *free*. While I don't like depending on any certain
> motherboard chipset for data storage, todays drives have now
> made PCI insufficient for maximum performance... not just
> from the drives in an isolated benchmark, but also
> considering the odds there are other PCI devices in use
> concurrently at least some of the time. Years ago, these
> devices may have been lower bandwidth, but today's (for
> example) Creative Labs sound cards or gigabit NICs leave a
> lot of competition for bandwidth.


--
The e-mail address in our reply-to line is reversed in an attempt to
minimize spam. Our true address is of the form che....TakeThisOut@prodigy.net.
 >> Stay informed about: raid vs network performance 

kony wrote in news:5omhm35rt4sbnsv3qe46ko743gnoi3ki8j@4ax.com
> On Tue, 18 Dec 2007 23:47:11 +0100, "Folkert Rienstra" <see_reply-to.RemoveThis@myweb.nl> wrote:
>
> > Eric Gisin wrote in news:13m3ilrkdtndfd2@corp.supernews.com
> > > I doubt Promise makes a hardware RAID card.
> >
> > Then silly you.
> >
> > > PCI is a mistake too.
> >
> > Even sillier you.
> >

>
> No, if one is spending a lot of money these days on a
> hardware RAID card, and the drives for it, it'd be a bit
> foolish to run that on a 32bit, 33MHz PCI bus.

Who said anything about 32bit, 33MHz ?
 >> Stay informed about: raid vs network performance 

kony wrote in news:01nhm3lndm4p47j782nhhget48oulibk2m@4ax.com
> On Tue, 18 Dec 2007 23:32:06 +0100, "Folkert Rienstra" <see_reply-to.DeleteThis@myweb.nl> wrote:
>
>
> > > Yep, but wouldn't that have been obvious by my prior statements?
> >
> > Actually it just casts some doubt on whether you are just another
> > babble-head, just like the babblebot.
> >
> > Who is the undisputed king of spelling errors and typos btw.

> I confess,

Apparently not a very good reader either.
Obviously I referred to the babblebot, not you.

> I do make a lot of typing errors.

Perhaps, but you correct them before sending, unlike the babblebot.

> If it bothers you too much, just ploke me.

Sorry, my newsclient doesn't have a ploke file.

>
>
> >
> > Oh, and you're likely to end up in babblebot's killfile now too.
>
> Boo hoo?
>
> Somehow I'll get by.
 >> Stay informed about: raid vs network performance 

Arno Wagner wrote in news:5ssutkF19kl26U1@mid.individual.net
> In comp.sys.ibm.pc.hardware.storage kony <spam.DeleteThis@spam.com> wrote:
> > On Tue, 18 Dec 2007 23:32:06 +0100, "Folkert Rienstra"
> > <see_reply-to.DeleteThis@myweb.nl> wrote:
>
>
> > > > Yep, but wouldn't that have been obvious by my prior statements?
> > >
> > > Actually it just casts some doubt on whether you are just another
> > > babble-head, just like the babblebot.
> > >
> > > Who is the undisputed king of spelling errors and typos btw.
>
> > I confess, I do make a lot of typing errors.
> > If it bothers you too much, just ploke me.
>
>
> > >
> > > Oh, and you're likely to end up in babblebot's killfile now too.
>
> > Boo hoo?
>
> > Somehow I'll get by.

> Hehe, Folkert still does not get it.

Oh, yes he does.

> Why ever would I killfile you?

The same reason you killfiled me and everyone else that shows you off
clueless, time after time.
You just have not killfiled him because he lives in another group that
you don't live in.

> We may disagree, but that is not an issue.

So babblebot, why then exactly do you have such a well filled killfile?
It's a personal thing then, right?

>
> Arno
 >> Stay informed about: raid vs network performance 

On Wed, 19 Dec 2007 21:36:26 +0100, "Folkert Rienstra"
<see_reply-to RemoveThis @myweb.nl> wrote:

>kony wrote in news:5omhm35rt4sbnsv3qe46ko743gnoi3ki8j@4ax.com
>> On Tue, 18 Dec 2007 23:47:11 +0100, "Folkert Rienstra" <see_reply-to RemoveThis @myweb.nl> wrote:
>>
>> > Eric Gisin wrote in news:13m3ilrkdtndfd2@corp.supernews.com
>> > > I doubt Promise makes a hardware RAID card.
>> >
>> > Then silly you.
>> >
>> > > PCI is a mistake too.
>> >
>> > Even sillier you.
>> >
>
>>
>> No, if one is spending a lot of money these days on a
>> hardware RAID card, and the drives for it, it'd be a bit
>> foolish to run that on a 32bit, 33MHz PCI bus.
>
>Who said anything about 32bit, 33MHz ?
>

asus p5k-vm, as the OP stated.

It's either 32bit/33Mhz, or moving to PCI Express.
 >> Stay informed about: raid vs network performance 

On Wed, 19 Dec 2007 21:39:09 +0100, "Folkert Rienstra"
<see_reply-to DeleteThis @myweb.nl> wrote:

>kony wrote in news:01nhm3lndm4p47j782nhhget48oulibk2m@4ax.com
>> On Tue, 18 Dec 2007 23:32:06 +0100, "Folkert Rienstra" <see_reply-to DeleteThis @myweb.nl> wrote:
>>
>>
>> > > Yep, but wouldn't that have been obvious by my prior statements?
>> >
>> > Actually it just casts some doubt on whether you are just another
>> > babble-head, just like the babblebot.
>> >
>> > Who is the undisputed king of spelling errors and typos btw.
>
>> I confess,
>
>Apparently not a very good reader either.
>Obviously I referred to the babblebot, not you.
>
>> I do make a lot of typing errors.
>
>Perhaps, but you correct them before sending, unlike the babblebot.
>


Hahaha, you obviously have not read many of my posts. I
almost never correct any typing or spelling errors because I
don't reread posts nor run a spell checker and rarely even
sit close enough to my monitor to even read what I typed.

Anyone who has a problem with that can just plonk me, but I
realize you are just trolling at this point.
 >> Stay informed about: raid vs network performance 

kony wrote in news:6kdkm3ltpjgjqfm5abr77oq7b3iu07pdii@4ax.com
> On Wed, 19 Dec 2007 21:36:26 +0100, "Folkert Rienstra" <see_reply-to.DeleteThis@myweb.nl> wrote:
> > kony wrote in news:5omhm35rt4sbnsv3qe46ko743gnoi3ki8j@4ax.com
> > > On Tue, 18 Dec 2007 23:47:11 +0100, "Folkert Rienstra" <see_reply-to.DeleteThis@myweb.nl> wrote:
> > >
> > > > Eric Gisin wrote in news:13m3ilrkdtndfd2@corp.supernews.com
> > > > > I doubt Promise makes a hardware RAID card.
> > > >
> > > > Then silly you.
> > > >
> > > > > PCI is a mistake too.
> > > >
> > > > Even sillier you.
> > > >
> >
> > >
> > > No, if one is spending a lot of money these days on a
> > > hardware RAID card, and the drives for it, it'd be a bit
> > > foolish to run that on a 32bit, 33MHz PCI bus.
> >
> > Who said anything about 32bit, 33MHz ?
> >

> asus p5k-vm, as the OP stated.

Pity that was not how the comment was made.
And if a board has no alternatives it has to be replaced
anyway (by something else with higher flavors of *PCI*.

>
> It's either 32bit/33Mhz,

> or moving to PCI Express.

And how is that _not_ PCI.
 >> Stay informed about: raid vs network performance