SATA vs SCSI

[Rob Nicholson]

If I wanted to have a space heater to keep my feet warm on a cold winters

night I would use AMD processors.

Err, the AMD-64 I have in my home PC runs surprisingly cool... The AMD
Athlon XPs we have in our development server - yes, they run like white hot.

Rob.

 

[Rob Nicholson]

Err, the AMD-64 I have in my home PC runs surprisingly cool... The AMD
Athlon XPs we have in our development server - yes, they run like white
hot.

Meant to say Athlon MPs....

 

[Anton Ertl]

Stay SCSI. SATA may look the same in some benchmarks, but the
fact of it is that SATA is a cheap, mass-market product, while
SCSI is a professional product. It is designed with a different
mind-set.

Mainly it's bought with a different mind-set.

We have had SCSI disks and ATA disks in our servers (which run all the
time), and now a few SATA disks. Some of either group have failed,
and we had compatibility troubles with the either interface.

If you want reliability, buy several drives (preferably from different
manufacturers to reduce the probability of systematic errors hitting
all drives at once) and build a RAID1 or RAID5 out of them. And buy
spare drives, and spare controllers for availability and to ensure
compatibility. 3 300GB SATA drives and 2 controllers are quite a bit
cheaper and (in a RAID 1 setup with 1 spare) much more reliable and
available than a single 300GB SCSI drive, even if the SCSI controller
was for free.

My opinion is that SCSI is mostly a cult. The additional price you
pay for SCSI is the tithe you pay to the church of SCSI (well, a part
of the higher price is also because it's not a mass-market product).
I heard the same arguments about the superiority of SCSI 10 years ago,
but our experiences did not confirm them.

It's not a cult, if you need a SCSI drive feature, like ultra-fast
drives. But most features that were unique to SCSI have been replaced
with cheaper alternatives using IDE or SATA drives (e.g., external USB
drives, NAS, and NCQ).

Of course. WD does not have SCSI products and so has to make
everybody believe that SATA is just as good.

Maybe WD knows that SATA is just as good, and that's why they are not
making SCSI drives.

Best technology: SCSI, without doubt. These are expected to
run 24/7 for years.

Yes, but not all of them do.

- anton

 

[Odie Ferrous]

I take it you are a gamer and also use AMD processor(s)


Absolutely! I never said it wasn't a "proven platform" since I gave you
real world applications were SATA shines. Unfortunately it's not in any
mission critical application where reliability can mean the difference
between life and death. SATA excels in the AMD crowd were the users are
only worried about measuring their manhood by how many GBs they have under
the hood.


Tell me that in another 20-years. Better yet, how about 5-years?


Seagate Cheetah! Is there really anything else?


Which is most likely attributed to pilot error. You crashed and burned
because of something you failed to do, like RTFM.


SCSI is far cheaper! Plus I *NEVER* doubt the SCSI arrays and solutions I
have deployed for my customers. Sure SATA drives are initially cheaper than
SCSI, but you get what you pay for. When downtime, lost productivity,
labor, and support costs are figured into the equation SATA solutions are
generally three to four times more expensive than SCSI over the predicted
life of the equipment.


It's been beaten before it was ever conceived. Hell, even an antiquated
narrow SCSI drive kills SATA.


List an example of a SATA drive that can beat the seek time and overall
performance of the latest generation 15K U320 Seagate Cheetahs? After you
do that we'll then discuss and compare reliability.

Like I said if I wanted to build a novelty box I would definitely go SATA.
If I wanted to have a space heater to keep my feet warm on a cold winters
night I would use AMD processors.

Rita

Rita,


I was "sort of" on your side - until you slagged off AMD processors.

Five years ago, I would not have dreamt of using AMD processors in a
server. (Inasmuch as I would not consider using VIA CPUs in even a
games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers, the
rest for less important machines.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel chips
into the dust where performance is concerned. And I'm talking
performance advantages to a very high degree - not just 5% or so.

As far as the SCSI / SATA debate is concerned - for anything *really*
mission-critical and especially when it is combined with a need for
performance, nothing currently matches SCSI.

However, I believe SCSI is on its way out. Partly because of marketing
hype, but also because SCSI is incredibly expensive to set up from
scratch, and the vast majority of users are scared of these costs - to
their detriment, admittedly.

I think that SCSI will be practically dead (from a supply point of view)
in well under five years.


Odie

 

[Arno Wagner]

[...]

Rita,

I was "sort of" on your side - until you slagged off AMD processors.

Five years ago, I would not have dreamt of using AMD processors in a
server. (Inasmuch as I would not consider using VIA CPUs in even a
games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers, the
rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of a
dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel chips
into the dust where performance is concerned. And I'm talking
performance advantages to a very high degree - not just 5% or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault. Personally I allways had AMD since my last
Intel 486 CPU and never had reliability problems related to the CPU.
The only really cool product by Intel at the moment is the Pentium M,
which ironicaly is a P-3 derivate. Seems the P-4 was really a dead
end.

As far as the SCSI / SATA debate is concerned - for anything *really*
mission-critical and especially when it is combined with a need for
performance, nothing currently matches SCSI.

However, I believe SCSI is on its way out. Partly because of marketing
hype, but also because SCSI is incredibly expensive to set up from
scratch, and the vast majority of users are scared of these costs - to
their detriment, admittedly.

I think that SCSI will be practically dead (from a supply point of view)
in well under five years.

You may be right on this one. Also with more and more people using
RAID, reliability may not be impacted too badly for systems that
are not too critical. One problem is what to do where currently
SCSI in RAID configuration is used. RAID6 or even higher redundancy?
Replicated servers? We will see. From an engineering POV it is
not a problem working with lower reliability components, as long
as they can be combined in a way to increase redundancy _and_
as long as you are aware of the lower reliability. So SATA
is definitely not up to SCSI standards, but it can be made to
work as well in most situations.

Arno

 

[Rita Ä Berkowitz]

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers, the
rest for less important machines.

Possibly in some obscure circles and third world countries? I'm not sure
AMD is ready to be taken as a serious contender in any "real world"
environments. For instance, even something as basic as laptops. Specialty
laptops that require maximum performance, durability, and reliability for
use in police vehicles, fire and rescue, and other demanding environment
where life and limb are at stake you'll always find a Panasonic Toughbook.
Guess what? You'll never see an AMD in a Panasonic Toughbook! Never have
and never will.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel chips
into the dust where performance is concerned. And I'm talking
performance advantages to a very high degree - not just 5% or so.

Sorry, not yet! This is a pipedream and marketing ploy that AMD would like
you to believe. One day this will be true, and I hope that it is, but that
day isn't yet upon us.

As far as the SCSI / SATA debate is concerned - for anything *really*
mission-critical and especially when it is combined with a need for
performance, nothing currently matches SCSI.
Yep!

However, I believe SCSI is on its way out. Partly because of
marketing hype, but also because SCSI is incredibly expensive to set
up from scratch, and the vast majority of users are scared of these
costs - to their detriment, admittedly.

SCSI might be on its way out, but it will be a long time before that
happens. Fortunately, intelligent people consider all costs of ownership
beyond the initial purchase price. SCSI is far cheaper in the long run.
Case in point, just the other day a gentleman tried to demonstrate how cheap
SATA is and tried to justify it by replacing his SATA drives every two
years. This exercise in pure stupidity does add greatly to the overall cost
of ownership. At least he is smart enough to realize SATA is still cutting
its teeth and isn't yet taken as a serious and reliable solution.

I think that SCSI will be practically dead (from a supply point of
view) in well under five years.

I think you said that five years ago when we were discussing UW SCSI and we
are now using U320. I don't mind you bumping the timeline up again since I
will still make money.







Rita

 

[Sambo]

[...]

Rita,

I was "sort of" on your side - until you slagged off AMD processors.

Five years ago, I would not have dreamt of using AMD processors in a
server. (Inasmuch as I would not consider using VIA CPUs in even a
games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers,
the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of a
dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel
chips into the dust where performance is concerned. And I'm talking
performance advantages to a very high degree - not just 5% or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink, fan.
And had decent protection for when something went wrong like the
heatsink not properly mounted on the cpu or the fan stops etc.

Personally I allways had AMD since my last Intel 486
CPU and never had reliability problems related to the CPU.

Sure, if you know what you are doing they are
usable, but with no protection at all initially.

The only really cool product by Intel at the moment is the Pentium M,
which ironicaly is a P-3 derivate. Seems the P-4 was really a dead end.

Oh bullshit. The Northwoods were very decent cpus and ran a lot
quieter than the AMDs. I have one that was so quiet when I installed
it that I had to check that the fan was spinning it was so quiet with the
motherboard at face level with the cpu being run up for the first time.

You may be right on this one. Also with more and more people using
RAID, reliability may not be impacted too badly for systems that
are not too critical. One problem is what to do where currently
SCSI in RAID configuration is used. RAID6 or even higher redundancy?
Replicated servers? We will see. From an engineering POV it is
not a problem working with lower reliability components, as long
as they can be combined in a way to increase redundancy _and_
as long as you are aware of the lower reliability. So SATA
is definitely not up to SCSI standards, but it can be made to
work as well in most situations.

There isnt any solid evidence that the best of the SATA
drives are any less reliable than SCSI drives individually.

 

[Folkert Rienstra]

[...]

Rita,

[snip]

I think that SCSI will be practically dead (from a supply point of view)
in well under five years.

You may be right on this one. Also with more and more people using
RAID, reliability may not be impacted too badly for systems that
are not too critical. One problem is what to do where currently
SCSI in RAID configuration is used. RAID6 or even higher redundancy?
Replicated servers? We will see. From an engineering POV it is
not a problem working with lower reliability components, as long
as they can be combined in a way to increase redundancy _and_
as long as you are aware of the lower reliability.

So SATA is definitely not up to SCSI standards,

Utterly clueless idiot pulls statement from arse.

 

[Arno Wagner]

:
[...]

Rita,

I was "sort of" on your side - until you slagged off AMD processors.

Five years ago, I would not have dreamt of using AMD processors in a
server. (Inasmuch as I would not consider using VIA CPUs in even a
games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers,
the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of a
dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel
chips into the dust where performance is concerned. And I'm talking
performance advantages to a very high degree - not just 5% or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink, fan.
And had decent protection for when something went wrong like the
heatsink not properly mounted on the cpu or the fan stops etc.

A CPU is an engineering product, intended to be mounted by
experts only. AMD did offer the pre-packaged version. AMD also
stated in ther cooling documentation that an incorrect heatsink
would likely kill the CPU. There is no "wrong" way to make a
technical component like this. There are just people that
do not read or do not understand the documentation and then
blame it on others.

Sure, if you know what you are doing they are
usable, but with no protection at all initially.

So what? Intel 486/586 CPUs also did not have protection.
It is not a fundamental flaw unless a dilettante gets his hands
on the component.

Oh bullshit. The Northwoods were very decent cpus and ran a lot
quieter than the AMDs.

Since when do CPUs produce noise?

I have one that was so quiet when I installed
it that I had to check that the fan was spinning it was so quiet with the
motherboard at face level with the cpu being run up for the first time.

Well, fan selection is not AMDs task. I had the same with all
my AMD CPUs, simply because I am competent so select a quiet
cooling solution.

There isnt any solid evidence that the best of the SATA
drives are any less reliable than SCSI drives individually.

Belive what you must.

Arno

 

[Arno Wagner]

Odie Ferrous wrote:

Possibly in some obscure circles and third world countries? I'm not sure
AMD is ready to be taken as a serious contender in any "real world"
environments.

You seem to be several years behind the times.

For instance, even something as basic as laptops. Specialty
laptops that require maximum performance, durability, and reliability for
use in police vehicles, fire and rescue, and other demanding environment
where life and limb are at stake you'll always find a Panasonic Toughbook.
Guess what? You'll never see an AMD in a Panasonic Toughbook! Never have
and never will.

Laptops are not basic. From the list of requirements you give it is
obvious that you do not consider them basic yourself. They are
perhaps the most demanding environment possible. And I agree thet the
Pentium M looks better than what AMD offers. But these are not for
servers or desktops. In servers and desktops, AMD has more than a
slight edge on Intel at the moment.

Sorry, not yet! This is a pipedream and marketing ploy that AMD
would like you to believe. One day this will be true, and I hope
that it is, but that day isn't yet upon us.

Are you using any AMD CPUs at the moment? I have seen the difference
personally.

Arno

 

[Sambo]

:

[...]

Rita,


I was "sort of" on your side - until you slagged off AMD
processors.

Five years ago, I would not have dreamt of using AMD processors in
a server. (Inasmuch as I would not consider using VIA CPUs in
even a games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers,
the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of
a dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel
chips into the dust where performance is concerned. And I'm
talking performance advantages to a very high degree - not just 5%
or so.
I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink, fan.
And had decent protection for when something went wrong like the
heatsink not properly mounted on the cpu or the fan stops etc.

A CPU is an engineering product, intended to be mounted by experts only.

No its not, and you need protection for fan failure anyway.

AMD did their usual, a quick and dirty design to get it out the
door as quickly as possible and did the stuff they should have
done in the initial design later, like the protection.

AMD did offer the pre-packaged version. AMD also stated
in ther cooling documentation that an incorrect heatsink
would likely kill the CPU. There is no "wrong" way to make a
technical component like this. There are just people that
do not read or do not understand the documentation and then
blame it on others.

If the cpu comes with the heatsink and fan, that eliminates
any possibility of not using an adequate heatsink and fan.

And you need protection for more than just the initial config
anyway, most obviously with fan failure. Stupid to fry the
cpu if the fan fails with something like the AMD cpus that
woud fry in an instant with no fan running.

So what? Intel 486/586 CPUs also did not have protection.

They didnt need it, the wouldnt fry.

It is not a fundamental flaw unless a
dilettante gets his hands on the component.

Yes it is, most obviously with fan failure.

Since when do CPUs produce noise?

Its the fan, stupid.

Well, fan selection is not AMDs task.

Wrong again.

I had the same with all my AMD CPUs, simply because
I am competent so select a quiet cooling solution.

Better if you dont have to.

Belive what you must.

You're the one believing without the evidence.

 

[J. Clarke]

:

[...]

Rita,


I was "sort of" on your side - until you slagged off AMD
processors.

Five years ago, I would not have dreamt of using AMD processors in
a server. (Inasmuch as I would not consider using VIA CPUs in
even a games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers,
the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of
a dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel
chips into the dust where performance is concerned. And I'm
talking performance advantages to a very high degree - not just 5%
or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink, fan.
And had decent protection for when something went wrong like the
heatsink not properly mounted on the cpu or the fan stops etc.

A CPU is an engineering product, intended to be mounted by experts only.

No its not, and you need protection for fan failure anyway.

AMD did their usual, a quick and dirty design to get it out the
door as quickly as possible and did the stuff they should have
done in the initial design later, like the protection.

AMD did offer the pre-packaged version. AMD also stated
in ther cooling documentation that an incorrect heatsink
would likely kill the CPU. There is no "wrong" way to make a
technical component like this. There are just people that
do not read or do not understand the documentation and then
blame it on others.

If the cpu comes with the heatsink and fan, that eliminates
any possibility of not using an adequate heatsink and fan.

And you need protection for more than just the initial config
anyway, most obviously with fan failure. Stupid to fry the
cpu if the fan fails with something like the AMD cpus that
woud fry in an instant with no fan running.

So what? Intel 486/586 CPUs also did not have protection.

They didnt need it, the wouldnt fry.

It is not a fundamental flaw unless a
dilettante gets his hands on the component.

Yes it is, most obviously with fan failure.

Since when do CPUs produce noise?

Its the fan, stupid.

Well, fan selection is not AMDs task.

Wrong again.

I had the same with all my AMD CPUs, simply because
I am competent so select a quiet cooling solution.

Better if you dont have to.

Belive what you must.

You're the one believing without the evidence.

I started to reply to this point by point, but the simple fact is that you
are so far from having a clue that it would be a waste of time.

With "advocates" like you Intel doesn't need enemies.

 

[J. Clarke]

You seem to be several years behind the times.

She's stuck somewhere in the mid '80s actually.

Laptops are not basic. From the list of requirements you give it is
obvious that you do not consider them basic yourself. They are
perhaps the most demanding environment possible. And I agree thet the
Pentium M looks better than what AMD offers. But these are not for
servers or desktops. In servers and desktops, AMD has more than a
slight edge on Intel at the moment.

More to the point, Intel offers economic incentives to manufacturers who use
their processors exclusively--the lack of AMD processors in a particular
product line often has more to do with this than with any technical merits
of the respective processors. The AMD Turions look to be about on a par
with the Pentium M for power consumption however the support chips may not
be quite as good in that regard as the ones provided by Intel for their
processors.

Are you using any AMD CPUs at the moment? I have seen the difference
personally.

I doubt that she has even seen a machine with an AMD chip. She seems more
interested in "playing" people (and has admitted as much) than she is in
actually discussing the technical merits of various technologies, there
being to her way of thinking only two that _have_ technical merits.

 

[Anton Ertl]

If the cpu comes with the heatsink and fan, that eliminates
any possibility of not using an adequate heatsink and fan.

Both Intel and AMD sell CPU trays without heatsink and fan, and boxed
CPUs with heatsink and fans. If you decide on a tray CPU, don't blame
the manufacturer.

BTW, we once had problems with cooling. The CPU was an Intel Celeron
1000. The shop had mounted the heatsink the wrong way round, and it
was obvious pretty quickly that there was a problem with the machine
(don't remember what it was). Anyway, the CPU survived. So, the
overheating protection is a defense against sloppy assembly (who knows
how many people are running permanently heat-throttled CPUs because
the heatsink is mounted badly or wrongly).

And you need protection for more than just the initial config
anyway, most obviously with fan failure. Stupid to fry the
cpu if the fan fails with something like the AMD cpus that
woud fry in an instant with no fan running.

Some older AMD CPUs (AFAIK Athlon before XP) fry after a few seconds
without a heatsink. With a properly mounted heatsink, the CPU takes
much longer to warm up, and I guess even the old unprotected ones
won't fry (but they will probably fail temporarily).

When I turn on my Athlon 64 system with regulated fan, the fan does
not spin the first few minutes. I have set the spin-up temperature to
35 degrees Celsius, so you see that it takes quite a while to warm up
the heat sink (ok, it is probably much faster, if the CPU is under
load).

- anton

 

[Rita Ä Berkowitz]

Laptops are not basic. From the list of requirements you give it is
obvious that you do not consider them basic yourself. They are
perhaps the most demanding environment possible. And I agree thet the
Pentium M looks better than what AMD offers. But these are not for
servers or desktops. In servers and desktops, AMD has more than a
slight edge on Intel at the moment.

OK, I can agree with a laptop being the most demanding environment.
Unfortunately, this only proves that Intel is more capable of offering
dependable and bulletproof CPUs.

As for servers and desktops how does AMD have "more than a slight edge on
Intel" now or any other time? I'm not seeing it out in the field, at least
in the US. What country?

Are you using any AMD CPUs at the moment? I have seen the difference
personally.

No, I am not using any AMD based system, but I do have three Proliant DL385s
that I recently took in as trade sitting on the floor ready for stripping
and salvage. I reluctantly took them, but giving a $1,000 discount off of
the customer's invoice for all three wasn't too bad of a deal since they are
loaded with U320 SCSI drives in carriers. I'll throw the CPUs (matched
pairs), memory, and MBs on eBay to recoup my initial outlay and to maximize
profit. The sad part about it all is I get more for these in parts than I
would selling it whole as a refurbished unit with a warranty. That being
said, I might just have to fire one up and configure it to see what all the
hype is about and to be fair to you guys.







Rita

 

[Rita Ä Berkowitz]

More to the point, Intel offers economic incentives to manufacturers
who use their processors exclusively--the lack of AMD processors in a
particular product line often has more to do with this than with any
technical merits of the respective processors. The AMD Turions look
to be about on a par with the Pentium M for power consumption however
the support chips may not be quite as good in that regard as the ones
provided by Intel for their processors.

And you're saying AMD doesn't offer "economic incentives to manufacturers"
either? The difference for any "incentive" to be effective is to supply a
quality product that won't drag a company into the toilet. Major
manufacturers and consumers have been burned by AMD so many times that they
were forced to drop AMD from the product lineup. The day that Panasonic
exclusively adopts an AMD processor for their Toughbook line is the day
anything you say might be taken with a shred of credibility.

I doubt that she has even seen a machine with an AMD chip. She seems
more interested in "playing" people (and has admitted as much) than
she is in actually discussing the technical merits of various
technologies, there being to her way of thinking only two that _have_
technical merits.

I see you are still mad because I spanked your tender little bottom years
ago by letting you make a total fool out of yourself. Yes, I admitted to
"playing *YOU* like a Stradivarius" because your ineptness and bullshit was
beyond the threshold a human being could withstand for losing dignity. I
just could bare the thoughts of you making a total ass out of yourself in
public.

It's time for you to let these feelings of rejection and failures go and
start your journey into adulthood. I hold no hard feelings against you and
you can cry on my shoulder if it makes you feel better.







Rita

 

[Folkert Rienstra]

:

[...]

[snip]

You're the one believing without the evidence.

I started to reply to this point by point,

No evidence of that.

but the simple fact is that you are so far from having a clue

So how about informing the rest of us then.

that it would be a waste of time.

Trying to make Roddles understand something is a waste
of time, especially when he is trolling under one of his nyms.

But this is a news group, not Roddles private podium.
So make an effort and allow the rest of us to run your
arguments into the ground.

 

[Arno Wagner]

:

[...]

Rita,


I was "sort of" on your side - until you slagged off AMD
processors.

Five years ago, I would not have dreamt of using AMD processors in
a server. (Inasmuch as I would not consider using VIA CPUs in
even a games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers,
the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of
a dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel
chips into the dust where performance is concerned. And I'm
talking performance advantages to a very high degree - not just 5%
or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink, fan.
And had decent protection for when something went wrong like the
heatsink not properly mounted on the cpu or the fan stops etc.

A CPU is an engineering product, intended to be mounted by experts only.

No its not, and you need protection for fan failure anyway.

Of course it is. It is an electronics component and strictly
''experts only''.

Obviously there is not point in cointinuing this discussion.

Arno

 

[Folkert Rienstra]

:

[...]

Rita,


I was "sort of" on your side - until you slagged off AMD
processors.

Five years ago, I would not have dreamt of using AMD processors in
a server. (Inasmuch as I would not consider using VIA CPUs in
even a games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for servers,
the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal characteristics,
the prices and the Multi-CPU support. I think this is an example of
a dominatnt player (Intel) having gotten lazy.

I have near-mission-critical systems here - and I am as comfortable
using AMD as I am Intel. However, the AMD chips grind the Intel
chips into the dust where performance is concerned. And I'm
talking performance advantages to a very high degree - not just 5%
or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough experience
with AMD CPUs and botched things like heatsink selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink, fan.
And had decent protection for when something went wrong like the
heatsink not properly mounted on the cpu or the fan stops etc.
A CPU is an engineering product, intended to be mounted by experts only.

No its not, and you need protection for fan failure anyway.

Of course it is. It is an electronics component and strictly
''experts only''.

Obviously there is not point in cointinuing this discussion.

Evidently, with you completely boozed up.

 

[Sambo]

:

[...]

Rita,


I was "sort of" on your side - until you slagged off AMD
processors.

Five years ago, I would not have dreamt of using AMD processors
in a server. (Inasmuch as I would not consider using VIA CPUs in
even a games machine.)

However, AMD is absolutely, most definitely, the way to go for
practically every application on the planet. Opteron for
servers, the rest for less important machines.

I totally agree. The only thing I did not like on the Athlon XPs
was their lack of heat-spreader and thermal protection. Now that
AMD has fixed that, I think the last disadvantage of these CPUs
has gone. On the other hand the rest if the CPU architecture
is far superiour to Intel. Just look at the thermal
characteristics, the prices and the Multi-CPU support. I think
this is an example of a dominatnt player (Intel) having gotten
lazy.

I have near-mission-critical systems here - and I am as
comfortable using AMD as I am Intel. However, the AMD chips
grind the Intel chips into the dust where performance is
concerned. And I'm talking performance advantages to a very
high degree - not just 5% or so.

I think Intel never had really much going for it that would have
made it significantly more reliable than AMD. There was a time
where on the low-end PC makers did not really have enough
experience with AMD CPUs and botched things like heatsink
selection, but
that is not AMDs fault.

Yes it was, AMD should have supplied everything, cpu, heatsink,
fan. And had decent protection for when something went wrong like
the heatsink not properly mounted on the cpu or the fan stops etc.

A CPU is an engineering product, intended to be mounted by experts
only.

No its not, and you need protection for fan failure anyway.

AMD did their usual, a quick and dirty design to get it out the
door as quickly as possible and did the stuff they should have
done in the initial design later, like the protection.

AMD did offer the pre-packaged version. AMD also stated
in ther cooling documentation that an incorrect heatsink
would likely kill the CPU. There is no "wrong" way to make a
technical component like this. There are just people that
do not read or do not understand the documentation and then
blame it on others.

If the cpu comes with the heatsink and fan, that eliminates
any possibility of not using an adequate heatsink and fan.

And you need protection for more than just the initial config
anyway, most obviously with fan failure. Stupid to fry the
cpu if the fan fails with something like the AMD cpus that
woud fry in an instant with no fan running.

Personally I allways had AMD since my last Intel 486
CPU and never had reliability problems related to the CPU.

Sure, if you know what you are doing they are
usable, but with no protection at all initially.

So what? Intel 486/586 CPUs also did not have protection.

They didnt need it, the wouldnt fry.

It is not a fundamental flaw unless a
dilettante gets his hands on the component.

Yes it is, most obviously with fan failure.

The only really cool product by Intel at the moment is the Pentium
M, which ironicaly is a P-3 derivate. Seems the P-4 was really a
dead end.

Oh bullshit. The Northwoods were very decent cpus and ran a lot
quieter than the AMDs.

Since when do CPUs produce noise?

Its the fan, stupid.

I have one that was so quiet when I installed
it that I had to check that the fan was spinning it was so quiet
with the motherboard at face level with the cpu being run up for
the first time.

Well, fan selection is not AMDs task.

Wrong again.

I had the same with all my AMD CPUs, simply because
I am competent so select a quiet cooling solution.

Better if you dont have to.

As far as the SCSI / SATA debate is concerned - for anything
*really* mission-critical and especially when it is combined with
a need for performance, nothing currently matches SCSI.

However, I believe SCSI is on its way out. Partly because of
marketing hype, but also because SCSI is incredibly expensive to
set up from scratch, and the vast majority of users are scared of
these costs - to their detriment, admittedly.

I think that SCSI will be practically dead (from a supply point
of view) in well under five years.

You may be right on this one. Also with more and more people using
RAID, reliability may not be impacted too badly for systems that
are not too critical. One problem is what to do where currently
SCSI in RAID configuration is used. RAID6 or even higher
redundancy? Replicated servers? We will see. From an engineering
POV it is
not a problem working with lower reliability components, as long
as they can be combined in a way to increase redundancy _and_
as long as you are aware of the lower reliability. So SATA
is definitely not up to SCSI standards, but it can be made to
work as well in most situations.

There isnt any solid evidence that the best of the SATA
drives are any less reliable than SCSI drives individually.

Belive what you must.

You're the one believing without the evidence.

I started to reply to this point by point, but the simple fact is that
you are so far from having a clue that it would be a waste of time.

Easy to claim.