SATA and ATA

[J. Clarke]

Agree with usually. Would be different for someone pushing really big
files around.

When I upgrade soon to SATA drives, I'm not expecting any perceptible
performance increase, though the thin cables will be nice.

Less nice when the connectors break. Note that I did not say "if".

 

[Folkert Rienstra]

SATA = Serial ATA; (P)ATA = Parallel ATA. The SATA cable is much
narrower than the PATA cable and, therefore, less likely to block
air flow in a case. The SATA cable (by spec) can be longer than
the PATA cable and, therefore, allows more freedom in placing HDs
w.r.t. the MB in a full tower case.

SATA is less sensitive to crosstalk and, probably, RFI;

But by doing so introduces other problems which then also have to be battled.

but I won't argue about whether or not those issues are of practical importance.

SATA supports one device per cable,

but not necessarily one HD per cable

while PATA supports two;

But also one.

I contend that this makes SATA better,

Nope, just different.

but others may think the opposite.

Exactly.

 

[Folkert Rienstra]

It's because the SATA standard calls for 150 or 300 as the standard
signalling rates,

while the PATA standard calls for 33, 66, 100, or 133,

And all previous modes.

 

[Folkert Rienstra]

PATA's udma-133 operates at 33MHz, which is pretty high for SE bus. SCSI
Ultra is only 20MHz.

You need LVD and 80-pin connectors to go higher.

What's with the 80-pin connectors?

 

[Folkert Rienstra]

Is that because of shielding on the serial cables? Otherwise I
can't imagine why the parallel interface would be limited.

[snipped]

The PATA interface is limited by crosstalk

Nope.

 

[Folkert Rienstra]

No, but not radically better than PATA.

His obviously is a small world.

True,
Nonsense.

but increases headroom for the future.

Is already at it's end (for 1.5 Gb) where Raid_in_a_box is concerned.

Agree that change to 300 MB/sec unnecessary.

Not for applications with multiple drives behind a mux on a single channel.

Clueless, as usual.

 

[John Doe]

Troll.

Path: newssvr19.news.prodigy.com!newsdbm06.news.prodigy.com!newsdst02.news.prodigy.com!newsmst01a.news.prodigy.com!prodigy.com!newscon06.news.prodigy.com!prodigy.net!border1.nntp.dca.giganews.com!nntp.giganews.com!green.octanews.net!news-out.octanews.net!authen.white.readfreenews.net.POSTED!not-for-mail
Reply-To: "Folkert Rienstra" <[email protected]>
From: "Folkert Rienstra" <see_reply-to myweb.nl>
Newsgroups: comp.sys.ibm.pc.hardware.storage
References: <[email protected]> <[email protected]> <[email protected]> <[email protected]>
Subject: Re: SATA and ATA
Date: Sun, 10 Apr 2005 01:19:25 +0200
MIME-Version: 1.0
Content-Type: text/plain; charset="Windows-1252"
Content-Transfer-Encoding: 7bit
X-Priority: 3
X-MSMail-Priority: Normal
X-Newsreader: Microsoft Outlook Express 6.00.2800.1437
X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1441
Lines: 20
Message-ID: <42588e2c$0$6058$892e7fe2 authen.white.readfreenews.net>
Organization: Read Free News
NNTP-Posting-Date: 09 Apr 2005 21:23:41 CDT
NNTP-Posting-Host: 14b168b3.authen.white.readfreenews.net
X-Trace: DXC=OGh2mEEiNaMlSHlB]=`R^Ab_[jUcf=dBGPH=X44`;MPI[m3>;UVXR3OjiVWP31XC\@6>oZm1@7WSHUY8[HT0[D2BdcRG[dhc8PG
X-Complaints-To: [email][email protected][/email]
Xref: newsmst01a.news.prodigy.com comp.sys.ibm.pc.hardware.storage:348675

a.h. wrote:

What technical differences are between SATA and ATA?

SATA sends data one bit at a time down a single pair and
receives it the same way, vs 8 bits in parallel for PATA. The
SATA interface has a transfer rate of 150 or 300 MB/sec vs 133
for the fastest version of PATA,

Is that because of shielding on the serial cables? Otherwise I
can't imagine why the parallel interface would be limited.

[snipped]

The PATA interface is limited by crosstalk

Nope.

 

[Eric Gisin]

What's with the 80-pin connectors?

To make ATA reach higher speeds, you could use LVD and almost twice the
connections.

Which is why they didn't go LVD, instead double data per clock.

 

[J. Clarke]

Troll.

He's just being his usual overly-pedantic self. I can see him in a college
somewhere making life Holy Hell for some poor lot of hapless students who
don't have the guts to give him a blanket party.

It's limited by the standard, not by any theoretical consideration. If
cross-talk was a hard physical limitation on parallel interfaces then U320
SCSI would not be possible.

Path:
newssvr19.news.prodigy.com!newsdbm06.news.prodigy.com!newsdst02.news.prodigy.com!newsmst01a.news.prodigy.com!prodigy.com!newscon06.news.prodigy.com!prodigy.net!border1.nntp.dca.giganews.com!nntp.giganews.com!green.octanews.net!news-out.octanews.net!authen.white.readfreenews.net.POSTED!not-for-mail
Reply-To: "Folkert Rienstra" <[email protected]> From:
"Folkert Rienstra" <see_reply-to myweb.nl> Newsgroups:
comp.sys.ibm.pc.hardware.storage References:
<[email protected]>
<[email protected]>
<[email protected]>
<[email protected]> Subject: Re: SATA and ATA Date:
Sun, 10 Apr 2005 01:19:25 +0200 MIME-Version: 1.0 Content-Type:
text/plain; charset="Windows-1252" Content-Transfer-Encoding: 7bit
X-Priority: 3 X-MSMail-Priority: Normal
X-Newsreader: Microsoft Outlook Express 6.00.2800.1437
X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1441
Lines: 20
Message-ID: <42588e2c$0$6058$892e7fe2 authen.white.readfreenews.net>
Organization: Read Free News
NNTP-Posting-Date: 09 Apr 2005 21:23:41 CDT
NNTP-Posting-Host: 14b168b3.authen.white.readfreenews.net
X-Trace:

DXC=OGh2mEEiNaMlSHlB]=`R^Ab_[jUcf=dBGPH=X44`;MPI[m3>;UVXR3OjiVWP31XC\@6>oZm1@7WSHUY
[HT0[D2BdcRG[dhc8PG[QUOTE]
X-Complaints-To: (e-mail address removed) Xref: newsmst01a.news.prodigy.com
comp.sys.ibm.pc.hardware.storage:348675

a.h. wrote:

What technical differences are between SATA and ATA?

SATA sends data one bit at a time down a single pair and
receives it the same way, vs 8 bits in parallel for PATA. The
SATA interface has a transfer rate of 150 or 300 MB/sec vs 133
for the fastest version of PATA,

Is that because of shielding on the serial cables? Otherwise I
can't imagine why the parallel interface would be limited.

[snipped]

The PATA interface is limited by crosstalk

Nope.

[/QUOTE]

 

[Odie Ferrous]

Hi, Folkert.

Thought your recent absence was down to your getting run down by a bus.

Never mind - the thought was nice while it lasted.


Odie

 

[Nick]

Yeah, the shortcut was a bit short, but ultimatly, that's the reason
why.

 

[Peter]

One can

buy 10,000 RPM drives with PATA interfaces but not with SATA.

Not true:
WD740GD
World's fastest Serial ATA drive: 10,000 RPM, 4.5 ms seek
http://www.dealtime.com/xGS-wd740gd

Data Transfer Rate (maximum)
- Buffer to Host
- Buffer to Disk 1200 MB/s max2
816 MB/s max
Average Read Seek 4.5 ms (average)
Track-to-track Seek3 0.6 ms (average)
Full Stroke Seek3 10.2 ms (average)
Average Latency 2.99 ms (nominal)
Rotational Speed 10,000 RPM
Buffer 8 MB

 

[J. Clarke]

Not true:
WD740GD
World's fastest Serial ATA drive: 10,000 RPM, 4.5 ms seek
http://www.dealtime.com/xGS-wd740gd

Data Transfer Rate (maximum)
- Buffer to Host
- Buffer to Disk 1200 MB/s max2
816 MB/s max
Average Read Seek 4.5 ms (average)
Track-to-track Seek3 0.6 ms (average)
Full Stroke Seek3 10.2 ms (average)
Average Latency 2.99 ms (nominal)
Rotational Speed 10,000 RPM
Buffer 8 MB

If I'm the one who wrote that I apologize--must not have had my coffee or
something--what I meant to write obviously was "One can buy 10,000 RPM
drives with SATA interfaces but not with PATA."

And I'm surprised that you're the only one that caught it.

 

[Rod Speed]

Yeah, the shortcut was a bit short, but ultimatly, that's the reason why.

Fraid not.

 

[David Dyer-Bennet]

Which means sequential transfers. Not random access, which is what
usually happens in the real world.

On servers, yes. On desktops, no. Transfers on my desktop tend to be
loading large executable files, reading large image files, and writing
large image files. Mostly I have enough memory so it's not swapping
very much, which would be the main source of random access.

 

[John Doe]

Yeah, the shortcut was a bit short, but ultimatly, that's the
reason why.

That sonds fishy.

 

[J. Clarke]

On servers, yes. On desktops, no. Transfers on my desktop tend to be
loading large executable files, reading large image files, and writing
large image files. Mostly I have enough memory so it's not swapping
very much, which would be the main source of random access.

And you defragment daily of course.

 

[Rod Speed]

On servers, yes. On desktops, no.

Fraid so, even on desktops.

Transfers on my desktop tend to be loading large executable
files, reading large image files, and writing large image files.

And all the usual caching of temporary internet files, etc etc etc.

Mostly I have enough memory so it's not swapping very
much, which would be the main source of random access.

Nope, its actually the net caching with desktops used for net access.

 

[Folkert Rienstra]

Not true:
WD740GD
World's fastest Serial ATA drive: 10,000 RPM, 4.5 ms seek
http://www.dealtime.com/xGS-wd740gd

Data Transfer Rate (maximum)
- Buffer to Host
- Buffer to Disk 1200 MB/s max2
816 MB/s max
Average Read Seek 4.5 ms (average)
Track-to-track Seek3 0.6 ms (average)
Full Stroke Seek3 10.2 ms (average)
Average Latency 2.99 ms (nominal)
Rotational Speed 10,000 RPM
Buffer 8 MB

'Ignore John--he's in "full of crap" mode'.

 

[Folkert Rienstra]

To make ATA reach higher speeds, you could use LVD

and almost twice the connections.

Ah, right, the D for Differential in LVD, ie putting the 40 extra
grounds in a 80 wire cable to better use for data.
Sorry, associated 80-pin with SCA connectors rather than double
density AMP/BERG headers and connectors.

Do you really need differential for going faster? I think it
really is for providing longer bus lenghts at lower signal
strengths and it's the lower signal that really provides the
better speeds. ATA doesn't really need the longer length.

Which is why they didn't go LVD, instead double data per clock.

LVD would still need double transition clocking.
LVD isn't faster by just being Low Voltage Differential.