Typical HDTach results for ATA133?

[Ohaya]

Hi,

I'm using HDTach 2.70 with a new Samsung 160GB (ATA133) drive. Device
Manager shows "Ultra DMA Mode" in the Current Transfer Mode.

It's been awhile since I've used HDTach, so I was wondering if you all
could tell me how this looks:

- Random Access Time: 15.6 msecs
- Read Burst Speed: 68.7 MB/sec
- Read speed - max 60.3MB/sec, min 3.8 MB/sec, average 50.5 MB/sec
- CPU Utilization: 36.0%

This was run under Win2K.

I have no idea what "typical" results would be, but I'm kind of
wondering about the CPU Utilization. Isn't this typically ~5%?

Thanks!

Jim

P.S. Just as a sanity check, I set the IDE channel to PIO only, and CPU
Utilization went to about 98%.

 

[S.Heenan]

Hi,

I'm using HDTach 2.70 with a new Samsung 160GB (ATA133) drive. Device
Manager shows "Ultra DMA Mode" in the Current Transfer Mode.

It's been awhile since I've used HDTach, so I was wondering if you all
could tell me how this looks:

- Random Access Time: 15.6 msecs
- Read Burst Speed: 68.7 MB/sec
- Read speed - max 60.3MB/sec, min 3.8 MB/sec, average 50.5 MB/sec
- CPU Utilization: 36.0%

- Random Access Time: 14.3 msecs
- Read Burst Speed: 76.9 MB/sec
- Read speed - max 62.7MB/sec, min 33.8 MB/sec, average 53.6 MB/sec
- CPU Utilization: 72.4%

Windows XP Pro,WD 800JB

 

[Folkert Rienstra]

- Random Access Time: 14.3 msecs
- Read Burst Speed: 76.9 MB/sec
- Read speed - max 62.7MB/sec, min 33.8 MB/sec, average 53.6 MB/sec
- CPU Utilization: 72.4%

Windows XP Pro, WD 800JB

And you think that that is OK?
Not even current 7k2 WD drives can do 60 MB/s, let alone such an old drive.

 

[Folkert Rienstra]

Hi,

I'm using HDTach 2.70 with a new Samsung 160GB (ATA133) drive. Device
Manager shows "Ultra DMA Mode" in the Current Transfer Mode.

It's been awhile since I've used HDTach, so I was wondering if you all
could tell me how this looks:

- Random Access Time: 15.6 msecs

15.6 ms would appear a bit slow

- Read Burst Speed: 68.7 MB/sec

Probably best ignored.

- Read speed - max 60.3MB/sec, min 3.8 MB/sec, average 50.5 MB/sec

There appears to be a bad spot on it with that 3.8 minimum.

- CPU Utilization: 36.0%

This was run under Win2K.

I have no idea what "typical" results would be, but I'm kind of
wondering about the CPU Utilization. Isn't this typically ~5%?

I don't know how that is measured but the bad spot may have something
to do with that too when the drive does retries.

 

[ohaya]

- Random Access Time: 14.3 msecs
- Read Burst Speed: 76.9 MB/sec
- Read speed - max 62.7MB/sec, min 33.8 MB/sec, average 53.6 MB/sec
- CPU Utilization: 72.4%

Windows XP Pro,WD 800JB

Hi,

Hmmm. So how are these reviews that I keep seeing getting CPU
Utilization in the single digits? Is it because they all use a
dedicated ATA133 controller card like the "Promise" that I keep
hearing about?

Jim

 

[Rod Speed]

Hmmm. So how are these reviews that I keep
seeing getting CPU Utilization in the single digits?
Is it because they all use a dedicated ATA133 controller
card like the "Promise" that I keep hearing about?

Nope, the better reviews spell out what hardware is used.

And you dont get anything like those cpu utes when just
using the motherboard ports on decent motherboards.

 

[Ohaya]

Nope, the better reviews spell out what hardware is used.

And you dont get anything like those cpu utes when just
using the motherboard ports on decent motherboards.

But, just out of curiousity, I ran HDTach on my work laptop (a Compaq Evo)
just for comparison. The other figures were worse than on the system with
the new ATA133 drive, but CPU utilization was something like "2%" vs. the
40%+ on the new drive.

Any ideas why this might be. I've confirmed and re-confirmed that "Ultra
DMA" is showing in Device Manager, so I'm puzzled!!!

 

[Rod Speed]

But, just out of curiousity, I ran HDTach on my work laptop (a Compaq Evo)
just for comparison. The other figures were worse than on the system with
the new ATA133 drive, but CPU utilization was something like "2%" vs. the
40%+ on the new drive.

Yeah, I dont get anything like those two previous high
ones on any of the desktop systems I've tried it on.

All of those use the motherboard IDE ports,
all with different motherboard chipsets.

Any ideas why this might be.

Dunno. Presumably the difference is in the driver.

Are you using the default XP driver for the IDE
channels or the one from the motherboard CD ?

That did make a considerable difference with the
read speed with all those systems I tried it on.

And I didnt use those max min average numbers,
I basically took an estimate of the LH side of the
chart by eye rather than a mathematical average.

I've confirmed and re-confirmed that "Ultra DMA"
is showing in Device Manager, so I'm puzzled!!!

Yeah, may just be some quirk of the driver.

 

[Ohaya]

Yeah, I dont get anything like those two previous high
ones on any of the desktop systems I've tried it on.

All of those use the motherboard IDE ports,
all with different motherboard chipsets.


Dunno. Presumably the difference is in the driver.

Are you using the default XP driver for the IDE
channels or the one from the motherboard CD ?

Sorry, I don't remember if I mentioned this, but this is a Win2K system.
Here're the basic specs:

MB: Asus A7A266
Drive: Samsung 160GB (SP1614N, I think) w/8MB cache
OS: Win2K Pro

In Device Manager, the IDE controller says "ALI something or other".

That did make a considerable difference with the
read speed with all those systems I tried it on.

And I didnt use those max min average numbers,
I basically took an estimate of the LH side of the
chart by eye rather than a mathematical average.

I don't remember whether I installed the motherboard drivers or just used
the default MS drivers. Remember this OS was installed awhile ago. I just
imaged the OS to the new drive.

Yeah, may just be some quirk of the driver.

I'm going to image the C: drive to a CD, then try to delete the IDE devices
in Device Manager and see if I can get the MS drivers to install, and then
re-run HDTach.

I'll post back.

This is really frustrating. I thought with the new drive, with the 8MB
cache, that it'd be better, so I'm disappointed so far.

 

[Richard Saunders]

Your CPU utilization looks high.

Asus A7N8X Deluxe, Athlon XP 1.8Ghz, WinXP Pro SP1

UDMA-100 WD1200JB Special Edition 8MB cache on Nvidia Nforce2 SPP/IGP
ATA Controller (onboard)
RAT: 13.1 ms
RBS: 92 MB/s
RS: max 50.4, min 28.2, ave 41.9
CPUU: 0.0%

2x WD360GD Raptor RAID-0 SATA-150 on Silicon Image Sil 3112 SATARaid
Controller (onboard)
RAT: 9.2 ms
RBS: 108.3 MB/s
RS: max 99.8, min 65.3, ave 88.7
CPUU: 0.0%

Reporting second run of HDTach 2.70. Variance between runs is < 10%.

 

[Ohaya]

Your CPU utilization looks high.

Asus A7N8X Deluxe, Athlon XP 1.8Ghz, WinXP Pro SP1

UDMA-100 WD1200JB Special Edition 8MB cache on Nvidia Nforce2 SPP/IGP
ATA Controller (onboard)
RAT: 13.1 ms
RBS: 92 MB/s
RS: max 50.4, min 28.2, ave 41.9
CPUU: 0.0%

2x WD360GD Raptor RAID-0 SATA-150 on Silicon Image Sil 3112 SATARaid
Controller (onboard)
RAT: 9.2 ms
RBS: 108.3 MB/s
RS: max 99.8, min 65.3, ave 88.7
CPUU: 0.0%

Reporting second run of HDTach 2.70. Variance between runs is < 10%.

Richard,

I agree that the CPU Utilization is high, but I also think that the Read
Burst Speed and Read Speed are low.

I did an experiment tonight, where I did a clean install of Win2K on the
system.

When I installed and ran HDTach on the clean Win2K installation, CPU
Utilization was ~14%, and Read Burst and Read Speed had gone up to about
80MB/s.

On the original Win2K installation, I can't get that low CPU Utilization and
higher RBS and RS, no matter which IDE driver I used (I've tried the default
Windows driver, ALI 2.05, and ALI 1.04 (from Asus)), all give approx. the
same results.

This is really puzzling. It almost seems like something in the original
Win2K installation is somehow interfering with the HDTach numbers, but I've
run this with most processes shut down.

Really frustrating!!!

 

[S.Heenan]

And you think that that is OK?
Not even current 7k2 WD drives can do 60 MB/s, let alone such an old
drive.

It is a 7200RPM WD 800JB. Made in December 2003. Old ?

 

[S.Heenan]

Nope, the better reviews spell out what hardware is used.

And you dont get anything like those cpu utes when just
using the motherboard ports on decent motherboards.

Regular IDE controller on an Asus A7N8X Deluxe Rev2.

 

[Folkert Rienstra]

Richard,

I agree that the CPU Utilization is high, but I also think that the Read
Burst Speed

and Read Speed are low.

No, it's not.

I did an experiment tonight, where I did a clean install of Win2K on the
system.

When I installed and ran HDTach on the clean Win2K installation, CPU
Utilization was ~14%, and Read Burst and Read Speed had gone up to about
80MB/s.

The read speed of the SpinPoint P80 SP1614N is ~62 MB/s

 

[Folkert Rienstra]

It is a 7200RPM WD 800JB. Made in December 2003. Old ?

The design is 2 years old. The 800-BB almost 3 years.
It could be the 3rd incarnation of the drive though.
But like I said, no current 7k2 WD drive can do 60 MB/s, AFAICT.

 

[Ohaya]

The design is 2 years old. The 800-BB almost 3 years.
It could be the 3rd incarnation of the drive though.
But like I said, no current 7k2 WD drive can do 60 MB/s, AFAICT.

Hi,

Ok, now I'm really confused. These are either ATA100 or ATA133 (the
Samsung) drives, right? Shouldn't the read speed theoretically be approx.
100MB/s and 133MB/s, respectively?

If the tops is ~60MB/s, then isn't that like an ATA66 drive?

Also, BTW, I don't remember if I posted it, but in testing with a clean
Win2K install and the Samsung drive, and using HDTach 2.70, I got burst read
speed of ~80MB/s.

Jim

 

[Eric Gisin]

Eric falls on floor, rolls over and dies laughing.

 

[Rod Speed]

Ok, now I'm really confused.

You are indeed.

These are either ATA100 or ATA133 (the Samsung) drives, right?
Right.

Shouldn't the read speed theoretically be approx.
100MB/s and 133MB/s, respectively?

Nope, thats just the speed the interface can do, not what
the drive itself can do. What the drive can do depends on
the rotation rate of the platters and the sectors per track.

If the tops is ~60MB/s, then isn't that like an ATA66 drive?
Nope.

Also, BTW, I don't remember if I posted it, but in testing
with a clean Win2K install and the Samsung drive, and
using HDTach 2.70, I got burst read speed of ~80MB/s.

Burst speeds are closer to the interface speed because they can
just be between the cache on the drive and the motherboard ram.

 

[Ohaya]

You are indeed.


Nope, thats just the speed the interface can do, not what
the drive itself can do. What the drive can do depends on
the rotation rate of the platters and the sectors per track.


Burst speeds are closer to the interface speed because they can
just be between the cache on the drive and the motherboard ram.

Rod,

Getting back to the original Subject of this thread then, what would you
expect the "typical" HDTach results to look like (burst read, read speed,
and utilization) for an "ATA133" drive vs. an "ATA100" drive?

Could you (or anyone else) discern the difference between an ATA133 drive
and an ATA100 drive based on HDTach results?

Jim

 

[Rod Speed]

Getting back to the original Subject of this thread then, what would you
expect the "typical" HDTach results to look like (burst read, read speed,
and utilization) for an "ATA133" drive vs. an "ATA100" drive?

Like I said, the ATA number is irrelevant. Its the physical
drive details that effect everything except the burst speed.
And the burst speed doesnt matter with modern OSs anyway.

Could you (or anyone else) discern the difference between an
ATA133 drive and an ATA100 drive based on HDTach results?

You could likely work it out to some extent from the burst
speed, but like I said, that number doesnt matter anymore.