Raptor RAID-0 array HDTach and Sandra Results

[Amused]

Is this about right?

HDTach:

2x 36.7 GB Raptors RAID-0 in the P4C800-E ICH5R

Read Speed -- maximum 95.4MB/s, minimum 37.4MB/s, average 68.7MB/s

Random Access Time 8.7ms

Read Burst Speed 116.2MB/s

CPU 4.6%

Sandra score: 64418

 

[camara120]

shouldnt the minimum read speed be higher?

 

[NFS4]

**Yawn** 🙂

This said, we must take one more moment to emphasize that sequential transfer rates are not important in most single-user and multi-user scenarios. While interesting from an academic standpoint, overuse of such "benchmarks" as SiSoft Sandra, HDTach, and ATTO PowerTools has contributed to an unwarranted fixation on transfer rates. Consider, for example, the Maxtor DiamondMax Plus 8 (not shown). The manufacturer makes no pretense as to the drive's market- the most entry-level of machines. This offering, however, delivers an outer-zone transfer rate (which is more or less the -only- thing ATTO and Sandra measure!) of 60.1 MB/sec. Those who erroneously depend on benchmarks such as these would thus draw the conclusion that the DiamondMax Plus 8 is a "faster" choice than the original Raptor, a drive which tops out at 57.4 MB/sec. In reality, the Raptor is twice as fast in typical real-world cases. Do not rely on transfer rates to judge a drive's performance.

http://www.storagereview.com/articles/200311/20031111WD740GD_2.html

Come back when you have some REAL hard drive benchies😀

 

[Amused]

Hey, I just built this damn machine and used what Benches I knew and could get quickly. Did you think I was bragging? Why would you yawn when I'm asking if my array is working up to snuff? I have no idea what are good numbers for an array like this and am asking for advice... not bragging.

Have any suggestions on another bench? How about the HDD test in PCMark02?

I got 2117 on that. Is that good?

 

[Amused]

Originally posted by: camara120
shouldnt the minimum read speed be higher?

That's what I was curious about myself.

 

[NFS4]

Originally posted by: Amused
Hey, I just built this damn machine and used what Benches I knew and could get quickly. Did you think I was bragging? Why would you yawn when I'm asking if my array is working up to snuff? I have no idea what are good numbers for an array like this and am asking for advice... not bragging.

Have any suggestions on another bench? How about the HDD test in PCMark02?

I got 2117 on that. Is that good?

I just put that b/c Sandra and the others are really useless😉

 

[1966]

Originally posted by: NFS4

Originally posted by: Amused
Hey, I just built this damn machine and used what Benches I knew and could get quickly. Did you think I was bragging? Why would you yawn when I'm asking if my array is working up to snuff? I have no idea what are good numbers for an array like this and am asking for advice... not bragging.

Have any suggestions on another bench? How about the HDD test in PCMark02?

I got 2117 on that. Is that good?

I just put that b/c Sandra and the others are really useless😉

so are your comments,how about some links to benchmarks you think are good?

 

[NFS4]

Originally posted by: 1966

Originally posted by: NFS4

Originally posted by: Amused
Hey, I just built this damn machine and used what Benches I knew and could get quickly. Did you think I was bragging? Why would you yawn when I'm asking if my array is working up to snuff? I have no idea what are good numbers for an array like this and am asking for advice... not bragging.

Have any suggestions on another bench? How about the HDD test in PCMark02?

I got 2117 on that. Is that good?

I just put that b/c Sandra and the others are really useless😉

so are your comments,how about some links to benchmarks you think are good?

I put a link in my first post. Storage Review always has the best hard drive benches.

 

[Amused]

Originally posted by: NFS4

Originally posted by: 1966

Originally posted by: NFS4

Originally posted by: Amused
Hey, I just built this damn machine and used what Benches I knew and could get quickly. Did you think I was bragging? Why would you yawn when I'm asking if my array is working up to snuff? I have no idea what are good numbers for an array like this and am asking for advice... not bragging.

Have any suggestions on another bench? How about the HDD test in PCMark02?

I got 2117 on that. Is that good?

I just put that b/c Sandra and the others are really useless😉

so are your comments,how about some links to benchmarks you think are good?

I put a link in my first post. Storage Review always has the best hard drive benches.

Any links to where I can download what you think are is the best of those tests for a desktop gaming and work machine?

 

[poppyq]

Originally posted by: Amused
Is this about right?

HDTach:

2x 36.7 GB Raptors RAID-0 in the P4C800-E ICH5R

Read Speed -- maximum 95.4MB/s, minimum 37.4MB/s, average 68.7MB/s

Random Access Time 8.7ms

Read Burst Speed 116.2MB/s

CPU 4.6%

Sandra score: 64418

Your access time may be lower than mine, but my two Maxtor DiamondMax 9's (Sata) in RAID0 have an average of 85.3MB/s clearly beating your raptors (in average read speed).

 

[Shagga]

HDTach:

2x 36.7 GB Raptors RAID-0 in the P4C800-E ICH5R (Partitioned)

Read Speed -- maximum 90.4MB/s, minimum 42.7MB/s, average 63.8MB/s

Random Access Time 8.6ms

Read Burst Speed 97.3MB/s

CPU 2.6%

Sandra 2003 Score: 51229

I'm running the exact same setup as you and get quite a bit less. Are your Raptors the old version or the new ones? If old, how the hell do I get my scores up there?

 

[ZL1]

Originally posted by: Shagga


I'm running the exact same setup as you and get quite a bit less. Are your Raptors the old version or the new ones? If old, how the hell do I get my scores up there?

about this old model/new model deal, how can you tell ? Im thinking about getting one of these and since I hear that the newer model is nicer I was wondering how to tell


Thanks
Dan

 

[Amused]

Originally posted by: Shagga
HDTach:

2x 36.7 GB Raptors RAID-0 in the P4C800-E ICH5R (Partitioned)

Read Speed -- maximum 90.4MB/s, minimum 42.7MB/s, average 63.8MB/s

Random Access Time 8.6ms

Read Burst Speed 97.3MB/s

CPU 2.6%

Sandra 2003 Score: 51229

I'm running the exact same setup as you and get quite a bit less. Are your Raptors the old version or the new ones? If old, how the hell do I get my scores up there?

Old version, I'm pretty sure.

I don't know. I didn't tweak anything. I just set it up and it ran like this. What RAID controller are you using? I'm using the Intel RAID controller and I did not install the IAA after I loaded Windows.

On the plus side, your CPU usage is half of what mine is.

 

[ZL1]

Originally posted by: Amused

Originally posted by: Shagga
HDTach:

2x 36.7 GB Raptors RAID-0 in the P4C800-E ICH5R (Partitioned)

Read Speed -- maximum 90.4MB/s, minimum 42.7MB/s, average 63.8MB/s

Random Access Time 8.6ms

Read Burst Speed 97.3MB/s

CPU 2.6%

Sandra 2003 Score: 51229

I'm running the exact same setup as you and get quite a bit less. Are your Raptors the old version or the new ones? If old, how the hell do I get my scores up there?

Old version, I'm pretty sure.

I don't know. I didn't tweak anything. I just set it up and it ran like this. What RAID controller are you using? I'm using the Intel RAID controller and I did not install the IAA after I loaded Windows.

On the plus side, your CPU usage is half of what mine is.

its most probably the controller, you got a very nice mobo
by the way did you just buy the drives ? where from ? I was going to buy mine from newegg, but Id really like the new version if I can find it


Thanks
Dan

 

[sharkeeper]

This is self explanatory

Ideal physical environment and setup = ideal maximum performance!

I'm no longer in possession of the specimen so don't ask for a HD Tach 2.70 benchmark. 🙂

Cheers!

 

[Amused]

Originally posted by: ZL1

Originally posted by: Amused

Originally posted by: Shagga
HDTach:

2x 36.7 GB Raptors RAID-0 in the P4C800-E ICH5R (Partitioned)

Read Speed -- maximum 90.4MB/s, minimum 42.7MB/s, average 63.8MB/s

Random Access Time 8.6ms

Read Burst Speed 97.3MB/s

CPU 2.6%

Sandra 2003 Score: 51229

I'm running the exact same setup as you and get quite a bit less. Are your Raptors the old version or the new ones? If old, how the hell do I get my scores up there?

Old version, I'm pretty sure.

I don't know. I didn't tweak anything. I just set it up and it ran like this. What RAID controller are you using? I'm using the Intel RAID controller and I did not install the IAA after I loaded Windows.

On the plus side, your CPU usage is half of what mine is.

its most probably the controller, you got a very nice mobo
by the way did you just buy the drives ? where from ? I was going to buy mine from newegg, but Id really like the new version if I can find it


Thanks
Dan

I got them a week ago or so. I bought them at ZipZoomFly. You can tell the new version by the seek time. The old ones are 5.2 and the new are 4.5.

 

[Amused]

Originally posted by: shuttleteam
This is self explanatory

Ideal physical environment and setup = ideal maximum performance!

I'm no longer in possession of the specimen so don't ask for a HD Tach 2.70 benchmark. 🙂

Cheers!

Care to share any tips on what the ideal setup and environment is?

 

[sharkeeper]

Care to share any tips on what the ideal setup and environment is?

Clean OS load, no fragmentation, no rogue software or drivers loaded, no unspecified parameters in hardware or software. Most importantly, no bottlenecks between the disk controller and system!

That said, system was a SuperMicro X5DAE with two 2.8 GHz Xeon CPU, 2048MB Registered ECC RAM, Dual 700W Power Supplies, 3DLabs Wildcat4 7210 display adapter, etc.

Cheers!

 

[camara120]

Are the minimum transfer rates low here due to the capabilities of the drives themselves or due to the RAID controller?

 

[GonzoDaGr8]

Originally posted by: shuttleteam

Care to share any tips on what the ideal setup and environment is?

Clean OS load, no fragmentation, no rogue software or drivers loaded, no unspecified parameters in hardware or software. Most importantly, no bottlenecks between the disk controller and system!

That said, system was a SuperMicro X5DAE with two 2.8 GHz Xeon CPU, 2048MB Registered ECC RAM, Dual 700W Power Supplies, 3DLabs Wildcat4 7210 display adapter, etc.

Cheers!

Go back and re-read Amused's posts..He just built the machine. Pretty much meaning that he has a clean OS.

 

[Amused]

Originally posted by: shuttleteam

Care to share any tips on what the ideal setup and environment is?

Clean OS load, no fragmentation, no rogue software or drivers loaded, no unspecified parameters in hardware or software. Most importantly, no bottlenecks between the disk controller and system!

That said, system was a SuperMicro X5DAE with two 2.8 GHz Xeon CPU, 2048MB Registered ECC RAM, Dual 700W Power Supplies, 3DLabs Wildcat4 7210 display adapter, etc.

Cheers!

Well, I had a clean install and no fragmentation. Just a single P4 3.2 Ghz, though. Oh, and all drivers loaded and software loaded.

Doing this on a system like that is fine and good, but what about benchmarks once your system is set up the way you will use it day to day? Isn't that what really counts?

 

[sharkeeper]

Go back and re-read Amused's posts..He just built the machine. Pretty much meaning that he has a clean OS

I did. There is an obvious bottleneck in his system as revealed by the burst reading. With the chipset we used there were no bottlenecks, hence the much higher results.

We have similar production systems getting well over 800 MB/S sustained transfers via PCI-X. (obviously not with raptors!)

The mainboard is NOT supposed to behave like this, however not all boards are created equal. There are some people getting the correct burst rates using desktop boards, however.

Doing this on a system like that is fine and good, but what about benchmarks once your system is set up the way you will use it day to day? Isn't that what really counts?

Sure it does, but you also want to reveal obvious problems before you continue. The working system posted benchmarks that are very similar, however the system is used quite heavily and you cannot expect accurate measurements with a system that is under stress such as this.

Cheers!

 

[Acanthus]

please show me one real world increase that justifies $400 worth of hard drives.

 

[Amused]

Originally posted by: Acanthus
please show me one real world increase that justifies $400 worth of hard drives.

i spent $200 on two Raptors. Not $400.

And it makes opening and closing programs snappier. It makes working with pics and videos MUCH faster and my boot time is great. And I can defreag in much less time.

I've been using RAID-0 for over 2 years now, and I can tell how slow other people's computers feel to me when they are using a single drive.

I built a machine just like my old P4 2.0 (same mobo, memory, video card, etc...) for my GF's uncle, except it had a single drive. And it really felt slower than my 4 100GB WD JBs. A lot less responsive in HD intesive tasks.

 

[Shagga]

I'm getting different figures everytime I run the benchamarks particularly with HD Tach 2.7. The access times and CPU utilisation stay the same but the burst rate etc changes quite a bit but averaging out the same.

I tried to uninstall the IAA but for what ever reason the Application won't let me. It just says I can uninstall the additional features but not the main programme. I believe the only difference really is that I'm running a P4 3.0GHz (800FSB) processor and Amused has a 3.2GHz.

Might do a clean install of XP etc and see if that works.

Originally posted by: ZL1

Originally posted by: Shagga


I'm running the exact same setup as you and get quite a bit less. Are your Raptors the old version or the new ones? If old, how the hell do I get my scores up there?

about this old model/new model deal, how can you tell ? Im thinking about getting one of these and since I hear that the newer model is nicer I was wondering how to tell


Thanks
Dan

Dan, I'm not sure. I am just aware that some new models were shipping very soon, well the 73GB version is, not sure about the "new" 36GB version. However, there is likely to be some referencing to the new version in the model number I would have guessed. Mind you when you look on WD website they show the "1st generation" Raptors only.

😉