WD6400AAKS faster than Raptor?

WD6400AAKS faster than Raptor?

http://forums.slickdeals.net/showpos...5&postcount=71

It looks right but is it true?

This I would like to see proven with real numbers and not theoretical.

Also seek times by his numbers are still slower at 6.6 vs. 4.6.

What happens when you partition a Raptor then?. It will probably blow his numbers away.

I don't think its linear... I know it doesn't work in practice. I am using 10% of my raptors in the first slice and getting 5.6ms. According to his calcs I should be getting 3.4ms.

i highly doubt a 7.2k rpm hdd will *ever* have the access time of a 10k rpm hdd - & thats will all this tricky partitioning wizardry out of the pic too... my 2 cents

I would like to "shortstroke" my 4 raptors in raid. How does one correctly shortstroke? I've tried creating partitions through windows but that does not reduce my access times. can someone help me and others who are also wondering. :shrug:

np doubting Thomas's :rofl:

I'll post some benchies in a few days or so when I get this rig built.


EBL

Quote:

---

Originally Posted by One_Hertz

I don't think its linear... I know it doesn't work in practice. I am using 10% of my raptors in the first slice and getting 5.6ms. According to his calcs I should be getting 3.4ms.

---

Of course you would not be getting 3.4ms. the Raptor's Rotational Latency
alone is 3ms, and there is a limit to how low you can shave Seek Times.
Drive heads are mechanical devices, and as such have a limit to how fast
they can physically move.

I state as much in the above quoted thread.

EBL

Quote:

---

Originally Posted by LagunaX

This I would like to see proven with real numbers and not theoretical.

Also seek times by his numbers are still slower at 6.6 vs. 4.6.

---

Look again, closely this time.


EBL

Nobody is faster than Raptor! ;)

Quote:

---

Originally Posted by EvilBellyLint

Look again, closely this time.


EBL

---

2ms seek time :eek:
Ok, I'll wait 4 your benchies :D

Quote:

---

Originally Posted by EvilBellyLint

Of course you would not be getting 3.4ms. the Raptor's Rotational Latency
alone is 3ms, and there is a limit to how low you can shave Seek Times.
Drive heads are mechanical devices, and as such have a limit to how fast
they can physically move.

I state as much in the above quoted thread.

EBL

---

So the raptors shave off less than half their seek time by using fastest 10% and you think your wd6400 will shave off 3/4s of your seek time by using fastest ~25%?

Optimistic just a wee bit, no?

I predict ~9ms at best

Quote:

---

Originally Posted by One_Hertz

So the raptors shave off less than half their seek time by using fastest 10% and you think your wd6400 will shave off 3/4s of your seek time by using fastest ~25%?

Optimistic just a wee bit, no?

I predict ~9ms at best

---

What will matter most is I/O per sec. I'll try to get a hold of
IOMeter or similar to test... along with HDTack/Tune just to
compare sustained throughput.

Of course I could always be optimistic as you say, but limited
initial data strongly suggests this drive will outperform the Raptor.
I'm not trying to push these new drives on anyone...lol just trying
to offer some solid alternatives to outdated technology.


peace

EBL

Edited to Add: even if your prediction of 9ms is correct,
there are factors like caching algorithms, data throughput,
etc... that determine "real world" performance, so we really
need to do some actual application testing if we want the
true full picture. Benchmarks are fun and all, but they don't
really tell the complete story.

Quote:

---

Originally Posted by EvilBellyLint

What will matter most is I/O per sec. I'll try to get a hold of
IOMeter or similar to test... along with HDTack/Tune just to
compare sustained throughput.

Of course I could always be optimistic as you say, but limited
initial data strongly suggests this drive will outperform the Raptor.
I'm not trying to push these new drives on anyone...lol just trying
to offer some solid alternatives to outdated technology.


peace

EBL

Edited to Add: even if your prediction of 9ms is correct,
there are factors like caching algorithms, data throughput,
etc... that determine "real world" performance, so we really
need to do some actual application testing if we want the
true full picture. Benchmarks are fun and all, but they don't
really tell the complete story.

---

Yep IOPS will be the best measure. We will see, too difficult to make any real calls right now... I don't believe it will beat the raptor, but that is just a guess...

There are actually a number of issues in the theory posted. Some for, some against. Most prominently:

1. The WD drive uses multiple platters. It is not all a straight seek, there is also an electrical shift from one platter to another, which will actually boost speeds (searching near the edge of a second platter versus searching towards the center of the first).

2. You cannot possibly assume that you can multiply the average seek time by .234 to obtain an adjusted seek time... it just doesn't work that way. The average full-stroke seek time of a 7200rpm drive is ~21ms - at closest approximation, that's what you should have looked at (versus ~10ms for the Raptor).

Now with this all said, I do believe it's likely possible to beat a raptor in IO performance thanks to the significantly faster sequential read speeds offered by current 7200rpm drives... but the fact is that the a good portion of the raptor must necessarily be faster than much of the 7200rpm drive.. now, exactly where - if ever - a crossover occurs, I cannot say for sure. I do know however that as a general rule I try not to fill a partition to the point where I would have to find out (excepting mass storage drives that I don't care about speed with).

I think you won't have much problem with over-filling a 100-150GB
partition on the WD6400AAKS if you only place tose applications
that must reside on the OS drive there, and isolate all others on
another drive.


EBL

lol the only way to take full advantage of lower ms and increased MB/s is not to use the castrated storage

create partition @ 10% 20% whatever% and thats it..

Generally 7.2 k RPM Hdd - 3.5" plates
Raptors 10 k RPM - 2.5" plates - seek will be allways lower
because it spins faster and the head needs to do less movement to "find data"

Generalized a lot
Never HHD's can overburst rate raptors maybe overspeed it
But Raptors are Raptors , and Raptors in Raid 0 are destroyers (:

Btw i hate partitions, just get a customizable defragmenter and order him to put data on the "fastest line" that's all

Quote:

---

Originally Posted by Kondik

Generally 7.2 k RPM Hdd - 3.5" plates
Raptors 10 k RPM - 2.5" plates - seek will be allways lower
because it spins faster and the head needs to do less movement to "find data"

---

i doubt raptors have 2.5" plates...

Quote:

---

Originally Posted by tiro_uspsss

i doubt raptors have 2.5" plates...

---

correct. They do not.


EBL

I broke out the MS paint to make a graphical representation of what you should expect.

The raptor (red) will start off with the best access times, and those will degrade as you reach the end point of the disc.

The 7200rpm drive (be it WD or, better, Samsung F1) will start with worse access times and although they will degrade as well, they will degrade at a lesser rate than those of the raptor because the portion of physical disc they travel over is smaller.

What EBL seems to be stating is that the 7200rpm drive will be always faster, and that is not true. The questions that will have to be answered are (referencing the attachment):
1. Does the raptor ever fall below the access time of the 7200 rpm drive (I would say probably yes)
2. How large is "X"?
3. Where is the endpoint of "Y"?
4. How large is "Z"?

For example, if the crossover (assuming there is one) occurs at 149GB, then you're most likely better off with the raptor if you're looking for access times. The crossover could alternatively be around 1GB though, and that would make the raptor silly. However, given that the raptors performance does have to degrade notably before even the outermost track of a 7200rpm drive is its equal, I would suggest that "Y" is most likely to be a value of such size that if you're only using it for your OS and a few apps, they would probably all fit within the zone and a raptor would be best for access times.

None of this is to speak of access patterns, of course... I mean, if you're only using the outermost few GB for random access and the rest is just non-speed-critical reading, then it'll be another vote for the raptor. Conversely, if the sequential read speeds offered by todays 7200rpm drives is attractive for your usage habits, then you should certainly get that drive.

Wouldn't it be possible to achieve way higher transfer speeds and access times if you combined the data density of a 1TB drive, 4 platters (is 5 possible?), only use the outer 20%, and have it spin at 10k rpm?

200GB, 115+MB/s (from 0% to 100% of the drive!) 5ms random access times? :>

Quote:

---

Originally Posted by MartinuZ

Wouldn't it be possible to achieve way higher transfer speeds and access times if you combined the data density of a 1TB drive, 4 platters (is 5 possible?), only use the outer 20%, and have it spin at 10k rpm?

200GB, 115+MB/s (from 0% to 100% of the drive!) 5ms random access times? :>

---

of course! I've always wondered why Seagate or other doesnt take just *one* dense-as-Paris platter (i think they have 320GB single platters now) & forget 10K rpm, go all the way - go 15K rpm - I mean Seagate has plenty of experience spinning HDDs that fast (SCSI range)...

single super dense platter
SATAII interface
32+ MB cache
15K rpm

= killer drive

Quote:

---

Originally Posted by tiro_uspsss

of course! I've always wondered why Seagate or other doesnt take just *one* dense-as-Paris platter (i think they have 320GB single platters now) & forget 10K rpm, go all the way - go 15K rpm - I mean Seagate has plenty of experience spinning HDDs that fast (SCSI range)...

single super dense platter
SATAII interface
32+ MB cache
15K rpm

= killer drive

---

= killer production costs and the price would have to be near what SSD are right now and it wont be able to beat SSDs regardless what they do to it.

Quote:

---

Originally Posted by One_Hertz

= killer production costs and the price would have to be near what SSD are right now and it wont be able to beat SSDs regardless what they do to it.

---

i will agree with the fact that it wouldnt beat a SSD - but production cost? puh-leez, they already make the platters left, right'n'centre (Seagates 7200.11 line-up), 32MB cache the already do in all higher end HDDs (again 7200.11), & the spindle motor :shrug: - they already have them from their SCSI line... sure it'll be an 'enthusiast' part & it'll kick the Raptor thus it'll be more expensive than Raptor - but still cheaper if compared to GB/$ re: SSD - & while this dream HDD of ours cant match a SSD in ms, it'll beat or come oh so close to MB/s (go look @ MB/s that seagate is advertising for its new 15K.6 SCSI HDDs - 160MB/s :shocked: )... the Raptor150 ATM is getting flogged of @ newegg for ~USD$170. Lets say the dream drive of urs has double the capacity (single ~300GB platter) & aforementioned specs.. what would u pay out of curiousity? me? mmm... USD$250-300...

Quote:

---

Originally Posted by tiro_uspsss

i will agree with the fact that it wouldnt beat a SSD - but production cost? puh-leez, they already make the platters left, right'n'centre (Seagates 7200.11 line-up), 32MB cache the already do in all higher end HDDs (again 7200.11), & the spindle motor :shrug: - they already have them from their SCSI line... sure it'll be an 'enthusiast' part & it'll kick the Raptor thus it'll be more expensive than Raptor - but still cheaper if compared to GB/$ re: SSD - & while this dream HDD of ours cant match a SSD in ms, it'll beat or come oh so close to MB/s (go look @ MB/s that seagate is advertising for its new 15K.6 SCSI HDDs - 160MB/s :shocked: )... the Raptor150 ATM is getting flogged of @ newegg for ~USD$170. Lets say the dream drive of urs has double the capacity (single ~300GB platter) & aforementioned specs.. what would u pay out of curiousity? me? mmm... USD$250-300...

---

They charge like what $500+ for a similar scsi part? Why 2x cheaper for sata?

Quote:

---

Originally Posted by One_Hertz

They charge like what $500+ for a similar scsi part? Why 2x cheaper for sata?

---

i'm not guessing how much it would be - i'm saying how much i would be willing to pay :up: ... besides, manufacturers always charge more for enterprise parts, u know the drill :rolleyes:

Quote:

---

Originally Posted by tiro_uspsss

i'm not guessing how much it would be - i'm saying how much i would be willing to pay :up: ... besides, manufacturers always charge more for enterprise parts, u know the drill :rolleyes:

---

Exactly... releasing something like a cheaper sata part with equal perforamnce will leave them with close to 0 enterprise sales. I don't see them doing that to themselves. Lots of servers are already beign ran on SATA hdds as it is.

Its not that they can't make a drive like this, its just that it wont be worth the effort...

Quote:

---

Originally Posted by One_Hertz

Its not that they can't make a drive like this, its just that it wont be worth the effort...

---

maybe, maybe not.. i just like dreaming :D

ps. we're a lil OT :D oops!

Quote:

---

Originally Posted by tiro_uspsss

of course! I've always wondered why Seagate or other doesnt take just *one* dense-as-Paris platter (i think they have 320GB single platters now) & forget 10K rpm, go all the way - go 15K rpm - I mean Seagate has plenty of experience spinning HDDs that fast (SCSI range)...

single super dense platter
SATAII interface
32+ MB cache
15K rpm

= killer drive

---

Why is a single platter better than using only the fastest 20% of 5 platters (or 25% of 4 platters)? Less movement for the arm, and no slower-further-into-the-disk-problems!

^Density of the data per platter?

4x 640GB @ 5% = 128GB

http://aycu22.webshots.com/image/437...7319839_rs.jpg

just a quickie.. i have yet to set the best performing settings @ bios

later ill post the 4x raptor.. ive posted several of those.. ill look for it here @ xs

i just know it takes 6x raptors to achieve that ^

http://www.xtremesystems.org/forums/...&postcount=283

That access time must be with the quiet feature turned off, correct? All the other documented access times I have seen for this drive are much higher.

Quote:

---

Originally Posted by Yukon Trooper

That access time must be with the quiet feature turned off, correct? All the other documented access times I have seen for this drive are much higher.

---

As has been stated (yet apparently, some still refuse to accept the math
behind HDD mechanics) short-stroking can DRAMATICALLY reduce seek times.

Excellent work up there, Napalm. :D :up:


EBL

Quote:

---

Originally Posted by Yukon Trooper

That access time must be with the quiet feature turned off, correct? All the other documented access times I have seen for this drive are much higher.

---

i dont have that feature @ hpt 3510 bios

are those documented access times @ true hard raid? :)


thanx EvilBellyLint

Omfg :shocked: :shocked: I hope that this "babies" will be soon available in EU :cool: I know it's not the right place to ask, but how much is the average MB/s for just one WD6400AAKS? :) Tnx, Greets!:up:

Quote:

---

Originally Posted by EvilBellyLint

correct. They do not.


EBL

---

Allright a small fixup the plates in Raptor aren't 2.5" but are definetley smaller than in 3.5" drive.

So Yes they're not 2.5" but yes, they're still smaller than 3.5's

Quote:

---

Originally Posted by EvilBellyLint

As has been stated (yet apparently, some still refuse to accept the math
behind HDD mechanics) short-stroking can DRAMATICALLY reduce seek times.

Excellent work up there, Napalm. :D :up:


EBL

---

Who refuses to accept the math? He used 5% of the drive and got 7.7, which is equal to a full raptor. By your "math" you said it will be 6.2 when using 25% of the drive. So yes your setup would give you 9-10ms and would be slower than the raptor, like I said.

@ Napalm Could you do an IOPS benchmark for both slices on the 6400s?

Yes, IOPS vs. Raptor.
Single and RAID tests, please
:D

Thanks for the testing, Napalm. Eagerly awaiting further results.

any chance that you or anyone else could post results of just 2 6400's in RAID0?

currently i have 2x150GB in raid0 and i am looking for something queit.
so far these 6400's are impressive.

thanks for the benchies!

Quote:

---

Originally Posted by One_Hertz

Who refuses to accept the math? He used 5% of the drive and got 7.7, which is equal to a full raptor. By your "math" you said it will be 6.2 when using 25% of the drive. So yes your setup would give you 9-10ms and would be slower than the raptor, like I said.

@ Napalm Could you do an IOPS benchmark for both slices on the 6400s?

---

I think you and I have different definitions of performance. I feel the
close-to-Raptor access times, plus superior throughput, firmware,
caching algorithms, and platter technology, will equate to better than
raptor performance. Are you saying it all rides on who has a millisecond
or so better access times? (not trying to be sarcastic here, serious question.)


EBL

alright guys ill post 1x 2x 3x 6400

and raptor vs 6400 iops

:up: ^much obliged, much obliged:D

Quote:

---

Originally Posted by NapalmV5

alright guys ill post 1x 2x 3x 6400

and raptor vs 6400 iops

---

Fantastic. Give us good news for the weekend!

6400 @ highpoint 3510

2x
http://aycu23.webshots.com/image/477...6391248_rs.jpg
3x
http://aycu34.webshots.com/image/461...1858560_rs.jpg
4x
http://aycu15.webshots.com/image/462...9574476_rs.jpg

1x - i cant create 1x on the hpt

benched 2x 3x several times and thats the best i can get outta the 2x and 3x

4x most efficient.. i wish i could run the 6400 on the areca 1210 but thats a no go currently


2x
http://aycu38.webshots.com/image/461...5328193_rs.jpg
3x
http://aycu18.webshots.com/image/451...4416466_rs.jpg
4x
http://aycu40.webshots.com/image/449...4757854_rs.jpg

thanks for these!
2 of those have a much higher transfer rate than my 2 raptors in raid0.
for some reason the access times on my raptors is ~9ms..

how exactly do u get benchmarks of only a certain amount of gigabytes on the drive?
my array is partitioned

when u create the array enter/input lower GB

added hd tune 2x 3x 4x ^

would u guys like 80GB raptor vs 6400 iops?

or @ 100% ?

wow those are some crazy results, lol.
it is cool seeing how they scale in performance.
thanks you very much for these results.
now i want to go get some of these and get rid of my noisy raptors, lol.

youre welocome ripken

raptor 740ADFD @ highpoint 3510

2x
http://aycu03.webshots.com/image/459...3629549_rs.jpg
3x
http://aycu20.webshots.com/image/448...9704048_rs.jpg
4x
http://aycu17.webshots.com/image/471...8575715_rs.jpg

2x
http://aycu17.webshots.com/image/471...8473676_rs.jpg
3x
http://aycu17.webshots.com/image/471...4307816_rs.jpg
4x
http://aycu09.webshots.com/image/481...0694627_rs.jpg


later iops @ equi GB

Would short-stroking still be applicable at a partition size of 150GB? Is it better to create a smaller partition?

~Ibrahim~

Quote:

---

Originally Posted by NapalmV5

4x 640GB @ 5% = 128GB

---

i've been following just vaguely the topic of this thread - so lemme get this straight; u partition -in this case ~32GB- of each of the 4 HDDs )do u get a total of 128GB partition).

What does one do with the rest of the remaining space left over on the HDDs? (the other 95%)

correct.. except for the partitioning part.. this is different its not partitioning

when i create the array @ 128GB it just uses 32GB from each drive

the other GBs were sacrificial to the performance gods :) lol


nothing.. what can u do with space that doesnt exist? lol

for actual storage id use these drives @ full but since im using them to install win/apps/games/etc whats the point of 2560GB if i dont need that much.. since 128GB is enough for me for now id rather have the much lower access time and increased MB/s

Quote:

---

Originally Posted by Kondik

Allright a small fixup the plates in Raptor aren't 2.5" but are definetley smaller than in 3.5" drive.

So Yes they're not 2.5" but yes, they're still smaller than 3.5's

---

ah, no. i'd like to know where u r getting this idea/info about the Raptors having supposedly smaller than 3.5" platters.. quite frankly, it sounds like a load of bs imo :shrug: :D

Quote:

---

Originally Posted by NapalmV5

correct.. except for the partitioning part.. this is different its not partitioning

when i create the array @ 128GB it just uses 32GB from each drive

the other GBs were sacrificial to the performance gods :) lol


nothing.. what can u do with space that doesnt exist? lol

for actual storage id use these drives @ full but since im using them to install win/apps/games/etc whats the point of 2560GB if i dont need that much.. since 128GB is enough for me for now id rather have the much lower access time

---

... so u 'waste' the other ~600GB on each HDD?? :shocked: :shocked: :shocked:

y cant u make a partition out of it & use it for something else? surely just because it is being 'used' doesnt mean that the first/'fast' partition will suffer will it? - i understand that it would suffer performance-wise *IF* a read/write occurs @ same time on diff partitions - but will it still be affected if the remaining partition is barely accessed? i cant imagine that it should be :shrug:

Napalm, any seek times for a single drive with all 640GB being used?

Quote:

---

Originally Posted by tiro_uspsss

... so u 'waste' the other ~600GB on each HDD?? :shocked: :shocked: :shocked:

y cant u make a partition out of it & use it for something else? surely just because it is being 'used' doesnt mean that the first/'fast' partition will suffer will it? - i understand that it would suffer performance-wise *IF* a read/write occurs @ same time on diff partitions - but will it still be affected if the remaining partition is barely accessed? i cant imagine that it should be :shrug:

---

Tiro, that's what I've been posting seemingly repeatedly for days, using the "waste" disk area for rarely-accessed archive data, but no-one seems to be listening. :( I guess some people just have more money than sense in the pursuit of speed... But then we can talk, using i-RAMs! :rofl:

The thing about the i-RAM of course (especially a pair of them) is it avoids this whole issue completely, since the OS/PF sits on that and you never have these sort of continual disk contention issues with OS access. Best solution all round, really, and still totally pwns everything discussed in this thread for access and streaming speed. :p:

Quote:

---

Originally Posted by IanB

Tiro, that's what I've been posting seemingly repeatedly for days, using the "waste" disk area for rarely-accessed archive data, but no-one seems to be listening. :( I guess some people just have more money than sense in the pursuit of speed... But then we can talk, using i-RAMs! :rofl:

The thing about the i-RAM of course (especially a pair of them) is it avoids this whole issue completely, since the OS/PF sits on that and you never have these sort of continual disk contention issues with OS access. Best solution all round, really, and still totally pwns everything discussed in this thread for access and streaming speed. :p:

---

yeah i agree - i have an i-ram, sure it sucks GB/$, but MB/s & ms :D:D:D

then again if u buy a 640GB HDD & use only ~30-40GB... catch my drift?

I can understand the 'reasoning' behind doing it, & if its ones cup of tea, by all means go ahead.. but me; i'm a media whore - the thought of wasting all that loooovely storage space is.. its an abmonination! :p: its criminal :D

oh why did i bother to reply..

lol u guys make it sound so dreadful by not using @ full :rofl:

but dont worry when these will be moved to the backup rigs.. will get used fully

Quote:

---

Originally Posted by Yukon Trooper

Napalm, any seek times for a single drive with all 640GB being used?

---

i can not create 1x on the hpt

i can create 1x on the areca but right now 6400 no worky on the areca

though ive used 1x (allow me to insert this: i got more money than sense.. stupendious reasoning lol :D) drive @ card and takes any hard drive to its performing limit.. onboard controllers dont

Wow at 8.4ms on raptors. Mine have 7.8... 5.6 after slicing.

Quote:

---

Originally Posted by NapalmV5

lol u guys make it sound so dreadful by not using @ full :rofl:

---

ahh yeah... lemme see if i can clarify..

the idea is that someone buys a 6400aaks cause its CHEAPER than Raptor
in return that someone gets: better MB/s & more storage (more storage for the time being)

i-ram cant be 'justified' cause its got really bad GB/$ (albiet it being the best performing RE: MB/s & ms)

right now @ newegg,
the RaptorX (150GB oem) costs: USD$175
the 6400aaks (oem) costs: USD$130

GB/$ ratio for 640, RX, i-ram:

640/130 = ~4.9
150/175 = ~0.857
4GB/~190 = ~0.02

now lets 'factor' in the slicing/partitioning one does. Lets make it a 40GB slice (so one would use 40/640 GB).

40/130 = 0.3

*if* one ends up not using the remaining partition(s), they definitely get 'ripped-off' even more than when buying a Raptor!
the ~8.5ms access time for a Raptor, is access time for the ENTIRE platter, whereas the ~7.7ms is for 40/640. As One Hertz pointed out, if u partition Raptor u can go even lower (~5.5ms). I reckon anyone doing this, would 'have' to make use of the extra space to make it well worth the $.

& while it might 'seem' like a bonus that, after one is done they can use full 640GB as actual storage, that would mean giving up a fast 'place' to hold the OS. What I mean by that is this.. last yr when I bought my Raptors, I had to 'coerce' myself to do so - I had never spent that kinda money on HDD subsystem purely for speed. But shortly after I realised: these Raptors are *ALWAYS* gonna provide me with fast storage, for this build, the next & the next. In fact they will provide me with fast storage till SSDs come waaaaay down in $$$ :D. One could buy those 6400aaks' now, have 'fast' storage - but that storage in the mean time is even more expensive than Raptor; & after using it for fast storage, they would be 'back to square one', because what are they gonna use as fast storage then? & dont say SSDs - cause they supposedly bought the 6400aaks cause they were cheap(er) in the first place.

for this idea to hold any merit (imho), one would either have to use the full capacity from 'day one' OR buy a 'storage' HDD with the best BFB RE: GB/$ - that way, one could use a partition of this HDD(s) (& have temporary more-expensive-than-raptor storage) & then down the track use it as a bfb storage drive. Otherwise they'd be getting ripped of now *&* later RE: GB/$ (they'd be getting ripped of 'later' *IF* the HDD they buy is *NOT* bfb re: GB/$) - that drive may well be the 6400aaks, but i have no idea, so get prices, do the math, think it thru...

just me thoughts/ideas... :up:

Quote:

---

Originally Posted by Yukon Trooper

Napalm, any seek times for a single drive with all 640GB being used?

---

People have been getting access Times of 12.1ms - 12.8ms, non-partitioned.
So subtracting avg. rotational latency (4.2ms) and people are getting roughly
7.9ms - 8.6ms seeks.

EBL

Quote:

---

Originally Posted by tiro_uspsss

ahh yeah... lemme see if i can clarify..

the idea is that someone buys a 6400aaks cause its CHEAPER than Raptor
in return that someone gets: better MB/s & more storage (more storage for the time being)

i-ram cant be 'justified' cause its got really bad GB/$ (albiet it being the best performing RE: MB/s & ms)

right now @ newegg,
the RaptorX (150GB oem) costs: USD$175
the 6400aaks (oem) costs: USD$130

GB/$ ratio for 640, RX, i-ram:

640/130 = ~4.9
150/175 = ~0.857
4GB/~190 = ~0.02

now lets 'factor' in the slicing/partitioning one does. Lets make it a 40GB slice (so one would use 40/640 GB).

40/130 = 0.3

*if* one ends up not using the remaining partition(s), they definitely get 'ripped-off' even more than when buying a Raptor!
the ~8.5ms access time for a Raptor, is access time for the ENTIRE platter, whereas the ~7.7ms is for 40/640. As One Hertz pointed out, if u partition Raptor u can go even lower (~5.5ms). I reckon anyone doing this, would 'have' to make use of the extra space to make it well worth the $.

& while it might 'seem' like a bonus that, after one is done they can use full 640GB as actual storage, that would mean giving up a fast 'place' to hold the OS. What I mean by that is this.. last yr when I bought my Raptors, I had to 'coerce' myself to do so - I had never spent that kinda money on HDD subsystem purely for speed. But shortly after I realised: these Raptors are *ALWAYS* gonna provide me with fast storage, for this build, the next & the next. In fact they will provide me with fast storage till SSDs come waaaaay down in $$$ :D. One could buy those 6400aaks' now, have 'fast' storage - but that storage in the mean time is even more expensive than Raptor; & after using it for fast storage, they would be 'back to square one', because what are they gonna use as fast storage then? & dont say SSDs - cause they supposedly bought the 6400aaks cause they were cheap(er) in the first place.

for this idea to hold any merit (imho), one would either have to use the full capacity from 'day one' OR buy a 'storage' HDD with the best BFB RE: GB/$ - that way, one could use a partition of this HDD(s) (& have temporary more-expensive-than-raptor storage) & then down the track use it as a bfb storage drive. Otherwise they'd be getting ripped of now *&* later RE: GB/$ (they'd be getting ripped of 'later' *IF* the HDD they buy is *NOT* bfb re: GB/$) - that drive may well be the 6400aaks, but i have no idea, so get prices, do the math, think it thru...

just me thoughts/ideas... :up:

---

The simple solution is you use short-stroke the WD6400AAKS as you stated,
use it for your OS, and the remainder of that drive gets used for off-peak
storage (data mirroring/backup.)

You won't "lose" any of that extra drive space... unless backing up data
isn't common practice.

EBL

ok i am confusde with this short stroking thing.
the only way to do it is when you build your array?

making a 20gb partition and putting your OS it is different from say shortstroking and making the array 20gb?

Quote:

---

Originally Posted by ripken204

ok i am confusde with this short stroking thing.
the only way to do it is when you build your array?

making a 20gb partition and putting your OS it is different from say shortstroking and making the array 20gb?

---

Short-stroking is indeed just another term for partitioning.
You can short-stroke a single drive (or multiple drives for
that matter) without creating an array, or you can create
a RAID partition if you do plan on an array. But the
array is by no means required or necessary.

The advantage to short-stroking a drive is two-fold. First,
when you create a partition, by default it "starts" at the
outermost sectors of your hard drive's platter/s and extends
inward. The drive heads are able to read data faster at these
outer sectors, so you increase your sustained throughput.

Second, since you are shortening the amount of physical space
your drive heads must travel in order to access data, your Seek
Times (and hence, Access Time) will be faster.

Hope this helps :up:

EBL

i know all of that, i am talking about for raid tho.
if i partition my 2 disk array to a 20gb partition, will it take the first 10gb of each disk?

and back to my question about does shortstroking=parititioning? does it matter if i do either one?

4x 6400 @ 80GB @ highpoint 3510
http://aycu31.webshots.com/image/470...0353384_rs.jpg

4x raptor @ 80GB @ highpoint 3510
http://aycu11.webshots.com/image/461...9444131_rs.jpg


ive tried to bench a single 6400 @ onboard mobo controller on several systems and none support the 6400 right now

the only controller i got that runs the 6400 is the highpoint 3510 and i cant create 1x raid0 on the hpt

WOW those results are close. Well within margin of error actually.

Edit: Just ran IOMeter as well and my 3x 74gb raptors @ 20gb on software raid beat both of your results by about 10% @ 1 Queue Depth. ~250 iops.

Very close.
Great results.
Looks like new WD truly are winners.
I bet in 6 months (cause the competition came from their own house) we'll se news on a better Raptor to tale the cake and take the premium. :)

Quote:

---

Originally Posted by One_Hertz

WOW those results are close. Well within margin of error actually.

Edit: Just ran IOMeter as well and my 3x 74gb raptors @ 20gb on software raid beat both of your results by about 10% @ 1 Queue Depth. ~250 iops.

---

so uve been comparing ur 20GB against my 80GB/full.. your iops are higher because of the cache being used.. @ real world true hard raid always wins over soft raid despite benches showing higher bursts

look guys i didnt post these benches to beat u guys up or to break records.. or to tell u guys how to partition/how to set up your hard drives.. to each his own.. since no one else.. i posted these benches so u guys can see the difference between the two.. thats all

if id wanted to brag my arse of.. 4x 640GB iodrives benches @ 3200MB/s @ 0.1ms would do.. :D

out!

@napalm
I've been checking this particular thread twice a day from the beginning, so all i can say is just continue what ur doin, dont let prehistoric dinosaur clans gets u :D

-tam2-

Quote:

---

Originally Posted by ripken204

i know all of that, i am talking about for raid tho.
if i partition my 2 disk array to a 20gb partition, will it take the first 10gb of each disk?

and back to my question about does shortstroking=parititioning? does it matter if i do either one?

---

Yes, if you partition a 2-disk array, it will utilize the first 10GB of each disk.

RAID tends to actually slow Access Times, so yes, slicing your RAID set
into a smaller partition for your OS (or Apps, whatever...) will combat this
by shaving milliseconds off your Access Times.

EBL

Quote:

---

Originally Posted by NapalmV5

so uve been comparing ur 20GB against my 80GB/full.. your iops are higher because of the cache being used.. @ real world true hard raid always wins over soft raid despite benches showing higher bursts

look guys i didnt post these benches to beat u guys up or to break records.. or to tell u guys how to partition/how to set up your hard drives.. to each his own.. since no one else.. i posted these benches so u guys can see the difference between the two.. thats all

if id wanted to brag my arse of.. 4x 640GB iodrives benches @ 3200MB/s @ 0.1ms would do.. :D

out!

---

I hear ya Bro. And I really appreciate all your work. Thanks much :cool:


EBL

Quote:

---

Originally Posted by NapalmV5

so uve been comparing ur 20GB against my 80GB/full.. your iops are higher because of the cache being used.. @ real world true hard raid always wins over soft raid despite benches showing higher bursts

look guys i didnt post these benches to beat u guys up or to break records.. or to tell u guys how to partition/how to set up your hard drives.. to each his own.. since no one else.. i posted these benches so u guys can see the difference between the two.. thats all

if id wanted to brag my arse of.. 4x 640GB iodrives benches @ 3200MB/s @ 0.1ms would do.. :D

out!

---

since when are bursts = sustained iops? I wasnt starting the u vs me thing, I was just saying there might be something wrong with your raptors as they seem quite slow in comparison to some of the other benches I've seen floating around... Just the 8+ms in hd tach and hdtune show that there is something wrong, as I have never seen above 8 on a raptor anywhere.

Thanks for the results anyways, every little bit helps.

my raptors get ~8.9ms in raid0..

Quote:

---

Originally Posted by ripken204

my raptors get ~8.9ms in raid0..

---

thats with ur onboard mobo RAID controller?

mine got 7.9ms; thats with 2x RX @ R0 : Areca1210...

ok, i'm a bit slow: in reference to what is this ms? the closest i can figure out is the 'full stroke seek' :
http://www.wdraptorx.com/en/specifications/

Quote:

---

Originally Posted by ripken204

my raptors get ~8.9ms in raid0..

---

150gb raptors are supposed to have a slightly higher response as far as I remember.

Quote:

---

Originally Posted by tiro_uspsss

thats with ur onboard mobo RAID controller?

mine got 7.9ms; thats with 2x RX @ R0 : Areca1210...

ok, i'm a bit slow: in reference to what is this ms? the closest i can figure out is the 'full stroke seek' :
http://www.wdraptorx.com/en/specifications/

---

Ugh, please tell me your not using the areca for just RAID-0 and that you just found that in some benching...

I would like to see some 4x raid0 on a P5K Premium :D

There are a lot of P5K Premium users out there let alone the P5K Series :rolleyes:

btw can you raid 6 drives on the P5K Controller? , raid0 that is......:D

Quote:

---

Originally Posted by Serra

Ugh, please tell me your not using the areca for just RAID-0 and that you just found that in some benching...

---

yeah i am using the areca just for R0, & the 'benching' are my own results from months ago

Quote:

---

Originally Posted by tiro_uspsss

ah, no. i'd like to know where u r getting this idea/info about the Raptors having supposedly smaller than 3.5" platters.. quite frankly, it sounds like a load of bs imo :shrug: :D

---

From a HW review page
Sadly it's in czech but i can translate it

http://www.zive.cz/default.aspx?article=132856

the importaint part

What makes Raptors faster than standart drives :
[Raptor při dosahování vyššího výkonu vychází z jednoduchého principu:[

Higher RPM speed utp the data search read and write
[Vyšší otáčky zrychlují vyhledávání dat a jejich čtení a zápis.]

The plate is physicaly smaller compared to 7200 rpm drives , therefore the search process is faster
[Plotna je fyzicky menší než u standardních 7200 ot./min disků, a tedy umožňuje rychlejší vyhledávání. ]
The head is faster and stronger can work with higher G's and move the electromagnet faster.
[Rameno operující s větším přetížením dokáže přesouvat elektromagnetem podstatně rychleji.]

Did i won a candy ? :yepp:

Quote:

---

Originally Posted by crackhead2k

I would like to see some 4x raid0 on a P5K Premium :D

There are a lot of P5K Premium users out there let alone the P5K Series :rolleyes:

btw can you raid 6 drives on the P5K Controller? , raid0 that is......:D

---

i'll be putting 2 of them on my P5K Premium.
do you want to throw in another 2 for me? lol

i'll have 2 of them tomorrow :)

Looks like a good "method" for those not having Raptors/SCSI U320 but having the 6400 + much extra money + the need or want for an extra PCIe controller. Personally, I've no need of either. If I wanted speed at large costs, then 2x RAID 0 Curtis HyperXCLR HXCLR-SCA10-18GB-V off Areca ARC-8060-Fibre is enough for my tastes for a few years yet, but I don't. Only really interested in feasible drive performances using normal onboard controllers but thanks for the info, it all helps. :up:

just got them up and running.
i am coming off of a raptor 150gb raid0 setup so i will let you guys know how these new drives 'feel' compared to the raptors

http://leanbulk.com/~brian/images/WD6400AAKS.jpg

ripken204

Nice results there....could you turn on write back cache from the Intel matrix software and run tests again if possible. Also, what stripe size did you go with ?

Thanks

ok, raptor 2x150gb - 64k, in situ 2x Antec MX1's external esata bracket to port 0+1 on commando mobo -

hdtach short bench, cache not cleared so not the greatest results but some sort of comparison(thats why cpu utilization hdtune so high).

even so the access time is what is important

Quote:

---

Originally Posted by bito

ripken204

Nice results there....could you turn on write back cache from the Intel matrix software and run tests again if possible. Also, what stripe size did you go with ?

Thanks

---

sure.
now look at my avg speed in hd tach, goof up?

http://leanbulk.com/~brian/images/WD6400AAKS_2.jpg

use atto disk benchmark or iometer and you will get more accurate results

also, queue depth of 8 then you will get a better idea of where the raptor excel

how about some results while actually using the drives as they were meant to be used?

making a 640 gig drive a 32 gig drive for performance is fine and all.
but I wouldnt do it.
so I dont consider these results very good so far, and rather misleading.

How abou some file copy tests in windows - just to get a feel for the drive...

i'll stick with a 7200.11 320gb :l
undt my raptors....

edit: i spose 320gb platters are wot to look out for now...:)

copying between my 640GB RAID0 and my Samsung F1 1TB averages at ~85MBps
copying a large file from my RAID0 to iteself averaged a little over 110MBps
these were measured by the numbers that vista tells me its transferring at, lol

i am definitely taking these over my raptors tho, unbelievably queit.

the raptors did seem a little faster, such as loading COD4 maps, but who really cares about being absolute #1 on the map when you need to wait for others to get in to even start a game, lol.

let me know if there are any more test you want me to do.
im not going to reformat just to see how fast a certain amount of GB is.

Is this a good drive for just a stand alone win Vista OS drive? or would a 750GB seagate be just a little better? What makes this drive so special? Sorry for my ignorance just trying to learn!

^It has only 2 very dense platters to store data. 320Gb each. And that is special at this moment in time. :)

Quote:

---

Originally Posted by ripken204

copying between my 640GB RAID0 and my Samsung F1 1TB averages at ~85MBps
copying a large file from my RAID0 to iteself averaged a little over 110MBps
these were measured by the numbers that vista tells me its transferring at, lol

i am definitely taking these over my raptors tho, unbelievably queit.

the raptors did seem a little faster, such as loading COD4 maps, but who really cares about being absolute #1 on the map when you need to wait for others to get in to even start a game, lol.

let me know if there are any more test you want me to do.
im not going to reformat just to see how fast a certain amount of GB is.

---

when your 50 or 50+, trust me you need the extra time to focus otherwise its a head-shot and your spawning again

im still one of the first on the map, just not #1, lol

Quote:

---

sure.
now look at my avg speed in hd tach, goof up?

---

=O 212mb/s add another 2 XD
not bad at all!