How to Speed up your Hard Disk :-) (Zak's Partition Theory)

I've tried this three times now, and it works :)

Ready?

Following on from this thread http://forums.hexus.net/showthread.p...ight=partition about how a partition is split....

I recently had the coolness of a PC upgrade so I got myself a new Western Digital AAKS 400 gig drive. And I partitioned it with 80 gig as the first partition and the rest for the second partition.

I have done this three times and tested it everytime, and I'd like to confirm that the outter edges of all platters MUST be the first partition, and it must FORCE the data out there... because the speed difference is good :)

The only way I've been able to PROVE it, (because HD Tacho sees it as one device, not as seperate partitions) is with Nero.

If you start Nero, and then ask to copy a CD, and then choose MORE and then CONFIGURE (hammer symbol) you can choose which drive to use for the CACHE and you can test all drives.

I have a Raptor 74 gig drive as C: (called XP) It has all my applications on too
I have the Western Digital 400 gig AAKS drive, and its partitioned as E: (called GAMES and has 20gig of those on) and F: (called DATA, with everything else on)

I summise that because the GAMES drive is SO near the outer edges of the platter that even with all the space already used it is STILL faster than my Raptor for a lot of stuff.

http://img48.imageshack.us/img48/956...espeedsge8.jpg
(The size is the space left, not the total)

So, if any of you guys have the same chance as I did, and can format and partition a drive to just use about 1/5 to 1/4 of the drives volume as a faster space.....please try.

I am sorely tempted to do that for XP install one day, when I have another drive to spare :)

by the way, I chose that amount of space and that drive, because it gives you virtually the same amount of space as a 74 gig Raptor for half the money and without the performance drop off as it gets "full" and you get a load of spare space left over too.

It's NOT as fast as a Raptor that's totally empty, but I'm noticing that once a Raptor is more than 1/3 full it really loses its magic. With this system it never loses it's magic cos it's all on the outter edges :) of a bigger drive.

My drive is partitioned to have one smaller (for OS) and one bigger for everything else, but since I have no NERO and no optical burning drive, can't tell anything :surrender:

Quote:

---

Originally Posted by Queelis

My drive is partitioned to have one smaller (for OS) and one bigger for everything else, but since I have no NERO and no optical burning drive, can't tell anything :surrender:

---

was it deliberate?

Can you install the same game on both partitiond and time the boot loads times and the level load times?

Interesting post.

I am contemplating attempting to speed up my drives (2x400GB) using a RAID 0 config.

Would you expect the performance benefits you're seeing, to be boosted by running 2x these 80GB partitions in RAID 0 config?

Am I reading this right. What you are doing is putting the partition at the outter edge of the platter therefore the head doesn't need to traverse too far across the disk in order to access the data. So a games drive of roughly 1/5 or 1/4 of the total disk size as the first partition will in effect be quicker than one say twice the size where the head has to travel twice as far to pick up the data.

If this is correct then I would see there is no reason why it won't benefit a RAID 0 config.

edited for crap spelling.

Interesting, my plan is to use the config I posted here: http://forums.hexus.net/showthread.php?t=115684

When i've backed everything up and read a little about RAID installs I will see what I can do/prove :P

Hmm, i'm planning on getting 2x 500Gb T166's and putting 'em in Raid 0. By this logic would that work something like this:

60GiB OS Partition
100GiB Games Partition

1: Outer Edge|30GiB Odd bits OS Partition|50GiB Odd bits Games Partition|Other crap| Inner Edge
2: Outer Edge|30GiB Even bits OS Partition|50GiB Even bits Games Partition|Other crap| Inner Edge

Aka superfast OS and Games partitions for responsive OS and fast load times, then slower area for my movies and series?

Would explain why at the moment on my current PC my OS is kinda slow and sluggish. As my OS partition is my last partition and I only have about 50GiB free space on 240Gb (2x 120Gb).

Quote:

---

Originally Posted by iranu

Am I reading this write. What you are doing is putting the partition at the outter edge of the platter therefore the head doesn't need to traverse too far across the disk in order to access the data. So a games drive of roughly 1/5 or 1/4 of the total disk size as the first partition will in effect be quicker than one say twice the size where the head has to travel twice as far to pick up the data.

If this is correct then I would see there is no reason why it won't benefit a RAID 0 config.

---

that is exacty what I think I'm getting....the first partition made ALWAYS seems to be faster and if you make it smallyou FORCE it to the outer edge :)

Or so it seems :)

I also considered maybe just creating a few small partitions on drives and RAIDING those (ignoring whats left) so see how fast they go.

When drives of varying sizes in the same product range use the same sized platters (eg. T166 400Gb, 500Gb), I assume the part that is 'disabled' is towards the centre of the platter? Just wonder if anyone knows, would be a little silly for the manufacturers to disable the fastest part of the drive for the smaller varieties -- but you never know; I mean SATA ports on enthusiast boards under the graphics card PCB, ingenius that, huh? :P.

Quote:

---

Originally Posted by Nemz0r

When drives of varying sizes in the same product range use the same sized platters (eg. T166 400Gb, 500Gb), I assume the part that is 'disabled' is towards the centre of the platter? Just wonder if anyone knows, would be a little silly for the manufacturers to disable the fastest part of the drive for the smaller varieties -- but you never know; I mean SATA ports on enthusiast boards under the graphics card PCB, ingenius that, huh? :P.

---

They don't necessary just trim the inner edge. For example they made a 250GB platter, but it got 30GB worth of sectors per platter that does not meet the required standard, the drive's firmware then is set not to use those area, and present itself as a 400GB drive instead of 500GB drive. Nowdays industry don't waste anything.

On my 500GB drive, I have 15GB OS (C:), 30GB Program/Games (D:), 30GB Download drive (E:), and the remaining 425GB for storage (F:). My 2nd 500GB drive I have a 30GB Cache drive (G:) and 470GB for storage (H:).

I did some experiment with my 4x300G drives back while, similar to above, but with the first 30GB of each drive join into a RAID0. Assume it will take over (D:) and (G:) and become (I:).

I: STR is about 140MB/s
I: to H: was about 30~45MB/s
I: to I: was about 55~60MB/s
C: to C: was about 35MB/s
D: to F: was about 30MB/s
D: to H: is however a full 75MB/s

In my opinion, depends on what you do you will have different "best" disk configuration:

Gaming:
Disk1 | RAID0 50G Games | RAID0 5G Swap | RAID1 30G OS | Simple ??G Archive
Disk2 | RAID0 50G Games | RAID0 5G Swap | RAID1 30G OS | Simple ??G Archive

Video Capturing (HDTV)
Disk1 | Simple 30G OS | Simple ??G Transcode
Disk2 | RAID0 200G Capture | Simple ??G Archive
Disk3 | RAID0 200G Capture | Simple ??G Archive (Optionally RAID5)
Disk4 | RAID0 200G Capture | Simple ??G Archive

Bittorrent Download or similar / Archiving:
Disk1 | Simple 30G OS | Simple 30GB Download | Simple ??G Archive
Disk2 | Simple 5G Swap | Simple 30GB Cache/Temporary | Simple ??G Archive
If you are archiving only, skip the swap partition, and probably the cache/temp file as well.

Making the partition smaller doesn't force it to the outside edge, it just means there's less space for things to go into therefore they're more likely to be nearer the edge. A large partition can do the same thing as long as you defragment it in a way that shunts data to the start of the partition.

The key thing is in putting all your non-performance critical stuff in a second partition out of the way, this leaves room nearer the edge for your speedy stuff.

Quote:

---

Originally Posted by kalniel

Making the partition smaller doesn't force it to the outside edge, it just means there's less space for things to go into therefore they're more likely to be nearer the edge. A large partition can do the same thing as long as you defragment it in a way that shunts data to the start of the partition.

The key thing is in putting all your non-performance critical stuff in a second partition out of the way, this leaves room nearer the edge for your speedy stuff.

---

If you are using Windows 95/98/ME I would say that is true. I find that windows explorer don't put file sequentially and my files always end up somewhere in the middle of the disk.

I could empty the whole partition, and start copying file from another hdd using single copy thread, and that partition end up with a few thousand fragments when it shouldn't have any if it was written linearly.

And if you use smaller partitions instead of a single big one, you don't need to defrag as much. The OS partition in fact rarely need any defragging since the programs aren't moving. So is your gaming partition.

Quote:

---

Originally Posted by kalniel

Making the partition smaller doesn't force it to the outside edge, it just means there's less space for things to go into therefore they're more likely to be nearer the edge.

---

no,...but making it the FIRST partiton does seem to.

ie when you have a new HDD, if you partition it, make the FIRST partiton the small one, as I said, about 1/5 of the drives volume. The rest of the sapce is up to you.

It "seems" (and I do stress seems) that the first partition created is substantially faster. The read heads move to the outisde of the disk and STAY there while you're using those files. If the partition is fragmented in any way, it is forced to be fragmented in the same zone, ie the outter edge. The outter area of the platters clearly has a faster speed in terms of inches/second, and with the heads not moving back and forth width wise much, and with the data all at the maximum velocity, it seems to work :)

I always do this when setting up my PC(s) :)

Hmmm, my setup currently has my Raptor as my boot/os drive
a 250gb as games, a 250gb as temp, a 250gb as media, 500gb as media 1 and 500gb as films..

OK: Theory...bust is apart if you so wish

New hard drive looks like this, though the platter count may vary from 1 to 4 (I guess)

http://www.zen100376.zen.co.uk/data/.../Platters2.jpg

Now, let's say 100 people across the world, with XP, all decided to partition their new drives: 1/4 and 3/4. The FIRST partition that they make is 1/4 of the size and the rest is the second. In every case the drive has 2 platters.

How does the Hard drive look? The red sections are the 1/4 of the volume.

---------------------------------------
Does it split the partiton with a WEDGE on both platters, looking like this?
http://www.zen100376.zen.co.uk/data/...itionWedge.jpg

--------------------
or
------------------

Does is partition the drive by using half of one of the platters as a SPLIT?
http://www.zen100376.zen.co.uk/data/...litPlatter.jpg

-------------------
or
-------------------

Does it use the outter RING of ONE PLATTER?
http://www.zen100376.zen.co.uk/data/...OnePlatter.jpg

-------------------
or
-------------------
Is it totally RANDOM?
http://www.zen100376.zen.co.uk/data/...plitRandom.jpg

------------------
or, as I think it does....
-----------------

Does is use the OUTER of BOTH?
http://www.zen100376.zen.co.uk/data/...Outterboth.jpg

------------------
(or
does it do it another way?)

The outter edges are not just moving faster, but for a set size will also be NARROWER than further into the platter, meaning the read heads don't need to move so far, and with the extra speed the platters are travelling at, the data speed increase is a given.


QUESTION: Does XP always do it that way? Are the HDD's themselves hardcoded to start at the outter edge? Am I just flukey, or is it a useable tool for everyone?

The internals of a disk's operation will be completely abstracted from the operating system. (edit: that is assuming the OS doesn't care about CHS/LBA addressing all that much)

All the operating system can do is address the drive. How those addresses relate to physical positions on the disk is entirely up to the manufacturer.

But this is how it will work:

Nearby addresses will be physically close to each other. The time to move something versus the time to do something electronically is huge... electronically is so much quicker.

So before moving the read/write heads, it'll swap from one platter head to another.

That makes Zak33's final image more or less the right one.

I'm now going to plug a spare SATA drive I have into a RAID controller and run some IOMeter tests on it.

Back in 20.

It'll either be the outer ring of one platter, or the very bottom drawing, but i'd be curious to know which (and indeed how or whether a utility such as partition magic could force some particular use).

Quote:

---

Originally Posted by Zak33

was it deliberate?

Can you install the same game on both partitiond and time the boot loads times and the level load times?

---

Well, yes, it was deliberate, but there are some issues.

First one the hard drive being 12gig, makes it difficult to install games :stupid:

Second, the partitions' have had their space reallocated, so that may have messed things up.

I find this quite intruiging. I'd love to know. Outter ring of one or both platters would seem the most logical. I'm gonna go googling for the answer.

If we assume that hard drive manufacturers know how to make HDDs perform at their best (and I think it's fair that they do), the bottom image would be pretty much how hard drives operate across the board. Clearly it's optimal to do concurrent reads across all the platters at once.

Reading a little more, I expect LBA-48 will be used at the lowest level of the OS. LBA addresses are arranged such that as the address increases you move through the sectors... ie around the disk. Once you've gone around you change head (onto another platter/side) and then over all the sectors again.

Once you've exhausted all that you have to move to a different cylinder... that's the bit that requires physical movement of the heads, hence why you do it less often for sequential reading :)

So yes, the last image is the 'correct' one.

Quote:

---

Originally Posted by aidanjt

If we assume that hard drive manufacturers know how to make HDDs perform at their best (and I think it's fair that they do), the bottom image would be pretty much how hard drives operate across the board. Clearly it's optimal to do concurrent reads across all the platters at once.

---

ok...well I agree, and I think its prolly right...BUT to take advantage of this, if you follow my basic sumise, and create the FIRST partition as about 1/5 to 1/4 of the drive's capacity, and use that partition for your speed related data, you will probably come outr very well.

QUESTION: Why did I spend all this time doing this?

Because I have been using a Raptor for over a year now, and I love it, but it gets slower after it's about 1/3 full, and I always need another drive for Data, films, music etc. Plus I've gone SFF and dont have rom for 4 or 5 drives. Most people use 320 or 250 gig drives as they are best value at the mo. But to have a fast boot drive is great.

So I wondered: Can a £50 hard disk perform nearly as fast as a Raptor and a spare disk? So I got a 400 gig AAKS WD drive and tried. And to be honest..it's not far short. When the Raptor has a fresh install on it, it's lightning, but it soon slows when a couple of games go in too, plus all the XP updates etc.

I have the answer!!

Quote:

---

Zone Effects: Modern hard disks use zoned bit recording to allow more data to be stored on the outer tracks of the hard disk than the inner ones. This directly impacts the media transfer rate of the disk when reading one zone of the disk as opposed to another; see here for details. Hard disks fill their space starting from the outer tracks and working inward. This means that if you split a hard disk into three partitions of equal size, the first partition will have the highest transfer rate, the second will be lower, and the third lower still. Therefore, you can put the more important files on the faster partitions if transfer performance is important to you.

---

So yes Zak you were right and actually had evidence from nero confirming it.

From Storage review. A site I had bookmarked from over 2 years ago.

Quote:

---

Originally Posted by Steve

So yes, the last image is the 'correct' one.

---

Thank you for looking and confirming :D

The next question is: Can a cheap ass drive perform better by creating this PARTITION on the outter edges, and so force the system to always have it's speed-orientated data in that fast zone?

In fact, without going mad (for which I am known, sadly) on the subect, can a cheap ass £54 drive
http://www.scan.co.uk/Products/Produ...oductID=567858

compete, daily, with a Raptor http://www.scan.co.uk/Products/Produ...oductID=410986 for £95, AND give the end user a spare 300+ gig of space?

Prolly not quite, but it's going to be a close call and it's worth helping people get the most from thier drives.

Wonder if DR can get a clear topped Raptor to watch the head action in?

OK, I've done some quick testing.

I used the IOMeter setup detailed in the second table on this page.

I setup a 20GB partition at the beginning of the disk, then a 190GB partition in the middle, and a 30GB one at the end.

This was on an old Maxtor 250GB SATA drive, 7200rpm with 16MiB cache.

I tested the two end partitions with 1GB test files in IOMeter.

Here are the results:

Code:

---

      First partition    Last partition
Read:      67.23MB/s        44.20MB/s
Write:      67.69MB/s        44.51MB/s
General:    16.86MB/s        13.46MB/s

---

The "last partition" is a third slower at sustained reading and writing. And we're not even at the end of the disk, assuming that the test file appeared towards the beginning of the 30GB partition.

For "general" performance testing, there is more randomness. That levels the playing field a little, giving a deficit of less than a fifth, because there's more physical movement to access data, slowing both cases down significantly.

So we can say the following things:

• Partitions start towards the outside of the disk and work inwards
• This is supported by what we know about LBA addressing used by disks.
• So we can assume LBA address 0 is at the very edge of the disk, on one of its platters, in one of its sectors.
• Because disks spin at a constant angular velocity, data can be transferred quicker to/from the outer edges, as they will be moving quicker over the read/write heads.
• The above is only true where ZBR (Zoned Bit Recording) is used. This puts more data in the outer sectors of a disk, because outer sectors have a bigger surface area. All disks use ZBR, unless you're using a 5.25" 4MB drive from the 80s.
• For sequential reading/writing, there can be a big performance difference between the outside and inside of a disk.

This isn't ground breaking news, because if you do an HDTach run across a full disk, a lot of the time you'll see it tail off as you get further along the disk.

Bottom line is, if you can keep your more frequently used data towards the beginning of the disk, it should read quicker.

De-fragmenting tries to do this to an extent, but controlling partition size is also a way to force the issue.

However, you should probably let the OS stay at the beginning, because some of the primitive bits of an OS that are used to do the initial boot strapping can't always see the whole disk. (There are workarounds to this, however).

edit: I should also add that if I had a Raptor to test against, it would likely massively own the Maxtor in the "General" test.

Quote:

---

Originally Posted by Steve

This isn't ground breaking news, because if you do an HDTach run across a full disk, a lot of the time you'll see it tail off as you get further along the disk.

Bottom line is, if you can keep your more frequently used data towards the beginning of the disk, it should read quicker.

De-fragmenting tries to do this to an extent, but controlling partition size is also a way to force the issue.

---

True, in fact years ago Norton had a Utility for Win98 to move the SwapFile to the outter edge. I'm deliberately creating the partition for both reasons.....rotational speed AND to stop the read heads needing to move laterally, which should ALSO keep the fragmentation down :)


Thanks for researching bud. Mine is all sumise and trial and error. So thankyou for puting it into context :)

This is nothing new really, UNIX admins have been using partitioning strategies for decades, on optimal linux servers, /boot, swap, and root are regularly the first partitions, followed by /var, then /usr/misc., then /home, for the same reasons outlined here. :)

So let's hammer out partition strategy, shall we?

How big does your XP partition need to be?

Mine is 50GB but I reckon 25GB would be fine if I was more prudent with my housekeeping. The OS and applications will be their usual responsive self.

Next, have a partition appropriately sized for games. This could be quite big if you have a lot of games... many take up a hell of a lot of space these days.

Then, use the rest for stuff that doesn't need rapid access. Movies, music, backups... none really depend on speed, stick em at the end :)

And aidanjt is right, *nix users love their partitions.

Quote:

---

Originally Posted by Steve

So let's hammer out partition strategy, shall we?

How big does your XP partition need to be?

Mine is 50GB but I reckon 25GB would be fine if I was more prudent with my housekeeping. The OS and applications will be their usual responsive self.

Next, have a partition appropriately sized for games. This could be quite big if you have a lot of games... many take up a hell of a lot of space these days.

---

nope. Not quite. Most people have 2 HDD's not one.

Have XP on the small fast partition of one, but keep it a sensible size so that other apps, such as PaintShop Pro, Office, Skype etc open like lightning. Use the rest of that drive for data, films

Have the second drive partitioned as well, and use the fast one for games, making it big enough to never run out of space. Use the rest for data, films etc.

Get clever and store stuff on one drive that will be acessed by the other drive..ie movies on the large patition and the movie player on the small partition on the other drive :)

Or am I being anal? ;)

Sounds good, but movie player/movies will make no difference.

Image/movie editor vs. scratch disk will though. As will page file :)

(now I'm being anal)

good thinking :)

I don't think it's anal it's just good practice. I'm currently trying to organise and delete all my crap and back up onto an external hard drive. Then I'm gonna do a windows reinstall (18 months old). Is it better to do the 2 drive system as above or Raid 0 like this;

2x 160gb disks

Part 1. 15- 20gb for OS and small applications eg FF,.
Part 2. Games
Part 3 Storage/data

NB: I used to use raid 0 and so I know about the backing up :)

Is it possible, and is there any mileage from taking two disks and making, say, 3 identically sized partitions of each and then making three RAID0 sets, or two RAID0 sets and 2 unraided, or RAID1, data partitions?

Quote:

---

Originally Posted by Thorsson

Is it possible, and is there any mileage from taking two disks and making, say, 3 identically sized partitions of each and then making three RAID0 sets, or two RAID0 sets and 2 unraided, or RAID1, data partitions?

---

I thought that too...and if it's possible....then it would be laser fast :)

Would this theory work on 5400 rpm laptop hard drives ? I was going to reinstall XP on my laptop and I was going to partition it anyway to keep my moves and stuff (which are changed frequently) on one and the OS in the other to reduce fragmentation and stuff. Its only a 120gb hdd.

It would be the same principle.

Very nice thread. Am currently working out what can be sent to an external drive, and (maybe) by the weekend will be ready for a full wipe & re-install. I've been putting it off for 6 months already, as i 've never had a windows OS stay up & running for more than 18 months before and this XP install is about 2 years now, but am getting some random wierdness (icons missing in bottom right etc).

Quote:

---

Originally Posted by MSIC

Very nice thread. Am currently working out what can be sent to an external drive, and (maybe) by the weekend will be ready for a full wipe & re-install. I've been putting it off for 6 months already, as i 've never had a windows OS stay up & running for more than 18 months before and this XP install is about 2 years now, but am getting some random wierdness (icons missing in bottom right etc).

---

thanks bud. I have got a bit of a thing going on with storage recently.....Josh fron HEXUS always had, and I've kinda caught it.

Steve was very kind to aid with his proper technical knoweldge and ability to find stuff too.

Quote:

---

Originally Posted by DougMcDonald

Interesting, my plan is to use the config I posted here: http://forums.hexus.net/showthread.php?t=115684

When i've backed everything up and read a little about RAID installs I will see what I can do/prove :P

---

YES

As explained in that thread - if you create your OS RAID 0 partition as the first volume in the array - it will use the outer cylinders (as per the first rule of partitioning) and therefore be faster.

I wonder how fragmentation will affect the speed increase? If the speed increase really is significant in practice, then to keep that speed increase the disk will need frequent defragging.

Quote:

---

Originally Posted by MSIC

It'll either be the outer ring of one platter, or the very bottom drawing, but i'd be curious to know which (and indeed how or whether a utility such as partition magic could force some particular use).

---

It is the bottom drawing. The partitions are created from the outer cylinders (vertical tracks on all platters) working inwards, and performance will generally get slower with each partition created - with a marked difference between the first and last. Rule of thumb is that is you want the fastest accross the board performance from the first partition is to make it no more than 28-33% of the total volume size (HD Tune can help determin this). 25% will always be good.

Fragmentation is still an issue and you still need to defrag regularly to maintain perfomance - keeps head seeking down when reading contiguous data and you should arrange tha stuff you want fastest on the outer cylinders when defragging (not possible with built in defrag tools).

Quote:

---

Originally Posted by peterb

I wonder how fragmentation will affect the speed increase? If the speed increase really is significant in practice, then to keep that speed increase the disk will need frequent defragging.

---

Fragmention will still be a problem, it just wont be as much of a chronic problem as it would be with one uber-partition that you get with default windows installs. Instead of defragging every week or whatnot, you can just do it with your regular filesystem cleanups.

Imagine how much fun you could have working out how to create partitions if you had a JBOD array :D

Over on bit-tech forums there is a huge thread about multipartitioning and backups and restores. The instruction were done zapwizard I think. Threads a year or older, but it had all the info on how to edit registry entries to move directories such as program files and my documents to where you wanted them to be etc.

There was also a method for reinstalling just windows within minutes and getting back all the documents as they were etc.

Quote:

---

Originally Posted by Steve

Imagine how much fun you could have working out how to create partitions if you had a JBOD array :D

---

LOL - Don't give him ideas now Steve.

Here's the guide from ZapWizard ... Its based on Win2K, but should apply just fine to XP.

http://www.zapwizard.com/Guides/Partitioning/index.html

Using that in addition to planning the partition order should help us all get cleaner, more responsive systems.

Having a partition only for my downloads would really help I think, because almost nothing else changes on my PC once setup. Very few random program installs (I use Altiris SVS anyway) and not too many new documents and such. I will just have to get used to getting to it through another link than the My Documents and clicking on the folder.

^ I do a very similar thing to that at the moment but without a seperate partition for settings. XP has been fine for 18 months with very little defraging required.

edited for clarity.

Quote:

---

Originally Posted by Sinizter

Here's the guide from ZapWizard ... Its based on Win2K, but should apply just fine to XP.

http://www.zapwizard.com/Guides/Partitioning/index.html

---

Ooh, that looks cool...I might give that a shot sometime, see how it goes, thanks :)

that's a good addition.... cheers :)

Quote:

---

Originally Posted by kidzer

Ooh, that looks cool...I might give that a shot sometime, see how it goes, thanks :)

---

++ It would be nice if Microsoft made Windows support this multi-partitioning schema without hacking up the registry.

Quote:

---

Originally Posted by aidanjt

++ It would be nice if Microsoft made Windows support this multi-partitioning schema without hacking up the registry.

---

That is probably worthwhile if you are not running out of drive letters on all desktops like me.

Quote:

---

Originally Posted by arthurleung

That is probably worthwhile if you are not running out of drive letters on all desktops like me.

---

looking at your Sig, with pc specs in, that IS a lot of letters!

I thought I was greedy on the disk space front...

Lol i thought i was greedy too..(goes off to count his gigabytes). I might try this partitioning system on my next install.

pls do....mnes doing well :)

Drive C, E, G and H are WDAAKS 500gig. Drive S is Maxtor dont know which one. Drive T is Hitachi Deskstar. Windows Vista give HDD transfer speed a 5.8.


http://img219.imageshack.us/img219/6240/hddvu4.jpg

Are these number any good?

Well, the C drive certainly proves the theory works quite well, as that's your first partition and it's faster than the others :)

G interests me.....was that un formatted?

What's good tool to test the disk performance? I don't really want to install Nero as I have no other need for it.

HD Tach, SiSandra? (not used that in a while).

Quote:

---

Originally Posted by Zak33

Well, the C drive certainly proves the theory works quite well, as that's your first partition and it's faster than the others :)

G interests me.....was that un formatted?

---

G is what was left over from the initial partition which is drive C. So i partitioned the 500GB HDD to a 100GB partition, C, and then G was the 365GB left over. I then took about 28GB and 2GB from the 365GB for Vista.

some high-end storage systems (i.e. ours) use this theory in practice - the entire system is made from 7200rpm sata disks, but it exceeds fibre-channel performance by using platter edges for "high priority" data

bump.
This thread should be stickied.

-Gobbob

Quote:

---

Originally Posted by Zak33

OK: Theory...bust is apart if you so wish

New hard drive looks like this, though the platter count may vary from 1 to 4 (I guess)

http://www.zen100376.zen.co.uk/data/.../Platters2.jpg

Now, let's say 100 people across the world, with XP, all decided to partition their new drives: 1/4 and 3/4. The FIRST partition that they make is 1/4 of the size and the rest is the second. In every case the drive has 2 platters.

How does the Hard drive look? The red sections are the 1/4 of the volume.

---------------------------------------
Does it split the partiton with a WEDGE on both platters, looking like this?
http://www.zen100376.zen.co.uk/data/...itionWedge.jpg

--------------------
or
------------------

Does is partition the drive by using half of one of the platters as a SPLIT?
http://www.zen100376.zen.co.uk/data/...litPlatter.jpg

-------------------
or
-------------------

Does it use the outter RING of ONE PLATTER?
http://www.zen100376.zen.co.uk/data/...OnePlatter.jpg

-------------------
or
-------------------
Is it totally RANDOM?
http://www.zen100376.zen.co.uk/data/...plitRandom.jpg

------------------
or, as I think it does....
-----------------

Does is use the OUTER of BOTH?
http://www.zen100376.zen.co.uk/data/...Outterboth.jpg

------------------
(or
does it do it another way?)

The outter edges are not just moving faster, but for a set size will also be NARROWER than further into the platter, meaning the read heads don't need to move so far, and with the extra speed the platters are travelling at, the data speed increase is a given.


QUESTION: Does XP always do it that way? Are the HDD's themselves hardcoded to start at the outter edge? Am I just flukey, or is it a useable tool for everyone?

---

My question if you don't mind.

If it works like we all think it does (ie the bottom one) does that mean that single platter drives should be slower?

I base this on (my crazy thoughts) the fact that a multi-platter drive is effectively RAID0 in one chassis - writing to more than one platter at the same time.

But, as far as I inderstand, single platter drives are just as fast as their larger multi-platter cousins.......... :confused: :help:

platter density

the more dense a platter, the more data can be written in a single spin

Quote:

---

Originally Posted by F1ZZY

My question if you don't mind.

If it works like we all think it does (ie the bottom one) does that mean that single platter drives should be slower?

I base this on (my crazy thoughts) the fact that a multi-platter drive is effectively RAID0 in one chassis - writing to more than one platter at the same time.

But, as far as I inderstand, single platter drives are just as fast as their larger multi-platter cousins.......... :confused: :help:

---

Single platter drive when compared to a multi-platter drive of a similar size will obviously have a higher platter density. More data per unit that the head has to travel.

I was comparing, say, a 250G single platter vs 750G on 3 platters (ie same density)

single head vs 3 heads writing the same data.

would the larger one be quicker (working as if 3 single platter drives in raid0)?

I thought Diskeeper (the over priced disk defrag software) moved files to the fastest area of the HDD by monitoring file usage and putting the most used data on the outer edge. So where is the open source free software that does this? Whatever game you happen to be playing migrates to the outer edge and loads faster. Partitions are not needed if the software does what it says on the tin.

I am going to be getting a new hybrid hard drive for my laptop just before I upgrade to Vista. Going to be partitioning it and I hope that the first one will be the fastest.

The only problem I have with this theory is that you don't actually know where the data is written to on the disk. the disk controller may report the logical blocks, but the actual sectors it writes to can be anywhere on the disk - the number of sectors per track can vary, and really it doesn't have to have a 512 byte sector layout at all (although I think they do). Certainly as the drive ages, the sectors won't be contiguous - as one starts to fail (with internal read/write error) - let us say sector 25 - the controller will map it out and allocate one of the spare sectors (which could be anywhere o the disk) as a replacement 25 - and that sector could be anywhere on the physical disk surface - just appearing as logical sector 25.

Each mfr will have their own algorithm for maximising access speed across the whole disk surface. That said, from tests Zak did, it seems to work, although I would expect the effect to diminish over time as various sectors fail and are replaced from the bank of spares. Although in practice I would expect teh bank of spares to be distributed across the disk surface to minimize head travel.

Conventional method = 1 drive for os and apps and 1 or more drives for storage.
BUT
With this partition method (for a gamer) you would have the 1st part of one physical disk for OS and the 1st part of another disk for games.....correct?

Where would you put the swap file if only 2 physical disks? Better to be on the games HDD or the OS HDD?

i didn't know you can have that much control about partitioning, i mean would the 1st partition always be on the outside or do you use a program that somehow allows you to specify where the partition goes?

i really need a disk upgrade, 250gb usually with 7-10% free! i know, silly!

Quote:

---

Originally Posted by F1ZZY

I was comparing, say, a 250G single platter vs 750G on 3 platters (ie same density)

single head vs 3 heads writing the same data.

would the larger one be quicker (working as if 3 single platter drives in raid0)?

---

I don't think they'd work as striped data (RAID 0), however it will still be unnoticeably quicker due to the fact that more of the data is on the outer tracks.

Quote:

---

Originally Posted by freddie

i didn't know you can have that much control about partitioning, i mean would the 1st partition always be on the outside or do you use a program that somehow allows you to specify where the partition goes?

---

Partitions move from outer to inner so the 1st partition is always on the outside.

Quote:

---

Originally Posted by kalniel

I don't think they'd work as striped data (RAID 0), however it will still be unnoticeably quicker due to the fact that more of the data is on the outer tracks.

---

Sorry for using the RAID term, but it was just to demonstrate the fact that it could feasibly write using both heads simultaneously, possible ; no?

I appreciate the outer disk edge thing but surely being able to write to 2 heads on 2 platters should be faster than 1 head on 1 platter.

Comparing speed data from different disks using a varying amount of same sized platters, it looks like they cannot write simultaneously in a striped (raid 0) fashion.....strange..!!:ill:

Anyone know which 5400rpm 2.5" SATA laptop hard drive has the highest data density that is available right now ?

Want to upgrade my laptop
1 - 4GB of RAM (if its cheap enough - like the Play.com Kingston memory)
2 - Drive with the highest data density and use its first partition for the OS.
3 - Expresscard SSD device to add 4gb of readyboost ... Any additional space (over 4gb) will be used to temporary file storage - to keep whatever media I want to watch on the train.

I am hoping this will have a favourable impact on performance as well as battery life.

Not wanting to throw the thread too off topic, but adding dense RAM to laptops generally saps battery life.

Quote:

---

Originally Posted by F1ZZY

I appreciate the outer disk edge thing but surely being able to write to 2 heads on 2 platters should be faster than 1 head on 1 platter.

Comparing speed data from different disks using a varying amount of same sized platters, it looks like they cannot write simultaneously in a striped (raid 0) fashion.....strange..!!:ill:

---

Well this intrigues me too.

I thought two platters, two head readers...bound to be faster. But nope...not so far for me. Single platter drives (which I guess are denser if we compare max disk capacity as being similar) seem faster.

RAID 0 isn't for access times, its for sustained speed. Unless you're doing something that would benefit from sustained higher speed, you won't notice the difference.

Copy a few gig of files off RAID 0 and compare it to a non RAID 0 system.

so all in all if i get another 500gb hdd, make the first partition 100gb and install OS and some games in their? that will make it faster then a raptor?

Having correctly aligned partitions is also important , but thats more of a SAN/Virtual Disk thing :)

Quote:

---

Originally Posted by Moby-Dick

Having correctly aligned partitions is also important , but thats more of a SAN/Virtual Disk thing :)

---

hehe what do you mean?

allighing the partition blocks with a RAID stripe essentially.

Disk performance may be slower than expected when you use multiple disks in Windows Server 2003, in Windows XP, and in Windows 2000

Quote:

---

Originally Posted by j.o.s.h.1408

so all in all if i get another 500gb hdd, make the first partition 100gb and install OS and some games in their? that will make it faster then a raptor?

---

if you forget RAID and just use the drive partition, and MAKE SURE ITS THE FIRST PARTITION YOU MAKE, it will be similar to a Raptor for the first stuf (OS install etc) and as it becomes more "full" it'll not slow down in the same way a Raptor does :) as yu'll never get anywhere near the inner parts of the platter. Those willbe the other 400 gig of drive for your data/films/music/photo's etc

Well...that's my experience so far :)

Quote:

---

Originally Posted by Steve

Not wanting to throw the thread too off topic, but adding dense RAM to laptops generally saps battery life.

---

Any links or more info ? Not something I was aware of.

Quote:

---

Originally Posted by Zak33

if you forget RAID and just use the drive partition, and MAKE SURE ITS THE FIRST PARTITION YOU MAKE, it will be similar to a Raptor for the first stuf (OS install etc) and as it becomes more "full" it'll not slow down in the same way a Raptor does :) as yu'll never get anywhere near the inner parts of the platter. Those willbe the other 400 gig of drive for your data/films/music/photo's etc

Well...that's my experience so far :)

---

ahh i see so there realy is not a reason to shell out so much money on a raptor hdd. i'l give this a go when i buy a second hdd and see if it works. so is the first partition ALWAYS the stuff that goes in the outside of the platter?

Quote:

---

Originally Posted by Zak33

Well this intrigues me too.

I thought two platters, two head readers...bound to be faster. But nope...not so far for me. Single platter drives (which I guess are denser if we compare max disk capacity as being similar) seem faster.

---

Yeah, it is a bit wierd. Number of platters makes little difference to read speeds if the data density is the same per platter.

The density itself seems to have a huge impact on read speeds though.

A sweet OS drive will be those samsung 333Gb single platter drives when they materialise (same as the 1Tb F1 drives but without the pricetag, I hope)

Quote:

---

Originally Posted by F1ZZY

A sweet OS drive will be those samsung 333Gb single platter drives when they materialise (same as the 1Tb F1 drives but without the pricetag, I hope)

---

when and where?

That intrigues me

The Seagate 160 gig drives have been sinlge platters and they are damn fast.

HEXUS.net - Headline :: Samsung launch new 1TB Spinpoint drive : Page - 1/1

:)

It's worth noting that only the 1TB F1 is on 333GB Platters. The 750GB version is said to be 3x250GB. Western Digital has also announced 320GB platters, and and I am one of many who are waiting to see who will first release the first 640GB drive (2 platter).

its for this reason why i have my 2nd partition as Photoshop Scratch :)

Quote:

---

Originally Posted by masscrazy

Drive C, E, G and H are WDAAKS 500gig. Drive S is Maxtor dont know which one. Drive T is Hitachi Deskstar. Windows Vista give HDD transfer speed a 5.8.


http://img219.imageshack.us/img219/6240/hddvu4.jpg

Are these number any good?

---

Hi, just a quick note. i have 2 pata hdd's and one sata 32mb catch 7200.11 seagate 500gb hdd. with this sata hdd i just made one partition for it and use it has a media files hdd. when i fired up nero just a min ago it indicated that the speed of this hdd is a whopping 95k+ whilist my others are around 40!

edit: im also runing my sata hdd on sata1 speed not the ful sata2 speeds that this drive can take because of my mobo.

here we go i got a pic of it :) the low speed hdd you see below is my usb connected one.

http://img.photobucket.com/albums/v7...nicespeeds.jpg

Barracuda SATA drive's are fast....always have been. But pls bear in mind while Nero is good....it's not infallible and it's only a guide to speed.

However....if you partitioned that drive to use about 80gig of it (first partition) for the OS, you'd have a lightning fast boot drive...

what would be a better tool to check my river speeeds? so roughly my barracuda sata drive is around 80-90 then?

This is a good read for those more interested in partitioning strategy

Morning all. just a quick question. i've ordered a 250gb hdd for my laptop and was wondering if this Theory works on laptop hdd's? if so do i simply create two partitions? first one being the actual OS partition?

All mechanical disks should have a similar addressing system, so yes.

Is this really worth doing?
I have a 500GB WD AAKS that should arrive tomorrow...

on a 250gb drive. how much space should the first partition(OS) be?