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

[F1ZZY]

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)



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?


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

Does is partition the drive by using half of one of the platters as a SPLIT?


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

Does it use the outter RING of ONE PLATTER?


-------------------
or
-------------------
Is it totally RANDOM?


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

Does is use the OUTER of BOTH?


------------------
(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..........

[directhex]

platter density

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

[Sinizter]

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..........

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.

[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)?

[ed^chigliak]

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.

[Sinizter]

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.

[peterb]

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.

[F1ZZY]

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?

[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?

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

[kalniel]

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.

[iranu]

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.

[F1ZZY]

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..!!

[Sinizter]

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.

[Steve]

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

[Zak33]

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..!!

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.

[Agent]

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.