TheRegister about the Triple Parity in ZFS

Quicksearch

Disclaimer

The individual owning this blog works for Oracle in Germany. The opinions expressed here are his own, are not necessarily reviewed in advance by anyone but the individual author, and neither Oracle nor any other party necessarily agrees with them.

Navigation

< Butterfly 2 | Preemptive Update >

TheRegister about the Triple Parity in ZFS

Wednesday, July 29. 2009

The story about the Triple Parity finally reached the Register today - Sun tripling RAID protection. I won´t comment the articles style ("Hey, that´s old ... and all other will have it anyway soon"). I would be astonished, if they had written "Hey, Sun ... RAID-TP in a Tier-1 product ... well done". But i want to comment this article:

That has to be logically true but, if the use of 3.5-inch disks switches over to 2.5-inch drives then that would reduce failed disk rebuild times. It would also likely increase the number of drives in an array, putting us back, roughly speaking, at square one.

I don´t think that this really true, at least not at this extend. You should consider that the industry reached the 1 TB a few days ago with the Western Digital WD10TEVT. In the 3.5" world the industry is able to put 2 TB in one drive.

Now just a little thought game: The Spinpoint M6 demonstrated, that´s possible to put 3 platters into 9.5mm. Lets assume that 1 milimeter on each side is used for casing and electronics. That´s an per-platter height of 2.5 mm. The maximum height of an 2.5" is specified with 15 mm. Let´s assume 1 mm for casing and electronics again. 13 mm for disks you would be able to put 5 platters into a 15mm height 2.5" casing. Switch back to this new 1 TB 2.5" drive. It provides 333 Gigabyte per platter. Such a fat small disk would provide you with 1660 Gigabyte on 2.5" and that´s not that far away from the 2 TB we have in 3.5". Of course you would not use such a disk in a notebook (to large, to fragile for mobile, too loud), but we talk about disks for usage in the controlled environment of storage chassis.

So, dear Chris Mellor, switching from 3.5" to 2.5" isn´t a jump back to square one. At the maximum it´s a jump one square back ...

Posted by Joerg Moellenkamp in General at 16:04 | Comments (2) | Trackbacks (0)

Defined tags for this entry: storage

, sun

Related entries by tags:

View as PDF: This entry | This month | Full blog

Trackbacks

Trackback specific URI for this entry

No Trackbacks

Comments

Display comments as (Linear | Threaded)

With the consideration of adding triple parity to ZFS, consideration should be made to using every bit on those underlying drives, bypassing the hardware error correction, since ZFS is guaranteeing the integrity of the data.

#1 David (Homepage) on 2009-08-01 19:04 (Reply)

I'm not sure about this ... at first, as long there are filesystem without checksum protection, you need this protection in the drives. So drives without it, would be special ones and thus more expensive. Or it should be configurable But when i think about the mechanics of the market, this will only happen, when Windows gets such a filesystem. Additionally it's an addtional layer of data protection, so the drive doesn't send every error to the OS.

#1.1 Joerg+M. (Homepage) on 2009-08-01 19:42 (Reply)

Add Comment

Name
Email
Homepage
In reply to
Comment	E-Mail addresses will not be displayed and will only be used for E-Mail notifications. To prevent automated Bots from commentspamming, please enter the string you see in the image below in the appropriate input box. Your comment will only be submitted if the strings match. Please ensure that your browser supports and accepts cookies, or your comment cannot be verified correctly. Enter the string from the spam-prevention image above: Standard emoticons like :-) and ;-) are converted to images. Enclosing asterisks marks text as bold (word), underscore are made via _word_.
	Remember Information? Subscribe to this entry