User: Password:
|
|
Subscribe / Log in / New account

KHB: Real-world disk failure rates: surprises, surprises, and more surprises

KHB: Real-world disk failure rates: surprises, surprises, and more surprises

Posted Jun 22, 2007 11:05 UTC (Fri) by jengelh (subscriber, #33263)
Parent article: KHB: Real-world disk failure rates: surprises, surprises, and more surprises

>they found no correlation between failure rate and disk type - SCSI, SATA, or fiber channel. The most reliable disk set was composed of only SATA drives, which are commonly regarded to be less reliable than SCSI or fibre channel.

No more SCSI myths heh.


(Log in to post comments)

KHB: Real-world disk failure rates: surprises, surprises, and more surprises

Posted Jun 27, 2007 15:13 UTC (Wed) by dvanzandt (guest, #45962) [Link]

I'm not going to give up my SCSI myths too quickly.<g>

I would like to know more about the rotational speed, # of platters, total capacity, i/o parameters, useage (db vs. file share vs. near-line storage, etc.) of the various drives first.

In addition, it would be very interesting to see which drive "types" died more often due to component and logic failure as opposed to "shedding" media.

Having said all that, I'm happier about specing some SATA rigs for my less affluent customers.

Were there any SAS drives in this mix? I am trying to download the study, but the server keeps timing out. If the answer is in it, "never mind."


Copyright © 2017, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds