[volunteergrid2-l] disk drive failure statistics

[David-Sarah Hopwood]

On 07/04/12 03:59, erpo41 at gmail.com wrote:
> In February of 2007, Google published a paper titled "Failure Trends
> in a Large Disk Drive Population"
> (http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/archive/disk_failures.pdf)
> analyzing the impact of various environmental factors and SMART
> readings on disk drive failure rates. This paragraph really caught my
> attention:
> 
> "Failure rates are known to be highly correlated with drive
> models, manufacturers and vintages [18]. Our results do
> not contradict this fact. For example, Figure 2 changes
> significantly when we normalize failure rates per each
> drive model. Most age-related results are impacted by
> drive vintages. However, in this paper, we do not show a
> breakdown of drives per manufacturer, model, or vintage
> due to the proprietary nature of these data."
> 
> I don't know about anyone else, but I want that data so I can choose
> the most reliable hard drives from the most reliable manufacturers.
> Furthermore, I want that data to be made public so hard drive
> manufacturers will face real pressure to improve reliability.

Yes, so do I.

> I've thought about several schemes for collecting this data from PCs
> across the world, but that effort is complicated by the fact that most
> desktops are not on and connected to the Internet 24/7. If a PC is off
> when its disk fails, or if it's not connected to the Internet, it
> won't be able to report the failure ever.
> 
> I think you see where I'm going with this. Tahoe-LAFS/VG2 may be the
> ideal way to collect this type of data.

VG2 doesn't by itself have a large enough sample of hard disks.

> So, two questions:
> 
> 1. Is there any reason why someone would object to having the tahoe
> client/server collect disk failure statistics and report them to a
> central server? Should this feature be opt-in or opt-out?

I would object if it were opt-out. Any feature that reports information
to a central server should always be opt-in.

The question in my mind is, why Tahoe? Any software could do this, and
Tahoe isn't in a better position to do it than other software. It would
have no interaction with any other code that is part of Tahoe.

> 2. Does anyone see any potential for error in this scheme?

Tahoe normally only has reason to look at the storage partition. If
the system has another disk that fails, Tahoe wouldn't see it, but a
program specifically designed to look for such failures on all
connected non-removable disks, would.

If the disk failure also takes out the partition on which Tahoe or
other software on which it depends is installed, then Tahoe won't be
able to report it.

So, I'm -1 on making this part of Tahoe.

-- 
David-Sarah Hopwood ⚥

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 554 bytes
Desc: OpenPGP digital signature
URL: <https://tahoe-lafs.org/cgi-bin/mailman/private/volunteergrid2-l/attachments/20120408/88409704/attachment.pgp>