On Mar 9, 2011, at 4:14 PM, Chris Murphy wrote:
> In any event, that one is expected to take precautions with RAID 5/6 or even 
> RAID-Z with respect to power management does not mean the incidence of silent 
> data corruption is higher.

RAID-Z, raids 0, 1, 10 0+1 are not capable of silent data corruption. All 
corruption is checked and managed due to the nature of the operations of these 
configurations.

> It simply means *IF* it happens to a RAID 5 array the problems can rapidly 
> become magnified requiring significant contingencies.

No it means that the others can't have it but RAID5 can, and will.

And to a degree that previously wasn't seen until very large numbers of raid5 
arrays were seen in use. Now that the industry has seen lots of raid5 use, and 
big big farms of computers that had been using raid5 started to notice an 
unexpected prevalence of silent data corruption, and disks have gotten cheaper 
making raid5 an unnecessary risk, many wise men have decided it's not being 
diligent to use raid5. 

> I might still be able to suck off a bunch of data from a non-array (or RAID 1 
> disk) despite file system corruption, or the corruption of even 10% of the 
> disk - I will have *better* recovery from RAID 5 if that same event happens 
> to 1 disk, but much worse recovery if that problem is propagated through the 
> entire array. I don't think this is a secret. Again, RAID 5 is not a new 
> thing.

You really don't understand silent data corruption. 

Data on a non-raided or raid 0 disk, it's silent data damage, and tracked by 
the bad block replacement. 

If you damage a raid5 and rebuild a member this doesn't involve silent data 
corruption, that was a data replacement operation. 

In silent data corruption the data is corrupted through faults and side effects 
of the raid5 process. 

> But I totally disagree with the wording used that implies there is a high 
> incidence of silent data corruption inherent to a RAID 5 system.

Well since other disk subsystem architectures can't have it, that's about as 
high of a difference as you can get, measurably. 

> Usually those systems have better drives, better interfaces, better cables, 
> and more resilient OS, with UPS systems. The net of that is silent data 
> corruption would be less likely by far than a non-arrayed setup of the same 
> capacity.

Again this ha nothing to do with the problem under discussion. 

> Let me use perhaps an imperfect analogy. Cars and airplanes. Cars = non-array 
> and airplanes = RAID 5. The likelihood you're going to have an accident with 
> a car is astronomically higher than an airplane. But if you have an accident 
> in an airplane the incidence of death is higher. Death is contingent on the 
> other happening first, which is very unlikely with airplane travel.

You're talking something different. 


-d

------------------------------------------------------------------------
Dan Shoop
[email protected]
GoogleVoice: 1-646-402-5293
aim: iWiring
twitter: @colonelmode



_______________________________________________
MacOSX-admin mailing list
[email protected]
http://www.omnigroup.com/mailman/listinfo/macosx-admin

Reply via email to