And so it begins; looks like SunOracle might be the first vendor to start shipping triple parity in their storage devices; scarey isn't it? I wondered who would be first because as we start down the route of 2Tb spindles and beyond, dual parity wasn't going to be enough; rebuild times etc were just going to get more frightening.
Now, everyone could have just decided to go down the XIV route and mirror everything; RAID-1 with chocolate chunks I like to think of it as. But I had a sneaky suspicion that we would start to see triple parity RAID systems. It'll be interesting to see what the performance is like and what the trade-off is. Will we see quad parity, enormous caches to hide the parity penalty, variable parity schemes which adjust according to load?
And if anyone is already shipping triple parity; apologies….
I read this, read Mellor’s comments regarding the same: http://www.theregister.co.uk/2009/07/29/triple_parity_raid/
Sounds like lunacy to me. If your data is that stinking important, it better be mirrored to another data center.
Maybe the Intel white paper on RAID6 is not accurate?
http://download.intel.com/design/storage/papers/30812202.pdf
The MTtDL is drastically greater RAID6 versus RAID5
(100 years to data loss in one comparison, see page 3).
With SMARTS, a lot of drive failures are avoided with proactive sparing.
Back to Mellor:
“Assume 3TB drives are coming, then 4TB ones, and we’re looking at 12 hours and 16 hours respectively for a rebuild of a full failed disk. Every added terabyte adds four hours to the rebuild time, half a day. That’s increasing the chances a third drive will fail in the rebuild period for second and first failed drive rebuilds.”
Where does everybody get that? It’s UBE that gets you, not wall clock time. You lose a drive in RAID6, you’re down to RAID5, you rebuild and are fine.
Think about the large data centers that have 2000 drives. Is the Enterprise storage vendor coming out twice a day or bi-weekly to replace drives? If coming out bi-weekly, think of the odds of this: (and why MTDL is so high with RAID6), you’ve lost a drive in a RAID6, you lose another drive in the SAME RAID6 array and during the rebuild of the spares, you get a UBE on the “degraded RAID5” PING! – this scenario can happen… asteroids do strike humans, ya know!
My point in all this is I’m not sure what problem triple parity solves.