Tom's Hardware article on SSD reliability in data centers

[frostedflakes]

Thought this was a really good read.

http://www.tomshardware.com/reviews/ssd-reliability-failure-rate,2923.html

Found this comment especially interesting, not something I had considered before.

We simply get significantly higher I/O [with SSDs] at a lower cost than we'd be able to get with standard drives. We've had many customers needing more I/O than what 4x 15k RPM SAS drives in RAID 10 provide, and an upgrade involves moving to a larger server chassis to support more than four drives, a larger RAID card, etc. Other configurations have needed 16+ 15k RPM drives to get the necessary I/O. Going with a single SSD (or a couple SSDs in RAID) greatly simplifies the configurations and makes them much cheaper overall.

That is then compounded by the fact that you generally use one SSD to replace 4+ standard drives on average. You're then looking at a 20%+ AFR with hard drives and 1.6% with an SSD.

 

[Concillian]

The HDD AFR gets inflated due to the RAID being non-redundant. You have each drive as a potential failure point, the RAID controller, battery backup, cabling for all drives, etc...

It's not talking about the specific components themselves, but each solution as a whole. The RAID server is much more complex and has more failure points that contribute to that AFR. They compound each other since any component failure counts as a system failure. The SSD is just one controller, one cable, one SSD. KISS.

 

[Emulex]

yeah but sas drives are all dual ported now. drive-1 goes to chassis-1 and drive-2 goes to chassis-2 so in raid-1/10 you can lose an entire path (wiring, chassis power) and still rock on. i'm not sure if folks are making that level of drive (intel will soon) that do not have a single point of failure. can't wait for the intel enteprise mlc 2.5" hot swappable drives. will need some faster raid controllers with trim/cut-through i/o on faster bus