Exhibit A: Hardware RAID5. Exhibit B: Software RAID5. Same controller, same disks. Seriously, fuck hardware RAID.pic.twitter.com/EsIurJpKlQ
Show this thread
-
The way I think about this is: software RAID is tested by hundreds of thousands of other people using the same OS. A given hardware RAID is tested daily by potentially only hundreds of other customers using the same controller. And emulated-in-the-driver "RAID" can burn in hell.
I think you underestimate the number of people running hardware RAID on any given controller (and have no idea it's garbage because "it's enterprise hardware").
-
-
Probably. I suspect some of the expensive ones might have really alarmingly small numbers of people using any given rev though? I believe (but can't prove) that the numbers for software RAID should still be much much larger.
-
Honestly, software RAID is unfortunately niche enough in datacenter settings that I wouldn't be surprised if more systems use a particularly popular LSI RAID card than e.g linux dm-raid. But I don't have any numbers, it's just a hunch.
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.