On Saturday 01 January 2011 20:30:31 Stan Hoeppner wrote: > Boyd Stephen Smith Jr. put forth on 1/1/2011 2:16 PM: > > Is your problem with RAID5 or the SSDs? > > RAID 5 > > > Sudden disk failure can occur with SSDs, just like with magnetic media. > > If > > This is not true. This is true. While single-block failures are most likely, controller failures will cause a whole-disk to fail. This is similar to a daughter card failing. While rare, I've certainly seen it happen, and some NAS steps use multipath across two HBAs to avoid the downtime associated with a HBA failure. This is very similar to RAID 1 across 2 SSDs. > The failure modes and rates for SSDs are the same as > other solid state components, such as system boards, HBAs, and PCI RAID > cards, even CPUs (although SSDs are far more reliable than CPUs due to > the lack of heat generation). Agreed. > > you are going to use them in a production environment they should be > > RAIDed like any disk. > > I totally disagree. Respectfully disagree. However, I do see your point that RAIDing SSDs is not *as* critical as RAIDing magnetic media. > > > RAID 5 on SSDs is sort of odd though. RAID 5 is really a poor man's > > RAID; yet, SSDs cost quite a bit more than magnetic media for the same > > amount of storage. > > Any serious IT professional needs to throw out his old storage cost > equation. Size doesn't matter and hasn't for quite some time. Everyone > has more storage than they can possibly ever use. Look how many > free*providers (Gmail) are offering _unlimited_ storage. I know I don't have all the local storage I need, and I have 6TB attached to my desktop. It's currently full to the point where I can't archive data that I acquire on less reliable media. I think the old equations are still valuable. If capacity is not a priority or easily satisfied, your observations are particularly valuable. > Also, I really, really, wish people would stop repeating this crap about > mdraid's various extra "RAID 10" *layouts* being RAID 10! They are NOT > RAID 10! > > There is only one RAID 10, and the name and description have been with > us for over 15 years, LONG before Linux had a software RAID layer. > Also, it's not called "RAID 1+0" or "RAID 1/0". It is simply called > "RAID 10", again, for 15+ years now. Simply not true. The correct naming for layered RAID has never been standardized. I frown on the "RAID 10" naming because it looks like it should be pronounced "RAID Ten". > It requires 4, or more, even > number of disks. RAID 10 is a stripe across multiple mirrored pairs. > Period. There is no other definition of RAID 10. All of Neil's > "layouts" that do not meet the above description _are not RAID 10_ no > matter what he, or anyone else, decided to call them!! While, this is pedantically true, it is a rather silly distinction to make. With all the layouts, the disks are divided into a number of blocks, then pairs of these blocks are mirrored and the data is striped across all the mirrors. This builds a RAID 1/0, where the "disks" are just parts of the physical disks. The "D" in RAID refers to physical disks, but for quite a while RAID is put into practice on top of various abstraction layers, so the mdadm blocks certainly qualify. -- Boyd Stephen Smith Jr. ,= ,-_-. =. bss@iguanasuicide.net ((_/)o o(\_)) ICQ: 514984 YM/AIM: DaTwinkDaddy `-'(. .)`-' http://iguanasuicide.net/ \_/
Attachment:
signature.asc
Description: This is a digitally signed message part.