Re: What's the typical RAID10 setup?

[David Brown <david@westcontrol.com>]

On 31/01/2011 23:52, Keld Jørn Simonsen wrote:
> raid1+0 and Linux MD raid10 are similar, but significantly different
> in a number of ways. Linux MD raid10 can run on only 2 drives.
> Linux raid10,f2 has almost RAID0 striping performance in sequential read.
> You can have an odd number of drives in raid10.
> And you can have as many copies as you like in raid10,
>

You can make raid10,f2 functionality from raid1+0 by using partitions. 
For example, to get a raid10,f2 equivalent on two drives, partition them 
into equal halves.  Then make md0 a raid1 mirror of sda1 and sdb2, and 
md1 a raid1 mirror of sdb1 and sda2.  Finally, make md2 a raid0 stripe 
set of md0 and md1.

If you have three disks, you can do that too:

md0 = raid1(sda1, sdb2)
md1 = raid1(sdb1, sdc2)
md2 = raid1(sdc1, sda2)
md3 = raid0(md0, md1, md2)

As far as I can figure out, the performance should be pretty much the 
same (although wrapping everything in a single raid10,f2 is more 
convenient).

For four disks, there are more ways to do it:

Option A:

md0 = raid1(sda1, sdb2)
md1 = raid1(sdb1, sdc2)
md2 = raid1(sdc1, sdd2)
md3 = raid1(sdd1, sda2)
md4 = raid0(md0, md1, md2, md3)

Option B:

md0 = raid1(sda1, sdb2)
md1 = raid1(sdb1, sda2)
md2 = raid1(sdc1, sdd2)
md3 = raid1(sdd1, sdc2)
md4 = raid0(md0, md1, md2, md3)

Option C:

md0 = raid1(sda1, sdc2)
md1 = raid1(sdb1, sdd2)
md2 = raid1(sdc1, sda2)
md3 = raid1(sdd1, sdb2)
md4 = raid0(md0, md1, md2, md3)

"Ordinary" raid 1 + 0 is roughly like this:

md0 = raid1(sda1, sdb1)
md1 = raid1(sda2, sdb2)
md2 = raid1(sdc1, sdc1)
md3 = raid1(sdc2, sdd2)
md4 = raid0(md0, md1, md2, md3)


I don't know which of A, B or C is used for raid10,f2 on four disks - 
maybe Neil knows?

The fun thing here is to try to figure out the performance for these 
combinations.  For large reads, A, B and C will give you much better 
performance than raid 1 + 0, since you can stream data off all disks in 
parallel.  For most other accesses, I think the performance will be 
fairly similar, except for medium write sizes (covering between a 
quarter and half a stripe), which will be faster with C since all four 
disks can write in parallel.

All four arrangements support any single disk failing, and B, C and 
raid1+0 have a 66% chance of supporting a second failure.


I don't think there is any way you can get the equivalent of raid10,o2 
in this way.  But then, I am not sure how much use raid10,o2 actually is 
- are there any usage patterns for which it is faster than raid10,n2 or 
raid10,f2?



--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html