Rich Freeman on 21 Aug 2016 14:51:47 -0700

[Date Prev] [Date Next] [Thread Prev] [Thread Next] [Date Index] [Thread Index]


On Sun, Aug 21, 2016 at 4:07 PM, Rich Mingin (PLUG) <> wrote:
> If close together failures are a concern as you say at the end, RAID6 *is*
> RAID5+hot spare minus rebuild time. The extra I/O is largely offset by the
> extra disk sharing the load.

Unless you have data going over some kind of shared pipe dividing the
bandwidth I'd think that the IO for striped raid would be the same.
Since the drives are all sychronized it should take the same amount of
time to seek 4 drives as 5, or to upload 1GB of data to 4 drives as
1.25GB of data to 5.  Maybe there is more CPU load, but that seems
unlikely to be the bottleneck.

I'd be interested in real-world differences between raid5/6.

Philadelphia Linux Users Group         --
Announcements -
General Discussion  --