Question about "segment size"
Does this therefore mean that in a 4 disk RAID0 volume with a segment size of 128k, that 128k of data is written to the first disk, the second 128k of data is written to the second disk etc.?
If the RAID0 volume has a UFS filesystem created on top with a block size of 8k, does this mean that 16 x 8k blocks are written to the first disk before moving on to the second disk in the stripe? This would therefore limit the performance of the volume to the throughput of a single spindle for small random I/O workloads?