Two parameters that are important in any workload are block size and interleave (stripe size). Block size is a measurement (usually in KB) of the I/Os that the storage sub-system has to handle. Many database-style applications such as Microsoft SQL Server and Microsoft Exchange use relatively small blocks (8KB – 32KB), though other applications may use larger blocks. Sequential workloads profit significantly from larger block sizes. In general, IOPs and throughput are inversely related to block size: a small block size yields high IOPs with low throughput, while a large block size results in high throughput with low IOPS.
Storage Spaces can utilize multiple physical disks by striping data across them. One of the parameters that can be adjusted when creating a storage space is how large this stripe is supposed to be. The default setting is 256 KB. This means that Storage Spaces stores 256 KB of data on each column that was assigned to the storage space. If, for example, you have eight disks in the storage pool and want to write 4 MB of data, each disk receives two 256KB stripes (4MB / 256KB (Stripe) / 8 Columns = 2x 256KB stripes per column).
To maximize performance, ensure that the interleave value used by the storage space is at least as large as the I/Os of your workload. I/Os that exceed the interleave size are split into multiple stripes, turning one write into multiple writes, reducing performance.