Any storage admins out there who are reading this right now will realize how crippling that could be in a production scenario. Having your storage throughput suddenly drop by 95 percent and your storage system take minutes to recover because you created a snapshot would be very bad indeed (think every phone in the help desk ringing at once). However, good storage admins will also recognize how incredibly unlikely this scenario is in most real-world situations.
The production loads you'll find out in the field are generally very bursty on a subsecond basis. That is, if you were to create a graph of the duty cycle of a primary storage array in a typical enterprise with a resolution of 10ms or 20ms, you'd see it bounce around all over the place. The array could be very busy, but still have a lot of slack space where no transactions were being executed. It's in this space where the on-demand portion of Compellent's Data Progression software gets its work done, and where it can work without impacting host I/O to any great degree.
In my artificial lab test, however, the array was being pushed to its limit -- effectively creating a 100 percent duty cycle. This left no room for Data Progression to do its work and created enough congestion between host writes and time-consuming SLC to MLC data migrations to cripple overall performance.
In the real world, if you have a write-heavy workload that requires the full raw performance of SLC flash 24/7, you probably won't want to leverage Compellent's Data Progression software at all. Instead, you'll deploy enough SLC capacity to hold all the data you intend to hit this way and configure the storage policy that applies to it to prevent Data Progression from moving it out of SLC flash. That would neatly sidestep the entire issue while still allowing less brutally assaulted volumes on the same array to take advantage of the economy presented by SLC/MLC tiering.
If your workloads are more typically bursty or heavy only during certain times of day (like the bulk of enterprise workloads out there), you may never notice the impact of snapshot migrations. Or, if you do, you might well avoid it by scheduling snapshots to occur slightly less frequently than you might have otherwise.
The rest of the story
Certainly, tiered flash isn't the only facet to Compellent or even the Storage Center 6.4 release. Generally speaking, Dell fields a very capable and cost-conscious midrange storage device in the Compellent product line.
Dual active-active SC8000 controllers based upon Dell's R720 industry-standard servers can be equipped with 4Gbps, 8Gbps, and 16Gbps Fibre Channel; 1Gbps and 10Gbps Ethernet iSCSI; and 10GBps FCoE host connectivity, as well as up to three redundant back-end 6Gbps SAS chains for disk shelf connectivity. Disk shelves come in three shapes and sizes with the 24-slot 2.5-inch SC220, 12-slot 3.5-inch SC200, and brand-new 84-slot 3.5-inch SC280. (The last one is limited to NL-SAS disks and clearly meant for high-density applications.) In the past, drives were generally sold on a per-disk basis, but Dell is starting to move more toward bundles that include a specific number of disks. For example, the SC280 is available in several half and fully populated configurations targeting various capacities.
Sign up for CIO Asia eNewsletters.