Results: Write Endurance
We typically spend a lot of time evaluating write endurance when we review enterprise-class SSDs. Write endurance is one of the major differentiators separating enterprise and client-oriented drives, after all. As MLC-based storage continues pushing its way into spaces previously filled by SLC NAND, we have to keep a close eye on this difficult-to-benchmark, but still very important variable involved in evaluating solid-state storage.
The rise of read-focused enterprise drives is making this type of testing even more important, since you really want to know what writes will do to storage hardware stacked in favor of reads. Naturally, we have to appreciate the companies that treat write endurance as a first-class specification, and much of the credit for this should go to JEDEC for the JESD218A write endurance testing standard. Instead of issuing vague ratings, we now see most companies specifying their drives to the JESD218A standard, which uses the JESD219A enterprise workload to quantify endurance. This closely matches the types of workloads we use in our Enterprise Workload Performance tests, employing sequential write patterns and large block sizes. The result is minimal write amplification and wear leveling, yielding a better indication of actual P/E cycles for the NAND.
| Endurance RatingSequential Workload, QD=1, 8 MB | Seagate 600 Pro | Micron P400m | Intel SSD DC S3700 |
|---|---|---|---|
| NAND Type | Toshiba 19 nm MLC | Micron 25 nm MLC | Intel 25 nm HET-MLC |
| RAW NAND Capacity | 256 GB | 340 GB | 264 GB |
| IDEMA Capacity (User Accessible) | 200 GB | 200 GB | 200 GB |
| Over-provisioning | 28% | 70% | 32% |
| P/E Cycles Observed (IDEMA) | 6,245 | 34,195 | 36,343 |
| P/E Cycles Observed (Raw) | 4,879 | 20,113 | 27,532 |
| Host Writes per 1% of MWI | 12.49 TB | 68.39 TB | 72.69 TB |
| $/PB-Written | $228.18 | $87.73 | $64.66 |
As we've seen time and time again, you get what you pay for when it comes to write endurance. Even though Seagate's 600 Pro is an enterprise drive, it is still a read-focused product. When you subject the 600 Pro to excessive writes, you basically throw away money. In fact, it took less than one day to consume 1% of its rated lifespan. If you used this SSD for 100% sequential writes, you could theoretically kill it in a little more than a month.
On the flip side, it's encouraging that we were able to get almost 5,000 P/E cycles out of 19 nm MLC NAND.
We actually had to tax this drive until 4% of its life was consumed in order to generate accurate data. It took nearly 25 TB of writes for the first percentage point to expire, which would have translated to an impressive 10,000 P/E cycles. We were understandingly skeptical of those results, so we kept writing until the values leveled off.
Even though this is the first SSD we've reviewed seemingly built for read-focused use, we expect that the 600 Pro's performance to mirror similar drives currently on other vendors' roadmaps. You should start seeing enterprise write endurance fall into three categories: the first involves read-focused MLC with ~5,000 P/E cycles; the second is best for mixed use, featuring eMLC with ~25,000-35,000 P/E cycles; the last is write-oriented SLC capable of 100,000+ P/E cycles.
