Most customers will never even come close to exceeding the write endurance limits of today's desktop-oriented SSDs. Write exhaustion requires continuous writing to a drive for weeks and months on end before you completely consume the usable life of each NAND cell. In the enterprise world, however, this is a much more likely scenario. Knowing the write endurance of an SSD can help IT professionals select drives that are best suited to their tasks.
This is a metric we're expecting to set Micron apart from its competition. The company chooses to use 34 nm SLC flash in its P320h, and that decision is impactful in two ways.
The first is write endurance. Typically, SLC is capable of 100,000 program/erase cycles, while eMLC is closer to 30,000. The MLC memory most commonly used today falls between 3,000 and 5,000 P/E cycles. In our testing, SLC (even from different manufacturers) consistently performs better than its rating. Micron's NAND is no exception. It doesn't come cheap, though. The RealSSD P320h runs roughly $10/GB.
Before we dig into the results, if you are unfamiliar with the different types of NAND or the concept of write exhaustion in general, take a look at Intel SSD 910 Review: PCI Express-Based Enterprise Storage.
In order to test write endurance, we write large-block, sequential data to the drive and continuously monitor the Percentage Lifetime Used SMART attribute. This tells us, on a scale from 0 to 100, the percentage of life exhausted from the drive's NAND. We started with a clean drive and wrote to it until the attribute reached 1%.
By writing sequential data, we demonstrate the maximum usable life of the flash, removing variables like wear-leveling and garbage collection. In this configuration, write amplification should be very close to 1.0x. We did run into an issue, though, that complicated testing. Mainly, Micron does not provide a SMART attribute that reports the total amount of data written to the drive. This definitely caused some concern because we had no way of knowing how much data had been written previously, which could have skewed our results. Normally, we rely on our testing software to keep track of this, but we always like to double-check our work. This could be a concern for system administrators that want a hard number. For most, though, the SMART attributes provided should be sufficient to successfully administer the P320h.
| Endurance Rating Sequential Workload, QD=1, 8 MB, Random | ||||
|---|---|---|---|---|
| Micron Real SSD P320h | Intel SSD 910 | Intel X25-E | Toshiba MK4001GRZB | |
| NAND Type | Micron 32 nm SLC | Intel 25 nm eMLC (HET) | Intel 50 nm SLC | Toshiba 32 nm SLC |
| RAW NAND Capacity | 1,024 GB | 896 GB | 77GB | 512 GB |
| IDEMA Capacity (User Accessible) | 700 GB | 800 GB | 64 GB | 400 GB |
| Over-provisioning | 22% (12.5% RAIN) | 12% | 20% | 28% |
| P/E Cycles Observed (IDEMA) | 276,652 | 46,339 | 237,968 | 225,064 |
| P/E Cycles Observed (Raw) | 185,700 | 41,374 | 198,307 | 175,831 |
| Host Writes per 1% of MWI | 1857.0 TB | 370.71 TB | 152.3 TB | 900.2 TB |
| $/PB-Written | $38.57 | $106.60 | $60.51 | $79.63 |
If you only consider write endurance and cost in dollars per petabyte written ($38), ignoring all else, the RealSSD P320h is our new champion. Based on our results, the P320h is clearly the best choice for customers who need a write-caching solution with high endurance for a reasonable price.
- Meet Micron's P320h PCI Express-Based SSD
- Micron's 32-Channel Controller Simplifies PCIe-Based SSDs
- Micron's Firmware And Monitoring Software
- Test Setup, Benchmarks, And Methodology
- Measuring Write Endurance: SLC Wins Again
- 4 KB Random Performance
- Enterprise Workload Performance
- Sequential Performance
- Enterprise Video Streaming Performance
- Power Consumption
- Micron's RealSSD P320h: The Future Of Enterprise-Class SSDs?
Such an apples to oranges comparison...
It using SLC and geared towards enterprise market...
IMO it understandable price...
Such an apples to oranges comparison...
Kinda surprised something like this didn't come out first as it makes more sense....
really ? Increasingly, performance is basically dependent on extracting parallelism. Whether in storage or in CPU performance.
Desktop/Mainstream users just dont do so much in parallel that they can fully use all the hardware.
I see a purpose for 16 core processors. How are we going to otherwise be able to run Crysis 6?
Use a 5000 core GPU ?
????????!!!!!!!!!!!
Thanks for the review, love to see this kind of advancement and a peak into the future new hardware brings with it, even if it isn't directly applicable to me at this point in time.
Can you put two of them in RAID0 ??
Signed,
Bonkers
It using SLC and geared towards enterprise market...
IMO it understandable price...
Eh, depending on how far in the future we're talking about, neither of those statements is iron-clad. In the case of a 16-core processor, it's pretty much guaranteed that we will eventually see one in the consumer space, at mainstream prices. Whether the extra cores on that CPU will offer any compelling benefit to the mainstream consumer is an open question, but at least those cores do offer meaningful performance benefits to hardcore multi-taskers.
Similarly, current consumer-grade SSDs offer very nearly instantaneous responsiveness already -- unless the user attempts to perform multiple disk-intensive tasks simultaneously. But who knows what the future holds? You could make a case that current enterprise-grade SSDs (or something similar to them) are far more likely to make a meaningful mark on the consumer market years from now than 16-core processors, because the benefits of CPU parallelism are limited in principle. By contrast, the benefit of storage speed is only limited by the speed of the components that rely on it; storage speed applies both to singular and parallel tasks.
That said, I agree with your sentiment if not with the particulars of your argument: my gut reaction to the article was that although 3.2 GB/sec is a very impressive number, I already feel like I'm flying at the ~0.5 GB/sec (at best) that I get out of my Intel 330. From the consumer perspective, performance comparisons between different SSDs almost always seem to me materially irrelevant, so it's hard to get too excited about the performance of an enterprise-grade SSD, even in the abstract.
Still, this is a worthy review of an interesting product. Appreciate the insight.
1989... 1MB of memory chips (card extra) was $100 wholesale !
We sold them by the boat load for Amiga computers.
And yes, that is 1 MegaByte...
an 8MB card retailed for $1,800 (and that's in 1989 Dollars).
I am glad you find it useful, it is something that I have always cared about and tested because I have been burned in the past.