Introduction, Specifications and Packaging
These Micron SSDs offer amazing IO consistency!
Introduction:
Micron paper launched their 5100 Series Enterprise SATA SSD lineup early last month. The new line promised many sought after features for such a part, namely high performance, high-performance consistency, high capacities, and relatively low cost/GB (thanks to IMFT 3D NAND which is now well into volume production since launching nearly two years ago). The highs and lows I just rattled off are not only good for enterprise, they are good for general consumers as well. Enterprises deal in large SSD orders, which translates to increased production and ultimately a reduction in the production cost of the raw NAND that also goes into client SSDs and other storage devices.
The 5100 Series comes in three tiers and multiple capacities per tier (with even more launching over the next few months). Micron sampled us a 2TB 'ECO' model and a 1TB 'MAX'. The former is optimized more for read intensive workloads, while the latter is designed to take a continuous random write beating.
I'll be trying out some new QoS tests in this review, with plans to expand out with comparisons in future pieces. This review will stand as a detailed performance verification of these two parts – something we are uniquely equipped to accomplish.
Specifications:
I'm going to spread the relevant performance specifications across the associated pages and charts of the review. I will also going to place markers indicating the specs on the charts themselves, making it clear if/when the tested part is not meeting its spec. Thanks to our exclusive in-house Latency Percentile results, I've greatly expanded our QoS charting to a new 'high resolution' method which allows us to easily confirm the various "9's" claims seen in enterprise product specs. Below are a few of the specs that do not fall into the other categories of this review:
As you can see, TBW goes up dramatically for a given accessible capacity when moving from ECO to PRO to MAX. Over-provisioning ranges from 10-20% for ECO, 20-30% for PRO, and a whopping 60-70% for the MAX model, meaning there is almost *double* the amount of NAND compared to the labeled capacity.
The 5100 Series is available in M.2 SATA (just not in as many capacities as the 2.5" variant).
There are some additional features worth a mention here. The big one is called Flex Capacity, which allows user-adjustable OP. You're limited to one direction (increasing OP) over the stock value for the particular line, but you can effectively match the endurance ratings of higher tiers and also get most of the steady state performance increases of those same lines. The reason you may not be able to perfectly match the higher line with a simple OP change is that the controller channel to flash die configuration may differ across models.
Packaging:
Enterprise customers will typically be buying these in bulk, but Micron fancied things up a bit for us here.
micron = elpida =
micron = elpida = ????
samsung still the best for memory.
Elpida was acquired by Micron
Elpida was acquired by Micron recently.
FYI,
“Read on for our full
FYI,
“Read on for our full review of the Micron 5100 MAX 960GB and 5100 ECO 1920GB Enterprise SATA SSDs!” link goes to a different article.
Whoops! I fixed it for Allyn.
Whoops! I fixed it for Allyn.
These seem to be quite
These seem to be quite capable drives, but in Crucial/Micron and Intel’s consumer and prosumer drives there has been some degradation in terms of durability and performance.
I think both Intel and Crucial/Micron should have continued to sell their 16nm 2D MLC parts like their MX200 series, which is actually better than their MX300. The 600 series from Intel also sucks and this trend is going to push people like me from the MX200 class drives into enterprise drives because i actually want SOME overprovisioning and quality.
N-RAM and STT-MRAM cant replace consumer grade NAND fast enough for me.
am i wrong or are these iops
am i wrong or are these iops numbers, terrible??
What kind of shit review is
What kind of shit review is this where the graphs don’t have any other drives for comparison? These numbers are completely arbitrary based on different testing conditions unless you give other drives for comparison.
“completely arbitrary based
“completely arbitrary based on different testing conditions”
Good thing in their methodology they try to keep the testing conditions completely the same you so can see how the drive performs compared to it’s rated specs. Enterprise devices aren’t judged by “What is best?” but rather “What is best for us?”. A slight distinction, but important none the less.
A certain other website used
A certain other website used to be the top dog of AllTime on enterprise hardware reviews, but if PCPer and Allyn keep up this kind of work AnoTher website might see some pageviews stolen!