Subject: Storage | November 20, 2017 - 10:56 PM | Allyn Malventano
Tagged: Z-NAND, SZ985, slc, Samsung, P4800X, nand, Intel, flash
We haven't heard much about Samsung's 'XPoint Killer' Z-NAND since Flash Memory Summit 2017, but now we have a bit more to go on:
Yes, actual specs. In print. Not bad either, considering the Samsung SZ985 appears to offer a bus-saturating 3.2GB/s for reads and writes. The 30 DWPD figure matches Intel's P4800X, which is impressive given Samsung's part operates on flash derived from their V-NAND line (but operating in a different mode). The most important figures here are latency, so let's focus there for a bit:
While the SZ985 runs at ~1/3rd the latency of Samsung's own NAND SSDs, it has roughly double the latency of the P4800X. For the moment that is actually not as bad as it seems as it takes a fair amount of platform optimization to see the full performance benefits of optane, and operating slightly higher on the latency spectrum helps negate the negative impacts of incorrectly optimized platforms:
Source: Shrout Research
As you can see above, operating at slightly higher latencies, while netting lower overall performance, does lessen the sting of platform induced IRQ latency penalties.
Now to discuss costs. While we don't have any hard figures, we do have the above slide from FMS 2017, where Samsung stressed that they are trying to get the costs of Z-NAND down while keeping latencies as low as possible.
Image Source: ExtremeTech
Samsung backed up their performance claims with a Technology Brief (available here), which showed decent performance gains and cited use cases paralleling those we've seen used by Intel. The takeaway here is that Samsung *may* be able to compete with the Intel P4800X in a similar performance bracket - not matching the performance but perhaps beating it on cost. The big gotcha is that we have yet to see a single Samsung NVMe Enterprise SSD come through our labs for testing, or anywhere on the market for that matter, so take these sorts of announcements with a grain of salt until we see these products gain broader adoption/distribution.
Subject: Storage | November 15, 2017 - 09:59 PM | Allyn Malventano
Tagged: NVDIMM, XPoint, 3D XPoint, 32GB, NVDIMM-N, NVDIMM-F, NVDIMM-P, DIMM
We're finally starting to see NVDIMM materialize beyond the unobtanium. Micron recently announced 32GB NVDIMM-N:
These come with 32GB of DRAM plus 64GB of SLC NAND flash.
These are in the NVDIMM-N form factor and can offer some very impressive latency improvements over other non-volatile storage methods.
Next up is Intel, who recently presented at the UBS Global Technology Conference:
We've seen Intel's Optane in many different forms, and now it looks like we finally have a date for 3D XPoint DIMMs - 2nd half of 2018! There are lots of hurdles to overcome as the JEDEC spec is not yet finalized (and might not be by the time this launches). Motherboard and BIOS support also needs to be more widely adopted for this to take off as well.
Don't expect this to be in your desktop machine anytime soon, but one can hope!
Press blast for the Micron 32GB NVDIMM-N appears after the break.
Introduction and Specifications
Back in April, we finally got our mitts on some actual 3D XPoint to test, but there was a catch. We had to do so remotely. The initial round of XPoint testing done (by all review sites) on a set of machines located on the Intel campus. Intel had their reasons for this unorthodox review method, but we were satisfied that everything was done above board. Intel even went as far as walking me over to the very server that we would be remoting into for testing. Despite this, there were still a few skeptics out there, and today we can put all of that to bed.
This is a 750GB Intel Optane SSD DC P4800X - in the flesh and this time on *our* turf. I'll be putting it through the same initial round of tests we conducted remotely back in April. I intend to follow up at a later date with additional testing depth, as well as evaluating kernel response times across Windows and Linux (IRQ, Polling, Hybrid Polling, etc), but for now, we're here to confirm the results on our own testbed as well as evaluate if the higher capacity point takes any sort of hit to performance. We may actually see a performance increase in some areas as Intel has had several months to further tune the P4800X.
This video is for the earlier 375GB model launch, but all points apply here
(except that the 900P has now already launched)
The baseline specs remain the same as they were back in April with a few significant notable exceptions:
The endurance figure for the 375GB capacity has nearly doubled to 20.5 PBW (PetaBytes Written), with the 750GB capacity logically following suit at 41 PBW. These figures are based on a 30 DWPD (Drive Write Per Day) rating spanned across a 5-year period. The original product brief is located here, but do note that it may be out of date.
We now have official sequential throughput ratings: 2.0 GB/s writes and 2.4 GB/s reads.
We also have been provided detailed QoS figures and those will be noted as we cover the results throughout the review.
Subject: Storage | November 6, 2017 - 03:22 PM | Jeremy Hellstrom
Tagged: crucial, Momentum Cache, NVMe, Crucial Storage Executive
The SSD Review noticed something very interesting in the latest update to Crucial's Storage Executive software, the Momentum Cache feature now works with a variety of non-Crucial NVMe SSDs. The software allows your system to turn part of your RAM into a cache so that reads and writes can initially be sent to that cache which results in improved performance thanks to RAM's significantly quicker response time. If you have a Crucial SSD installed as well as another NVMe SSD and are using the default Windows NVMe driver, you can set up caching on the non-Crucial SSD if you so desire. Stop by for a look at the performance impact as well as a list of the drives which have been successfully tested.
"Crucial’s Momentum Cache feature, part of Crucial Storage Executive, is unlocked for all NVMe SSDs, or at least the ones we have tested in our Z170 test system; the key here, of course, is that a compatible Crucial SSD must initially be on the system to enable this feature at all."
Here are some more Storage reviews from around the web:
- Patriot Hellfire 240GB @ Benchmark Reviews
- Team Group CARDEA Zero 240GB M2 SSD @ Guri of 3D
- HP S700 SSD Review @ OCC
- Western Digital (WD) My Cloud Home 6TB @ Kitguru
- Seagate IronWolf Pro 12TB SATA III HDD Review @ NikKTech
- Seagate BarraCuda Pro 12TB HDD @ Kitguru
Introduction, Specifications and Packaging
It’s been two long years since we first heard about 3D XPoint Technology. Intel and Micron serenaded us with tales of ultra-low latency and very high endurance, but when would we have this new media in our hot little hands? We got a taste of things with Optane Memory (caching) back in April, and later that same month we got a much bigger, albeit remotely-tested taste in the form of the P4800X. Since April all was quiet, with all of us storage freaks waiting for a consumer version of Optane with enough capacity to act as a system drive. Sure we’ve played around with Optane Memory parts in various forms of RAID, but as we found in our testing, Optane’s strongest benefits are the very performance traits that do not effectively scale with additional drives added to an array. The preferred route is to just get a larger single SSD with more 3D XPoint memory installed on it, and we have that very thing today (and in two separate capacities)!
You might have seen various rumors centered around the 900P lately. The first is that the 900P was to supposedly support PCIe 4.0. This is not true, and after digging back a bit appears to be a foreign vendor mistaking / confusing PCIe X4 (4 lanes) with the recently drafted PCIe 4.0 specification. Another set of rumors centered around pre-order listings and potential pricing for the 280 and 480 GB variants of the 900P. We are happy to report that those prices (at the time of this writing) are way higher than Intel’s stated MSRP's for these new models. I’ll even go as far as to say that the 480GB model can be had for less than what the 280GB model is currently listed for! More on that later in the review.
Performance specs are one place where the rumors were all true, but since all the folks had to go on was a leaked Intel press deck slide listing figures identical to the P4800X, we’re not really surprised here.
Lots of technical stuff above, but the high points are <10us typical latency (‘regular’ SSDs run between 60-100us), 2.5/2.0 GB/s sequential reads/writes, and 550k/500k random read/write performance. Yes I know, don’t tell me, you’ve seen higher sequentials on smaller form factor devices. I agree, and we’ve even seen higher maximum performance from unreleased 3D XPoint-equipped parts from Micron, but Intel has done what they needed to do in order to make this a viable shipping retail product, which likely means sacrificing the ‘megapixel race’ figures in favor of offering the lowest possible latencies and best possible endurance at this price point.
Packaging is among the nicest we’ve seen from an Intel SSD. It actually reminds me of how the Fusion-io ioDrives used to come.
Also included with the 900P is a Star Citizen ship. The Sabre Raven has been a topic of gossip and speculation for months now, and it appears to be a pretty sweet looking fighter. For those unaware, Star Citizen is a space-based MMO, and with a ‘ship purchase’ also comes a license to play the game. The Sabre Raven counts as such a purchase and apparently comes with lifetime insurance, meaning it will always be tied to your account in case it gets blown up doing data runs. Long story short, you get the game for free with the purchase of a 900P.
Subject: Storage | October 12, 2017 - 02:34 PM | Jeremy Hellstrom
Tagged: tr200, toshiba, BiCS, Toshiba TC58
The Tech Report tested out the 460GB version of the Toshiba TR200 SSD which uses 64-layer BiCS 3D flash. It is not quite compliant with Ryan's Law, but an MSRP of $150 for this drive is quite affordable. The drive uses Toshiba's own TC58 controller and like many current budget drives it lacks a RAM cache, making do with a psuedo-SLC cache. Performance wise it came out about the same as the Trion 100, which is to say at the bottom of the SSD pack, but the Trion drive has a RAM cache which offers some hope for higher end models based on the same flash. Pop by for the full review and think about this as a stocking stuffer for anyone you like, who is still spinning rust.
"Toshiba's first client drive with BiCS flash inside is the entry-level TR200. Join us as we find out just how much storage performance you can get on a budget these days."
Here are some more Storage reviews from around the web:
- Toshiba TR200 960GB SSD @ Kitguru
- Toshiba TR200 SSD 960GB @ Guru of 3D
- Adata's SE730H 512GB portable SSD @ The Tech Report
- WD My Passport SSD 256GB @ Kitguru
- Toshiba L200 1TB 2.5-inch Internal Hard Drive Review @ NikKTech
- Synology DiskStation DS418j NAS @ Modders-Inc
Subject: Storage | October 11, 2017 - 11:16 PM | Allyn Malventano
Tagged: western digital, wdc, WD, STO, Spin Torque Oscillator, SMR, PMR, Microwave Assisted Magnetic Recording, microwave, MAMR, HAMR, FMR
Today Western Digital made a rather significant announcement in the field of HDD technology. We’ve previously talked about upcoming ways to increase the density of HDD storage, with the seeming vaporware Heat Assisted Magnetic Recording (HAMR) forever looming on the horizon, just out of reach.
WD, like others, have been researching HAMR as a possible way of increasing platter densities moving forward. They were even showing off prototypes of the technology back in 2013, but a prototype is a far cry from a production ready, fully reliable product. Seagate had been making stronger promises of HAMR, but since we are already 5 years into their 10-year prediction of 60TB HAMR HDDs (followed by further delays), it's not looking like we will see a production ready HAMR HDD model any time soon.
Ok, so HAMR is not viable for now, but what can we do? Seems WD has figured it out, and it's a technology they have been kicking around their labs for nearly a decade. Above we see the PMR limit of ~1.1 Terabits/square inch. SMR pushes that figure to 1.4, but we are running up against the so-called 'writeability limit', which is the point at which the write head / magnetic field is too small to overcome the paramagnetic threshold of the smaller magnetic domains of higher density media. We are used to hearing that the only way to raise that limit was to heat the media with a laser while writing (HAMR), but there is a different / better way - Microwave Assisted Magnetic Recording, or MAMR for short.
Don't let the 'microwave' part of the term fool you - we are not microwaving the media with sufficient energy to actually heat it. Instead, we are doing something *way* cooler. The slide above shows how smaller grain size (higher density) requires a stronger write field to reach sufficient energy levels to reliably store a bit of data. Now check out the next slide:
This is a lot to grasp but allow me to paraphrase greatly. Imagine a magnet with a north and south pole. If you came along with a stronger magnet and attempted to reverse its polarity by directly opposing the currently stored state, it's generally difficult to do so. Current HDD tech relies on the field being strong enough to overcome the stored polarity, but MAMR employs a Spin Torque Oscillator, which operates at a high enough frequency (20-40 GHz) to match the ferromagnetic resonance of the media. This causes a precession of the stored field (like a gyroscope) and tilts it about its vertical axis. This resonance adds the extra energy (in addition to the write field) needed to flip the field to the desired direction. What's amazing about this whole process is that thanks to the resonance effects, the STO can increase the effectiveness of the write field 3-4x while only consuming ~1/100th of the power compared to that needed to generate the write field. This reduction in the damping constant of the media is what will enable smaller magnetic domains, therefore higher platter densities in future MAMR-equipped HDDs.
One of the best things about this new tech is that it is just a simple addition to all of other technologies already in place today. Western Digital was already making their drive heads with an advanced 'damascene' process, silently introduced about three years ago. To oversimplify the description, damascene is a process that enables greater physical precision in the shape of the head, which helps increase density. What makes this process a bigger deal now is that it more easily enables integration of the Spin Torque Oscillator into the head assembly. Aside from this head-level change and another pair of leads to provide a very small drive current (~1-2mA), every other aspect of the drive is identical to what we have today. When it comes to a relatively radical change to how the writing can be accomplished at these upcoming higher densities, doing so without needing to change any of the other fundamental technologies of the drive is a good thing. By no change, I really mean no change - MAMR can be employed on current helium-filled drives. Even SMR.
Western Digital also slipped in another announcement, which is the shift from the older style 'nested actuator' (introduced with 2TB HDDs back in 2009), to a newer 'micro-actuator'. The newer actuator moves the articulation point much closer to the head compared to the previous technology, enabling even finer head tracking, ultimately resulting in increased track pitch. WD currently sits somewhere around 400 tracks per inch (TPI), but they hope to reach 1 million (!) thanks to this new tracking combined with MAMR and improved media chemistry.
Now this doesn't mean we will see a sudden influx of 40TB HDDs hitting the market next week. WD still has to scale up production of STO-enabled heads, and even after that is complete, the media technology still needs to catch up to the maximum capabilities of what MAMR can achieve (creating smaller magnetic domains on the disk surface, etc). Still, it's nice to know that there is a far simpler way to flip those stored bits around without having to resort to HAMR, which seems to be perpetually years away from production. Speaking of which, I'll leave you with WD's reliability comparison between their own HAMR and MAMR technologies. Which would you choose?
Oh yeah, and about that supposed SSD vs. HDD cost/GB crossover point. It may not be as soon as we previously thought:
Full press blast appears after the break.
Subject: Storage | October 5, 2017 - 01:37 AM | Tim Verry
Tagged: western digital, SMR, hgst, HelioSeal, big data, 14tb
Western Digital is raising the enterprise hard drive stakes once again with the announcement of a 14 TB 3.5” hard drive. The HGST branded Ultrastar Hs14 uses fourth generation HelioSeal and second generation host-managed SMR (shingled magnetic recording) to enable a 14 TB drive that is just as fast as its smaller capacity enterprise predecessors despite the impressive 1034 Gb/sq in areal density. Western Digital claims the new hard drive offers up 40% more capacity and twice the sequential write performance of its previous SMR drives.
The 3.5” SMR hard drive comes in SATA 6Gbps and SAS 12 Gbps flavors with both equipped with 512 MB cache, operating at 7200 RPM, and supporting maximum sustained transfer speeds of 233 MB/s. The enterprise drive is geared towards sequential writes and is intended to be the storage target for big data applications like Facebook, video streaming services, and research and financial workloads that generate absolutely massive amounts of raw data that needs to sit in archival storage but remain easily accessible (where tape is not as desirable). According to the data sheet (PDF), it is also aimed at bulk cloud storage and online backup as well as businesses storing compliance, audit, and regulatory records.
For those curious about Shingled Magnetic Recording (SMR), Allyn shared some thoughts on the technology here.
Western Digital rates the drive at 550 TB/year and supports the Hs14 with a five year warranty. The drive is currently being sampled to a small number of OEMs with wider availability to follow.
Subject: Storage | October 4, 2017 - 09:24 PM | Allyn Malventano
Tagged: x299, VROC, skylake-x, RAID-0, Optane, Intel, bootable, boot
We've been playing around a bit with Intel VROC lately. This new tech lets you create a RAID of NVMe SSDs connected directly to newer Intel Skylake-X CPUs, without the assistance of any additional chipset or other RAID controlling hardware on the X299 platform. While the technology is not fully rolled out, we did manage to get it working and test a few different array types as a secondary volume. One of the pieces of conflicting info we had been trying to clear up was can you boot from a VROC array without the currently unobtanium VROC key...
Well, it seems that question has been answered with our own tinkering. While there was absolutely no indication in the BIOS that our Optane Memory quad RAID-0 was bootable (the array is configurable but does not appear in the bootable devices list), I'm sitting here looking at Windows installed directly to a VROC array!
Important relevant screenshots below:
For the moment this will only work with Intel SSDs, but Intel's VROC FAQ states that 'selected third-party SSDs' will be supported, but is unclear if that includes bootability (future support changes would come as BIOS updates since they must be applied at the CPU level). We're still digging into VROC as well as AMD's RAID implementation. Much more to follow, so stay tuned!
We've been hearing about Intel's VROC (NVMe RAID) technology for a few months now. ASUS started slipping clues in with their X299 motherboard releases starting back in May. The idea was very exciting, as prior NVMe RAID implementations on Z170 and Z270 platforms were bottlenecked by the chipset's PCIe 3.0 x4 DMI link to the CPU, and they also had to trade away SATA ports for M.2 PCIe lanes in order to accomplish the feat. X99 motherboards supported SATA RAID and even sported four additional ports, but they were left out of NVMe bootable RAID altogether. It would be foolish of Intel to launch a successor to their higher end workstation-class platform without a feature available in two (soon to be three) generations of their consumer platform.
To get a grip on what VROC is all about, lets set up some context with a few slides:
First, we have a slide laying out what the acronyms mean:
- VROC = Virtual RAID on CPU
- VMD = Volume Management Device
What's a VMD you say?
...so the VMD is extra logic present on Intel Skylake-SP CPUs, which enables the processor to group up to 16 lanes of storage (4x4) into a single PCIe storage domain. There are three VMD controllers per CPU.
VROC is the next logical step, and takes things a bit further. While boot support is restricted to within a single VMD, PCIe switches can be added downstream to create a bootable RAID possibly exceeding 4 SSDs. So long as the array need not be bootable, VROC enables spanning across multiple VMDs and even across CPUs!
Assembling the Missing Pieces
Unlike prior Intel storage technology launches, the VROC launch has been piecemeal at best and contradictory at worst. We initially heard that VROC would only support Intel SSDs, but Intel later published a FAQ that stated 'selected third-party SSDs' would also be supported. One thing they have remained steadfast on is the requirement for a hardware key to unlock RAID-1 and RAID-5 modes - a seemingly silly requirement given their consumer chipset supports bootable RAID-0,1,5 without any key requirement (and VROC only supports one additional SSD over Z170/Z270/Z370, which can boot from 3-drive arrays).
On the 'piecemeal' topic, we need three things for VROC to work:
- BIOS support for enabling VMD Domains for select groups of PCIe lanes.
- Hardware for connecting a group of NVMe SSDs to that group of PCIe lanes.
- A driver for OS mounting and managing of the array.
Let's run down this list and see what is currently available:
Check. Hardware for connecting multiple drives to the configured set of lanes?
Check (960 PRO pic here). Note that the ASUS Hyper M.2 X16 Card will only work on motherboards supporting PCIe bifurcation, which allows the CPU to split PCIe lanes into subgroups without the need of a PLX chip. You can see two bifurcated modes in the above screenshot - one intended for VMD/VROC, while the other (data) selection enables bifurcation without enabling the VMD controller. This option presents the four SSDs to the OS without the need of any special driver.
With the above installed, and the slot configured for VROC in the BIOS, we are greeted by the expected disappointing result:
Now for that pesky driver. After a bit of digging around the dark corners of the internet:
Check! (well, that's what it looked like after I rapidly clicked my way through the array creation)
Don't even pretend like you won't read the rest of this review! (click here now!)