Slashdot Mirror
Intel Launches Mainstream Optane SSD 800P Series Based On 3D Xpoint Memory (hothardware.com)
MojoKid writes: Intel just launched a new family of consumer-targeted Optane solid state drives today, dubbed the Intel Optane SSD 800P. Unlike Intel Optane Memory sticks, which accelerate hybrid storage configurations with hard drives through intelligent data caching, or Intel's flagship Optane SSD 900P that's aimed squarely at hardcore enthusiasts with big budgets, these M.2 form factor Intel Optane 800P SSDs target the meat of the mobile and desktop markets, with higher capacities than Optane Memory but more affordable pricing than the 900P. In the benchmarks, the Optane SSD 800P series drives offered a mixed-bag of performance, with sequential transfers that top out at about 1.4GB/s, but with small file transfers, 4K random and mixed workloads, latency, and overall QoS looking strong. Intel will initially be offering two drives in the Optane SSD 800P series, with M.2 80mm 58GB and 118GB models. Suggested pricing for the drives is $129 for the 58GB capacity and $199 for the 118GB drive.
"What matters" varies from person to person. These things have impressive endurance for their sizes and consistent low latency. There are uses for that.
I don't need them, but I'm sure someone else does. Let them buy it and go grab a 950 for yourself.
Maybe it's just me, but I struggle to see the point of Optane as compared to a regular flash-based SSD.
From what. I can see, it's optimised as a high speed but small SSD that can then be used as a cache for a spinning HDD.
In the benchmarks I've seen however, it doesn't seem to be markedly faster than a fast M.2 NVMe SSD.
Specialist Mac support for creative pros, Melbourne
This stuff is still kinda expensive, I wonder who even buys this
Careful there, not sure about these particular ones but Intel's current crop emaciates the Samsung even though on paper and synthetical benchmarks (IOPS and transfer rate) the Samsung does better.
Testing it myself, the Samsung does good until you transfer ~2-3GB and then it drops like a brick to the lower 1000s of IOPS instead of the 100,000 or more it gave you.
The problem there is that Samsung gives you a good RAM cache (backed up with huge capacitors on their DataCenter models) but once you request synced rates or exceed that cache, the controller lags behind. In the mean time, the Intel continues chugging along at 70-90k IOPS.
Custom electronics and digital signage for your business: www.evcircuits.com
Here's the short version of SSD history for the last 2 years. Micron bought Elpida or whatever and now there are 2 manufacturers of flash chips instead of 3. Suddenly there's a giant shortage on DDR4, GDDR5, and all flash products that store data. WHAT A COINCIDENCE. I'm sure it's not price fixing and artificial shortages caused by the almost monopoly that some asshole Asian regulators allowed the be made by the merger. So Intel's kinda big. Do they have their own flash chip manufacturing plant so there's FINALLY a third competitor back in the market or are they just having one of those two crooked rackets make Optane chips?
These are not really consumer products. Basically what you get out of an Optane drive is more durability (hence 10DWPB instead of 0.3DWPD @ 5 year warranty), and low latencies at low queue depths ( 10uS @ QD1 instead of 30uS+ @ QD1 for a NAND drive, random read).
But that's it. Everything else about Optane is non-competitive with NAND, at least so far. The price is ridiculous, the throughput at higher queue depths isn't really all that impressive.
No consumer is going to notice the lower latencies at low queue depths for the types of activities Intel advertises the product for (such as gaming), because all of those activities involve bulk reading and writing which NAND does very well, and most involve a certain degree of sequential reading or writing which modern NAND drives (such as the Samsungs) optimize very well. At higher queue depths the Intel advantage goes away entirely, so it wouldn't move the needle even for concurrent random server workloads.
Consumers for the most part never hit the actual durability limits of a NAND drive. For one, even with the lower durability the NAND drive is typically going to be double or triple the capacity of the Optane drive at the same price point, and for two, consumer use cases do not usually do 10 full drive writes per day over the life of the device or anything even close to that.
Basically, like the idiotic optane 'disk cache' Intel tried to hawk last year, this drive is a pretty bad fit as a consumer device. In this offering Intel at least put the proper durability that Optane is *supposed* to have in the specs. Around 8900TB... nothing to sneeze at when most NAND drives have durabilities in the 200-400TB range. There is something to be said for that, even without real-life integrity/retention data available yet. But... it's still just not a consumer-oriented device.
-Matt
I thinking I'm missing the point of these.
More expensive than a Samsung EVO 960.
Smaller than a 960.
Half the read performance of a 960.
Half the write performance of a 960.
I was excited when I first read the headline, I thought, FINALLY samsung will have some competition again and prices will come down. So much for that dream
Relative latencies:
SRAM 1X
DRAM 10X
Optane 100X
NAND 100,000X
Rust 10,000,000X
https://hothardware.com/review...
The same gains as going from HDD to SDD (1000X) are realized again going from SDD to Optane.
Probably one of those things, you don't know why you'd even need it, until you have it, then you won't want to live without it.
Or you're not demanding enough to even notice either way.
Probably one of those things, you don't know why you'd even need it, until you have it, then you won't want to live without it. Or you're not demanding enough to even notice either way.
Or it's just not convenient to split the bits that could use Optane. I had the same issue with SSD/HDD, apart from bulk media (photos, audio, video) the primary space consumer is games. And a lot of that is cut scenes and textures and music loops and voice acting etc. that don't benefit a lot, while the main executable, scripts, maps, UI elements etc. is 1-5% of the game. But as long as Steam doesn't give me an easy way to say this 1GB go on SSD, the remaining 19GB go on HDD it's not worth the hassle, let's just wait until the price drops so I can put all 20GB on SSD. And I think Optane will be the same, it could be useful for a few things but most of it would be wasted.
Live today, because you never know what tomorrow brings
I would be happy with 64-96 gigs of Optane ram, and no SSD
Probably be faster than my 80 gig X25 8 gig setup now.
The hype gave way to reality and the devil you don't know with underwhelming TBW v. flash when price factored in. I've got to hand it to Intel for at least trying something other than flash but Xpoint is fundamentally a lost cause in terms of mass appeal.
I pray for silicon gods to mass-produce super high density MRAM and put flash out of its misery. While the IOPs are impressive using this capacity in any kind of sustained way is basically impossible with current SSD systems. You'd fry the damn thing in a matter of days.
You don't mean 'decimate' either, as that simply reduces by 10%. I think he meant 'annihilate'.
These things CLAIM to have impressive endurance. That remains to be seen.
During Xpoint's development, just about every promised spec, including endurance, was decreased by several orders of magnitude.
When the first generation of Xpoint devices launched, they included a huge amount of extra hardware for over provisioning. If Xpoint doesn't need it, why include it? And why so much of it (more than an SSD needs).
Further, the only endurance spec that matters is the one on the box. Samsung's products carry a similar warranty for a much lower cost. And they're proven in the real world.
Anyone needing that small latency advantage for random access workloads already has something much better. RAM.
Even with the ridiculous RAM prices now, the trend is moving to in-memory computing for workloads that benefit from it.
If you care about latency you're going to want to just keep your shit in RAM. That's the trend on the enterprise side.
Consumers and even high end gamers do not benefit from that small latency advantage. Optane drives only beat traditional drives when you do synthetic, random access tests or crank the queue depth down for no reason. People moving large files don't benefit. Gamers don't benefit - assets are loaded from sequential blobs and (ideally) kept in RAM/VRAM. People working with media and shit don't benefit as their video/design/etc. files are big sequential blobs.
About the only real life, consumer level workloads that I can see benefiting are virus scans and code compiling.
The focus on latency by review sites is because INTEL IS PAYING THEM.
This started back with the 900P on PC Perspective. PC Perspective developed their own benchmark just for reviewing these new drives from Intel.
https://www.pcper.com/reviews/...
Except, that's not what happened. What happened was Intel approached "Shrout Research", which is run by Ryan Shrout of PC Perspective. Intel paid him money for a "white paper", gave him samples of the product for that white paper, and gave him direction on what the white paper should say and how to test things.
PC Perspective then took the conclusions from the white paper and presented it as an unbiased review, without disclosing the fact that the site owner was paid for that shit, or that the site was using the samples given for the "white paper" as the samples tested in the review (which is why they had so many to test with when other sites were lucky to get one), or that they white paper even existed.
PC Perspective got called out on all of this. Their response? Adding a vague disclaimer to the very end of the very last page of the review.
Disclaimer:
Ownership of PC Perspective also operates consulting firm Shrout Research. Shrout Research has provided research, consulting, and analysis for many companies in the high-tech industry including AMD, Intel, NVIDIA, Qualcomm, and Arm. A white paper was published by Shrout Research using 900P engineering samples and was commissioned by Intel. All testing for this review was conducted separately and on retail samples of the 900P. This review was not commissioned or sponsored by Intel.
That disclaimer should actually say: Intel paid for this review and our new testing methodology that focuses on the only thing that Optane is good at.
We know that the review testing was not conducted separately from the white paper (people have gone through both and shown that shit was copied) and we know that they didn't buy their own retail products to test with (based on the date the review was published and the availability of the product).
PC Perspective has been scrambling to downplay this and spin it ever since some Scottish YouTube guy called them out on this shit. But at the end of the day, tech sites that review these things are suddenly starting to care about latency as the biggest thing? GEE, I WONDER WHY!
Careful there, not sure about these particular ones but Intel's current crop emaciates the Samsung even though on paper and synthetical benchmarks (IOPS and transfer rate) the Samsung does better.
Testing it myself, the Samsung does good until you transfer ~2-3GB and then it drops like a brick to the lower 1000s of IOPS instead of the 100,000 or more it gave you.
The problem there is that Samsung gives you a good RAM cache (backed up with huge capacitors on their DataCenter models) but once you request synced rates or exceed that cache, the controller lags behind. In the mean time, the Intel continues chugging along at 70-90k IOPS.
What drive are you testing, exactly? Is it an NVMe drive?
Are you using the proper drivers from Samsung? If you're on Windows, the default driver from MS is kind of shitty. You'll want to download the NVMe driver from Samsung. I'm not sure what the situation is on Linux.
The 960 series from Samsung has much better sustained IOPS performance after reaching steady state and in an extended load than the 950 series. It approaches that of the Samsung/Intel enterprise drives (which have gobs of over provisioning). I'm not sure how the 860 series behaves, but that's limited by SATA anyway.
You can drastically improve minimum IOPS by increasing over provisioning using Samsung Magician. I haven't tried this on any of the boxes I care about performance on, though. On those I use RAID.
Google calc: 10 * 58 GB / (3 GB/s * 24 hours ) = 0.22% gum-stick NVME duty cycle
I've plucked interface bandwidth from the article:
With a mere two more orders of magnitude of endurance, this small Optane product would make a perfect ZFS SLOG drive (aka ZIL).
The 3 GB/s bandwidth on an M.2 gum-stick is not unreasonable for a busy(ish) ZFS server rated for peak operation over at most a 20% operational duty cycle (34 hours per week).
And this is not unreasonable ZIL write bandwidth once you declare all NFS write traffic 100% synchronous (per the standard), which BSD really wants to do in the first place (Linux not so much, last time I checked).
I'm pretty sure this slack-ass durability is why the memory product is so long delayed.
Just imagine if I had plugged in the bandwidth of an entire DDR4 lane.
If Holly didn't contain some future Intel Optane product, I'll eat my radioactive hair net requisition forms.
Holly Returns
Kicking bottom, or what?
I would say for every spec that matters, optane is a huge improvement over both the Samsung 950 and 960. I had two Samsung 950 PRO's (in RAID-0), and then replaced them with a single 960 PRO. Just like the linked article shows, performance on these are all over the place, often not demonstrating good performance until you hit high queue depths, which isn't "common" for a single user desktop.
Just a quick test I ran just now shows read speeds of 1903MB/s, and write of 1076MB/s. And then a second run show 1724/938. Unpredictable and bursty. Optane is just better at maintaining a consistent speed because of the low latencies. That also means it works better with single threaded applications no matter if they use large buffer or small, overlapped I/O or not. So poorly written applications (from an I/O perspective -- which a LOT are) will actually perform much better.