Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned • Hacker News Board

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#51

Post by incrudible » Sun, Jan 17, 2021, 12:53 PM UTC

singhrac wrote: post #13

d_silin wrote: post #7

I'd like to express my thoughts on this, from business exec point of view. Consumer-grade Optane SSDs are not competetive with flash memory, simple as that. On performance and write endurance, flash-based SSD are "good enough", while also much better on cost-per-GB vs Optane. This reduces available market for Optane to gaming enthusiasts and similar customers - a very small slice of the total PC market. Now, for ente…

Are gaming enthusiasts a small market (in dollar terms)? I think the move is probably somewhat reasonable in terms of cutting costs, but I wonder why they didn't just license the technology to someone with experience selling to gamers (e.g. Corsair).

Most games are still optimized for hard disks, sometimes duplicating assets multiple times to sequentially read them when necessary.

The latest consoles have SSDs+APIs that outclass anything available on PC today, so you might see fast NVMe SSDs as a requirement in the future. Even then, games will be optimized for the latency of SSDs, not Optane.

In short: No, that's not a market.

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#52

Post by adrian_b » Sun, Jan 17, 2021, 2:05 PM UTC

daxfohl wrote: post #32

exmadscientist wrote: post #24

Earlier quoted context omitted.

They also make glorious boot/OS drives. Those typically see a heavy mix of reads and writes, which is where Optane's dominance over NAND is strongest. The 900P/905P was pretty much the absolute best C: drive money could buy.

Genuinely curious, are disk writes a big part of booting? I'd imagine it to be mostly large sequential reads. Especially since operating systems have a long history of booting from HDD and still need reasonable support for that, I wouldn't expect the boot process has a whole lot of disk thrashing. I also can't think of a reason why it would need to.

This depends a lot on the operating system and on how it is configured.

On my Gentoo Linux, there are absolutely no writes during booting.

On the other hand, for my job, I have installed Windows 10 Enterprise on several kinds of embedded computers.

Some of those computers used some ancient model of Transcend SATA SSDs, which had an extremely low writing speed, of only around 40 Mbyte/s, much like a memory card (and not like a good one).

After the default installation of Windows 10, the booting was unbelievably slow, it could take maybe a half hour or so. When Windows 10 decided that it must install updates, it was much worse. The computer became available after booting only after a few hours.

I had to waste a few days with the unhelpful Windows Knowledge Base and with some more helpful Internet forums, until I discovered how to shut down all the Windows services that wanted to write to the SSD during booting, so that eventually the booting time of Windows reached an acceptable value of less than a minute.

On the same hardware Linux booted almost instantly, because the SSD reading speed was decent, unlike its writing speed.

There are Linux distributions that I do not use, e.g. Ubuntu, and I would not be surprised if those also come with default configurations that attempt to write during booting, e.g. for updating file indexing databases, or other such crap.

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#53

Post by Dylan16807 » Sun, Jan 17, 2021, 2:25 PM UTC

exmadscientist wrote: post #41

Dylan16807 wrote: post #37

Earlier quoted context omitted.

At queue depth 1 the 980 pro delivers 20k reads per second / 45k writes per second. That still sounds like a huge amount. Optane is faster, but is it enough to matter outside some extremely demanding niches?

The other reason Optane excels is latency. This is why single-threaded use cases, like system boot, love it. IOPS do not tell the whole story here. Consider disk A, at 1M IOPS, against disk B, at 1k IOPS. Suppose the workload is light, at only 500 IOPS, which are "small" enough to service quickly. Which disk is higher performing? You might say they're both capable of the task, so just get the cheaper one. This is wro…

> The other reason Optane excels is latency.

It's not an "other reason". IO operations at queue depth 1 are a direct measurement of latency. Queue depth 1 is not about throughput at all.

> Suppose the workload is light, at only 500 IOPS, which are "small" enough to service quickly.

I will assume the workload is light in CPU too, since spending half the time waiting for the disk is apparently not an instant disqualification.

> So disk A is in fact actually 1000x faster, if you're waiting on its result. Which, for single-threaded operations, you often are. If you're instead optimizing for throughput, you don't care.

If you're waiting on a bunch of results and disk A gets them to you significantly faster, it sounds like your initial premise of "only 500 IOPS" was wrong or misleading.

If you have a response time you want to meet, then you should measure IOPS with a sliding window of that many milliseconds. If it's still 500 at most, then disk B will still be fine for meeting your target.

If it turns out that "500" actually comes in bursts of 50 operations, and you want to be done in 10 milliseconds, then you should label your workload as "5k IOPS". Put in a drive that does at least 10k and you'll see all calculations done in under a frame; basically perfect latency. A drive a million times faster would have no practical difference.

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#54

Post by varispeed » Sun, Jan 17, 2021, 3:30 PM UTC

d_silin wrote: post #7

I'd like to express my thoughts on this, from business exec point of view. Consumer-grade Optane SSDs are not competetive with flash memory, simple as that. On performance and write endurance, flash-based SSD are "good enough", while also much better on cost-per-GB vs Optane. This reduces available market for Optane to gaming enthusiasts and similar customers - a very small slice of the total PC market. Now, for ente…

So if I am a professional, I am no longer good enough for Intel to buy this product? Optane gives insane compilation speed boost when you store large codebases on it. Now only big corporations will be able to get competitive advantage over smaller businesses not being able to afford enterprise deal with Intel. I think something like that should be illegal.

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#55

Post by K33P4D » Sun, Jan 17, 2021, 4:08 PM UTC

I believe they are chopping some segments within Intel to strategically play the next coming months with the release of their dedicated DX2 GPU (400-600$)by outsourcing its fab with either TSMC or Samsung...and they'll kill that also after a year, smh team blue cant catch a break these days.

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#56

Post by to11mtm » Mon, Jan 18, 2021, 10:50 PM UTC

hedora wrote: post #45

d_silin wrote: post #7

I'd like to express my thoughts on this, from business exec point of view. Consumer-grade Optane SSDs are not competetive with flash memory, simple as that. On performance and write endurance, flash-based SSD are "good enough", while also much better on cost-per-GB vs Optane. This reduces available market for Optane to gaming enthusiasts and similar customers - a very small slice of the total PC market. Now, for ente…

From a large-scale purchasing and architectural roadmap point of view, this tells me they won’t enjoy the economies of scale that flash enjoys, and the enterprise drives will be dead in a few years. Either that, or they’re transitioning to offer consumer grade NVDIMMs, but the hardware APIs for those are really difficult to take advantage of for general purpose compute.

> From a large-scale purchasing and architectural roadmap point of view, this tells me they won’t enjoy the economies of scale that flash enjoys, and the enterprise drives will be dead in a few years.

I think a lot of OEMs and users quickly figured out that a 128Tb m.2 SSD wasn't much more than a 32gb Optane module cost-wise, at which point you can have your whole boot drive and more on an SSD.

I'm not certain whether enterprise drives will die off as quickly, I suppose it depends on market trends. One marketed plus of 3D XPoint technology was far better write endurance and lack of need for garbage collection. If a data center has a lot of rolling data to process it might not be a bad fit.

Re: Intel Kills Off All Optane-Only SSDs for Consumers, No Replacements Planned

#57

Post by daxfohl » Mon, Jan 25, 2021, 4:26 PM UTC

cm2187 wrote: post #50

daxfohl wrote: post #43

Earlier quoted context omitted.

https://www.tomshardware.com/reviews/fastest-windows-10-boot... I should have just googled it. So 4 seconds for optane and 5 for Samsung. I'm surprised, but it looks legit. Though I wonder now if pcie4 changes things since the article was published.

That's my point in the other post. Is that 1 second boot time gain really worth the money? Not arguing against it for heavy duty enterprise workloads. But as a consumer, at one point the extra performance is wasted on them.

Sure, but if you're a power user with deep pockets, you may still be interested. But you'll want to know whether you can something tangible out of it on your workstation, and it's not exclusively a multitenant cloud database optimizer (or worse, a regression for typical workstation workload performance).

So, the Windows boot speed comparison provides an indication that it'll give some benefit to personal workstations too. Whether it's worth it or not is another question entirely.