How fast - plenty especially when using in a vsan array. I manage a Software Defined Storage array with Micron 9300 Pros on a dual port 25GbE iSCSI connection. I can start up a 300GB RAM HANA DB in 2 minutes. How big - will depend on the DWPD rating. Micron 9300 Pro series are 3.84, 7.68, & 15.36TB all at 1DWPD. Micro 9300 MAX series are 3.2, 6.4, & 12.8TB all at 3DWPD. I would assume these will have similar capacities. How much - if you have to ask you cannot afford it.
very smart analysis, i dont know why they dont give you a nobel prize. its like saying TSMC 5nm transistors are better than older ones. therefore there is no point in anything else existing.
Stop being a douche (if you can, that is). I know you get a tingly sensation in your peepee every time you think of SSDs but they are not the answer to everything. If you need DRAM levels of performance then NAND *will not* do it. And it's not like NAND manufacturers will be eager to give you stuff for free because they're DEFINITELY not the same companies manufacturing DRAM (Samsung? Micron? For example...).
You made a stupid comparison and you think getting sarcastic will get you out of it? Sure, and if they improve energy efficiency at this rate pretty soon they'll generate electricity.
The example of consoles is probably the worst because they were stuck with *slow* SATA HDDs for the past ~15 (!) years. Storage was the only thing that was not upgraded for all that time - small, low performance 5400RPM SATA2 HDDs. Of course it would become a severe bottleneck at some point. They benefit a lot because boosting performance by 2-5GB/s means boosting it by 2000-5000%. This makes a difference for real life performance but still doesn't put it anywhere near DRAM levels of performance.
have u heard of this thing called "network", is it possible that some1 might not care to use RAM or SSD that is faster than his network (in bw or latency) but does care not use storage that is slower than his network.
and oh i dont know there are two big consoles coming this year that made that exact point. very little generational jump in memory size compared to previous generations, but they made the point that reading disk at approx 5GB (xbox) and 9GB (ps) per second changes what you can do with it.
Rather than making snide comments to me, why don't you make valid counter arguments. When I said that even the fastest SSDs are orders of magnitude slower than DRAM, I made a factual statement that refuted your "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM..." Even Optane Memory acts as nothing more than a large cache between the DRAM and storage on SAP HANA hosts.
I have heard of this thing called a "network," however, your assessment of a home network is quite wrong. Even a slow 5400 RPM USB powered drive is fast enough on sequential reads and writes to take the full bandwidth of a 1GbE connection. Most homes don't have more than GbE for their home network. With that speed networking having SSD on it is a waste as you will be network limited pretty bad.
Yes SSD is getting faster and that is a good thing, but it has a VERY long way to go before it can ever be a competitor to DRAM.
you don't know what u r talking about. Cobble together some anecdotes and generalize about the whole market. I said competitive pressure. that means any application not every application. and I already gave u an example that increased its Oct investment in disk at the expense of ram.
your statement was no such thing as fact that refuted my statement. again its like saying no other node from the past can compete with tsmc 5nm, and that it exclusively sets the price of transistors.
the rest of it was nonsense about home networks and what not that I could never respond too. its like me saying more supply prices go down, and u talk about most Pol can't buy meat because apple are cheaper.
Much of the benefit of an SSD comes from access times, and while a network does add significant latency, it is still at least an order of magnitude faster (perhaps two) than a hard disk's access time. This is why network-based SSD block storage is a viable thing.
I know that SSD based block storage is a very viable thing. I run a DC that uses NVMe based SDS on a dual port 25GbE iSCSI connection. The difference in performance between that and our old 8Gb Fibre Channel 10k array is night and day. However, asfacea's comment seemed to be more home network related than storage network related.
@schujj07, don't worry about @azfacea. Valid counter arguments are a foreign concept to them. For the past few years tt's always some immature comment about how SSDs already replaced all HDD, HDD aren't used by anyone because SSDs already do everything, better capacity, better price. Now that the recording got old they switched to "OMG GBps, will be better than RAM".
Keep in mind that they appear to have the understanding of a child, looking at the flashy numbers and peak performance. Like someone bulging their eyes at phone camera MP count and immediately concluding that DSLRs or dedicated cameras will be dead by the end of the month.
its not a conspiracy theory if several govt are investigating it. lets also forget how so many ppl have felt about dram in the last few years. those are all my alt accounts.
but let's focus on the real issue here which is that I have posted too many comments. but i have a soln for your problem. piss off. don't read them if u don't like comments. u r in the wrong place not me.
Bandwidth is only one part of the equation. In majority of workloads latency is far more critical because that is what the end-user actually experiences. There is still an order of magnitude difference between DRAM (10's of nanoseconds) and SSD/NAND (10's of microseconds). No interface is going to solve the latency issue because it boils down to the fundamental physics of DRAM and NAND architectures.
All the hype around 3D Xpoint was primarily because it had a latency that was - from the marketing marketing hype - approaching that of DRAM. But even XPoint latency, which is far superior to any NAND on the market, is still way too high to replace DRAM for general purpose computing. The idea that NAND could replace DRAM based on iterations of current technology is is nonsense.
you're so focused on your obnoxious replies that you can't even see the fact that ssds are mostly the exact same dram companies with the exact same price fixing waves
Meanwhile here comes DDR5 with 2-3X the bandwidth of DDR4.
This is like saying "if mobile GPUs keep getting better there will be no reason to have desktop GPUs". Its factually incorrect. DRAM will always be faster then NAND, and you will always have a need for both. They are different types of memory for different applications.
if anand tech don't like the continuity between story and comments they can always make comments a toggle able section or use discuss or something. I am using comments exactly as the mainstream does, and not abusing them in any special manner.
I am very skeptic of "group think". and have strong opinions which are mostly right but also sometimes wrong. that does lead to confrontatious threads sometimes. if u can't bear that get out of the kitchen. go watch sesame street instead.
when ppl attack with condescending dismissals implying my ignorance, and w/- facts BTW, I am going get back at them
Just because you think you are right doesn't mean you are. The people who have responded to you aren't using "group think" to dismiss your point. The fact that you are asking that we provide hard facts to counter your "opinion" but don't provide any hard evidence yourself shows ignorance on your part. Multiple people have no provided you with evidence to counter your point but you don't listen. That puts us in an impossible position where no matter what we say, how much evidence we provide, etc... in your mind we will always be wrong and you will always be right. Don't forget that the people who are countering your argument and opinions, like @Kristian Vättö, & myself work in the IT field. For myself I deal with these things on a daily basis and have studied it for years.
here is where the negativity in this thread started and its not me:
i said "competitive pressure" and not replace DRAM with SSD, he replied:
" Even the fastest SSD are several orders of magnitude slower than DRAM. "
in other words i am that ignorant. he didnt even bother to read or think about my comment. just an impulsive pushback that i am wrong and ignorant. dont have have a clue, and if only I wasnt ignorant of DRAM performance numbers I'd know better than to say that.
In other words not a counter argument, just an education reply is what he gave. and w/- facts BTW. he is dead wrong, I am right, with this kinda of performance growth for SSDs it truly means they are begging to compete with DRAM in at least some applications. and Xbox/PS is perfect example.
he started with a condescending dismissal, and i gave him a taste of his own medicine with the network comment, i could have phrased it differently but why should I? when he is being like that.
now what does he do, turn it into an argument about the messenger. and so does the rest of "group think" echo chamber
There is absolutely no way that SSD can put competitive pressure on DRAM. I stated earlier that even Optane, the fastest SSD & can be used as NVDIMMs, is still only able to be used as a caching layer as an NVDIMM between RAM and normal Storage. Even at 60 DWPD endurance, NVDIMM Optane would burn through its R/W cycles very quickly if it were the RAM in a system. Yes the greater the amount of RAM the longer it would take, but that is only slowing the the inevitable. Not to mention if it was your only RAM it would TANK your performance. Think about putting SDRAM into a modern system and see what would happen to your performance. Bandwidth is important but latency is the biggest issue and SDRAM has far lower latency than Optane.
Lets get into your PCIe 4/5 VS DDR4/5 argument. The fastest SSD will typically use an x4 bus, some like the Samsung P1725a use a PCIe 3 x8 in a HHHL for enterprise usage, however, that is still only the bandwidth of PCIe 4 x4. PCIe 4 x4 has 8GB/s max theoretical bandwidth and PCIe 5 will double that to 16GB/s. Even the non-existent PCIe 5 x4 SSD has lower max bandwidth than the slowest DDR4 RAM which is DDR4-2133, 16GB/s vs 17GB/s. Modern CPUs all use dual-channel RAM so that makes the bandwidth for the system minimum 34GB/s but if we figure that most computer use at least dual 2666MHz now that makes it 42.5GB/s. Again this is sheer bandwidth numbers. Also all those 5.5GB/s numbers you see on SSD are sequential data transfers at a queue depth of 64 or 128.
I did read and think about your "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM which is still controlled by a price fixing triad" comment. I dismissed the price fixing triad part and focused on the SSD performance & competitive pressure part. Your statement about it being able to provide competitive pressure is so blatantly wrong it is comical. I already went over the numbers earlier in the post so I won't rehash that here. With the PS5/XBX we will see better loading times and that's about it with the faster storage. If the storage was running at the speed of RAM instead of 0.1 sec loading time it would be 0.0001 sec. However, if we were to replace the RAM speed with something equal to the SSD performance, we would see the PS4/XBX perform like the PS2/Xbox. The only applications that are sped up by faster storage are applications that are already storage speed limited, ie loading times in games. The reason is the data is stored on the drive and having a faster drive means the data gets sent to the CPU faster. I know this advantage very well. When the data center I mange upgraded from an 8Gb Fibre Channel SAN with 10k spinning disks to a dual port 25GbE iSCSI software defined storage (SDS) array with NVMe disk, loading times for SAP HANA DBs decreased dramatically. On the old SAN it would take 20 minutes to start a 300GB RAM DB, FYI HANA is an in RAM DB and for every GB of disk needed for the DB you need the same amount of RAM. Now with the SSD backed SDS array that same DB loads in 2 minutes.
Your berate me on the network claim but your entire post on that was nonsensical. I assumed you were talking about a home network, but it was hard to follow the post. "have u heard of this thing called "network", is it possible that some1 might not care to use RAM or SSD that is faster than his network (in bw or latency) but does care not use storage that is slower than his network." The only thing someone can figure is that you are talking about a home network and not a SAN. As I had said even a slow HDD will be plenty for 1GbE network. Say you are a video editor, are you going to be doing the editing over your network onto some NAS or will you be editing the file locally? The answer is locally and then transfer the file to the NAS for long term storage/backup. Since most home have 1GbE network and the transfers will be sequential in design, HDD storage will be fast enough for that network speed. You are so severely network limited at 1Gb that using an SSD on 1GbE network is just a stupid waste of money. If you are lucky enough to have the money for 5GbE or 10GbE network, then yes SSD would work or having a RAID 50 array would make sense.
I think at this point I have covered almost all your incorrect talking points. FYI just because you say "he is dead wrong, I am right" doesn't make you right. You might not have liked my reply about how much slower SSD is to DRAM, but it was a counter argument. I didn't think I needed to provide you with hard numbers, however, by your comment "just an education reply is what he gave. and w/- facts BTW" it is obvious I should have. I figured it was common knowledge the performance difference between DRAM and SSD. However, I should have know that common knowledge isn't very common.
In case you didn't get it from the middle part of my post, I actually do know what I am talking about as this is my profession. Please think before you post something so utterly ridiculous as "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM" and then dismiss a legitimate counter post. FYI there are tech experts who visit this site to learn about the new things coming out and see reviews of products to help us make our decisions for the stuff we manage.
you just said the same thing as before only using more words. "dram is faster therefore nand cant compete" completely missing the point that SsD is becoming fast enough for many applications. and missing the fact sad are improving faster than dram in all of size, price, bandwidth and latency. than dram in the past 5 years. I'll wait 4 your mea culpa in a few years
Wow you are such a hypocrite. You complain that I post without facts, then you complain when I listed in-depth facts. Your belief with SSD is so engrained in your being that there is NOTHING anyone here could say, write, prove, etc... for you to realize you are wrong. For us IT Professionals you are like talking to a wall or are just a pebcak error.
@azfacea - the main hole in your argument is latency. When you say "SSDs are improving faster than DRAM in... latency" you are **sort of** correct. Absolutely, more sophisticated controllers as well as the NVMe protocol and PCIe interfaces have demonstrably reduced the latency of high end SSDs, particularly when they are subjected to intensive workloads. What you are referencing here is the overall latency - or "response time" of SSDs, which includes interface, protocol and controller overheads. At that level, you are absolutely correct when you say latency is improving (on high end/enterprise devices).
However, here's the problem: As Kristian Vättö pointed out to you above, the fundamental design of NAND flash means that it takes substantial time to read, program and (critically!) erase the cell. This latency, inherent to NAND flash cells, hasn't really changed. In fact if anything, the move from SLC -> MLC -> TLC -> QLC, which is a significant driver in the capacity and price improvements you are touting, has seen a substantial increase in latency at the NAND flash layer. Even ignoring this, according to Kristian's numbers above, we're still at the level of 10s of microseconds for NAND vs 10s of nanoseconds for DRAM. That's in the region of 1000 times higher latency.
Here are two articles by Kristian Vättö which explore how NAND flash works (planar and 3D-NAND) and are useful in understanding the fundamental physics at play here. Kristian used to be the SSD editor here at Anandtech and now works for Samsung. - https://www.anandtech.com/show/5067/understanding-... - https://www.anandtech.com/show/8216/samsung-ssd-85... They're old articles, but that doesn't matter. The fundamental design hasn't changed and (obviously!) fundamental physics don't change.
3D-XPoint marketing hype claimed it would approach DRAM latency, but it's still nowhere near responsive enough to challenge DRAM, even ~3 years (?) after release. Maybe RE-RAM or MRAM or some other technology comes along and challenges the DRAM "triad", but that absolutely will require new technology.
We're not going to get anywhere near DRAM latency by iterating on existing NAND flash technology. Ryzen CPUs have shown us we can get measurable system-wide performance gains from dropping particular RAM latency settings from 18, to 16, to 14 clock cycles. Remember, NAND flash at the cell level is in the order of 1000 times slower. It's simply not fit-for-purpose as a challenger for DRAM.
TL;DR: NAND Flash cells, because of physics, have vastly highly latency than DRAM. While it's good to be optimistic and excited about the future of tech, NAND latency simply isn't going to get anywhere near DRAM through gradual iteration, which seems to be what you are suggesting.
Thank you @rhysiam for going even further in explaining this. If I remember correctly MRAM is already as fast as DRAM but its capacity is so much smaller that it isn't feasible for general computing. I do believe it is used in satellites though.
@azfacea if you still don't believe us build a computer with the fastest PCIe 4 SSD you can find and only 1GB RAM. Install Win 10 onto it and try using the computer. You will see the effect of much higher latency and the protocol overhead first hand. That computer will be absolutely impossible to use, especially if you try having multiple browser tabs open. The lack of RAM is the problem. I have a laptop from 2013 with 4GB RAM and Win 10 on it with a Samsung 850 Evo SSD. Even having 2GB "free" on bootup this laptop is slow. It is having to disk swap so much that it affects the performance quite a lot. Remember that is with 4x more RAM than I am saying you try.
If there is need for very high amount of fast swap space, than nowadays bandwidth and latencies of storage can compete almost with devices from generation before (or some even <1 decade). With DDR4 there is enough bandwidth for common applications and with widespread mainboards that most users wont experience limiting performance on daily usage patterns. If DDR4 (DDR3?) is that much cheaper than later DDR5 one would need ~35 32GB ram modules (each on todays price level for around 1/2$ for each GB) at a ~500$ cost for 1TB.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
40 Comments
Back to Article
06GTOSC - Wednesday, April 8, 2020 - link
What is the expected max writes from a drive like this?Billy Tallis - Wednesday, April 8, 2020 - link
Based on their usual product naming scheme, these should be 1 DWPD and 3 DWPD.Hulk - Wednesday, April 8, 2020 - link
Normal questions. How fast? How big? How much?schujj07 - Wednesday, April 8, 2020 - link
How fast - plenty especially when using in a vsan array. I manage a Software Defined Storage array with Micron 9300 Pros on a dual port 25GbE iSCSI connection. I can start up a 300GB RAM HANA DB in 2 minutes.How big - will depend on the DWPD rating. Micron 9300 Pro series are 3.84, 7.68, & 15.36TB all at 1DWPD. Micro 9300 MAX series are 3.2, 6.4, & 12.8TB all at 3DWPD. I would assume these will have similar capacities.
How much - if you have to ask you cannot afford it.
azfacea - Wednesday, April 8, 2020 - link
cool, if SSD performance keeps improving like this, it can provide competitive pressure to DRAM which is still controlled by a price fixing triad.schujj07 - Wednesday, April 8, 2020 - link
Even the fastest SSD are several orders of magnitude slower than DRAM.azfacea - Wednesday, April 8, 2020 - link
very smart analysis, i dont know why they dont give you a nobel prize. its like saying TSMC 5nm transistors are better than older ones. therefore there is no point in anything else existing.close - Thursday, April 9, 2020 - link
Stop being a douche (if you can, that is). I know you get a tingly sensation in your peepee every time you think of SSDs but they are not the answer to everything. If you need DRAM levels of performance then NAND *will not* do it. And it's not like NAND manufacturers will be eager to give you stuff for free because they're DEFINITELY not the same companies manufacturing DRAM (Samsung? Micron? For example...).You made a stupid comparison and you think getting sarcastic will get you out of it? Sure, and if they improve energy efficiency at this rate pretty soon they'll generate electricity.
The example of consoles is probably the worst because they were stuck with *slow* SATA HDDs for the past ~15 (!) years. Storage was the only thing that was not upgraded for all that time - small, low performance 5400RPM SATA2 HDDs. Of course it would become a severe bottleneck at some point. They benefit a lot because boosting performance by 2-5GB/s means boosting it by 2000-5000%. This makes a difference for real life performance but still doesn't put it anywhere near DRAM levels of performance.
Hul8 - Saturday, April 11, 2020 - link
I don't think there's a Nobel price for correcting hot takes on the internet.azfacea - Wednesday, April 8, 2020 - link
have u heard of this thing called "network", is it possible that some1 might not care to use RAM or SSD that is faster than his network (in bw or latency) but does care not use storage that is slower than his network.azfacea - Wednesday, April 8, 2020 - link
and oh i dont know there are two big consoles coming this year that made that exact point. very little generational jump in memory size compared to previous generations, but they made the point that reading disk at approx 5GB (xbox) and 9GB (ps) per second changes what you can do with it.schujj07 - Wednesday, April 8, 2020 - link
Rather than making snide comments to me, why don't you make valid counter arguments. When I said that even the fastest SSDs are orders of magnitude slower than DRAM, I made a factual statement that refuted your "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM..." Even Optane Memory acts as nothing more than a large cache between the DRAM and storage on SAP HANA hosts.I have heard of this thing called a "network," however, your assessment of a home network is quite wrong. Even a slow 5400 RPM USB powered drive is fast enough on sequential reads and writes to take the full bandwidth of a 1GbE connection. Most homes don't have more than GbE for their home network. With that speed networking having SSD on it is a waste as you will be network limited pretty bad.
Yes SSD is getting faster and that is a good thing, but it has a VERY long way to go before it can ever be a competitor to DRAM.
azfacea - Thursday, April 9, 2020 - link
you don't know what u r talking about. Cobble together some anecdotes and generalize about the whole market. I said competitive pressure. that means any application not every application. and I already gave u an example that increased its Oct investment in disk at the expense of ram.your statement was no such thing as fact that refuted my statement. again its like saying no other node from the past can compete with tsmc 5nm, and that it exclusively sets the price of transistors.
the rest of it was nonsense about home networks and what not that I could never respond too. its like me saying more supply prices go down, and u talk about most Pol can't buy meat because apple are cheaper.
azfacea - Thursday, April 9, 2020 - link
pct investment*not "Oct investment"
GreenReaper - Thursday, April 9, 2020 - link
Much of the benefit of an SSD comes from access times, and while a network does add significant latency, it is still at least an order of magnitude faster (perhaps two) than a hard disk's access time. This is why network-based SSD block storage is a viable thing.schujj07 - Thursday, April 9, 2020 - link
I know that SSD based block storage is a very viable thing. I run a DC that uses NVMe based SDS on a dual port 25GbE iSCSI connection. The difference in performance between that and our old 8Gb Fibre Channel 10k array is night and day. However, asfacea's comment seemed to be more home network related than storage network related.close - Thursday, April 9, 2020 - link
@schujj07, don't worry about @azfacea. Valid counter arguments are a foreign concept to them. For the past few years tt's always some immature comment about how SSDs already replaced all HDD, HDD aren't used by anyone because SSDs already do everything, better capacity, better price. Now that the recording got old they switched to "OMG GBps, will be better than RAM".Keep in mind that they appear to have the understanding of a child, looking at the flashy numbers and peak performance. Like someone bulging their eyes at phone camera MP count and immediately concluding that DSLRs or dedicated cameras will be dead by the end of the month.
rpg1966 - Wednesday, April 8, 2020 - link
Ignore him, he has this price-fixing conspiracy theory in his brain, and can't help but comment on it every time there's a slightly-relevant article.azfacea - Thursday, April 9, 2020 - link
its not a conspiracy theory if several govt are investigating it. lets also forget how so many ppl have felt about dram in the last few years. those are all my alt accounts.but let's focus on the real issue here which is that I have posted too many comments. but i have a soln for your problem. piss off. don't read them if u don't like comments. u r in the wrong place not me.
deil - Thursday, April 9, 2020 - link
~100x slower, sata is 1000x slower than DRAM.azfacea - Thursday, April 9, 2020 - link
and whats the math pcie 4 and 5 SSD VS ddr4 and ddr5could u also do the math on GB per dollar, max GB, TB, ... in a 1u, 2u, ....
include some raid setups in your TCO.
Kristian Vättö - Friday, April 10, 2020 - link
Bandwidth is only one part of the equation. In majority of workloads latency is far more critical because that is what the end-user actually experiences. There is still an order of magnitude difference between DRAM (10's of nanoseconds) and SSD/NAND (10's of microseconds). No interface is going to solve the latency issue because it boils down to the fundamental physics of DRAM and NAND architectures.rhysiam - Saturday, April 11, 2020 - link
Thank you @Kristian. This. Just this!All the hype around 3D Xpoint was primarily because it had a latency that was - from the marketing marketing hype - approaching that of DRAM. But even XPoint latency, which is far superior to any NAND on the market, is still way too high to replace DRAM for general purpose computing. The idea that NAND could replace DRAM based on iterations of current technology is is nonsense.
kn00tcn - Wednesday, April 8, 2020 - link
you're so focused on your obnoxious replies that you can't even see the fact that ssds are mostly the exact same dram companies with the exact same price fixing wavesazfacea - Wednesday, April 8, 2020 - link
what u say is patently false. 6.5 + China insurgency is not at all the same as 3 entrenched. we've seen how diff is x86 with just one insurgent.obnoxious indeed. cant see facts indeed.
TheinsanegamerN - Friday, April 10, 2020 - link
Meanwhile here comes DDR5 with 2-3X the bandwidth of DDR4.This is like saying "if mobile GPUs keep getting better there will be no reason to have desktop GPUs". Its factually incorrect. DRAM will always be faster then NAND, and you will always have a need for both. They are different types of memory for different applications.
azfacea - Thursday, April 9, 2020 - link
if anand tech don't like the continuity between story and comments they can always make comments a toggle able section or use discuss or something. I am using comments exactly as the mainstream does, and not abusing them in any special manner.I am very skeptic of "group think". and have strong opinions which are mostly right but also sometimes wrong. that does lead to confrontatious threads sometimes. if u can't bear that get out of the kitchen. go watch sesame street instead.
when ppl attack with condescending dismissals implying my ignorance, and w/- facts BTW, I am going get back at them
schujj07 - Friday, April 10, 2020 - link
Just because you think you are right doesn't mean you are. The people who have responded to you aren't using "group think" to dismiss your point. The fact that you are asking that we provide hard facts to counter your "opinion" but don't provide any hard evidence yourself shows ignorance on your part. Multiple people have no provided you with evidence to counter your point but you don't listen. That puts us in an impossible position where no matter what we say, how much evidence we provide, etc... in your mind we will always be wrong and you will always be right. Don't forget that the people who are countering your argument and opinions, like @Kristian Vättö, & myself work in the IT field. For myself I deal with these things on a daily basis and have studied it for years.schujj07 - Friday, April 10, 2020 - link
Edit: Multiple people have NOW provided you with evidence to counter your point but you don't listen.azfacea - Thursday, April 9, 2020 - link
here is where the negativity in this thread started and its not me:i said "competitive pressure" and not replace DRAM with SSD, he replied:
" Even the fastest SSD are several orders of magnitude slower than DRAM. "
in other words i am that ignorant. he didnt even bother to read or think about my comment. just an impulsive pushback that i am wrong and ignorant. dont have have a clue, and if only I wasnt ignorant of DRAM performance numbers I'd know better than to say that.
In other words not a counter argument, just an education reply is what he gave. and w/- facts BTW. he is dead wrong, I am right, with this kinda of performance growth for SSDs it truly means they are begging to compete with DRAM in at least some applications. and Xbox/PS is perfect example.
he started with a condescending dismissal, and i gave him a taste of his own medicine with the network comment, i could have phrased it differently but why should I? when he is being like that.
now what does he do, turn it into an argument about the messenger. and so does the rest of "group think" echo chamber
sa666666 - Thursday, April 9, 2020 - link
It's obvious you have a huge chip on your shoulder. Looks like another HStewart in the making.schujj07 - Thursday, April 9, 2020 - link
There is absolutely no way that SSD can put competitive pressure on DRAM. I stated earlier that even Optane, the fastest SSD & can be used as NVDIMMs, is still only able to be used as a caching layer as an NVDIMM between RAM and normal Storage. Even at 60 DWPD endurance, NVDIMM Optane would burn through its R/W cycles very quickly if it were the RAM in a system. Yes the greater the amount of RAM the longer it would take, but that is only slowing the the inevitable. Not to mention if it was your only RAM it would TANK your performance. Think about putting SDRAM into a modern system and see what would happen to your performance. Bandwidth is important but latency is the biggest issue and SDRAM has far lower latency than Optane.Lets get into your PCIe 4/5 VS DDR4/5 argument. The fastest SSD will typically use an x4 bus, some like the Samsung P1725a use a PCIe 3 x8 in a HHHL for enterprise usage, however, that is still only the bandwidth of PCIe 4 x4. PCIe 4 x4 has 8GB/s max theoretical bandwidth and PCIe 5 will double that to 16GB/s. Even the non-existent PCIe 5 x4 SSD has lower max bandwidth than the slowest DDR4 RAM which is DDR4-2133, 16GB/s vs 17GB/s. Modern CPUs all use dual-channel RAM so that makes the bandwidth for the system minimum 34GB/s but if we figure that most computer use at least dual 2666MHz now that makes it 42.5GB/s. Again this is sheer bandwidth numbers. Also all those 5.5GB/s numbers you see on SSD are sequential data transfers at a queue depth of 64 or 128.
I did read and think about your "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM which is still controlled by a price fixing triad" comment. I dismissed the price fixing triad part and focused on the SSD performance & competitive pressure part. Your statement about it being able to provide competitive pressure is so blatantly wrong it is comical. I already went over the numbers earlier in the post so I won't rehash that here. With the PS5/XBX we will see better loading times and that's about it with the faster storage. If the storage was running at the speed of RAM instead of 0.1 sec loading time it would be 0.0001 sec. However, if we were to replace the RAM speed with something equal to the SSD performance, we would see the PS4/XBX perform like the PS2/Xbox. The only applications that are sped up by faster storage are applications that are already storage speed limited, ie loading times in games. The reason is the data is stored on the drive and having a faster drive means the data gets sent to the CPU faster. I know this advantage very well. When the data center I mange upgraded from an 8Gb Fibre Channel SAN with 10k spinning disks to a dual port 25GbE iSCSI software defined storage (SDS) array with NVMe disk, loading times for SAP HANA DBs decreased dramatically. On the old SAN it would take 20 minutes to start a 300GB RAM DB, FYI HANA is an in RAM DB and for every GB of disk needed for the DB you need the same amount of RAM. Now with the SSD backed SDS array that same DB loads in 2 minutes.
Your berate me on the network claim but your entire post on that was nonsensical. I assumed you were talking about a home network, but it was hard to follow the post. "have u heard of this thing called "network", is it possible that some1 might not care to use RAM or SSD that is faster than his network (in bw or latency) but does care not use storage that is slower than his network." The only thing someone can figure is that you are talking about a home network and not a SAN. As I had said even a slow HDD will be plenty for 1GbE network. Say you are a video editor, are you going to be doing the editing over your network onto some NAS or will you be editing the file locally? The answer is locally and then transfer the file to the NAS for long term storage/backup. Since most home have 1GbE network and the transfers will be sequential in design, HDD storage will be fast enough for that network speed. You are so severely network limited at 1Gb that using an SSD on 1GbE network is just a stupid waste of money. If you are lucky enough to have the money for 5GbE or 10GbE network, then yes SSD would work or having a RAID 50 array would make sense.
I think at this point I have covered almost all your incorrect talking points. FYI just because you say "he is dead wrong, I am right" doesn't make you right. You might not have liked my reply about how much slower SSD is to DRAM, but it was a counter argument. I didn't think I needed to provide you with hard numbers, however, by your comment "just an education reply is what he gave. and w/- facts BTW" it is obvious I should have. I figured it was common knowledge the performance difference between DRAM and SSD. However, I should have know that common knowledge isn't very common.
In case you didn't get it from the middle part of my post, I actually do know what I am talking about as this is my profession. Please think before you post something so utterly ridiculous as "if SSD performance keeps improving like this, it can provide competitive pressure to DRAM" and then dismiss a legitimate counter post. FYI there are tech experts who visit this site to learn about the new things coming out and see reviews of products to help us make our decisions for the stuff we manage.
azfacea - Friday, April 10, 2020 - link
you just said the same thing as before only using more words. "dram is faster therefore nand cant compete" completely missing the point that SsD is becoming fast enough for many applications. and missing the fact sad are improving faster than dram in all of size, price, bandwidth and latency. than dram in the past 5 years. I'll wait 4 your mea culpa in a few yearsschujj07 - Friday, April 10, 2020 - link
Wow you are such a hypocrite. You complain that I post without facts, then you complain when I listed in-depth facts. Your belief with SSD is so engrained in your being that there is NOTHING anyone here could say, write, prove, etc... for you to realize you are wrong. For us IT Professionals you are like talking to a wall or are just a pebcak error.rhysiam - Saturday, April 11, 2020 - link
@azfacea - the main hole in your argument is latency. When you say "SSDs are improving faster than DRAM in... latency" you are **sort of** correct. Absolutely, more sophisticated controllers as well as the NVMe protocol and PCIe interfaces have demonstrably reduced the latency of high end SSDs, particularly when they are subjected to intensive workloads. What you are referencing here is the overall latency - or "response time" of SSDs, which includes interface, protocol and controller overheads. At that level, you are absolutely correct when you say latency is improving (on high end/enterprise devices).However, here's the problem: As Kristian Vättö pointed out to you above, the fundamental design of NAND flash means that it takes substantial time to read, program and (critically!) erase the cell. This latency, inherent to NAND flash cells, hasn't really changed. In fact if anything, the move from SLC -> MLC -> TLC -> QLC, which is a significant driver in the capacity and price improvements you are touting, has seen a substantial increase in latency at the NAND flash layer. Even ignoring this, according to Kristian's numbers above, we're still at the level of 10s of microseconds for NAND vs 10s of nanoseconds for DRAM. That's in the region of 1000 times higher latency.
Here are two articles by Kristian Vättö which explore how NAND flash works (planar and 3D-NAND) and are useful in understanding the fundamental physics at play here. Kristian used to be the SSD editor here at Anandtech and now works for Samsung.
- https://www.anandtech.com/show/5067/understanding-...
- https://www.anandtech.com/show/8216/samsung-ssd-85...
They're old articles, but that doesn't matter. The fundamental design hasn't changed and (obviously!) fundamental physics don't change.
3D-XPoint marketing hype claimed it would approach DRAM latency, but it's still nowhere near responsive enough to challenge DRAM, even ~3 years (?) after release. Maybe RE-RAM or MRAM or some other technology comes along and challenges the DRAM "triad", but that absolutely will require new technology.
We're not going to get anywhere near DRAM latency by iterating on existing NAND flash technology. Ryzen CPUs have shown us we can get measurable system-wide performance gains from dropping particular RAM latency settings from 18, to 16, to 14 clock cycles. Remember, NAND flash at the cell level is in the order of 1000 times slower. It's simply not fit-for-purpose as a challenger for DRAM.
TL;DR: NAND Flash cells, because of physics, have vastly highly latency than DRAM. While it's good to be optimistic and excited about the future of tech, NAND latency simply isn't going to get anywhere near DRAM through gradual iteration, which seems to be what you are suggesting.
schujj07 - Saturday, April 11, 2020 - link
Thank you @rhysiam for going even further in explaining this. If I remember correctly MRAM is already as fast as DRAM but its capacity is so much smaller that it isn't feasible for general computing. I do believe it is used in satellites though.@azfacea if you still don't believe us build a computer with the fastest PCIe 4 SSD you can find and only 1GB RAM. Install Win 10 onto it and try using the computer. You will see the effect of much higher latency and the protocol overhead first hand. That computer will be absolutely impossible to use, especially if you try having multiple browser tabs open. The lack of RAM is the problem. I have a laptop from 2013 with 4GB RAM and Win 10 on it with a Samsung 850 Evo SSD. Even having 2GB "free" on bootup this laptop is slow. It is having to disk swap so much that it affects the performance quite a lot. Remember that is with 4x more RAM than I am saying you try.
rhysiam - Saturday, April 11, 2020 - link
I wonder if we'll get a response?schujj07 - Monday, April 13, 2020 - link
Doesn't look like it. I think @azfacea has crawled back under his/her bridge to sulk at the beating he took from experts.rhysiam - Tuesday, April 14, 2020 - link
I don't want to beat anyone! I'd just like to debate things based on a healthy mixture of knowledge/understanding as well as curiosity/humility.Never mind. At least if we see similar perspectives being touted in future we can just point him/her back to this discussion.
back2future - Saturday, April 11, 2020 - link
If there is need for very high amount of fast swap space, than nowadays bandwidth and latencies of storage can compete almost with devices from generation before (or some even <1 decade).With DDR4 there is enough bandwidth for common applications and with widespread mainboards that most users wont experience limiting performance on daily usage patterns.
If DDR4 (DDR3?) is that much cheaper than later DDR5 one would need ~35 32GB ram modules (each on todays price level for around 1/2$ for each GB) at a ~500$ cost for 1TB.