Should SATA get updated specs? Example SATA 4.0 @ 36Gbps, 48Gbps or 64Gbps.

[Tetras]

I doubt it ever will be, as for most people more than 1-2TB of storage just isn't necessary any more. If the current (and IMO unsustainable) cloud storage paradigm collapses we can revisit this, but I don't see consumer u.2 becoming a thing when most users are using a single m.2, or maybe two.

And, of course, thanks to the flexibility of PCIe any PCIe slot or m.2 slot can be made into u.2 easily and cheaply, and any m.2 drive can be stuck in a 2.5" u.2 caddy. If you really want offboard drives, they are available for enthusiasts willing to pay a slight premium and do a small amount of DIY assembly.

What exactly is it that you're advocating?

- Do not update SATA
- Use U.2 more widely on consumer boards/SSDs
- Do nothing, because grandma doesn't need more storage

 

[lexluthermiester]

Why did SAS switch to a new connector for 12 Gbps and up then, if the SATA connector already worked?

You keep saying that and I keep giving you opinions that you keep ignoring, so whatever.

Fixed that for you.

 

[WhitetailAni]

???????????

Are... are you going to answer?

 

[defaultluser]

Hard drives will stop being made before they reach the 600 MB/s SATA3 peak.

SATA SSDs would benefit, but maybe not so much (most mainstream SATA SSDs hit maybe 200 MB/s sustained write after the SLC cache is saturated.) Read speeds would benefit.

 

[ThrashZone]

Because it's U.2 or because of the capacity you're getting out of it? U.2 doesn't make flash chips any cheaper and you're obviously going to be paying more if there are more flash chips in the package. That doesn't make U.2 expensive, it makes high capacity flash drives expensive. When you're looking at something like 8TB flash drives, no crap it's going to be expensive.

Edit: 1k USD for a 8TB flash drive actually doesn't sound that bad in the grand scheme of things. You'd be within a couple hundred of that if you had a bunch of smaller M.2 drives instead. Also, for anything that's 1-2TB, it makes a lot more sense just to go with M.2. You don't need the extra space that U.2 offers, so it's kind of waste of money unless you need that capacity, but if you do, it's actually not that bad. It's just a niche product that most people aren't willing to spend that kind of money on.

Edit 2: Also, if you did just use M.2 drives instead, how many PCIe lanes would you need to accomplish the same thing? That's a consideration as well because it's not like systems with a lot of PCIe lanes are cheap either.


That sums this up nicely.

Hi,
Well even some i9's my 10900k included and of course older only have 16 pci-e lanes yes there is that
My x99 and x299 doesn't matter with 44 lanes but how many people went for hedt
But they would need m.2 add-on cards

All the u-2 2.5" ssd's I've looked at even the smaller ones were stupid priced as bad as optane matter of fact
But this was back when x299 came out so a while back I lost interest back then in it.

As far as shear size I doubt I would ever use anything over 1tb this size is just easier on the pocket book price wise and easier to have duplicates for backup so no I'm not in the 4-8tb group

 

[mechtech]

Thunderbolt is really, really expensive though, it requires very expensive controllers and cabling. And it's hardly suitable for internal usage anyway - there's likely too much RF noise inside of a PC for that to be reliable. Why not just use native PCIe?

You know what would be cool, a pcie board that you could plug multiple ssds into, I know they exist for nvme, etc. Be neat if they had about 8 sata ports on a board and capacity was cumlative in windows/bios. I could take all my old 500gb and 256gb drives and put them on one pcie card and plug it in for TB of storage lol. Might not get super speeds, but get 1 large drive, but I guess if one died probably lose everything like a raid..........sigh......

Right, and even that would be a great upgrade! However, 24 or 36Gbps is easily doable and either one would make SSD's in 2.5" or 3.5" form factor really fast!

Yes it would for sure. I wonder if hypothertically speaking if a motherboard got a new sata rev/spec if old existing sata drives would see any performance increase or if they would need a new controller also?

 

[Aquinus]

That was YOUR suggestion, not mine. I couldn't care less about U.2 in a PC.

Why not? It gives you everything you want, using a protocol that's well established, with backwards compatibility with PCIe devices. It just doesn't give you direct backwards compatibility with SATA drives. It's the next best thing though because at least PCIe can give you SATA ports though an add-on card. I still think unifying around a single protocol with a modern interconnect is the way to go. Going purely PCIe won't stop you from using SATA devices, but it enables so many things.

All the u-2 2.5" ssd's I've looked at even the smaller ones were stupid priced as bad as optane matter of fact
But this was back when x299 came out so a while back I lost interest back then in it.

If you're buying a U.2 drive for smaller capacities, you're just not using your brain. M.2 options are vastly superior in that regard all the way around. U.2 comes into play when you want a lot of flash storage without using 16 PCIe lanes to do it. We're talking 8TB drives, like the one Intel has for $1.1k USD (I thought it was just 1k, my mistake.) For something like that, it's actually a lot more reasonably priced given the capacity. Now, depending on your needs, you could also go get a 8TB HDD at a fraction of the price but it comes at the cost of performance. You could also get 4 M.2 cards, but then you're roasting PCIe lanes. If you need both M.2 NVMe speeds at HDD capacities, that's when you're considering U.2 because you can't fit that into an NVMe card.

I think the point is that PCIe is the future and everything should probably revolve around it at this point in time. It's a solid protocol, we have good slots for it, and we have cabling for it, it can be extended to support just about everything, and it's everywhere. What's not to like about that?

 

[ThrashZone]

Hi,
I didn't say I was going to or thinking of buying small u.2
I said even the price of the smaller ones were stupid
That means the larger ones were really stupid to get the translation complete

lol no way I'm paying 1k.us+ x3 or x4 for 8tb m.2's that's just crazy talk
Might be bang for bucks for you but I believe it's complete overkill seeing I don't need that much storage maybe you need that much

 

[Count von Schwalbe]

Hi,
I didn't say I was going to or thinking of buying small u.2
I said even the price of the smaller ones were stupid
That means the larger ones were really stupid to get the translation complete

lol no way I'm paying 1k.us+ x3 or x4 for 8tb m.2's that's just crazy talk
Might be bang for bucks for you but I believe it's complete overkill seeing I don't need that much storage maybe you need that much

True, mass storage in flash is for the deep-pocketed anyways. U.2 is comparable to other forms of SSD on a $/GB basis. And flash storage is the only thing SATA3 is insufficient for.

 

[ThrashZone]

True, mass storage in flash is for the deep-pocketed anyways. U.2 is comparable to other forms of SSD on a $/GB basis. And flash storage is the only thing SATA3 is insufficient for.

Hi,
I'm not having one bit of problem with sata
I've got 6 ports on my z490 2 unused
And x99 has 10 with 6 unused
x299 has 6 with 2 unused
So plenty of room for more 1-2tb ssd's or hdd's when I need and are on sell I'll buy more.

Not to mention all the m.2 slots unused if m.2's ever come down on price.

 

[R-T-B]

Hi,
Cost of U2 is more than enough to laugh at it

I think you are thinking of cost of flash. U.2 adapters aren't exactly pricey.

 

[Count von Schwalbe]

Hi,
I'm not having one bit of problem with sata
I've got 6 ports on my z490 2 unused
And x99 has 10 with 6 unused
x299 has 6 with 2 unused
So plenty of room for more 1-2tb ssd's or hdd's when I need and are on sell I'll buy more.

Not to mention all the m.2 slots unused if m.2's ever come down on price.

Beg your pardon. I was referring to the throughput of SATA being insufficient for SSD's, as that would be the only real reason for a new standard.

 

[lexluthermiester]

???????????

Are... are you going to answer?

No.

Why not? It gives you everything you want

Once again, you're missing the point and I'm not going to explain it again.

I wonder if hypothertically speaking if a motherboard got a new sata rev/spec if old existing sata drives would see any performance increase or if they would need a new controller also?

They would continue to operate at their rated speed and the SATA port they're connected to would sync down to the spec the drive firmware reports to the controller, as it does now. SATA1 & SATA2 drives still work perfectly on a SATA3 connector. Likewise a SATA3 drive works perfectly, though at slower speed on a SATA1 or SATA2 port. If SATA4 existed the same functionality would continue.

 

[Chrispy_]

M.2 isn't really limiting though

Physical size limitations; I'd already explained to @lexluthermiester that M.2 was fine from a bus/bandwidth/protocol perspective. He had a valid argument that there's only so much NAND you can pack onto an M.2 2280. We currently have 20TB hard drives but no amount of money will get you a 20TB M.2 drive.

U.2 is the solution for physically larger form factors that but it's not on consumer boards and neither is it trivial for consumers to pick up a U.2 drive.

 

[Valantar]

No.

Once again, you're missing the point and I'm not going to explain it again.

It's really quite fascinating to see you present a question and a view on that subject, have a number of people argue against your stance, and for you to then entirely refuse to engage with those points of view. Did you create this thread just to have your opinions validated? Were you not actually interested in discussing this?

From what I can tell, "the point" that you're referring to is that faster SATA would allow for faster storage that isn't mounted to the motherboard while maintaining backwards compatibility with SATA3 and earlier. Yet as several people have argued, beyond SAS12 speeds, that doesn't seem technically feasible - despite your repeated statements to the contrary it seems quite unlikely that SAS would have moved to a different connector entirely if they could have kept using the SATA connector. There's also the inherent inefficiencies of AHCI to account for - there's a reason why m.2 drives got significantly faster once they moved to NVMe.

And, as I and others have pointed out, u.2 does most of what you're asking for: case mounted, fast, flexible storage. It isn't backwards compatible to SATA, but as long as motherboards also have SATA ports that doesn't ultimately matter - instead it's backwards compatible to PCIe, which also makes it a lot more flexible. You can use both at the same time. And, of course there are the advantages of storage devices running natively on PCIe, a line of argumentation that you've entirely refused to engage with. We've already got a huge market for PCIe-based SSDs after all, so why push for updating a standard which would then require not one, but two new lines of controller designs (host side and device side), rather than keep iterating on existing PCIe-based designs that are fast, efficient, and work well? Faster SATA would also need more platform PCIe lanes, and through the additional controller (PCIe host -> SATA host controller -> SATA device controller vs. PCIe host -> PCIe device controller) meaning it's an inherently more expensive and less efficient solution.

IMO, keeping SATA3 as a legacy low power, low speed interface mainly for HDDs is great, and with current platforms integrating a serviceable number of SATA controllers, that seems to be a sustainable solution while we keep iterating PCIe-based storage for faster stuff.

Physical size limitations; I'd already explained to @lexluthermiester that M.2 was fine from a bus/bandwidth/protocol perspective. He had a valid argument that there's only so much NAND you can pack onto an M.2 2280. We currently have 20TB hard drives but no amount of money will get you a 20TB M.2 drive.

U.2 is the solution for physically larger form factors that but it's not on consumer boards and neither is it trivial for consumers to pick up a U.2 drive.

That's a somewhat valid argument, but it's also a product of pricing: there's no way any ordinary consumer could afford a 20TB SSD, and as flash capacities and prices are both bound to density, these will scale in lockstep. So when flash becomes "affordable" in those capacities, it will also fit on an m.2 drive. This means that this argument is ultimately in the realm of theory rather than reality, as price is far more of a hindrance than availability for most users. Nobody cares that you can't fit 20TB of flash on an m.2 2280 drive when you can't even afford 4TB.

And while u.2 isn't technically on consumer boards, it is trivial to adapt regular PCIe or m.2 to u.2, making it accessible for enthusiasts who want it. The reason it isn't on consumer boards is simply that it isn't necessary, and doesn't bring any real benefits over m.2 for the vast majority of PC builds. It's still easily and relatively cheaply available if you want it.

 

[Deleted member 24505]

I am quite happy with M.2. I am sure if you need more space you could get a PCIe M.2 adapter with a fair few slots on it and stack it with the biggest size M.2 available, it would not take up too much space either.

 

[Calmmo]

At this point Sata will simply just die along with HDD's, im cool with it. 5-10 years time boards likely wont even get sata ports.

 

[lexluthermiester]

We currently have 20TB hard drives but no amount of money will get you a 20TB M.2 drive.

Exactly.

U.2 is the solution for physically larger form factors that but it's not on consumer boards and neither is it trivial for consumers to pick up a U.2 drive.

Also correct.

 

[Aquinus]

Nobody cares that you can't fit 20TB of flash on an m.2 2280 drive when you can't even afford 4TB.

^ I think that's the important takeaway when it comes to U.2, or even higher capacity M.2 cards to be completely honest.

IMO, keeping SATA3 as a legacy low power, low speed interface mainly for HDDs is great, and with current platforms integrating a serviceable number of SATA controllers, that seems to be a sustainable solution while we keep iterating PCIe-based storage for faster stuff.

This is exactly what I've been thinking this entire time. There is no reason to abandon SATA, but there aren't any good reasons to try pushing forward with it either.

Once again, you're missing the point and I'm not going to explain it again.

That's probably because you're all over the place and aren't making a whole lot of sense.

I am quite happy with M.2. I am sure if you need more space you could get a PCIe M.2 adapter with a fair few slots on it and stack it with the biggest size M.2 available, it would not take up too much space either.

You can get adapters from PCIe to U.2 as well, can't you? So regardless if your board has it or not, it's just PCIe. I think that's one of the biggest advantages of M.2 and U.2 NVMes.

 

[Assimilator]

M.2 drives are indisputably a massive step backwards from the ease of serviceability of 2.5"/3.5" drives. For the latter, to swap a drive you unplug two cables from the existing drive, plug those same two cables into the new drive, and bob's your auntie. Whereas with M.2 you need to get to the motherboard (which is typically on its side in a case) and possibly remove expansion card(s) to access the M.2 slot and drive; you need to unscrew that tiny fiddly screw (make sure not to strip it or lose it!); you need to be careful that you don't slip and smash, or drop, the screwdriver into the motherboard; and you need to be careful that you don't drop or smash the tiny, light, fiddly M.2 drive.

The other advantage of 2.5" drives that I haven't seen mentioned is their superior heat dissipation properties compared to M.2 drives. The latest PCIe 4.0 M.2 controllers are approaching power consumption of 10W and I reckon that PCIe 5.0 controllers will breach that threshold, which exceeds what an entire motherboard chipset draws in some cases. Attempting to cool that on the motherboard, which is already a relatively hot and airflow-less area, is not a good idea - M.2 heatsinks are available but area also a kludge that cause more compatibility issues with Z-heights. We're even starting to see motherboards that are designed around M.2 slots and cooling them, which is just silly to me; the way to deal with heat-producing components is to move them away from each other and put them in containers that are able to absorb and dissipate that heat well, and that's exactly what 2.5" enclosures do.

So, what's really needed is a replacement for SATA, not an update to the standard. U.2 failed on the desktop precisely because it was built on top of SATA Express, using the large and clunky SFF-8639 connector, which made the drives, cables and connectors unreasonably complex and therefore expensive. What U.2 should have done was dump anything SATA and instead be a simple 4-lane PCIe connector on the motherboard, connecting to a simple 4-lane PCIe cable, that connects to a simple 4-lane PCIe connector on a 2.5" drive, all talking NVMe. Essentially, an M.2 slot designed for use with a cable as opposed to direct motherboard connection.

And we already have a working connector and cable standard that exposes and uses four PCIe lanes, while providing up to 15W of power over a 0.8m passive (therefore cheaper) cable: Thunderbolt 3. With some redesign to eliminate the unnecessary DisplayPort support, harden against the frequency emissions inside a computer chassis, and make the connectors physically dissimilar to USB-C, I don't see any reason why a TB3 derivative ("TB3 NVMe") can't be the true successor to SATA on the desktop.

The only downside of course, is that you now have 3 data connectors (SATA, M.2, and now TB3 NVMe). But I think you'd very quickly see TB3 NVMe become the dominant standard over all three because it makes drive swaps simple again; SATA would fall away because the SSD manufacturers would abandon it in favour of TB3 NVMe for 2.5" drives, making HDD manufacturers the only SATA users; and you'd see far fewer M.2 slots because TB3 NVMe allows you to have the performance of M.2 NVMe with the installation simplicity of a 2.5" drive.

Honestly, this could lead to a different form-factor for drives too. Instead of the tiny M.2 or the huge 2.5" form factors, why not one in between that is essentially a combination cooling and protective enclosure for an M.2 drive? Kinda like those external SSD-to-USB adapters that you can buy, except a little larger (1.25") so you can fit two of them in the space a current 2.5" drive goes. That would satisfy both those who like M.2 because it's small and those who like SATA because it's simple, and would neatly overcome the heat dissipation problem of high-end SSDs.

I'd rather a board come with more Nvme slots than an updated sata spec. I stopped using sata when boards starting being equipped with 3+ Nvme slots

For me it would only be appealing if the extra bandwidth came at no cost to the bandwidth of pcie which I find doubtful. Even now using x amount of nvme disables sata ports on most boards equipped with 3+.

.

NVMe is not a slot. NVMe is a storage communications interface protocol. M.2 is a slot.

 

[lexluthermiester]

^ I think that's the important takeaway when it comes to U.2, or even higher capacity M.2 cards to be completely honest.

Nobody in the consumer sector wants U.2. Full stop.

That's probably because you're all over the place and aren't making a whole lot of sense.

No, I have been very consistent. Your failure to follow along is not my problem.

Once again, STOP with the ego driven comments or the mods will be asked to help you sort yourself out.

At this point Sata will simply just die along with HDD's, im cool with it.

That's an opinion, one that is not in majority.

 

[oxrufiioxo]

NVMe is not a slot. NVMe is a storage communications interface protocol. M.2 is a slot.

Cool, didn't realize i had to be so specific in a thread clearly about storage..... I guess some people might want to use nvme slots (M.2) for BT/Wifi/GPU/NFC or connecting them to their vibrators who knows...

 

[ThrashZone]

Beg your pardon. I was referring to the throughput of SATA being insufficient for SSD's, as that would be the only real reason for a new standard.

Hi,
Well you'd never know it from the majority of non disk benchmarks
Most don't care what type of ssd one uses and I've compared os installed on m.2 to sata 3dmark/.....
Not one showed any difference in favor of the rated speed of an m.2 verses as you say "insufficient" sata ssd speed

The only benchmarks that m.2's make a difference on is passmark/ pcmark.../ crystal disk mark and others like them

Fact is not many people transfer large or small blocks of data disk to disk/.. where an m.2 speed would make a real noticeable difference in using a m.2 or likely even a U.2 ssd
So until the prices of these overrated use ssd's come down a lot it's niche use products.

People overstating the importance of m.2's speed is just being misleading.

 

[chrcoluk]

You're missing the point. SSD's are limited by SATA3 speeds and there is only so much NAND you can fit on a 2280 NVMe PCB. The standard 2.5" and 3.5" form factor drives have MUCH more internal volume for NAND to be built into. The only reasonable way forward for inexpensive mass storage is to increase the SATA spec and make drives that fit into the existing 2.5/3.5" form factor. NVMe is a great answer for primary boot drives. It's a shitty answer for expanded internally mounted storage.

SATA needs updating! That updating needs to be done with the existing connector to maintain backward compatibility.

Now thats a pretty solid argument.

One of the things that has bugged me about m.2 aside from the fragility of screw installation is that its inefficient on space and has big space constraints, especially as the drives are installed flat to the board. We keep getting board manufacturers removing other connectivity to squeeze on these slots even though we can easily use m.2 via pci-e boards.

In terms of nand capacity, the sata space cost on the board is merely the connector, and as you said is much more room in a 2.5 inch or 3.5 inch casing to fit more nand chips for larger capacity drives. As well as things like power loss connectors, dram etc.

 

[mechtech]

I am quite happy with M.2. I am sure if you need more space you could get a PCIe M.2 adapter with a fair few slots on it and stack it with the biggest size M.2 available, it would not take up too much space either.

Yes, same, however there are drawbacks. Some throttle from heat, and some motherboards have only 1 slot, or 2. If they could get 6 slots on a motherboard like SATA, then maybe sata would start to vanish???