32GB iPhone 7 Has 8 Times Slower Storage Performance Than 128GB Model (thenextweb.com) 159
An anonymous reader quotes a report from The Next Web: Apple isn't telling you everything about its phones. Few weeks back, GSMArena reported that the 32GB iPhone 7 and 7 Plus had significantly slower storage performance than the 128GB and 256GB models of the device. In a new video, Unbox Therapy's Lew Hilsenteger conducted a series of speed tests that confirm the discrepancy in storage speeds between the different configurations of Apple's phone -- and it turns out the 32GB iPhone is about eight times slower than the larger capacity storage version of the device. For his first test, Hilsenteger used the free PerformanceTest Mobile app to compare the read and write speeds of the iPhone. While there was little difference between the read speeds of the 32GB and 128GB models, there's a huge disparity when it comes to write speed. The 32GB iPhone writes at 42MB per second, which is nearly eight times slower than the 128GB version's 341MB per second. Hilsenteger then performed a real-world speed test, which included transferring movies from a MacBook to the iPhone using a USB cable. While the 256GB model took two minutes and 34 seconds to complete the 4.2GB file transfer, the 32GB iPhone 7 needed a total of three minutes and 40 seconds for the same transmission.
Re:non-news is non-news (Score:5, Insightful)
Unless Apple is doing some sort of quasi RAID like read/write access against all available memory chips (vs treating them like a sequential memory space which may end earlier rather than later depending on what memory capacity you selected at purchase time)... why should a higher capacity device have faster read/write times than a lower capacity of the same generation?
If anything, this sounds like another example of Apple attempting to balkinize the market in a way favorable to them and those who are most willing and/or able to pay them the most for devices.
Re:non-news is non-news (Score:4, Interesting)
Re:non-news is non-news (Score:5, Interesting)
On my shelf not three feet away I've got an early prototype of a a logic board for a system later shipped with 2, 4 or 8 flash memory chips back in 2003... a board I owned a good bit of code for. At no point was there any talk of us accessing multiple chips at a time, instead the existing sequential read/write capacity was enough for our needs.
The same goes for any embedded device today, regardless of potential # of memory chips... the manufacturer is only going to parallelize read/write access under two circumstances:
1) no one on the test team noticed them doing so,
2) there is actually a need to do so in order to boost performance... which may not be applicable across all units.
#2 breaks down as it's like putting a hardware raid controller in every PC/server mobo with multiple sata ports. Sure some % of users may end up with multiple HDs attached... why should the manufacturer pay the added cost of baking this extra speed in when it is clearly an add on (or premium upgrade) option?
Re: (Score:3)
Re:non-news is non-news (Score:5, Interesting)
A single NAND die isn't capable of 341MB per second. They're clearly using parallel writes.
Re: (Score:2)
This.
Also *all* high performance flash drive out there now use multiple controllers even, so not only are they writing across the flash in parallel, they are striping the controllers too. (yes, drives != phone, just pointing out that parallel ops is where the market is going).
Re: (Score:1)
Re: (Score:2)
You are clearly wrong if you believe there are multiple flash memory die on the 128GB model.
The phones use either ONE SK Hynix H23Q1T8QK2MYS 128GB chip or ONE Toshiba THGBX6T0T8LLFXE 128GB chip
Re: (Score:2)
Re: (Score:3)
Is it not possible that system architectures, and the approach to memory handling, have changed in the last 13 years?
Re: (Score:2)
Since 2003, there's been a market need for enormously more speed. That's the market advantage that flash drives have at all over HDDs, given that flash is still ~10x as expensive, so every feasible trick to boost speed is used. Sandforce alone is an engineering firm with dozens of engineers. I also have done flash access for my day job and I also did it a simple way, but I had different design requirements and accessing slowly in series was still blazing fast.
Re: (Score:3)
Re: (Score:2)
Re:non-news is non-news (Score:5, Informative)
All modern NAND flash memory does "quasi-RAID". Writes are split across all chips in parallel, so the larger the capacity, the more chips, the faster the write speed. Check out any USB thumb drive with various capacities - larger models of the same line will be faster.
That said, 128GB should only be 4 times faster than 32GB, so if these figures are correct then the 32GB units are also using lower spec memory.
Mass data (Score:5, Informative)
That depends 100% on the sort of controllers & memory layouts that are involved.
Do you have specific information that Apple does this? I don't.
Given that:
- nearly all modern smartphone/tablets/etc. do no go the extra headache to implement some weird custom solution for their mass storage.
- instead they all go for simple, standard, cheap of the shelf technology.
- [ BTW: eMMC (embed MMC - i.e.: an SD Card, without the plastic package, but directly available over an MMC bus) seems to be the most frequent solution ]
- Most of the flash anywhere, including thousands of SD Cards on the market right now, follow the exact same tendency: bigger model have more chips and can spread their write/erases among more chips ("quasi-RAID") giving better performance. That's why the "Class 10 UHS III" SDXC cards are only available on the bigger models, smaller models are slower. Same difference between microSDXC and regular SDXC cards (bigger cards can pack more chips and you have a greater choice of faster cards. At the micro level, it's only 128GB and above capacity that usually come with "Class 10 UHS III").
- Even more gory details if you care to read the benchmarked read/write speeds of each card. (again, more chips - found in larger package or bigger capacity - manage higher write/erase speeds).
Given all the above, there's high expectation that iPhones are following the trend.. :
But hey instead of speculating and calling each other names, let's check actual real heardware
iFixit, Chipworks [chipworks.com], SK Hynix Datasheet [skhynix.com]
What a surprise~ iPhone are exactly everyone else~ and source cheap of the shelf parts instead of re-inventing the wheel~~ Who would have though this~~~
iFixit's 32Gb iPhone use H23QEG8VG2ACS - a stack of 4 chips, with 256Gibits total (or 32GiB if used alone like in this phone).
Chipworks's 128GB iPhone use - a stack of 8 chips, with 1024Gibits total (or 128GiB when used in alone configuration)
So without even taking into account anything else, 32GB iPhone can only spread their writes among half of the chips available to a 128GB iPhone.
So they already start with a 50% malus at the hardware level.
That said, 128GB should only be 4 times faster than 32GB, so if these figures are correct then the 32GB units are also using lower spec memory.
Nope. At all. Like you said it entirely depends on the flash configuration. 128 isn't necessarily 4x more chips than 32.
Some constructor would go for 8x more chips of half the capacity.
In Apple case, they went for 2x more chips at 2x more capacity (more expensive but faster, enabling them to have bigger marging on the smaller/slower 32GB).
Which again goes back to the point of what I have posted... and this article.
Which goes back to the answer which you were given:
- YES, nearly every last constructor of flash is doing "quasi-RAID", i.e.: stacking/bonding more chips in the same package and spreading the write/erase among that.
That single fact can account for a huge part of the difference between models.
Then the thing is designed by Apple.
They run iOS on it. i.e.: the same "Darwin" core ( Mach microkernel + BSD monolithic kernel + BSD user space) as Mac OS X, only with a different interface.
They probably *still* use the same asinine file system as always HFS+
And that one is completely inadequate for flash.
It's a classical "inplace" writing file system.
This dramatically increase the "write amplification" typical with random-writes flash media. (each time you need to change some data, you would need to erase and re-write a whole block).
This probably *also* accounts for the dramatic performance
Re:Mass data (Score:5, Interesting)
- ZFS (...which Apple *STIL* isn't using)
Indeed. *sigh*
Thank goodness for OpenZFS on OS X.
Apple and ZFS (Score:2)
I'm betting that once Apple is done ridiculling themselves with their "too little, too late + NIH" catastrophe with APFS,
their probably going to silently acquire OpenZFS, and rebrand it as "Apple's CoW System".
I'm taking bets.
See Copland and NextStep for Apple's historical precedent.
(And see CUPS, LLVM, the KHTML-WebKit-Blink family, and countless of better external technologies that Apple ended-up buying/acquiring/taking over.
OpenZFS - if/when my prediction happens - will be just one extra point on this li
Re: (Score:1)
Re: (Score:1)
They probably *still* use the same asinine file system as always HFS+ And that one is completely inadequate for flash.
One of the many reasons Apple is developing APFS.
Re: (Score:2)
Unfortunately, unless they failed to document it, APFS currently lacks data checksumming, which is less than ideal when storing data on flash (particularly TLC flash). Here's hoping they fix that oversight in the final version.
Re: (Score:2)
Apple's *New Future SSD filesystem* vs *Copland* (Score:2)
As pointed by krakelohm above [slashdot.org],
and dgatwood below [slashdot.org],
that "potential future successor to 'HFS Plus'" is NOT in production yet, and misses important features.
Let's be frank.
This thing is so much over-due, and has been post-poned so much, that it might as well be considered as Apple's new "Copland [wikipedia.org]".
(And in this metaphore, ZFS is probably the thing that will play NextStep's role as the "external technology that got bought and hastily re-branded in order to save the situation in a last-ditch effort".
I'm starting to
Re:non-news is non-news (Score:5, Informative)
Bingo. One NAND die is not all that fast; it's when you put multiple dies together - either via multiple packages or, in the case of the iPhone, layering - that you get the absurdly high transfer rates solid state NAND storage is known for.
AnandTech's SSD Anthology even 7 years later is still the single best primer on the subject of flash storage: http://www.anandtech.com/show/2738/6 [anandtech.com]. It goes over how this concept works in greater detail.
The one thing you won't find in there though, but is similarly important for understanding smartphone storage, is SLC caching. Most phones these days are using Triple Level (TLC) storage, which means storing 3 bits in a single cell. This greatly brings down the cost per byte of NAND, however it makes it slower to program and erase. As a result the iPhone (and most other phones) have an area of NAND that is pseudo-single level (SLC), which only stores 1 bit per cell. The purpose of the pseudo-SLC area is to serve as a cache; quickly absorb and coalesce writes, and then write them out to the slower TLC NAND transparently to the user.
The size of the pseudo-TLC area is generally proportional to the size of the total NAND. That means the larger iPhones have a larger pseudo-SLC area. And if you understand caching, then you understand what happens when you exceed that cache size. Most likely some of the tests in TFA were big enough to overflow the pseudo-SLC on the 32GB phone, but not on the larger model. Which is why there's such a large performance difference on some tests, but not in other things like transferring files.
Re: (Score:2)
That said, 128GB should only be 4 times faster than 32GB, so if these figures are correct then the 32GB units are also using lower spec memory.
The 8x speed increase is for the 256GB model vs the 32GB model -- 8 times the storage.. 8 times the speed.
The confirmation of the hypothesis would come when someone posts the same benchmark for a 128GB model.
Re: (Score:1)
That said, 128GB should only be 4 times faster than 32GB, so if these figures are correct then the 32GB units are also using lower spec memory.
This is only if the 128 GB model has 4 times the chips and the 256 GB model 8 times. So if there is a single 32 GB chip in the entry model, how do they fit 8 chips in the 256 GB one? More specifically, where on that picture https://d3nevzfk7ii3be.cloudfr... [cloudfront.net] is there room for 7 more chips?
That doesn't make sense, they probably fit higher density chips. And they shouldn't be faster since there isn't more parallelism.
Re: (Score:2)
There aren't four times as many chips used for the flash memory in the 128GB model, there are exactly the same number of chips. One.
Re: (Score:2)
Or alternatively (but unlikely) they are using bigger capacity chips in the cheaper model. Say 2x16 and then 8x8 for the bigger model. Either way I think it would be a sign that they decided explicitly to give a perf benefit to the larger device.
Think of it this way though: 32GB model is going to your low end customers. These are people that are either light users or it is their first smart phone. Anything you give them will likely be vastly better than they were used to so why (other than being moral) treat them the same as your "good" customers?
Good point about target buyer. The difficulty now comes on Apple's part to say that, technically explain why it is the way it is (which they won't), or come up with an interesting damage control plan for people feeling "unequal", even though they are, in fact, on an unequal playing field... so to speak. I'll change my last name if they recall all of the device and re-ship with equal speed somehow cooked in. ;)
Re: (Score:2)
Re: (Score:2)
Good point? on what basis? There is hardly any evidence to support his conjecture.
There is pretty good evidence to support it from their point and mine; you just have to desire to accept it or discard it:
Personal observation. I know (and don't know but observe) 100, 150, something like that people and their habits. My observations match up with the "point" that the parent comment made about "low end customers", expanding to "target buyer" in my logical jump, based on my observational data.
Re: (Score:2)
I see no evidence that people who buy the smaller iphones are either light users or first time buyers. Most people buy them because they are cheaper.
Re: (Score:2, Redundant)
There are many simple reasons why this could be the case.
1. 32gig chips may be older chips. We had 32gig capacity iPhones for a while chances starting at the 3GS they may be still using the same chips from 7 years ago. Why use those old chips? Probably because they are cheaper then brand new 32gig chips. And people buying the 32gig model get so because they are cheaper.
2. Fragmentation iOS and your apps take up a lot of space. Small storage increases the chance of running into fragmented storage needs
Re:non-news is non-news (Score:5, Informative)
Unless Apple is doing some sort of quasi RAID like read/write access against all available memory chips
"Quasi RAID" is actually how all SSDs work. The controller spreads the writes across multiple flash chips. This is why NVMe is so much faster, the OS can give the SSD controller thousands of outstanding IO requests instead of the max of 32 with SATA. The iPhone uses a single eMMC flash chip which integrates the controller and the NAND on one die. The eMMC chip will do the same thing, only across flash cells instead of entire chips.
In the end, all this comes down to is the fancy 128/256GB eMMC flash comes with a nicer onboard controller than the 32GB one, hence higher bandwidth. That said, with such a huge difference there is no doubt Apple ordered the cheapest 32GB flash they could find. You probably can find the same eMMC chips in a $50 cheap Chinese Android phone. For a $500+ phone they should be paying the extra $2 for higher bandwidth 32GB eMMC chips.
Re: (Score:1)
Re: (Score:2)
Various chips have various speeds too; specifically newer chips tend to have both more capacity, better speed and higher price (until a point where the old ones' price starts climbing again...)
If the phone doesn't use a different number of chips, but chips from a different generation - 'economy class' 32GB nearing end-of-life, vs bleeding edge 'high performance' 128GB ones, that would explain the disproportion too.
Re: non-news is non-news (Score:2)
They probably have multiple chips in the flash storage module/package. One 32 GB, eight 16 GB, or eight 32 GB, depending on the model of phone. Having a four-by-32 GB version would probably mean another variation of controller hardware, lower write speeds, and possibly higher cost.
Re: (Score:2)
That's normally how flash storage works, yes. Usually the whole thing is RAID 0 ed many ways, and on the PC side, the bigger flash drives in the same series are faster up to a point. (up to the point that the bottleneck becomes the controller or the interface to the host PC)
Re: (Score:2)
Most large SSDs are faster than their smaller models of the same series, so yes, there some quasi-RAID going on.
But it doesn't explain the 8x difference. At the very best, it should be 4x.
Re: (Score:2)
Except that basically every SSD works this way.
The more chips, the more throughput because each chip can be written to simultaneously.
Obligatory (Score:1)
Re: (Score:3)
Chances are the smaller storage means they are using older storage. If you want to make the low end model more affordable going with an older slower component is a way to actually lower the cost.
Well... (Score:1)
Re: (Score:2)
Why?
Unlike a spinning disc/disk where assuming identical rotational speeds and platter counts... a higher capacity one is going to be able to read/write bits faster simply because they happen to land under the heads more often for a higher capacity driver than a lower capacity one... for a solid state storage device... those 'free' size 'advantages go away.
Re: (Score:1)
Why?
The summary mentioned similar read speed so most likely the reason is the same as discussed here (random link).
http://www.howtogeek.com/165542/why-solid-state-drives-slow-down-as-you-fill-them-up/ [howtogeek.com]
Re: (Score:2)
The link you provide offers one possibility.
Another is that as memory chips have gotten better/faster, many of those issues have been able to be worked out so they are less impactful depending on your memory size.
Re: (Score:3, Funny)
So you are suggesting that the higher level HW or SW is doing some sort of RAID like operation to hit all chips equally? If so, that should scale linearly with the # of chips/amount of storage... yet it doesn't seem to.
Re: (Score:3)
You will see this with a lot of SSDs as well larger capacity models have better write performance because many are capable of paralleling writes. It takes some small bit of time to program a flash block, there is not need to keep data contiguous on a medium with no seek time, therefore you can spray data all over the flash medium and that is fine because you are logically mapping all the blocks anyway.
Its not surprising to me that even the embedded NAND or NOR flash in smart phone would act like a raid0 ov
Re: (Score:2)
Write interleaving? (Score:3)
I wonder how the flash is organized. Is it just a question of a single flash chip of varying size, or is it possible that the 128GB model is somehow comprised of 4x 32GB segments which allow write interleaving to happen?
The only other explanation that I can think of would be that 128GB represents a level of density that requires superior flash chips which really are faster, and that 32GB uses older parts that are just plain slower.
Re: (Score:2)
Non-issue? (Score:3)
It does suck if your phone doesn't get the performance that could be achieved (and is achieved by other phones) but I'm not sure what this would mean in real life.
Do you need this performance on a mobile device such as a phone? As the data transfer test proved, it's not eight times slower for that, it only takes somewhat longer.
I thought it was normal the fewer flash chips perform worse.
Re: (Score:2)
You must not be an American! *the previous point being pointed out by an American.
Need? Since when were the bill of rights, general contract law or general mobile phone performance specifications based on 'need'?
Re: (Score:3)
Most people aren't using a data cable any more. Remember when Apple finally allowed people to "cut the cable" and the rest of the world said, "about damn time"? Also, remember that the majority of people have Windows PCs, not Macs, and iTunes on Windows is a favorite past time for everybody to bash. Hence, the vast majority of people are using their iPhones in cordless mode, and presumably real world Wi-Fi on the iPhone is not enough to saturate the write limit.
And for those who do still transfer by cable,
Re: (Score:2)
Re: (Score:2)
The gap is so wide it makes me wonder if there is some other explanation. Maybe the controller doesn't support hardware encryption, so the CPU has to do it.
Re: (Score:1)
lol, I thought you were going to say:
Rithmetics (Score:3, Insightful)
Re: (Score:3)
Two minutes and 34 seconds is hardly eight times faster than three minutes and 40 seconds for the same transmission.
The 32GB iPhone writes at 42MB per second, which is nearly eight times slower than the 128GB version's 341MB per second
Re: (Score:3)
Which does seem to be the difference between buying a car with a top speed of 150 mph and one with a top speed of 800 mph. You never really get to go faster than 150 mph just because your car CAN.
Re: (Score:2)
Internal write speed vs the USB bottleneck ...
Re: (Score:2)
Wait...it's lightning (or maybe just the iPhone) still using USB 2 for data transfer? Because in a proper setup, USB 3 can do more than 341MB/s on large files in continuous transfer.
Re: Rithmetics (Score:1)
The point is that whilst it may be eight times slower in some synthetic benchmarks in terms of real world performance it's not so stark and both leave enough time to boil a kettle for a cup of tea when transferring a movie, unless you have a WiFi kettle, in which case enough time to transfer every Michael Caine movie.
Re: Rithmetics (Score:2)
In other words, the headline is sensational because the authors didn't understand how the hardware works.
Re: Yay (Score:1, Insightful)
some of us love walled gardens because of the peace and quiet, with all the whingers somewhere outside.
Re: (Score:2)
"Invest heavily"... Oh yes, a 9€ lightning to jack adapter or two is such a heavy investment to make after spending 989€ on a 128Gb iPhone 7 or 1199€ on a 128Gb iPhone 7+.
You're one of those who has an investment in Android and "pretends" that if only X was different, you'd consider an iPhone.
Faker.
Re: (Score:2, Flamebait)
Re: (Score:1)
Normal (Score:5, Insightful)
Well, the 32er model has also 4 times less memory than the 128er model, so it's in no haste to save stuff, it will fill up quickly enough anyway.
"8 times slower"? (Score:5, Insightful)
When writers use words like that, do they understand what they mean in mathematical terms? I have my doubts.
Re: (Score:2)
I've given up on this. It used to drive me nuts.
I eventually had to install (yet another) "idiot jargon translation" plug-in in my brain at the "A is X times than B" point to flip and convert that to something more like "B is X times than A" to help reduce the risk of rupturing an aneurysm.
Re: (Score:2)
Bah. It appears Slashdot has an "idiot jargon translator" of its own that removed my less / more blocks marked with gt and lt symbols.
"A is X times [ less ] than B" -> "B is X times [ more ] than A"
Re: (Score:2)
t' = timeToMakeTheSameStorageOperationOn128GB()
ASSERT(t / t' >= 8);
Just look at the iOS code.
Re: (Score:3)
Re: (Score:2)
People who use that phrase are 8 times slower than people who use the proper phrasing. (unless, of course, they're measuring slowness as seconds per task, in which case it turns out to be exactly right)
Re: (Score:1)
People don't buy iPhones based on performance (Score:3)
Re: (Score:2)
Re: (Score:2)
As long as the phone is not remarkably slow, does it matter if the storage is slower than the upper model? People buy the iPhone for iOS and its ergonomics.
Agreed. Add on teen to tween factors ("I have what the others have so I'm part of the 'in' group" et al) and it's like almost every other device/product. It can even be compared to clothing in price/quality/brand-name-BS. You have to analyze something to see if it's a real Gucci or a fake; the t[w]eens don't care; they focus on impression.
Speed isn't something that's critical for handheld storage with limited processor speeds/bandwidth from the air or cables/etc unless you're testing to find flaws or bes
there news, Apple's stock crashes (Score:2)
as massive numbers of dissatisfied customers return their new iPhone 7's complaining that they are too slow!
Apple is said to be refusing the returns claiming, "at least they don't catch fire!"
Re: (Score:2)
8 times slower, huh (Score:2)
That's a meaningless statement. Remember when we used to pretend people here knew a little arithmetic and numbers.
256/32 =8 (Score:2)
Under what circumstances would a user notice? (Score:3)
Are there situations where a user would notice a slower flash write speed on their cell phone?
The only time I can think of where a phone would need to write massive amounts to flash is during an OS upgrade (which is hopefully a rare thing) -- even during an app install, the user is likely to be bounded by their network's download speed, not by the speed of writing to flash. Similarly, while recording live video, the phone only needs to write at the bandwidth of the video stream, no faster.
Is there some use case I'm missing?
I've seen this with Mac's too (Score:1)
I remember something like this being said about the MacBook Air. The bigger capacity drives were faster than the smaller ones. Even a difference between the 13" MBA and the 11" with similar drive capacity. For me I just found it probably a difference in suppliers on one manufacture vs another. You also have some other hardware differences. Probably similar to some PC notebooks having similar hardware but different results. Your going to have some variations in performance.
8x slower (Score:1)
Do they mean that it has 1/8 the speed, or 12.5%? Because there is no real measurement of "8x slower" unless you have a common base for comparison.
You can say the 32GB model is 8x faster, but "8x slower" doesn't really make sense.
Re: (Score:2)
Writing other than data transfer (Score:2)
256 / 8 = 32GB (Score:1)
Or that the larger sizes can access more layered wafers in parallel?
Re:Makes it hard to access stored data.. Wrong (Score:5, Funny)
Re: (Score:1)
calm down sir... the video clearly shows that you are BSing
Re: (Score:1)
There is no legal requirement to not release tax returns while under audit, but there is plenty of legal advise not to, from tax lawyers.