Here are some Bonnie++ disk benchmark results:
Code:
Version 1.96 ------Sequential Output------ --Sequential Input- --Random-
Concurrency 1 -Per Chr- --Block-- -Rewrite- -Per Chr- --Block-- --Seeks--
Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP K/sec %CP /sec %CP
localhost 2G 80 99 12496 14 8106 9 676 92 22882 15 327.6 29
Latency 220ms 6356ms 3549ms 43282us 736ms 1672ms
Version 1.96 ------Sequential Create------ --------Random Create--------
localhost -Create-- --Read--- -Delete-- -Create-- --Read--- -Delete--
files /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP /sec %CP
16 692 75 +++++ +++ 7478 29 774 82 +++++ +++ 2843 78
Latency 2418ms 16588us 11687us 792ms 53us 1538us
1.96,1.96,localhost,1,1327374309,2G,,80,99,12496,14,8106,9,676,92,22882,15,327.6,29,16,,,,,692,75,+++++,+++,7478,29,774,82,+++++,+++,2843,78,220ms,6356ms,3549ms,43282us,736ms,1672ms,2418ms,16588us,11687us,792ms,53us,1538us
not the fastest disk speed in the world :-/
Btw, this bad performance is the source of 90% of all "hangs" on the Prime :-( The CPU is nice and fast, but the disk sucks.
What do other tablets look like in this test?? sucks vs a laptop or desktop would be expected.
fenturi said:
What do other tablets look like in this test?? sucks vs a laptop or desktop would be expected.
Click to expand...
Click to collapse
Here are some results from other phones/tablets:
http://forum.xda-developers.com/showthread.php?t=1169910
It would be useful if you could put this all into perspective for the rest of us. Are you able to say something like XX% slower than the Galaxy Tab 10.1/Motorola Xoom/etc.?
NeoteriX said:
It would be useful if you could put this all into perspective for the rest of us. Are you able to say something like XX% slower than the Galaxy Tab 10.1/Motorola Xoom/etc.?
Click to expand...
Click to collapse
I do not own any other android tablet. So, if you know somebody, let him run the benchmark from http://forum.xda-developers.com/showthread.php?t=1169910
fenturi said:
What do other tablets look like in this test?? sucks vs a laptop or desktop would be expected.
Click to expand...
Click to collapse
My USB stick is faster on my Laptop (but not on the ATP)
I ran some bench on mine, Stock ICS, and here's the result
With side by side comparaisons, that's how awefull the storage is....
That's pretty bad. How does this effect the usage of the tab? Is it noticeable?
Sent from my DROID2 using xda premium
It's hard to know what's causing it but there is definitely a lot of freezes in the otherwise butters smooth animations. If I'm downloading torrent in the background, the device become unusable and applications (mainly the launcher) stop responding.
Every media take much to long to load,
I also suspect big movie files to suffer from that.
Transferring files on and from a computer is a pain and often the tablet simply stop responding.
In my opinion the storage speed is the bottleneck of the Prime performance wise. It s like using a computer with a slow ass HDD versus a one with a super fast SSD.
Of course i wish someone could re-run the bench on their tablet to confirm this.
kokusho said:
It's hard to know what's causing it but there is definitely a lot of freezes in the otherwise butters smooth animations. If I'm downloading torrent in the background, the device become unusable and applications (mainly the launcher) stop responding.
Every media take much to long to load,
I also suspect big movie files to suffer from that.
Transferring files on and from a computer is a pain and often the tablet simply stop responding.
In my opinion the storage speed is the bottleneck of the Prime performance wise. It s like using a computer with a slow ass HDD versus a one with a super fast SSD.
Of course i wish someone could re-run the bench on their tablet to confirm this.
Click to expand...
Click to collapse
I wonder if it's just that the internal SD card is slow, or if it's poorly optimized in software? I guess we'll find out once the bootloader tool is released.
My fingers are crossed for poor software optimization!
That write speed is just too low, I'll try the benchmark on my TP tonight.
When custom roms/mods etc. arrive we will have the chance to test it under ext4,JFS and other filesystems so i believe we'll see better performance
I remember seeing early reviews on the TF201 that the internal memory is unusually slow.
Why would Asus put such a high build quality on everything but the storage speed?
I have a feeling this is not hardware related but rather software related. There is no logical explanation why the flash memory inside our devices is so much slower than the common average.
What I want to know is how much bandwidth is available for the internal storage?
For example: I purchase a 64GB SSD drive that is meant for internal 2.5" storage drives. I hook it up externally and plug it into a powered ESATA port. The max read/write speeds of the SSD are around 300mb/s but the port's max read/write speeds are only around 200mb/s.
Did Asus make some unnecessary sacrifices to make the price of the Prime reasonable? I really hope not.
On a different note:
Copying files from Windows 7 to the Prime is immensely slow.
On Mac OS X 10.7.2 (Hackintosh) copying the same file is MUCH faster.
Using AndroBench -
Seq Read 19.59 MB/s
Seq Write 4.01 MB/s
Random Read - 2.71 MB/s
Random Write - 0.25 MB/s
SQLite Insert - 14.17 TPS
SQLite Update - 16.68 TPS
SQLite Delete - 17.79 TPS
Really bad in the ranking compared to the other devices.
And anyone thry this benchmark tool and post the results? http://db.tt/6WHshUYt
Its J Disk Benchmark
Using androbench:
17.3 Sequential Read
6.46 Sequential Write
2.88 mb/s 739.12iops 4k random read
.28 mb/s 71.91iops 4k random write
15.01 TPS 19.98sec SQlite Insert
15.57 TPS 19.26sec SQlite Update
16.44 TPS 18.24 SQlite Delete
2510.25 msec Browser
4176.5 msec Market
5403.0 msec Camera
5284.0 msec Camcorder
Just noticed there is no /system/etc/init.d folder for any speed enhancements/tweaks
Well, I wanted to test Bonnie++ also on a USB stick on the ATP, but somehow it took insanely long, so I canceled that. I also suspect it to be a S/W problem, which gives hope for it to be fixed in an update.
I've not got my Prime with me to perform the tests, but having seen the results posted in here, I have to say that my SGS2 absolutely *smokes* the Prime in terms of I/O throughput. Very disappointing, I think that this thread needs to be brought to the attention of Asus.
chrisfu said:
I've not got my Prime with me to perform the tests, but having seen the results posted in here, I have to say that my SGS2 absolutely *smokes* the Prime in terms of I/O throughput. Very disappointing, I think that this thread needs to be brought to the attention of Asus.
Click to expand...
Click to collapse
I get the feeling they knew about this before launch.
Related
Here is a thread that seems to be making the rounds throughout the forums...
http://forum.xda-developers.com/showthread.php?t=1010807
Following the guidelines in the thread, here are my results with CM7 using a Kingston 8GB Class 6 card...
Before:
Write - 6.6 MB/s
Read - 15.2 MB/s
After:
Write - 5.8 MB/s
Read - 94.4 MB/s
I would recommend playing with the values to see what works best for your particular SD card... Not quite sure
if it is a placebo type effect, but apps like the Gallery and games that use the SD card are noticeably faster...
Have fun...
I did extensive testing on a patriot class 10 8gb card today.
I had lowest standard deviation on results using 1024 buffer. I also had the highest reads at that buffer with a higher write speed.
I had the highest write speed at 4096, but the read speeds were slower than 1024.
I rebooted several times to make sure that wasn't playing into it, and reran many test. All results were relatively consistent.
~11.6 write
~86 read
@1024
~11.9 write
~79.4 read
@4096
~10.8 write
~71.9 read
@128
The change wasn't huge for me. Most have reported 2048 as the best setting.
Also, I updated my cm7_mod to include this. Working on making it installable w/ the scripting...
http://forum.xda-developers.com/showthread.php?t=1008612
It's only meant to be used with cm7_tablet_tweaks as a base now.
Couldn't such a buffer size setting be usefull for emmc (internal memory) too ?
I'm using dalingrin's OC kernel with the IO issue, and it feels slower than my SD card...
I've commited this tweak already today. I would be interested to find the optimal value for mmcblk0.
Jaostar said:
Couldn't such a buffer size setting be usefull for emmc (internal memory) too ?
I'm using dalingrin's OC kernel with the IO issue, and it feels slower than my SD card...
Click to expand...
Click to collapse
My current kernel should not have any IO issues.
dalingrin said:
I've commited this tweak already today. I would be interested to find the optimal value for mmcblk0.
My current kernel should not have any IO issues.
Click to expand...
Click to collapse
Instructions for tweaking the emmc are in that thread. I wouldn't mind taking the time to test and crunch the numbers but sd tools only wants to test my SD card.
EDIT:
App called J Disk Benchmark 2.0 can test internal memory. Working on testing now.
Uhm... my SD card tests faster...
I hope people don't go over board and incorporate this type of permformance increases in their roms by default based on bench mark tools. there is value in increasing readahead for some access patterns, mainly when doing lots of sequencial reads. the trade off of course is at the expense of memory usage. nook even with its 500mb of memory is still not considered high in memory. setting the readahead to 2mb is quite aggressive and will work well in some work loads like galary when reading lots of files around 2mb in size while in other work loads it may actually have negative affects. I am not saying that this specific tweak is bad because I haven't done any tests myself, but don't always believe the numbers u see from benchmark tools.
I'm only setting it to 1024k. I feel like that is plenty high.
dalingrin said:
I'm only setting it to 1024k. I feel like that is plenty high.
Click to expand...
Click to collapse
Yes 1024 is what I'm running really gave the best all around performance.
I think I found the internal memory and it's set to 128 by default
can't find any real difference between 64 and 4096. That looks like the only other mmc device though, so it must be it.
chisleu said:
App called J Disk Benchmark 2.0 can test internal memory. Working on testing now.
Uhm... my SD card tests faster...
Click to expand...
Click to collapse
Yep, it's the same for me, my Class 6 SD card achieves 6,3/11,6 and the internal memory only 4,86/7,52...
BTW :
J Disk Benchmark 2.0 doesn't use the cache, so this tweak wont affect the results...
Jaostar said:
Yep, it's the same for me, my Class 6 SD card achieves 6,3/11,6 and the internal memory only 4,86/7,52...
BTW :
J Disk Benchmark 2.0 doesn't use the cache, so this tweak wont affect the results...
Click to expand...
Click to collapse
Balls.
I'm going to jack it to 1024 and hope that works then.
OK, I can't get any meaningful numbers anymore. I think yesterday's test was a fluke. I can't get any real changes from 128 to 4096 (or in between) with fast or slow SD cards, big or small, black or dark black.
The write speed on slower cards is lower (5-6mb/s) and the faster cards are higher (10-12MB/s) and read speed for all is 80-90mb/s.
Maybe this is a performance mod not for us?
Run Speed Battle. What's your score?
My score using my Macbook Pro i7 with Firefox 10 and 8gb of ram is in the 400-500 range. My score using my HTC Flyer tablet (1.5 GHz Scorpion single core, with 1gb ram) with Opera Mobile is in the 25-35 range. When using Opera Mini or the stock Honeycomb browser, it's even lower, somewhere in the 10-20 range.
I ran this test because I was confused why my desktop browser is so much faster than browsing on a tablet. From these numbers, you would conclude that it's on the order of 10x faster. Naively, I just assumed that the biggest factor behind loading a website was the connection speed. But since the same connection is used for both my tests, I guess this can't be the reason. Certainly, CPU matters when it comes to processing the webpage, but does it matter this much?
So perhaps someone else can explain: why is mobile browsing on the order of ten times slower than desktop browsing?
TSGM said:
Run Speed Battle. What's your score?
My score using my Macbook Pro i7 with Firefox 10 and 8gb of ram is in the 400-500 range. My score using my HTC Flyer tablet (1.5 GHz Scorpion single core, with 1gb ram) with Opera Mobile is in the 25-35 range. When using Opera Mini or the stock Honeycomb browser, it's even lower, somewhere in the 10-20 range.
I ran this test because I was confused why my desktop browser is so much faster than browsing on a tablet. From these numbers, you would conclude that it's on the order of 10x faster. Naively, I just assumed that the biggest factor behind loading a website was the connection speed. But since the same connection is used for both my tests, I guess this can't be the reason. Certainly, CPU matters when it comes to processing the webpage, but does it matter this much?
So perhaps someone else can explain: why is mobile browsing on the order of ten times slower than desktop browsing?
Click to expand...
Click to collapse
Err, because that's not a connection test, but a javascript test. Thus executing code... Can't expect a phone to compete with a full fledged top of the line computer, can you?
Pretty obvious is it not? Wow...
Sent from my Nexus S using xda premium
I just think it's quiet obvious, but that mostly comes from that it has always been this way for me. I think it's just because of the fact that a Mac is a Mac and a tablet is a.. tablet
CdTDroiD said:
Pretty obvious is it not? Wow...
Sent from my Nexus S using xda premium
Click to expand...
Click to collapse
I'm sorry, call me stupid, but I don't think it's obvious at all.
Let us assume that there is an upper limit for the computing speed and resources required to render a typical internet page. I would have assumed that the kind of processors found in tablets are already near this upper limit. So, as a made up figure, a 486 machine running Windows 3.1 might be able to render a given page in 10 seconds, and my modern desktop might render it in 3. A tablet might be able to render it in 5. A supercomputer might render it in 2.5. This is assuming all these machines are on the same connection.
The point is that there is a point of diminishing returns, where the principle bottleneck of rendering a page is the connection speed.
However, because I noticed a substantial difference in loading times between a tablet and a desktop, I was forced to conclude that the principle bottleneck in speed wasn't the connection speed, but rather the CPU's capability in loading various scripts (or whatnot). I'd simply assumed that the technology in 2011 (regardless of whether it took tablet or desktop form) was already close to the plateau of diminishing returns. This, I found surprising.
...but then again, I guess everybody here thinks it's obvious that the principle bottleneck is not connection speed, but something else.
It is definitely obvious. You can make a 1000-page post explaining why you THINK it isn't obvious, but it will still be obvious.
I'm completely sorry.
Mr. Holmes said:
It is definitely obvious. You can make a 1000-page post explaining why you THINK it isn't obvious, but it will still be obvious.
I'm completely sorry.
Click to expand...
Click to collapse
I understand. Thanks.
Can you explain to me what is the relation between browsing speed and CPU? Is it a linear relation? I would have expected it to vary to a plateau. This is the point I am most curious about. I don't think the functional dependence is at all obvious, but I am happy to hear your explanation.
Last summer, I decided to buy a Nexus 7 for using it mainly as an ebook reader. It's perfect for that with its very sharp 1280x800 screen. It was my first Android device and I love this little tablet.
I'm a fan of retro gaming and I installed emulators on every device I have: Pocket PC, Xbox, PSP Go, iPhone, iPad3, PS3. So I discovered that the Android platform was one of the most active community for emulation fans like me and I bought many of them, and all those made by Robert Broglia (.EMU series). They were running great on the N7 but I found that 16GB was too small, as was the screen.
I waited and waited until the 32 GB Nexus 10 became available here in Canada and bought it soon after (10 days ago). With its A15 cores, I was expecting the N10 to be a great device for emulation but I am now a little disapointed. When buying the N10, I expected everything to run faster than on the N7 by a noticeable margin.
Many emulators run slower on the N10 than on the N7. MAME4Ddroid and MAME4Droid reloaded are no longer completely smooth with more demanding ROMs, Omega 500, Colleen, UAE4droid and SToid are slower and some others needed much more tweaking than on the N7. I'm a little extreme on accuracy of emulation and I like everything to be as close to the real thing as possible. A solid 60 fps for me is a must (or 50 fps for PAL machines).
On the other side, there are other emus that ran very well: the .EMU series and RetroArch for example. These emulators are much more polished than the average quick port and they run without a flaw. They're great on the 10-inch screen and I enjoy them very much. The CPU intensive emulators (Mupen64Plus AE and FPSE) gained some speed but less that I anticipated.
So is this because of the monster Nexus 10's 2560x1600 resolution? Or is it because of limited memory bandwith? Maybe some emulators are not tweaked for the N10 yet. I wish some emulators had the option to set a lower resolution for rendering and then upscale the output. I think that many Android apps just try to push the frames to the native resolution without checking first if there is a faster way.
The N7 has a lower clocked 4 core CPU but has only 1/4 the resolution. I think that it's a more balanced device that the N10 which may have a faster dual core CPU but too much pixels to push. It's much like the iPad3 who was twice as fast as the iPad2 but had a 4x increase in resolution.
I am now considering going for a custom ROM on the N10 but I wonder if I will see an increase in emulation speed. Maybe those of you who did the jump can tell me. I'm thinking about AOKP maybe.
Any suggestion on that would be appreciated, thanks!
The emulators just need to be tweaked a bit to better perform on the completely different processor architecture. Really our processor is far more powerful than the Nexus 7 so the emulators should run faster. I too am a fan of the old games, and I play Super Nintendo and Game Boy Advance (and some Color) games quite often. I find performance to be perfect with no issues at all, but then again those arent exactly "demanding" emulators.
We do not have any sort of memory bandwidth limitation on the Nexus 10. The tablet has been designed to give the full needed 12.8 GB/s of memory bandwidth that is required for 2560x1600 resolution.
EniGmA1987 said:
The emulators just need to be tweaked a bit to better perform on the completely different processor architecture. Really our processor is far more powerful than the Nexus 7 so the emulators should run faster. I too am a fan of the old games, and I play Super Nintendo and Game Boy Advance (and some Color) games quite often. I find performance to be perfect with no issues at all, but then again those arent exactly "demanding" emulators.
We do not have any sort of memory bandwidth limitation on the Nexus 10. The tablet has been designed to give the full needed 12.8 GB/s of memory bandwidth that is required for 2560x1600 resolution.
Click to expand...
Click to collapse
Hmm, if no memory bandwidth limitation exists on the N10, wouldn't I be able to run GTA 3 at 100% screen resolution and not have significantly lower FPS, as compared to 50% resolution?
Even Beat Hazard Ultra seems to be a bit laggy on the N10. When I inquired about it to the developer, he said:
Having to render to that size of screen [2560x1600] will slow the game down. It’s called being ‘fill rate bound’. Even for a good processor it's a lot of work as the game uses quite a lot of overdraw.
The solution is to draw everything to a smaller screen (say half at 1280x800) and then stretch the final image to fill the screen.
Click to expand...
Click to collapse
A sad true my nexus 10 get dam hot and i have to play games at 1.4 or 1.2 that sux
Sent from my XT925 using xda app-developers app
espionage724 said:
Hmm, if no memory bandwidth limitation exists on the N10, wouldn't I be able to run GTA 3 at 100% screen resolution and not have significantly lower FPS, as compared to 50% resolution?
Even Beat Hazard Ultra seems to be a bit laggy on the N10. When I inquired about it to the developer, he said:
Click to expand...
Click to collapse
But fillrate isnt memory bandwidth. We need both more MHz and more raster operations to get higher fill rate of pixels per second. We can overclock the GPU to get the MHz, and that will help, but we have to find a way to solve the higher heat output too from that. More ROP's are impossible as it is a hardware design for how many we have. If we ever get to overclock up to around 750 MHz then we should see a 30-40% improvement in fill rate. At that point we may have memory bandwidth problems, but we wont know for sure until we get there. But the 12.8GB/s of bandwidth that we currently have is enough to support 2560x1600 resolution at our current GPU power. Our Nexus 10 also has the highest fillrate of any Android phone or tablet to date, about 1.4 Mtexel/s. And if we have memory bandwidth limitations, then we would see no improvement at all from the current overclock we do have up to 612-620MHz because the speed wouldnt be where the bottleneck is. Yet we can clearly see in benchmarks and real gaming that we get FPS increases with higher MHz, thus our current problem is the fillrate and not the memory bandwidth.
Also, the solution is not to render the game at half the resolution as that is a band-aid on the real problem. If the developer of a game would code the game properly we wouldnt have this problem, or if they dont feel like doing that then they should at least stop trying to put more into the game than their un-optimized, lazy project is capable of running nicely.
espionage724 said:
Hmm, if no memory bandwidth limitation exists on the N10, wouldn't I be able to run GTA 3 at 100% screen resolution and not have significantly lower FPS, as compared to 50% resolution?
Even Beat Hazard Ultra seems to be a bit laggy on the N10. When I inquired about it to the developer, he said:
Click to expand...
Click to collapse
With that logic you could buy any video card for a PC and it would run any game at the resolution the video card supports. That isn't the case because rendering involves more than just memory fill rate. There are textures, polygons, multiple rendering passes, filtering, it goes on and on. As EniGmA1987 mentioned nothing has been optimized to take advantage of this hardware yet, developers were literally crossing their fingers hoping their games would run 'as is'. thankfully the A15 cpu cores in the exynos will be used in the tegra 4 as well so we can look forward to the CPU optimizations soon which will definitely help.
Emulators are more cpu intensive than anything else, give it a little time and you won't have any problems with your old school games. Run the new 3DMark bench to see what this tablet can do, it runs native resolution and its not even fully optimized for this architecture yet.
2560*1600*4*60/1024/1024 = 937,3 MB/s for a 60 fps game at 32-bit depth. Most emulators don't use 3D functions so fillrate, rendering, overdraw won't be a factor. Most emulators are single-threaded (correct me if I'm wrong) and the A15 should shine in this particular situation and even more so in multi-threaded scenarios. With its out-of-order pipeline and greatly enhanced efficiency it should be perfectly suited for the job.
We have the fillrate, we have enough CPU power and I'm still wondering why simple app like emulators aren't much faster than that. Is it Android? Is it the Dalvik VM? Or is it because some emulators need to be written in native code instead of using Java VM? I'm not a developer and I have only minimal knowledge in this department. I can only speculate but I'm curious enough about it that I started googling around to find why.
Lodovik said:
2560*1600*4*60/1024/1024 = 937,3 MB/s for a 60 fps game at 32-bit depth
Click to expand...
Click to collapse
Just curious but what is that calculation supposed to be? total bandwidth needed? Cause I don't see your bit depth in there, unless the 4 is supposed to be that? If that is true than you are calculating on 4-bit color depth?
And then the result would just be bandwidth required for pixel data to memory wouldnt it? It wouldnt include texture data in and out of memory and other special functions like post processing.
2560*1600 = number of pixels on the screen
4 = bytes / pixels for 32-bits depth
60 = frames / second
/1024/1024 = divide twice to get the result in MB
Actually, I made a typo the result is 937,5 MB/s or 0.92 GB/s. This is just a rough estimate to get an idea of what is needed at this resolution just to push the all pixels on the screen in flat 2D at 60 fps, assuming that emulators don't use accelerated functions.
My point was that with 12.8 GB/s of memory bandwith, we should have more than enough even if this estimate isn't very accurate.
Thanks for the explanation
If there really were a memory bandwidth limitation the newer Trinity kernels and newest KTManta should help. In addition to the higher GPU speed they both allow (KTManta up to 720MHz) both ROM's have increased memory speeds which increase memory bandwidth to 13.8GB/s, up from 12.8 on stock.
Thanks for the info. There's so many configuration options available for the Nexus 10. I really enjoy having all those possibilities.
EniGmA1987 said:
If there really were a memory bandwidth limitation the newer Trinity kernels and newest KTManta should help. In addition to the higher GPU speed they both allow (KTManta up to 720MHz) both ROM's have increased memory speeds which increase memory bandwidth to 13.8GB/s, up from 12.8 on stock.
Click to expand...
Click to collapse
=Lodovik;40030*1600*4*60/1024/1024 = 937,3 MB/s for a 60 fps game at 32-bit depth. Most emulators don't use 3D functions so fillrate, rendering, overdraw won't be a factor. Most emulators are single-threaded (correct me if I'm wrong) and the A15 should shine in this particular situation and even more so in multi-threaded scenarios. With its out-of-order pipeline and greatly enhanced efficiency it should be perfectly suited for the job.
We have the fillrate, we have enough CPU power and I'm still wondering why simple app like emulators aren't much faster than that. Is it Android? Is it the Dalvik VM? Or is it because some emulators need to be written in native code instead of using Java VM? I'm not a developer and I have only minimal knowledge in this department. I can only speculate but I'm curious enough about it that I started googling around to find why.
Click to expand...
Click to collapse
You are taking what I said out of context. I was responding to someone else, thus the "quote" above my post.
Since you posted I loaded up some Super Nintendo, N64, and PlayStation games on my n10 without any issues. It may just be your setup. There are a lot of tweaks out there that could easily increase performance. One great and very simple one is enabling 2D GPU rendering which is in developer options. Just do some searching. GPU Overclocking won't help much, as you said above your games are only 2D. I am sure you can get them running just fine.
What read & write speeds (MB/s) are you getting on your XTZ? Internal storage, not external SD Card.
I usually measure it on my phone with https://play.google.com/store/apps/details?id=air.com.anotherflexdev.sdcardtester.SDCardTester&hl=en but I am sure there are better apps that allow fine grained measure slike 4k random accesses vs sequential and so on.
I am having trouble finding that data for the Xperia Tablet Z and it is an important factor in my purchasing decision.
Thankyou.
brugobo said:
What read & write speeds (MB/s) are you getting on your XTZ? Internal storage, not external SD Card.
I usually measure it on my phone with https://play.google.com/store/apps/details?id=air.com.anotherflexdev.sdcardtester.SDCardTester&hl=en but I am sure there are better apps that allow fine grained measure slike 4k random accesses vs sequential and so on.
I am having trouble finding that data for the Xperia Tablet Z and it is an important factor in my purchasing decision.
Thankyou.
Click to expand...
Click to collapse
I am attaching andro bench test results for the tablet z.
4k random writes, for example, come to about 1.1MB/s.
Thanks a lot.
So 47MB/s sequential and 15MB/s write. That means you can copy a movie from the tablet to a USB2 disk at max speed and copy from the disk to the tablet at like 60% speed.
As a reference, here is Anantech's latest benchmarks on other devices. It is the Note 3 review just skip to the NAND section.
http://www.anandtech.com/show/7376/samsung-galaxy-note-3-review/4
An USB2.0 disk will yield about 25MB/s sequential, a cheap old internal PC HDD is about 90MB/s (both write and read though) and a real SSD between 150MB/s on SATA 2 up to 450ish on SATA3. IOPS are another matter of course.
I like this tablet but I think I will wait for a tablet with faster eMMC and faster WIFI (ac). Maybe next model.
Thanks for your input.
Posting tablet NAND data instead of smartphone. I cannot edit previous post. I hope this is useful for those who land here from the search box.
http://anandtech.com/show/7378/samsung-galaxy-note-101-2014-edition-review/2
As provided above by francobarber:
Xperia Tablet Z Sequential read: 47.34 MB/s
Xperia Tablet Z 4kB Write: 1.1 MB/s
I want to have a new micro SD card ready to go when I pick up my V30+ next week. There are some decent deals for 128GB cards at BestBuy and Amazon. I have tried searching for the info but haven't had any luck finding the maximum read and write speeds the LG V30's micro SD slot is capable of.
Samsung EVO Plus 128GB - BestBuy
Samsung EVO Select 128GB - Amazon
They are essentially the exact same card, just different branding due to when they were manufactured. Same specs and all but the EVO Select seems to be the newer of the two where the EVO Plus has been around since 2015. If the V30's micro SD card slot isn't capable of 100MB's read and 90MB's write, then I may as well go for something cheaper and slightly slower and save $7.
SanDisk Ultra Plus 128GB - BestBuy
Is anyone aware of what the maximum capabilities of the V30's micro SD slot is capable of? Is there a way to test this that someone wouldn't mind testing and posting their results?
jcsww said:
Is anyone aware of what the maximum capabilities of the V30's micro SD slot is capable of? Is there a way to test this that someone wouldn't mind testing and posting their results?
Click to expand...
Click to collapse
Somebody did that a few weeks ago, I'll see if I can find the post.
EDIT
I was mistaken. It was the internal storage read/write speeds they tested.
V30 Internal storage speed?
https://forum.xda-developers.com/lg-v30/help/v30-internal-storage-speed-t3687990
They were trying to determine whether the LG V30/V30+ had UFS 2.0 or 2.1. It has UFS 2.1. (Earlier this year, Samsung shipped some S8 phones with both standards -- the Snapdragon S8 got 2.0 while the Exynos S8 got 2.1, while all chipset versions of the S8+ got 2.1.)
But several websites have done thorough reviews and have stated what's inside the V30/V30+, including exact components...
ChazzMatt said:
Both the LG V30 and V30+ have Toshiba UFS 2.1 (THGAF4G9N4LBAIRB) internal storage
LG's press release:
http://www.lgnewsroom.com/2017/08/l...ier-with-premium-cinematography-capabilities/
Memory:
V30: 4GB LPDDR4x RAM / 64GB UFS 2.1 ROM / MicroSD (up to 2TB)
V30+: 4GB LPDDR4x RAM / 128GB UFS 2.1 ROM / MicroSD (up to 2TB)
Click to expand...
Click to collapse
Other sites even give the manufacturer and component number:
https://www.androidheadlines.com/2017/10/lg-v30-review-ultimate-creativity-tool.html
Inside is a Qualcomm Snapdragon 835 chipset with Adreno 540 GPU, 4GB of LPDDR4X ram and either 64GB or 128GB of Toshiba UFS 2.1 (THGAF4G9N4LBAIRB) internal storage, all with microSD card support for expandable storage.
Click to expand...
Click to collapse
This 6-inch display features a Quad-HD+ (1440 x 2880, 538 PPI) resolution 18:9 panel with nearly zero bezels all around, and is covered in Gorilla Glass 5. It’s also both Dolby Vision and HDR10 compliant. Inside is a Qualcomm Snapdragon 835 chipset with Adreno 540 GPU, 4GB of LPDDR4X ram and either 64GB or 128GB of Toshiba UFS 2.1 (THGAF4G9N4LBAIRB) internal storage, all with microSD card support for expandable storage.
Click to expand...
Click to collapse
As it’s pushing the same resolution screen as the G6 with a processor and GPU boost, it’s pretty obvious why the phone feels so blazing fast all the time. Combine this with Toshiba UFS 2.1 (THGAF4G9N4LBAIRB) storage and you’ll quickly understand that LG has outfitted the V30 with the highest end components available right now.
Click to expand...
Click to collapse
Even the Toshiba UFS 2.1 storage inside is a perfect match for Samsung’s best UFS 2.1 storage, which is used in most flagships now, and averages out just as fast as those chips. See the results of the benchmark suite we run for each phone, including 3DMark Slingshot, GeekBench 4, AnTuTu V6 and Futuremark’s PCMark internal storage test.
Click to expand...
Click to collapse
https://www.anandtech.com/show/11789/hands-on-with-the-lg-v30
Under the hood, the V30 is powered by Qualcomm's Snapdragon 835, with LG using a heatpipe to assist in cooling. This is paired with 4 GB of LPDDR4X, and either 64GB or 128GB of UFS 2.1 storage.
Click to expand...
Click to collapse
Click to expand...
Click to collapse
Just used the A1 SD card speed test app. LG V30 - Samsung 128GB Evo Select formatted as a 'removable' storage device - did the standard 4GB size write / read test twice without closing apps etc (so bit of a real life test) and once did reboot (waited 5 minutes before launching), ran the accurate test (does write, then reboot again with another 5 minute wait, then does read):
Test 1
Read - 64.01 MB/s
Write - 35.38 MB/s
Test 2
Read - 65.25 MB/s
Write - 33.13 MB/s
Test 3 (accurate test)
Read - 60.56 MB/s
Write - 37.63 MB/s
Based on other benchmarks I have seen for this SD card (~95 MB.s read and ~70 MB/s write), it does appear the V30 is not able to get full speed out of it.
And just for 'fun' here is what the internal memory was capable of in this app (only ran the 4GB test once):
Read - 524.87 MB/s
Write - 199.30 MB/s
I am wondering if even if it were stuck at the slower speeds, would this have any impact on the camera, video, music, etc? I am planning on using a 128G SD card also if I get this phone.
pjcforpres said:
Just used the A1 SD card speed test app. LG V30 - Samsung 128GB Evo Select formatted as a 'removable' storage device - did the standard 4GB size write / read test twice without closing apps etc (so bit of a real life test) and once did reboot (waited 5 minutes before launching), ran the accurate test (does write, then reboot again with another 5 minute wait, then does read):
Test 1
Read - 64.01 MB/s
Write - 35.38 MB/s
Test 2
Read - 65.25 MB/s
Write - 33.13 MB/s
Test 3 (accurate test)
Read - 60.56 MB/s
Write - 37.63 MB/s
Based on other benchmarks I have seen for this SD card (~95 MB.s read and ~70 MB/s write), it does appear the V30 is not able to get full speed out of it.
And just for 'fun' here is what the internal memory was capable of in this app (only ran the 4GB test once):
Read - 524.87 MB/s
Write - 199.30 MB/s
Click to expand...
Click to collapse
Excellent! Thank you!
banshee28 said:
I am wondering if even if it were stuck at the slower speeds, would this have any impact on the camera, video, music, etc? I am planning on using a 128G SD card also if I get this phone.
Click to expand...
Click to collapse
That should be enough to handle 4k and pictures being directly written to the micro SD card. You will want a card that is better than those speeds but there isn't any need to go for anything super expensive that are rated for super fast performance.
Found Out Too late..
While the measurement numbers are great info - I didn't need to run a test, I noticed as soon as I tried to play some PSone and PSP games. Any game with heavy disc access while trying to play (sports games especially, due to commentary) stuttered like I was running them off of an external USB hard drive. Move the game to internal storage and (obviously, from the benchmarks, above) no trouble at all.
This is disappointing, as I picked up this phone expressly due to its specs for playing games (It was on sale, and replaced my cheapie Blu phone). Not the end of the world; I can move games to internal that are particularly problematic, but rather annoying and ironic, as the games most affected are the ones taking up the most space, requiring the extra MicroSD storage...
Vinc3Has3 said:
While the measurement numbers are great info - I didn't need to run a test, I noticed as soon as I tried to play some PSone and PSP games. Any game with heavy disc access while trying to play (sports games especially, due to commentary) stuttered like I was running them off of an external USB hard drive. Move the game to internal storage and (obviously, from the benchmarks, above) no trouble at all.
This is disappointing, as I picked up this phone expressly due to its specs for playing games (It was on sale, and replaced my cheapie Blu phone). Not the end of the world; I can move games to internal that are particularly problematic, but rather annoying and ironic, as the games most affected are the ones taking up the most space, requiring the extra MicroSD storage...
Click to expand...
Click to collapse
Go AOSP/non-Stock, format microSD to ext4, flash custom kernel and see how it changes things,
write speed will be improved by 100% (so twice as fast), read speed approx. around 10-20% (or more) compared to exfat.
Also custom kernel got general speed improvements so that might make a difference - haven't tried running anything particularly heavy off the microSD though.
That particular thing is probably the reason why Android/Google doesn't recommend using microSDs - it can really degradate and mess with experience/fun at times
zacharias.maladroit said:
Go AOSP/non-Stock, format microSD to ext4, flash custom kernel and see how it changes things,
write speed will be improved by 100% (so twice as fast), read speed approx. around 10-20% (or more) compared to exfat.
Also custom kernel got general speed improvements so that might make a difference - haven't tried running anything particularly heavy off the microSD though.
That particular thing is probably the reason why Android/Google doesn't recommend using microSDs - it can really degradate and mess with experience/fun at times
Click to expand...
Click to collapse
Thank you for this info! I will definitely look into it - Although I just ran a few tests of my OLD phone, (A Blu Vivo 2(?) XL(?) - I forget), and it's read time from the micro Sd is atrocious, like 32 read and 24 write, and yet it plays PSone games just fine from the Micro SD - the SAME Micro SD that the LG V30 is stuttering on (and I've tried a drawer-full, now) - which leads me to believe it's some other type of bottleneck. After all, an actual PSone cd only reads form 150 to 300 KB (not MB) of data per second. Even with a single emulator emulating individual autonomous chips, there should be headroom, I would think, to keep things going.
... Aannnnd this moves me off-topic from this thread - So I'll stop right there.