Hey I recently found this image and it has brought up a bunch of questions hopefully you guys can answer for me.
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
The MyDevice is a "lag fixed" Galaxy S
1. As seen above, the Nexus One which is the only 2.2 device listed on the graph has its large increase on the benchmark from the CPU (blue bar). Can we expect a similar increase on the CPU bar when Froyo & JIT comes to our device? Or will the different architecture on our different CPU lead to different results (aka not as much increase on CPU)
2. As you can see the Lag Fix gives a giant boost to the benchmark all of which is from I/O performance. My first question on this is in which way does I/O performance actually manifest. I know 3D/2D = Games, CPU = Processing/Multitasking. In which area does this increase in I/O (I'm assuming Input Output?) appear, what do you see change?
3. My second question on the I/O increase is how much does this giant I/O increase actually speed up the phone. I currently own a Nexus One (about to buy a Galaxy S) and you can see that the I/O score is actually less the Galaxy S even without lag fix, however I have never experienced any lag on my Nexus one that people seem to encounter on their non lag fixed Galaxy S. Does this mean the giant I/O increase really isn't indicative of anything?
Thanks in advance for your answers!
1. to be seen, probably yes
2. concurrent memory I/O operations will not block each other
3. it does indicate, that samsung chose a less than optimal filesystem
HelloH said:
2. concurrent memory I/O operations will not block each other
3. it does indicate, that samsung chose a less than optimal filesystem
Click to expand...
Click to collapse
Source for the RFS thing? I've never actually seen one, or what evidence led to the conclusion (and am genuinely interested).. I'm growing increasingly
In regards to choosing a less than optimal filesystem, I/O for the galaxy S is the same speed as the nexus one. And to the best of my knowledge, nobody has actually identified where wear leveling takes place on this phone. It is possible that EXT2/3 disables wear leveling.. We also don't know if the major I/O improvements are isolated to Quadrant.
The I/O fix vastly inflates (inaccurately) the Quadrant score. It's great for showing off though
Okay so the giant increase in I/O benchmarks looks cool but doesn't really mean that area of your phone is going to improve 800% faster or something as the benchmark would indicate?
& ...
andrewluecke said:
Source for the RFS thing? I've never actually seen one, or what evidence led to the conclusion (and am genuinely interested).. I'm growing increasingly
In regards to choosing a less than optimal filesystem, I/O for the galaxy S is the same speed as the nexus one. And to the best of my knowledge, nobody has actually identified where wear leveling takes place on this phone. It is possible that EXT2/3 disables wear leveling.. We also don't know if the major I/O improvements are isolated to Quadrant.
Click to expand...
Click to collapse
So the source of the Galaxy S lag isn't the RFS filesystem but something called 'wear levelling' that occurs somewhere (most likely to do with he file system as the problem goes away when you use another one) that hasn't been identified yet?
So what is wear levelling?
*edit*
Also the current 2.2 leaks don't have the CPU boost seen in the OP. Is that because JIT is not enabled yet on 2.2 leaks?
LevitateJay said:
Okay so the giant increase in I/O benchmarks looks cool but doesn't really mean that area of your phone is going to improve 800% faster or something as the benchmark would indicate?
& ...
So the source of the Galaxy S lag isn't the RFS filesystem but something called 'wear levelling' that occurs somewhere (most likely to do with he file system as the problem goes away when you use another one) that hasn't been identified yet?
So what is wear levelling?
*edit*
Also the current 2.2 leaks don't have the CPU boost seen in the OP. Is that because JIT is not enabled yet on 2.2 leaks?
Click to expand...
Click to collapse
No.. Some people think RFS is slow because it can't do concurrent writing/reading properly (or something like that). But I have yet to have seen any proof, only the claim being made. EXT2/3 is thought to work around that, BUT, unless someone shows me evidence pertaining to that claim (I hear a lot of the claim being made, but no proof), its random guessing potentially. I just want to be sure that the claim isn't a result on chinese whispers being played.
On solid state drives, wear leveling is the distribution of writes equally on a drive to allow it to last longer. There is a performance penalty often for doing so, but it should be done. Nobody seems to have identified which mechanism provides write leveling on these drives, so whilst EXT3 may be significantly faster, until we know EXACTLY where wear leveling is performed, I'm concerned that some of the full-lag fixes might potentially lead to reliability problems. we don't know if the storage will last nearly as long. I doubt the current EXT3 image on top of RFS should affect wear leveling, but we also have no way of knowing if the current way really increases performance in all cases
I would be surprised if wear-leveling was done at the file-system level - I thought that was generally at controller level, and it's transparent to the file system? After all, FAT32 is routinely used on Flash memory, yet pre-dates it, and I'm pretty sure NTFS doesn't do wear-leveling either, but is usually used for SSDs on computers running Windows.
Either way, storing an ext2/3 image within the RFS file system is very unlikely to be hurting anything, even if it was done at file-system level, because the RFS layer is still there.
Not always on embedded systems. On Sata drives though, generally yes, but on embedded, they generally assume the developers will implement it themselves..
And yes, an image on RFS wont hurt, but, I believe before people start wiping RFS completely, they should understand how the controller interacts at a lower level
Another parallel stream of thought could be - maybe nexus one with froyo is "inaccurately" inflating quadrant's cpu related score calculation
dreamtheater39 said:
Another parallel stream of thought could be - maybe nexus one with froyo is "inaccurately" inflating quadrant's cpu related score calculation
Click to expand...
Click to collapse
True. However there are some other CPU benchmarks such as the MFLOPS test which Nexus one does show a giant boost in compared to the Galaxy, and received a lot of this boost from Froyo so the increase there isn't too inflated.
Related
Hello,
I take no credit for this at all. I saw it on the I900 post. and it works on vibrant. It gets rid of the sleep->awake lag.
NOTE: YOU MUST DO THE UNLAGFIX. DO NOT RUN THIS IF YOU HAVE NOT!
http://forum.xda-developers.com/showthread.php?t=760571
Author: RyanZA
Donation Link for him: https://www.paypal.com/cgi-bin/webs...=PP-DonationsBF:btn_donateCC_LG.gif:NonHosted
I wonder if a better place for this would be the Themes and APPS section...
I only say this bc it is an app...
I don't think so - I think the subject matter of this post and APP clearly deal with development as it pertains to the many lag fixes that are out now. Furthermore, any additional developments, questions, concerns, and problems would be much better address here by DEVELOPERS rather than the larger number of laymen who read the Themes and Apps section.
I am running Vibrant6 Eclair on my phone, and have ALWAYS had problems implementing any lag fix. Be it Ryan's one click, or MODACO's playlogos1 script hack. I've never been able to increase by Quadrant score, and have constantly run into "cannot read mounted card", "file already exists", i've even had the lag fix run all the way through, and had 890 quadrant scores.
This APP finally worked for me.
I installed the APK - then I "unrooted my phone" (option in the apk)
Then rebooted, then "re-rooted" my phone (with newest Busybox / SU )
Then rebooted, got into the phone, and ran this "one click app" again.
Chose "ONE CLICK LAG FIX"
Waited about 5-8 minutes, then phone auto rebooted.
I get on, run quadrant - 2125.
However, the phone seems to be running CHOPPIER and more SLUGGISH with regards to live wallpapers and home screen scrolling - whether or not the wallpaper is static or live. I was hoping that the lag fix, with such a high quadrant score, would make my phone UI run smoother (launcher pro) however, it doesn't seem to be the case. I have been using the phone for 3 hours now though, and not ONE single "hanging lag". Used to happen quite frequently - although for only 5-10 seconds and not overly annoying, still annoying to say the least.
Hopefully with the implementation of better roms, we will be able to get rid of this home screen lag issue.
Just wanted to confirm this lag fix works on my phone, running stock kernel, vibrant6 eclair. Just run the app and watch it go.
I can tell you from trying 10+ lag fixes.
This one is by far the BEST. Now I did not unroot. I dont know if that matterrs.
But i have a 2200+ Quad and the sleep->awake lag is GONE. and All the other lag is GONE.
I have no complains. Using a TMO vibrant here.
QUOTE=RyanZA; Ah, that issue! This lag fix will also take a long time to back up. It is not a different lag fix from the others, just a safer and easier to use lag fix. People who can already install the more advanced lag fixes should rather use those! This is aimed more at people who don't want the complications of those methods. = end quote
So people know, this is a simple ext2 lag fix... Most of the fixes in this forum are much more stable if you research... This app is for the lazy/ignorant if you don't know what you are doing or don't want to learn a better way of doing it... This is not a better/different fix... In fact this is a less stable lag fix..
Sent from my SGH-T959 using XDA App
Yeah I posted this on the market for RyanZA - just search for Galaxy S, Vibrant or LagFix it should pop up. I'm running his 2.3 LagFix which has a few more enhancements over the current Market app.
My more recent Quadrant:
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
Stock Kernel, RyanZA's 2.3 lagfix.
QUADRANT MEANS JACK $HIT... why is it constantly referenced as a good indicator?
Maybe everyone should flash cyanogens FAKE rom that had a 9k quadrant score, lol.
s15274n said:
QUADRANT MEANS JACK $HIT... why is it constantly referenced as a good indicator?
Maybe everyone should flash cyanogens FAKE rom that had a 9k quadrant score, lol.
Click to expand...
Click to collapse
Ok, give me a benchmark utility that you find as a good indicator, and I will post that instead. Just be sure to get your panties out of a wad when I do - ok?
Its not a bad benchmark app, especially when there are few variables.. But start comparing different phones and the free version is just an average of 4 different benchmarks... Our display is what has us at the top of the list.. Not cpu or memory..
Sent from my SGH-T959 using XDA App
Letting ya know this works..I first ran the Quadrant and for a 750 then I did not unroot or anything installed the tools and did the oneclick lag fix ran the Quadrant again and got 2042
s15274n said:
QUADRANT MEANS JACK $HIT... why is it constantly referenced as a good indicator?
Maybe everyone should flash cyanogens FAKE rom that had a 9k quadrant score, lol.
Click to expand...
Click to collapse
It isn't that bad of an indicator if you didn't purposely rigged up your phone to 'cheat' the system.
Here is a really good read on why I completely disregard Quadrant and the scores our lag fix generate. PLEASE READ THIS BEFORE ARGUING.
Curious, what are the linpack scores after the lag fix? Stock is low 8's.
s15274n said:
Here is a really good read on why I completely disregard Quadrant and the scores our lag fix generate. PLEASE READ THIS BEFORE ARGUING.
Curious, what are the linpack scores after the lag fix? Stock is low 8's.
Click to expand...
Click to collapse
The problem is that linpack only benchmarks the cpu, while the lag fixes address the i/o issue that plagues the vibrant, so linpack won't be a reliable solution either
s15274n said:
Here is a really good read on why I completely disregard Quadrant and the scores our lag fix generate. PLEASE READ THIS BEFORE ARGUING.
Curious, what are the linpack scores after the lag fix? Stock is low 8's.
Click to expand...
Click to collapse
The thing is thats benchmarking different things... Linpack only benchmarks the ability of the Virtual Memory I think... and the lag fix doesnt change anything but how the data is read/written, but we can tell how much of a difference it makes on the data rw speeds...
now doing a quadrant with a vibrant in one hand and a droid x in the other is too many variables.. bc we can only get the average of the four tests it does.... now if you had the pro version it would be a little different...
I have been running the without a lag fix since last sat... had the lag fix for a while before taking it off... I cannot tell a difference in the two... I think its just a placebo effect... but like its been said before, this phone is fast before any tweaking..
Apologies, I was not implying Linpack is a better BM... just curious if they got the same score. I assume they do then. I just wish people would quit acting like the quadrant score means something with this lag fix, it does not.
I would much rather have stability than a high quadrant.... I show someone a 2000+ and they dont care...
If the do care they pull out their phone and show me FULL FLASH on their JIT compatible 2.2 enable device and that it works with a score less than 1500.. Then the guy with the i*hone starts laughing at me for being a douche...
Does this let me change the font?
I've never had a lag problem with animations off. Only experienced some lag with animations turned "all on" . Try it . I don't think we really need this fix.
Sent using xda app....
You'll be surprised. I saw a huge difference after I applied this fix. What you think you don't need, and the difference you get after you apply this fix is huge.
Before in the android market I would get 'stalls'. Now I can go non-stop only stopping to fetch the next 20 or whatever apps.
What I'm trying to say is unless you try this fix, don't dismiss it. It is a huge boost in performance.
Yes, this fix is a true lag fix. It fixed my sleep-wake lag. it fixed it all.
Anyone running differnt versions I highly reccomend uninstalling it. and using this.
It makes your quad a BIT lower. maybe 10-20 pts. But, its HELLA stable and works like a charm.
I thought in read in the specs before buying this phone that it had 512 MB of RAM.
When I check in my task manager it says I only have 326 MB of RAM total..
Don't tell me we (Canadians) have less ram than everyone else??
it is not just the Canada version
all SGS phones have 512 of RAM but only 326 available for end users the rest are used by the phone services
Isn't it a 2.1 thing?
Sent from my GT-I9000 using Tapatalk
The kernel supports up to 326MB RAM. Newer versions support full 512MB.
I guess when Froyo is out officially we will have full 512MB support.
Its sounds to me this phone was made for frayo and 2.1 is just each what they had to go with the Iphone 4 would have gotten alot of sgs customers If the galaxy didn't release when it did
Sent from my GT-I9000M using XDA App
phandroid.com has a couple of shots of a Leaked Samsung Fascinate Equipment Guide . The second photo is quite interesting, it says
Onboard memory : 512MB Flash/384MB RAM
What does that mean ?? We have 384MB of RAM after all ??
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
PhoenixFx said:
phandroid.com has a couple of shots of a Leaked Samsung Fascinate Equipment Guide . The second photo is quite interesting, it says
Onboard memory : 512MB Flash/384MB RAM
What does that mean ?? We have 384MB of RAM after all ??
That's another phone.. Doesn't mean much.
Our official news/press release said we have 512MB, so we have 512MB. Don't get too worried. Samsung may have decided simply to put the RAM to better use for now (to speed up other areas). Apparently, the epic uses a RAM disk to speed things up, so it's possible ours has a 160MB Ramdisk too
Click to expand...
Click to collapse
Ok that's it, I'm selling my phone now.
Well, let's hope Froyo shows us the light.
andrewluecke said:
That's another phone.. Doesn't mean much.
Click to expand...
Click to collapse
I am relatively new to android, but from what I have read on the internet Fascinate is simply another Galaxy S variant customized to Verizon, just like Captivate, Vibrant and Epic 4G, isnt it ?? Why would they mess around with the core components just for one carrier ?
andrewluecke said:
Our official news/press release said we have 512MB, so we have 512MB. Don't get too worried. Samsung may have decided simply to put the RAM to better use for now (to speed up other areas). Apparently, the epic uses a RAM disk to speed things up, so it's possible ours has a 160MB Ramdisk too
Click to expand...
Click to collapse
I would like to believe that too , My only concern is Gingerbread compatibility. I know even if we have 512MB Gingerbread is not guaranteed. But 384MB means a definite no go , right ??
PhoenixFx said:
I am relatively new to android, but from what I have read on the internet Fascinate is simply another Galaxy S variant customized to Verizon, just like Captivate, Vibrant and Epic 4G, isnt it ?? Why would they mess around with the core components just for one carrier ?
Click to expand...
Click to collapse
They added a flash for one... It might be to save money for the carrier. But, this variant uses EVDO which I believe is US only, and its possible they need more space on the circuit board too, for other features they add. Either way, our phone is advertised as 512MB.
PhoenixFx said:
, My only concern is Gingerbread compatibility. I know even if we have 512MB Gingerbread is not guaranteed. But 384MB means a definite no go , right ??
Click to expand...
Click to collapse
Nobody knows. In the rumour world, there is a crapload of BS. Don't believe anything you hear unless Google says it directly (and publicly). Remember, Kevin Rose told us he SAW the iPhone before it was released, and it had multiple batteries. And that guy constantly says rumors (the only ones I see him ever get right are obvious ones or ones which have proof already if you know where to look). If rumors by idiots like him consume the the internet in hours, its easy for anyone else to do the same.
To the best of my knowledge, Google has never stated the RAM required.. That being said, the epic 4g apparently uses a 160GB RAMdisk to speed it up. It's possible our phone does the same (which explains the memory gap). But I have seen nobody prove or disprove whether we have 512MB of RAM which can be accessed by the OS. All I know is that Samsung have stated we do and haven't retracted it..
@andrewluecke: Come oon man must you QOUTE a big picture and the write some words as a comment?? WTF we are not stupid we now that you answered to the post abowe!!!
omaga said:
@andrewluecke: Come oon man must you QOUTE a big picture and the write some words as a comment?? WTF we are not stupid we now that you answered to the post abowe!!!
Click to expand...
Click to collapse
Don't blame me, I didn't even notice.. These forums should be thumbnailing the pics anyway
The photo is in line with previous speculation that the galaxy s has 384mb ddr(?) ram and 128mb onedram(fast ram dedicated to graphics??) / onenand(not actually ram??? 0_0) .. its all a bit confusing.
EDIT: found the relevant topics
http://ip208-100-42-21.static.xda-developers.com/showthread.php?t=742244
http://forum.xda-developers.com/showthread.php?p=7642223
EDIT2: at first I was a little concerned, but after reading the other topics, I'm fairly reassured that the "ram issue" isn't really a bit issue at all, once compared to nexus one, desire etc.
SEMC seems to run a Sony Ericsson blog. And his post is mainly guesses, as with the others. Nobody has actually proven anything. However, the arguments against 512MB of ram are that 128MB is flash, and that Samsung don't know the difference between RAM and flash (which doesn't make too much sense, as they clearly differentiate between the two elsewhere).
Until proven otherwise, there is no reason to believe that we don't have 512MB of physical RAM.
oswade said:
EDIT2: at first I was a little concerned, but after reading the other topics, I'm fairly reassured that the "ram issue" isn't really a bit issue at all, once compared to nexus one, desire etc.
Click to expand...
Click to collapse
I checked it as well, the Desire has 576 mb but it shows only 400 mb,
my old X10 has 384 but only shows 270 mb, it might be the kernel, but Ive read on a unreliable website that the rest was dedicated to the GPU just like a shared videocard on a Laptop...
Yeah, it's likely some is dedicated towards GPU and such, and it's likely to be OneDRAM. But, there doesn't seem to be any definitive proof..
iam sure its the kernel guys.. my old desire after flash mod kernel can get full 512mb and free memory up to 300mb using advanced task manager..
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
What does this mean for us? Possible that we only have 384 megs of ram?
and this is a dev issue how? it belongs in the Q&A section.
Since a lot of people here are trying to figure out how to free up ram up to the 512 limit ( or even close to it) it could belong here.
This has been discussed at length how much ram ourphones have. Posting a picture of a vzw ad does not helped dev's do anything with freeing up our ram.
Sent from my SAMSUNG-SGH-I897 using XDA App
Hmm, just checked gsmarena and there is nothing on the ram of the fascinate, so this might just be true. O.O On gsmarena, it shows as all the other galaxy s phones with 512 mb of ram.
if it is, that kinda sucks, even though you get camera flash, i would gladly take the extra 130mb~ or so of ram :/
Can I just make a quick point here without stepping on anyone's feet?
When you buy a computer advertised to have 4gb of ram, do you actually get to use all 4gb of that ram? No. Your computer takes some of it and divides it up for other purposes. Some is strictly for the OS, some goes and get dedicated to your GPU, and the rest you get to use. The story is the same for our phones. There is a 512mb chip in there for ram. You will only get to use ~380mb of it.
Same for a hard drive. As I've said once before...
Miztaken1312 said:
Sure you buy a 1TB hard drive, but you actually only get to use around 850GB of it due to formatting and whatnot.
Click to expand...
Click to collapse
It's all there, you just won't ever get to use it all for yourself.
miztaken1312 said:
Can I just make a quick point here without stepping on anyone's feet?
When you buy a computer advertised to have 4gb of ram, do you actually get to use all 4gb of that ram? No. Your computer takes some of it and divides it up for other purposes. Some is strictly for the OS, some goes and get dedicated to your GPU, and the rest you get to use. The story is the same for our phones. There is a 512mb chip in there for ram. You will only get to use ~380mb of it.
Same for a hard drive. As I've said once before...
It's all there, you just won't ever get to use it all for yourself.
Click to expand...
Click to collapse
That is cuz how microsoft's file system, NTFS, which counts 1024 kb = 1 mb. That is why it is off. This has nothing to do with NTFS. This is most likely that the ram isnt there. If what you said is the case, that would mean all of the galaxy s phones would be advertised as 304 mb, cuz that is all the is usable at stock.
And your hard drive comparison, thats because for 1 TB to show up in windows, it would have to be 1024 GB instead of the normal 1000 GB just because NTFS has a different way of counting bytes.
miztaken1312 said:
Can I just make a quick point here without stepping on anyone's feet?
When you buy a computer advertised to have 4gb of ram, do you actually get to use all 4gb of that ram? No. Your computer takes some of it and divides it up for other purposes. Some is strictly for the OS, some goes and get dedicated to your GPU, and the rest you get to use. The story is the same for our phones. There is a 512mb chip in there for ram. You will only get to use ~380mb of it.
Same for a hard drive. As I've said once before...
It's all there, you just won't ever get to use it all for yourself.
Click to expand...
Click to collapse
No, that is a really terrible analogy. You buy a 1TB hard drive. You get 1TB, counted in decimal. Just because you don't comprehend the difference between binary and decimal doesn't mean you're suddenly losing space. IT IS THE SAME AMOUNT OF SPACE.
Pretend I point to a can of paint and say it is navy blue. Some other guy comes along and says it is actually 000080 in RGB Hex value. You return your can of pain to the store and yell at the manager that you didn't get navy blue.
That's pretty much what you're saying about hard drives. You are not losing anything at all. Period. End of discussion. A computer simply interprets bits in a different numbering system than what we are used to (binary vs. decimal). There is no magic. There is no loss.
Likewise, your 4GB of RAM analogy is also incredibly flawed. When I buy 4GB of RAM, do I get 4GB? Yes, absolutely. There is exactly 4096KB of RAM there. I can have it sitting on my desk and there is 4GB there. I can install it in my machine and there is 4GB there. What it is used for is irrelevant. It is still 4GB that I paid for. I know that for a fact.
For our phones, we do not know for sure that there is exactly 512MB of RAM and, even if we did, we do not know if there is exactly 208MB of RAM being used for system processes or dedicated to the GPU. It could just be reserved for absolutely no purpose or it could not exist at all (after all, 208MB of RAM is an absurdly large amount of RAM to use for the system when we're still using EVEN MORE for android processes we can clearly see in any decent task manager). You don't know and neither do I.
It has nothing to do with the NTFS file system. It has to do with how the OS counts (megabyte vs mebibyte - base 10 vs base 2).
In regards to RAM, PC manufacturers do state if the GPU is using shared memory. Other than a non-discrete GPU, RAM in a computer isn't typically statically reserved.
The Galaxy S has never had 384~ MB available to the user. The most that can be squeezed out at present, and still have a fully functional phone, is 340~ MB.
So perhaps a developer has more to say about this... since they DEVELOP? It is awful lot of RAM to be used for unknown stuff
Eh, he still has a point. There's 512 there, just some of it is used for the system. I forgive Samsung for this since all android phones (heck, all OS's) suffer this phenomena.
I read somewhere that Samsung chose to statically allocate it rather than dynamically, just to really increase stability. So the cappy may be worse but still you always see this in some form
Sent from my SAMSUNG-SGH-I897 using XDA App
Then why Galaxy Tab shows 444 of available RAM?
Because that's a tablet?
Sent from my SAMSUNG-SGH-I897 using XDA App
The specs of the Galaxy S and Galaxy Tab are the same, apart from the screen resolution.. Even the Quadrant scores are the same.
DirtySoul said:
The specs of the Galaxy S and Galaxy Tab are the same, apart from the screen resolution.. Even the Quadrant scores are the same.
Click to expand...
Click to collapse
You just said the RAM was different.
Anyways, that doesn't change my point that some RAM is always taken by the system OS. Android is a little unique in that each hardware distributor is allowed to tweak the OS so the level of system RAM reserved changes but its still there always
Sent from my SAMSUNG-SGH-I897 using XDA App
fatttire said:
You just said the RAM was different.
Anyways, that doesn't change my point that some RAM is always taken by the system OS. Android is a little unique in that each hardware distributor is allowed to tweak the OS so the level of system RAM reserved changes but its still there always
Sent from my SAMSUNG-SGH-I897 using XDA App
Click to expand...
Click to collapse
They said the amount of *AVAILABLE* RAM shows differently. Insinuating that when two pieces of hardware that are identical show different amounts of available RAM (available, not physically present) that there is something else going on that we the user aren't aware of.
Unknowns like this lead to people asking questions. People asking questions lead to answers. Answers lead to optimizations by brilliant XDA developers. Brilliant XDA developers making optimizations lead to terribly happy users like myself.
So it's in the interest of everyone posting in these forums to ask questions and try to come up with possible answers besides "No".
Yes, we know OSes use RAM and allocates it to various things. I think the issue as stated by others already is that we don't know how MUCH RAM is being used by the OS in our case.
If one device says we have 340 MB RAM available, and another almost identical device says 444 MB RAM available then that means it's POSSIBLE that our brilliant XDA developers could discover how to free up another 100 MB RAM to do fascinating things with.
It's NOT possible for them to discover that if people asking questions and helpful suggestions are shut down by negative people simply stating "NO".
https://github.com/cmsgs/android_device_samsung_galaxys/blob/master/config
you can go here and check out the reserved memory allocation. See line 766 and 1394 under "reserved memory config." the reserved mem adds up to approx. 140 mb. give or take a few. That would put us pretty close to 512. Some of that can be freed up as has been done on the i9000 forum. They have successfully freed up 40-50 mb to be used as free ram, although freeing up too much from certain locations can have negative results such as hindering 720p playback. See speedmod froyo in the i9000 forum for details. [KERNEL] SpeedMod Froyo 340MB RAM Optimized + Sharpness fix by Hardcore. I also think sztupy, developer of z4mod (I believe) had something to do with it.
Just a matter of time and hopefully we will have the same.
I know they're both advertised as having 512MB, but the Tab has more physical RAM than the phone. You can find a post somewhere in the forum talking about the memory chip configuration. The Tab has 128MB more than the phone. That's the primary reason the Tab has so much more available memory.
crazililazn said:
That is cuz how microsoft's file system, NTFS, which counts 1024 kb = 1 mb. That is why it is off. This has nothing to do with NTFS. This is most likely that the ram isnt there. If what you said is the case, that would mean all of the galaxy s phones would be advertised as 304 mb, cuz that is all the is usable at stock.
And your hard drive comparison, thats because for 1 TB to show up in windows, it would have to be 1024 GB instead of the normal 1000 GB just because NTFS has a different way of counting bytes.
Click to expand...
Click to collapse
I just had to chime in - to satisfy the MS/HDD argument, an even better analogy: You purchase a Dell computer that is advertised to have a 500gb HDD. It arrives at your door only for you to find that (GASP!) the Windows install took 10gb, leaving you with only 490gb.
I believe that most if not all mobile handset manufacturers do this to some extemt. My Droid Incredible had 16gb of onboard storage advertised. They didn't mention that 4gb of that was reserved for the actual Android OS. It honestly never crossed my mind to feel swindled - it's just how it is.
That being said, I grow tired of this thread popping up as bumped when I check the Dev Forums for updates. While this discussion certainly has merit, it's nothing new to developers, nor does it have merit for them in particular.
Mods, can we get this thread locked or moved?
Z4mod is from Z4ziggy
tiger4j said:
https://github.com/cmsgs/android_device_samsung_galaxys/blob/master/config
you can go here and check out the reserved memory allocation. See line 766 and 1394 under "reserved memory config." the reserved mem adds up to approx. 140 mb. give or take a few. That would put us pretty close to 512. Some of that can be freed up as has been done on the i9000 forum. They have successfully freed up 40-50 mb to be used as free ram, although freeing up too much from certain locations can have negative results such as hindering 720p playback. See speedmod froyo in the i9000 forum for details. [KERNEL] SpeedMod Froyo 340MB RAM Optimized + Sharpness fix by Hardcore. I also think sztupy, developer of z4mod (I believe) had something to do with it.
Just a matter of time and hopefully we will have the same.
Click to expand...
Click to collapse
Howdy,
I've been using the CM7 nightly builds for a while now and figured it'd be nice to have a kernel that's based on CM7 with overclocking, RAM hack and couple of other tweaks. This kernel is pretty similar to the volkKernel but I wanted to have my own
Changes:
* Overclocking up to 1500 mhz (only through pimp my cpu at the moment)
* Default I/O scheduler of NOOP
I'll try to keep it up to date with the latest CM7 kernel sources.
[Releases]
Third release based on nightly #114
http://www.mediafire.com/?r57gqyuvhujwk6g
Second release based on nightly #101
* Removed RAM hack
* Balanced out the CPU clock values a little bit
http://www.mediafire.com/?1waipap3c71hat3
Initial release based on nightly #79
http://www.mediafire.com/file/w3e0s3vxwtznclz/cm7_79.zip
very nice welcome on board ^^
fallout0 said:
Howdy,
* Overclocking up to 1500 mhz (only through pimp my cpu at the moment)
Click to expand...
Click to collapse
Can't use setcpu?
i would like to use OC via CMParts ^^
Hmmm pardon me for asking, but why is it a 32mb RAM hack now instead of 64mb? Is it to resolve the gallery bugs?
I am using the original cpujauste o/c code that's why it only works with pimp my CPU. ill look into the others tomorrow to get that working
The 64mb hack caused issues for people with 1080p recording and the gallery. ill try it again and see how it works
ok, i found some bugs.
1. Reboot doesn't work. I guess thats because of the 32MB Ram Hack (for the vorkkernal, reboot doesn't work either)
2. After running a couple of hours, you only get around 50% of your CPU performance. Maybe the scheduler isn't optimized well. I recognized it by playing n64oid and it has lagged. Also I only get 3900 points at Antutu instead of ~5000 points.
ranrick said:
ok, i found some bugs.
1. Reboot doesn't work. I guess thats because of the 32MB Ram Hack (for the vorkkernal, reboot doesn't work either)
2. After running a couple of hours, you only get around 50% of your CPU performance. Maybe the scheduler isn't optimized well. I recognized it by playing n64oid and it has lagged. Also I only get 3900 points at Antutu instead of ~5000 points.
Click to expand...
Click to collapse
I think it's actually booting at ~700mhz by default so unless you set it up in pimp my cpu it'll stay at ~700 mhz. Probably why it's lagging.
We need more people working on kernels, thanks for doing so. Any improvements on battery life? Personally I find CM7 battery life to be pretty bad.
fallout0 said:
I think it's actually booting at ~700mhz by default so unless you set it up in pimp my cpu it'll stay at ~700 mhz. Probably why it's lagging.
Click to expand...
Click to collapse
Yep, now running with 1ghz again ^^
Can i request Voodoo Sound support?
Hey fallout0,
Nice work mate.
I think the general consensus is to not have the 64mb hack in kernels judging from a couple of poles about only 20% wanting the hack, probably less now.
I prefer to not have the hack at all imho, far too many instabilities for zero gain that being said I have yet to find a completely stable o/c kernel to use - stock seems to be the only completely stable kernel.
Be trying yours later on today so keep up the good work!
-smc
somemadcaaant said:
Hey fallout0,
Nice work mate.
I think the general consensus is to not have the 64mb hack in kernels judging from a couple of poles about only 20% wanting the hack, probably less now.
I prefer to not have the hack at all imho, far too many instabilities for zero gain that being said I have yet to find a completely stable o/c kernel to use - stock seems to be the only completely stable kernel.
Be trying yours later on today so keep up the good work!
-smc
Click to expand...
Click to collapse
Hey
Cheers
The ram hack and even overclocking support are pretty nasty hacks. Having said that I like the ability of adjusting voltages/maximum frequencies and until there is a better solution I think it's worth having this one
I agree about the RAM hack. I tried volkKernel and besides the reboot issue I didn't have any problems with the 32mb RAM hack. However the extra 32mb of RAM might not even be that useful.
I'll see how things pan out with this one then remove/add things as people complain
fallout0 said:
Hey
Cheers
The ram hack and even overclocking support are pretty nasty hacks. Having said that I like the ability of adjusting voltages/maximum frequencies and until there is a better solution I think it's worth having this one
I agree about the RAM hack. I tried volkKernel and besides the reboot issue I didn't have any problems with the 32mb RAM hack. However the extra 32mb of RAM might not even be that useful.
I'll see how things pan out with this one then remove/add things as people complain
Click to expand...
Click to collapse
Can't the reboot issue be easily resolved? According to RC, the bootloader expects the reboot-information to be at 128MB + 11 bytes, while the system writes it to [MB Reserved for Graphics]+11 bytes. As long as no ram-hack is applied, it'll of course be in the right place. Shouldn't it be easy for a kernel to just copy what is at [MB RESERVED]+11 to [128MB]+11 before shutdown?
Just talking by the seat of my pants here, haven't looked at any of the sourcecode, but it certainly feels feasible.
::Trym
I wish for that kernal:
- option on 32mb hack
- AVP/SD ram OC
- CMPart OC settings
thats it ^^
He-hey!))) This kernel is almost burnt my phone off.... Came upstairs after the dinner and found the phone off and very-very hooot... So, now I'm waiting for it to cool down a bit... Hope it'll turn on again)))
Update: Thank God that it didn't turn into BRICK))) Came on again and I've flashed it back to vorkkernel.
I am using MIUI ROM.
Very good works!! I have now tested with CM7 ROM "nightly full-77" version.
Fantastic Quadrant Score!!!
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
TrymHansen said:
Can't the reboot issue be easily resolved? According to RC, the bootloader expects the reboot-information to be at 128MB + 11 bytes, while the system writes it to [MB Reserved for Graphics]+11 bytes. As long as no ram-hack is applied, it'll of course be in the right place. Shouldn't it be easy for a kernel to just copy what is at [MB RESERVED]+11 to [128MB]+11 before shutdown?
Just talking by the seat of my pants here, haven't looked at any of the sourcecode, but it certainly feels feasible.
::Trym
Click to expand...
Click to collapse
I thought about it, and decided against it. Writing random information into active RAM is never a good idea.
so far so good with this kernel on RC1...
we want more OC !!!
moooooooore!
Should I still disable encryption on the stock kernel if I am gong to flash a custom kernel like elemental x anyways?
No because it will do it for you anywat
Sent from my Nexus 6 using XDA-Developers mobile app
Raymondlikesroot said:
Should I still disable encryption on the stock kernel if I am gong to flash a custom kernel like elemental x anyways?
Click to expand...
Click to collapse
biggiesmalls657 said:
No because it will do it for you anywat
Sent from my Nexus 6 using XDA-Developers mobile app
Click to expand...
Click to collapse
a kernel doesn't do it for you, it ALLOWS you to do it yourself.
---------- Post added at 10:49 PM ---------- Previous post was at 10:48 PM ----------
to decrypt, you have to reformat your storage, which mean you have to move everything or lose it.
The kernel is just force disabling encryption... keep in mind you have to FORMAT the userdata section on your internal storage... not just wipe it. You have to wipe Data, Dalvik, Cache and system aka everything but internal storage... then after thats done you have to FORMAT DATA to rid of the Encryption then make sure to flash the kernel that disables force encryption. Its just making it so it does not auto encrypt on startup but you still need to do the Format on top of the wiping to clear Encryption for good and yes make sure to do it because Snap 805 doesnt have decrypt on chip so youll see much better read write speeds from it so its worth the extra work.
As your attorney I recommend that you don't disable encryption. After my wife's phone was stolen I was very uncomfortable that the thieving scum could potentially see personal info on it, despite it being locked with both SIM & phone PINs (e.g. photos on the SDXC card). Encryption would have made her data safe.
I've run my Nexus 6 both unencrypted (9 months) and encrypted (6 months) and I see no difference whatsoever. None at all. The benchmarks that people waved around a year ago may well be accurate, and a write takes an extra 5 milliseconds. So what? In real life, no difference in performance or battery life, and peace of mind.
Edit: This looks like a deliberate disagreement with misfitpierce's "write speed" comment above. It isn't - I saw his/her final comment after I'd already submitted my post, but I'll leave my post as it is because I believe that it's correct. Benchmarks don't really reflect the user experience.
There is noticeable difference with encryption off on the nexus 6. the 6p encrypts and decrypts on the cpu in real time whereas a process is ran on the 32 bit snap 805. As for someone stealing your phone the encryption would only help them if they stole the phone and reflashed the rom to bypass the lock but left your stuff or tried to extract via pc and most of the time when someone steals a phone they are pretty dumb or are just attempting to flash if capable to erase everything asap so you cannot track or retrieve the phone. Paranoid to think otherwise tho it is possible. Personally thats a low risk tho and if someone wanted your info bad enough theyd get it regardless... I guess leave encrypted if you leave credit card info openly avail on your device etc but if your good about security the risk is minimum for the benefit on decryption. Just my 2 cents.
:The snag is that the Nexus 6 performs the file encryption/decryption on the CPU rather than dedicated hardware, which hurts performance and battery life"
Look that up anywhere! Thats a proven fact! Snapdragon 805 32 bit cpu was not properly set up to handle encryption without taxing the processor hardcore. I've noticed over 2 more hours SOT with encryption gone and over 30% read and write speed increase at times so... you choose what you wanna do,
"over 30% read and write speed increase"
Would that be from 0.08 seconds to 0.05 seconds...?
dahawthorne said:
"over 30% read and write speed increase"
Would that be from 0.08 seconds to 0.05 seconds...?
Click to expand...
Click to collapse
Nah thats MB/s writes that go from 6MB/s write/read to over 18 aka 30% increase or 3X more efficient. Your wrong, just deal with it and keep your encryption. Who cares what your want to do, you obviously seem to think that the nexus 6 aka the only phone handling encryption without a dedicated chip is not sacrafacing performance and is doing it by magic... I guess the phone farts out magic unicorns for you to.
{
"lightbox_close": "Close",
"lightbox_next": "Next",
"lightbox_previous": "Previous",
"lightbox_error": "The requested content cannot be loaded. Please try again later.",
"lightbox_start_slideshow": "Start slideshow",
"lightbox_stop_slideshow": "Stop slideshow",
"lightbox_full_screen": "Full screen",
"lightbox_thumbnails": "Thumbnails",
"lightbox_download": "Download",
"lightbox_share": "Share",
"lightbox_zoom": "Zoom",
"lightbox_new_window": "New window",
"lightbox_toggle_sidebar": "Toggle sidebar"
}
Just look it up online and do research about how the newer snapdragons handle the encryption not seperately and have a dedicated chip to handling it which is not affecting performance or battery. You must not know a lot about technology so I apologize but I did try to explain in easy to understand terminology, errr I mean words...
Even the crappy Intel Z3580 in my Zenfone 2 handles encryption on its own side chip which does not affect read or write speeds and or the battery at all. Have a good day and I'm done cause from here you can research this stuff yourself. Not complicated.
And youll say this is a benchmark tho and those dont mean anything... thats arrogance... Benchmarks hold some value but this is not just a benchmark. This is seen day to day and does affect performance. Try it yourself and see.
Just want to chime in and add my experience with encryption on or off.
I notice no drop in either performance or battery life. That's not saying there isn't a difference with encryption on or off (as already stated, there is a difference in read/write speed), but I'm just saying that for everyday use I see no difference.
(Going from 6 MB/s to 18 MB/s is not a 30% increase, rather 200%)
Raymondlikesroot said:
Should I still disable encryption on the stock kernel if I am gong to flash a custom kernel like elemental x anyways?
Click to expand...
Click to collapse
I vote no. The performance change is minimal and only shows up on boot or copying large files.
@misfitpierce
I'm on holiday and my N6 isn't great for writing long replies so I'll keep it short.
You seem to have ignored my earlier implied apology about the read/write speeds and continue to think that I have some sort of personal grudge against you. I haven't, but I really have to say that your ill-written and innumerate rant does you no favours.
I realised when I had posted my hundredth post and magically became a Senior Member that that status does not automatically confer knowledge on all of us. Most, certainly, but not all.
Please feel free to apologise and I shall accept it gracefully...
Im sorry then bud but the way you implied its such a small change and its like your conveying false info to people. Its not just benchmark hoohaa junk. Im well aware that benchmarks typically dont mean much in terms of daily use but I do apologize if I've offended you @dahawthorne but its not as small a change as you stated.
The difference is there... its more of if people care enough to want to see it in day to day. It does improve battery because the CPU is being taxed much less but then again if you only answer a few texts daily and phone calls and dont transfer files or watch giant sized movies aka files or anything of that nature then you wont see much difference because the CPU isnt doing very much to begin with. If you download torrents and all that all day and do tons of stuff there is a noticeable difference. I guess it depends on how much you actually do on your phone daily.
Thanks. We can agree to differ. I don't say you're wrong, I say only that the benchmarks in real life use don't make as substantial a difference as you think.
And seriously, thanks for having the chutzpah to say "sorry". Even though I asked for it, pretty much tongue in cheek, it's good of you to recognise that both our opinions are valid.
The OP can no doubt make up his own mind based on all the comments above. Battery v security. I say security, but I get your point too.
misfitpierce said:
Im sorry then bud but the way you implied its such a small change and its like your conveying false info to people. Its not just benchmark hoohaa junk. Im well aware that benchmarks typically dont mean much in terms of daily use but I do apologize if I've offended you @dahawthorne but its not as small a change as you stated.
The difference is there... its more of if people care enough to want to see it in day to day. It does improve battery because the CPU is being taxed much less but then again if you only answer a few texts daily and phone calls and dont transfer files or watch giant sized movies aka files or anything of that nature then you wont see much difference because the CPU isnt doing very much to begin with. If you download torrents and all that all day and do tons of stuff there is a noticeable difference. I guess it depends on how much you actually do on your phone daily.
Click to expand...
Click to collapse
i have an encrypted n6, since nov 2014, and do not own any form of computer(so no transferring files), and im a very heavy user. the only differences that i can see only existed before 6.0, after 6.0 there arent any differences that any person can see(maybe there are, but they are not seen). read/write is a bit better when not encrypted, but since i dont own a computer, i dont see that. as i can see, performance isnt affected in one bit, as my encrypted n6 has crushed many unencrypted n6.