Aces High Bulletin Board
General Forums => Hardware and Software => Topic started by: MrRiplEy[H] on December 04, 2014, 10:40:52 AM
-
That's right folks, 2000 terabytes of writes and the Samsung 840 pro and Kingston HyperX 3k are still alive:
(http://techreport.com/r.x/endurance-2pb/seq-read.gif)
-
Heh, nice huh. I don't have a Kingston, but have 2 840 Sams in the same size and one 830 in 128. Good intel to know, for sure. I figured the Samsung SSDs in my boxes would outlast the other surrounding hardware for the most part.
-
The chart you just quoted is the "sequential read" test. It does not surprise me if most any SSD would be fine with a fixed sequential write of that quantity. Not much of a test as it caters to the strength of the SSD, but in reality, it is rare to have fixed size sequential writes.
Even at that soft read test, four of the units appeared to have failed.
Is there is a test which threads (4, at least) multiple writes, of random sizes (1K to 4K), while doing multiple reads of those files at a random size of 1K to 4K? That would come closer to matching real world.
EDIT: Does it show the actual number of operations? That would yield a better measure of longevity when used in conjunction with the amount.
-
The chart you just quoted is the "sequential read" test. It does not surprise me if most any SSD would be fine with a fixed sequential write of that quantity. Not much of a test as it caters to the strength of the SSD, but in reality, it is rare to have fixed size sequential writes.
Even at that soft read test, four of the units appeared to have failed.
Is there is a test which threads (4, at least) multiple writes, of random sizes (1K to 4K), while doing multiple reads of those files at a random size of 1K to 4K? That would come closer to matching real world.
EDIT: Does it show the actual number of operations? That would yield a better measure of longevity when used in conjunction with the amount.
Yes they show random reads and writes too. Source: http://techreport.com/review/27436/the-ssd-endurance-experiment-two-freaking-petabytes
That's not a 'soft read test' they write the devices full and erase them as fast as they can muster. Every device in the test endured multiple times the advertised writes (the advertised endurance is usually 5-10 years of typical use), even the failed ones not to mention the two remaining ones. Writing an SSD full is multiple times harder for the device than regular use because in regular use the wear leveling algorithms ensure that if multiple small writes are done on a device the load is distributed evenly to the free clean blocks. This means that if you don't fill up your drive but do a lot of micro writes, your drive is going to last a very very long time despite it having only 4000-8000 write cycles per memory block (rated).
For the general consumer you can think of this like you have a storage house of 1000 six-packs of beer. You have to discard the six pack after you consume all of the cans. If you would drink every can one by one from each six pack you would have to throw out a lot of six packs. But if you drink a can here, can there you will spend an eternity before you have to dump even the first six pack (well, unless you are a total wino and drink your whole 1000x6 can lot every time at once like they're doing in this test).
(http://techreport.com/r.x/endurance-2pb/seq-write.gif)
(http://techreport.com/r.x/endurance-2pb/ran-read.gif)
(http://techreport.com/r.x/endurance-2pb/ran-write.gif)
(http://techreport.com/r.x/endurance-2pb/write.gif)
-
The OS breaks all write and read requests into 4K blocks (if the request is larger than that), as that is the memory page resolution for a virtual memory Intel system. The only way to do actual larger blocks is to by-pass the operating system and do raw reads/writes, which do not need a filesystem.
If the driver supports scatter/gather, then the writes can be combined, if they are sequential on the media. The purpose of using multiple threads is to mitigate the sequential nature of a single thread. The operating system is always writing data, independent of the application.
By writing 4K chunks (or smaller), it bypasses the scatter/gather attempts of the driver, if applicable. Using different size writes, below that (on 1K boundaries) imposes a higher degree of randomness in the testing, when using multiple threads.
Doing a full erase (filesystem level, or drive level?) and then filling it up again is not realistic at all. Fill the drive with files, then update the files and change the size of those more closely resembles what happens in the reality. Doing what they are doing is a general reliability test which cannot be related to real usage.
My interests lie in what would a real-life test be like compared to this static canned test. Still need the actual count of operations performed to give the data some real meaning in terms of longevity.
-
The OS breaks all write and read requests into 4K blocks (if the request is larger than that), as that is the memory page resolution for a virtual memory Intel system. The only way to do actual larger blocks is to by-pass the operating system and do raw reads/writes, which do not need a filesystem.
If the driver supports scatter/gather, then the writes can be combined, if they are sequential on the media. The purpose of using multiple threads is to mitigate the sequential nature of a single thread. The operating system is always writing data, independent of the application.
By writing 4K chunks (or smaller), it bypasses the scatter/gather attempts of the driver, if applicable. Using different size writes, below that (on 1K boundaries) imposes a higher degree of randomness in the testing, when using multiple threads.
Doing a full erase (filesystem level, or drive level?) and then filling it up again is not realistic at all. Fill the drive with files, then update the files and change the size of those more closely resembles what happens in the reality. Doing what they are doing is a general reliability test which cannot be related to real usage.
My interests lie in what would a real-life test be like compared to this static canned test. Still need the actual count of operations performed to give the data some real meaning in terms of longevity.
The testing software handles its i/o through the operating system so the write load is similar to any other write load. This kind of testing is the worst case scenario for an SSD because it's being repeatedly 100% filled with data and then erased, which places multiple times more stress on the memory cells than your daily 80% reads 20% writes use that fills up typically less than 1% of the drive on daily basis.
If the drive can outlive this stress test it can walz through any regular use you can throw at it.
The average consumer writes 5-10 gigabytes a day to their drives. It will take the consumer 200 000 days to achieve the 2 petabyte mark of this test. That's 547 years of daily use. It's very likely that the drive will die to other causes way before it reaches the first 100 years.
-
I talked with a support guy that prep and replace drives at work, we are using dell laptops so we can dock them.
What kills normally kills SSD drives is taking place during power-up ( not written data), ie electronic circuit failures.
-
It would seem logical that the first ripple out of a (below-par) PSU will kill the SSDs onboard.
-
I am doing a real life test on my ssd evo than they cant do with their programs. I have it sitting outside of the case on the carpet. when I turn off the computer I unplug the ssd, then plug it back in when it comes back up. I dont really have any date on it that I dont back up somewhere else. just doing it literally for the kick of it. as I kick the ssd once or twice when I play.
so far it is holding up. as for the petabyte limit, I am not so sure as I am not a vegetarian. I am just really having a kick out of how long the ssd will last. so far no bad sectors and no lost data that I know of.
semp
-
I am doing a real life test on my ssd evo than they cant do with their programs. I have it sitting outside of the case on the carpet. when I turn off the computer I unplug the ssd, then plug it back in when it comes back up. I dont really have any date on it that I dont back up somewhere else. just doing it literally for the kick of it. as I kick the ssd once or twice when I play.
so far it is holding up. as for the petabyte limit, I am not so sure as I am not a vegetarian. I am just really having a kick out of how long the ssd will last. so far no bad sectors and no lost data that I know of.
semp
You do realize that the SSD is suspectible to ESD shock just like any ohter computer component. Just don't come here bragging if/when your carpet zaps the drive with static and it dies. But it's funny that you chose the most powerful and long lasting media of your computer to be the usb backup lol. Or are you hotplugging it with sata also, without a hotplug bed? Prejudice is hard to get by I guess.
-
It would seem logical that the first ripple out of a (below-par) PSU will kill the SSDs onboard.
Just as logical as the ripple kills any component onboard, like the control board of your spinning hdd.
We have a server running mysql databases (around 1 Tb) on Samsung 840 pros. Not a single hiccup for 2 years. On the other hand we haven't had a SAS drive break yet either but let's see.
-
Your systems are not the typical PC bought online or from Best Buy either. The problem is that low end PC systems have PSUs that are time bombs when it comes to SSDs. Your typical HDD is not anywhere near as sensitive as an SSD is.
-
Your systems are not the typical PC bought online or from Best Buy either. The problem is that low end PC systems have PSUs that are time bombs when it comes to SSDs. Your typical HDD is not anywhere near as sensitive as an SSD is.
And you base your claim to which data exactly? Source of information please. It defies logic that the same integrated circuits that control SSDs would magically be more sensitive than those controlling spinner hdds. To me it seems that people are really stuck with the myth of unreliability caused by early production runs firmware problems that bricked many drives. That was entirely a software bug, not a hardware fault.
-
And you base your claim to which data exactly? Source of information please. It defies logic that the same integrated circuits that control SSDs would magically be more sensitive than those controlling spinner hdds. To me it seems that people are really stuck with the myth of unreliability caused by early production runs firmware problems that bricked many drives. That was entirely a software bug, not a hardware fault.
The power driving the hard drive motor(s) are all regulated and filtered on the HD circuit board. The R/W heads are also regulated and filtered. Transient power transitions can cause a lot of problems, for hard drives, due to the density they are packing data today.
The SSD memory circuits take power directly from the power supply of the computer. Some have a capacitor to help modulate any transient voltage variations, but most do not. There is no real need for it due to how the device stores data, but it can lead to damage of the device.
Take a meter and read the resistance across the circuits.
-
The power driving the hard drive motor(s) are all regulated and filtered on the HD circuit board. The R/W heads are also regulated and filtered. Transient power transitions can cause a lot of problems, for hard drives, due to the density they are packing data today.
The SSD memory circuits take power directly from the power supply of the computer. Some have a capacitor to help modulate any transient voltage variations, but most do not. There is no real need for it due to how the device stores data, but it can lead to damage of the device.
Take a meter and read the resistance across the circuits.
If this was a real world problem, the designers would have taken action already. It is not obviously. SSDs have 3-5 years warranties, you think the OEMs would intentionally make devices that are prone to catastrophic failure? Come on folks, you're not making any sense whatsoever. If anything SSDs have superior endurance because they lack any moving parts.
-
I built,or had built my latest computer in 2011,IIRC it was Feb of that year.
I went and put an SSD of 120 gigs into it with a 1TB storage drive. I run the OS and AH on the SSD and thats pretty much all I do on this computer,I average about 15 hours per week in AH.
This is my real world test and so far I havent had a single issue with the SSD. It has about 40 to 50 gigs of data on it so far. Now I'm sure you tech guys could estimate the usage as I have no idea but it's coming close to 4 years now and I still have a year of warranty left on it if it should fail.
When I first got this system I had concerns do to the fact that many SSD were failing and Skuzzy suggested that AH would run just as well on a HD, so I made a backup of the game and my settings,etc. incase the SSD failed and decided to run AH on the SSD to see how long it would last before failure.
I would still recommend someone install a regular HD for storage,even though the prices of SSD's are coming down. That said I will likely only use an external HD on my next build!
:salute
-
If this was a real world problem, the designers would have taken action already. It is not obviously. SSDs have 3-5 years warranties, you think the OEMs would intentionally make devices that are prone to catastrophic failure? Come on folks, you're not making any sense whatsoever. If anything SSDs have superior endurance because they lack any moving parts.
Yeah, and PSUs never fail. :rolleyes:
-
well, my ssd survived another real world test. my maid didnt notice it and ran the vacuum cleaner over it. had to replace both cables. the case is pretty scratched as hell. but it is still working.
semp
-
Yeah, and PSUs never fail. :rolleyes:
What did that have to do with this discussion?
-
If this was a real world problem, the designers would have taken action already. It is not obviously. SSDs have 3-5 years warranties, you think the OEMs would intentionally make devices that are prone to catastrophic failure? Come on folks, you're not making any sense whatsoever. If anything SSDs have superior endurance because they lack any moving parts.
I simply stated a couple of facts. Easily verifiable facts, at that. Many, if not most, SSD's do not have any power modulation/filter circuits. The enterprise class of SSD's do have power filtering. All HD's have power filtering.
The reasons are quite logical.
-
I simply stated a couple of facts. Easily verifiable facts, at that. Many, if not most, SSD's do not have any power modulation/filter circuits. The enterprise class of SSD's do have power filtering. All HD's have power filtering.
The reasons are quite logical.
Yep but this can not be a real world problem, OEMs would be crazy to build devices so prone to damage and the real world experiences of millions of users prove it. Grasping straws it is.
-
OEMs would be crazy to build devices so prone to damage
oh no...pinto anyone!
-
oh no...pinto anyone!
They sure didn't build another pinto after the law suits and reputation loss. You guys are fighting windmills here. But that's fine. You can continue using the 1960s storage technology as the rest of the world enjoys the superior I/O provided by the SSDs :)
-
They sure didn't build another pinto after the law suits and reputation loss. You guys are fighting windmills here. But that's fine. You can continue using the 1960s storage technology as the rest of the world enjoys the superior I/O provided by the SSDs :)
Actually Ford did built more pintos! The fix was a simple solution that wasnt implemented in the original design. All ford did was cut the filler tube and add a section of rubber hose,this allowed the tank to separate from the filler tube. The filler tube was shearing off in rear-end collisions and this was found to be the cause of the fires.
I know because I builts some of them,they were simply phazed out of production.
Now that I've hijacked that,Skuzzy which SSD's carry the filtering circuits,I'd like to know for a future build.
:salute
-
oh no...pinto anyone!
It's funny how the Pinto is the only one that gets mentioned. Yet Ford sold more Crown Vic's and Mustangs with prone fuel tanks....
-
It's funny how the Pinto is the only one that gets mentioned. Yet Ford sold more Crown Vic's and Mustangs with prone fuel tanks....
dont forget the trucks that could have been fixed with 20 bucks worth of steel on the roofs.
semp
-
dont forget the trucks that could have been fixed with 20 bucks worth of steel on the roofs.
semp
I'll try to forget the flaws of GM and Dodge. Wait.....if I did that then I would be a hypocrite. Bottom line is that more Crown Vic's and Mustangs were sold and go unnoticed. But ignorance is bliss to most these days.
-
The point is that it would never happen to Ripley, or someone like me, but suggesting one of these to someone that has just a few dollars to spare is asking for trouble. Probably, that's exactly why Skuzzy doesn't make recommendations like that, but it is precisely why I suggested that you (Ripley) should ask a few more questions before you give recommendations. Someone that has just lost a ton of data on their drive is a poor candidate for an SSD without a few changes first. It's just plain and simple.
I see recommendations on the Internet all the time that just put my teeth on edge, as in the audio recommendations for 5.1 headsets (just a for instance). Headsets, though, are relatively cheap.
-
The point is that it would never happen to Ripley, or someone like me, but suggesting one of these to someone that has just a few dollars to spare is asking for trouble. Probably, that's exactly why Skuzzy doesn't make recommendations like that, but it is precisely why I suggested that you (Ripley) should ask a few more questions before you give recommendations. Someone that has just lost a ton of data on their drive is a poor candidate for an SSD without a few changes first. It's just plain and simple.
I see recommendations on the Internet all the time that just put my teeth on edge, as in the audio recommendations for 5.1 headsets (just a for instance). Headsets, though, are relatively cheap.
SSDs are cheap too. You can get a 512Gb SSD for the price of a gaming headset, heck I just bought an Intel 256Gb SATA + 800Gb PCI-E SSD combo for the price of a high-end headset. If SSDs would have a wide spread reliability problem it would be all over the internet by now, especially considering the whine tsunami the early firmware problems created. Seems pretty silent.
Anyway 'for the guy who just lost a ton of data' the main concern is NOT whether to get a SSD or not. It's BACKUPS BACKUPS BACKUPS. And in case someone missed it: BACKUPS!
I don't really appreciate the way how first people make unwarranted claims about SSD memory cell degradation and when proven wrong by orders of magnitude (even compared to manufacturer ratings) they keep coming up with more theoretical problems that are not an issue in practical life.
HDDs still have their place, they're excellent low cost data strorages. A 4Tb hdd costs peanuts. I would not build a mid or high-end PC without a SSD as a boot drive anymore though. The 4Tb hdd is best served for low priority archived data and the medium for your USB external hdd for example. With USB3 you can take a backup of your drives fairly quickly at any time. Even if an external hdd doesn't qualify for 'backup' it's most likely the closest an average consumer ever comes to one.
-
I would never build another system for myself without a SSD.
Load time is just too big difference to ignore.
I still make Ghost backups to a spinning device, cost difference for a 2tb drive is just too high to ignore :)
-
Morfiend, I built my first SSD system around the same time and the same fashion, as most do I'm assuming, using a smaller 128g sized SSD for boot/OS and a few select things I use a lot, and a spinner drive for everything else.
I had put AH on the SSD, and ran it for about 6 months with no trouble, and then moved AH to the spinner drive after reading that all the small writes AH does could be a problem with the SSD drive, and it being the OS/Boot drive, was just a headache I didn't figure was worth the risk.
Reading that you've run it so long without any problems, I'm going to stick AH back on an SSD, but not the boot drive, I picked up a couple Samsung 840s, which are now "older" drives, on the Black friday sales, got 2 for about 60% off their already cheap sale price. I'll put one in each gaming box, and move my Steam folder to them as well as Aces High. That way, even if AH does crash it out, I won't really care as much as it'll not be my OS/Boot drive and I can just replace it and reinstall the games that get nuked.
Skuzzy - have you had any long term AH players who install the game on an SSD have a failure mainly due to the many small read/writes? Just trying to get a feel for what the odds are, as from what I understand it is playing Russian Roulette with the drive in at least some measure.
-
They sure didn't build another pinto after the law suits and reputation loss. You guys are fighting windmills here. But that's fine. You can continue using the 1960s storage technology as the rest of the world enjoys the superior I/O provided by the SSDs :)
So you equate a 1927 Model A ford to a 2015 Aston Martin? Yes, they all have wheels, and motors, and such things. Are they the same? Well,..I know the answer, but I wonder if you do?
Current hard drive technology has little to do with the original drum drives and analog heads used in the original IBM storage units.
Yep but this can not be a real world problem, OEMs would be crazy to build devices so prone to damage and the real world experiences of millions of users prove it. Grasping straws it is.
I am not grasping at straws. Again, I stated a few facts and made no other comment. You seem bent on making this about something else. Why all the exaggerated hyperbole?
Gman,I have not had any reports of failures, but slow downs have been reported.
Personally, I do not care what a person uses for storage. I would be remiss in not warning of the potential issues Aces High could cause, if run on the SSD. It really is quite silly to run Aces High from an SSD. There is really nothing to be gained from it, aside from the very first time the game is loaded. Anyone claiming it helps speed the game up is suffering from the placebo effect, or they have a very, very poor system in which an SSD is masking real problems.
-
So you equate a 1927 Model A ford to a 2015 Aston Martin? Yes, they all have wheels, and motors, and such things. Are they the same? Well,..I know the answer, but I wonder if you do?
Current hard drive technology has little to do with the original drum drives and analog heads used in the original IBM storage units.
I may have exaggerated a bit but a fact is that technology is moving into a direction and traditional hdd:s are fast becoming antiquated. SSD pricing is coming down all the time and the adoption is going mainstream.
I am not grasping at straws. Again, I stated a few facts and made no other comment. You seem bent on making this about something else. Why all the exaggerated hyperbole?
I read your comment as a continuum to the previous negativity against the technology. I would understand it IF the enthusiast sites I frequent at would have had even a single report of a SSD frying out due to a bad power supply - but I just don't see that happening. And trust me, every enthusiast nowadays runs SSDs. Some even in raid arrays. Back in 2013 there were some users having problems with power outs bricking their drives but again this was a firmware problem, not an electronic failure. The drives 'came alive' by reflashing the firmware. And these were users who had an unstable power grid and should have been using a UPS anyway.
-
I have nothing against the technology. Never have. As an engineer, I just take the logical approach to it all. I have no vested interests in any technology. If I see the potential for a problem, I will state so and why.
Your claims are not founded in reality as to hard drives fast becoming antiquated. If that were true the hard drive companies would stop developing the technology and SSD's would be all they were doing. The fact is, they have hard drive technology, in the labs, which quadruples the storage space of the current technology.
SSD's and hard drives are going to coexist for a long time. It is going to take a major paradigm shift in SSD technology to become as cost effective as hard drives are. As long as they can keep packing the densities in hard drives, the longer they will stay around.
For mass live storage, the hard drive is still the most cost effective solution. That's just a fact. An irrefutable fact based on years and years of compiled data.
By the way, "enthusiast sites" are just that. They tend to be full of hyperbole and awash with marketing, nit picking the bits and pieces they want in order to satisfy their agendas. Just because a lot of people, on a site, say something, does not mean it is a fact. Opinions, no matter how well supported, are just that, and nothing more.
I do not make claims, nor statements I cannot backup. More often that not, I will tell you how to verify what I have said. If I do not, one can always ask and I will be happy to satisfy that question. My only agenda is the people playing Aces High get the best experience they can.
-
I had considered moving AH to my HHD but I was just too lazy... :o
Then I thought I would just make a backup and run the game on the SSD to see how long it would last and if there was any problems. I dont see any benefit except to quick start time.
That said Skuzzy you didnt answer my question,maybe you missed it in all the pinto drivel but which SSD's use filtering circuits? I'm considering an upgrade and might include a new SSD with more capacity.
:salute
-
I had considered moving AH to my HHD but I was just too lazy... :o
Then I thought I would just make a backup and run the game on the SSD to see how long it would last and if there was any problems. I dont see any benefit except to quick start time.
That said Skuzzy you didnt answer my question,maybe you missed it in all the pinto drivel but which SSD's use filtering circuits? I'm considering an upgrade and might include a new SSD with more capacity.
:salute
I did miss it. Sorry. I carefully chose my wording there, as I do not have access to every SSD on the market. I can say, with a lot of confidence the enterprise SSD's do all appear to have some filtering on the power.
I have not found any consumer grade SSD's with that feature. However, I do not have direct access to all of them either, thus there may be some with it. I am just not aware of them.
-
TY!
:salute
-
TY!
:salute
The drives have a 5 year warranty and you're worried about filtering? LOL! Backups are necessary in any case so my advice is stop worrying and get yourself a new drive. The Samsung 850s (Evo or Pro) have both rocked in tests.
-
The drives have a 5 year warranty and you're worried about filtering? LOL! Backups are necessary in any case so my advice is stop worrying and get yourself a new drive. The Samsung 850s (Evo or Pro) have both rocked in tests.
I dont get it? I have an SSD now and have run the gane for several years.
I was simply inquiring about the filtering curcuitry and if there were and specific drives that might have it.
You seem to be very defensive about this,or is it just a case of selective reading? It really doesnt mater either way,if and when I plan my next build it will be obsolete before I order any parts!
:salute
-
I dont get it? I have an SSD now and have run the gane for several years.
I was simply inquiring about the filtering curcuitry and if there were and specific drives that might have it.
You seem to be very defensive about this,or is it just a case of selective reading? It really doesnt mater either way,if and when I plan my next build it will be obsolete before I order any parts!
:salute
I was under the impression that you were delaying a purchase decision based on which devices have the filtering, my bad. You're right, I am defensive because so many writers are writing with a very negative prejudice (for example guncrasher who says he got the SSD just to see if he can break it). That's like buying a brand new Smith&Wesson and then leaving it outside in the rain and mud just to see if it jams.
-
Thanks for the reply/info Skuzzy.
I'm still not going to run AH on my primary/boot/OS SSD, it's not worth the risk of having to take care of all that is entailed in a primary/boot drive failure. As I said, I WILL however risk it on a slave SSD drive, as if AH happens to contribute to any problems (slight chance is what I'm understanding here, very slight, but still there), it'll only have AH and a few other easily reinstalled games on it.
Again, thanks for the reply.
-
Thanks for the reply/info Skuzzy.
I'm still not going to run AH on my primary/boot/OS SSD, it's not worth the risk of having to take care of all that is entailed in a primary/boot drive failure. As I said, I WILL however risk it on a slave SSD drive, as if AH happens to contribute to any problems (slight chance is what I'm understanding here, very slight, but still there), it'll only have AH and a few other easily reinstalled games on it.
Again, thanks for the reply.
G, in 2 or 3 years let me know how you are making out with the slave drive! I suppose if I had 2 SSD's in the same box I would do the same thing! :o
I keep my game machine pretty trim,I have another desktop and monitor right beside it to use so all I really do is game on my main machine. I dont even have email setup on it.... :rofl
Hopefully Santa will bring me a new vidcard and then I shouldnt need to upgrade for another few years.
:salute