Overclock.net › Forums › Components › Hard Drives & Storage › SSD › Samsung 840 EVO read speed drops on old-written data in the drive
New Posts  All Forums:Forum Nav:

Samsung 840 EVO read speed drops on old-written data in the drive - Page 290

post #2891 of 3279
Quote:
Originally Posted by SATDK View Post

As to the 'instant' upgrade in speed. I am even more skeptical than @Sheyster. Samsung has been known to fix benchmarks before and this would be old hat for them to do it here (simply tell the firmware to report the file as 'read', regardless of the truth).

    Not possible.  The SSD must return the data requested consistantly, or your computer won't even get past the booting stage, let alone run a transparent benchmark like SSD Read Speed Tester does.  There's no "pretending" that the data was read.  For instance, SSD Read Speed Tester doesn't play any games: It reads the files just like any other program.  It literally has the contents of the file it's testing (up to 16 MiB at a time) loaded in RAM during the test.  The test cannot move on to the next file until the contents of the current file being testing are successfully read from the SSD into RAM.
    Since there's way too much data on a SSD for a trick like RAPID to deal with, the only delay that could have been improved is the error correction processing time.  Still, the data has to pass checksum (or your computer would quickly become unbootable), so Samsung had to improve the actual decoding algorithm so that it produces fewer errors.

    edit: Oh, and by the way, I'm not receiving a single cent for posting these facts. wink.gif
Edited by Techie007 - 5/17/15 at 12:39pm
My desktop PC
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-3770K Gigabyte P67A-D3-B3 NVIDIA GeForce 8400 GS  1x Corsair 8 GB 
Hard DriveHard DriveHard DriveOS
Kingston SV300S3 WesternDigital WD10EZEX Samsung HD154UI Windows 7 Ultimate SP1 x64 
MonitorMonitorKeyboardPower
Daewoo L947BK Gateway FPD1530 HTK-2001 Dynex DX-400WPS 
MouseAudio
Kensington K72400 Realtek ALC889 
  hide details  
Reply
My desktop PC
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-3770K Gigabyte P67A-D3-B3 NVIDIA GeForce 8400 GS  1x Corsair 8 GB 
Hard DriveHard DriveHard DriveOS
Kingston SV300S3 WesternDigital WD10EZEX Samsung HD154UI Windows 7 Ultimate SP1 x64 
MonitorMonitorKeyboardPower
Daewoo L947BK Gateway FPD1530 HTK-2001 Dynex DX-400WPS 
MouseAudio
Kensington K72400 Realtek ALC889 
  hide details  
Reply
post #2892 of 3279
Maybe you should be @Techie007 wink.gif
NEWBIE
(23 items)
 
  
CPUMotherboardGraphicsGraphics
AMD 8320e Asus Sabertooth R2.0 xfx r9 290 xfx r9 290 
RAMHard DriveHard DriveHard Drive
G.Skill rip jaws  Samsung 840 Pro WD BLUE 64MB Cache Ocz vertex 3 
CoolingCoolingCoolingCooling
Swiftech h220x  alphacool nexxos st30 280mm radiator alphacool coolplex pro LT10 100mm reservoir Swiftech h220 rad only 
OSMonitorMonitorKeyboard
Windows 7 64 Bit ENTERPRISE edition Acer 23" 1080p  asus 19" Dell Media Center  
PowerCaseMouseMouse Pad
Rosewill Photon 1200W Phanteks Enthoo Pro Logitech G5 or Steel Series MW2 edition Generic Cheapy 
AudioAudioAudio
GEMINI HSR-1000 Logitech 5.1 surround ZALMAN clip on mic 
  hide details  
Reply
NEWBIE
(23 items)
 
  
CPUMotherboardGraphicsGraphics
AMD 8320e Asus Sabertooth R2.0 xfx r9 290 xfx r9 290 
RAMHard DriveHard DriveHard Drive
G.Skill rip jaws  Samsung 840 Pro WD BLUE 64MB Cache Ocz vertex 3 
CoolingCoolingCoolingCooling
Swiftech h220x  alphacool nexxos st30 280mm radiator alphacool coolplex pro LT10 100mm reservoir Swiftech h220 rad only 
OSMonitorMonitorKeyboard
Windows 7 64 Bit ENTERPRISE edition Acer 23" 1080p  asus 19" Dell Media Center  
PowerCaseMouseMouse Pad
Rosewill Photon 1200W Phanteks Enthoo Pro Logitech G5 or Steel Series MW2 edition Generic Cheapy 
AudioAudioAudio
GEMINI HSR-1000 Logitech 5.1 surround ZALMAN clip on mic 
  hide details  
Reply
post #2893 of 3279
LOL, and he said facts too. Some people get paid, some people buy what they're selling and parrot it for free - and Samsung's bottom line benefits.
post #2894 of 3279
Quote:
Originally Posted by trparky View Post
 

Yes lawyers. How else do you expect a company to behave? When have you ever known a company to be open and forthcoming with information? Information is passed through a gauntlet of legal levels. Heck, for all we know whatever changes Samsung has done is now being patented as we speak. And to speak openly about it would allow for their competition to get an unfair advantage against them while the patent makes its way through the patent courts.

 

Patents don't work their way through "patent courts" but instead work their way through patent examiners who are tasked with trying to refute your reasoning for asking for a patent.  They don't get to court unless they are actually issued and someone sues someone else.  In that case it is federal circuit courts.  I have several and have had to defend them in court on two occasions.  That being said, it is highly likely that Samsung has discovered some new IP while trying to fix this issue and this could very well be one of the reasons why it took so long for them to get it out.  Once you release something into the public domain there is nothing stopping your competitors from trying to patent your ideas.  You also only have one year from that point to file.  You guys think the other flash manufacturers aren't watching this very closely?  I bet SanDisk, Toshiba and others are disassembling their firmware right now as we speak.

 

Since I have returned my drives I no longer have a dog in this fight.  From where I sit though I would give them 90% probability that they have fixed it this time.  Only time will tell for sure.

post #2895 of 3279
Quote:
Originally Posted by Techie007 View Post

    Not possible.  The SSD must return the data requested consistantly, or your computer won't even get past the booting stage, let alone run a transparent benchmark like SSD Read Speed Tester does.  There's no "pretending" that the data was read.  For instance, SSD Read Speed Tester doesn't play any games: It reads the files just like any other program.  It literally has the contents of the file it's testing (up to 16 MiB at a time) loaded in RAM during the test.  The test cannot move on to the next file until the contents of the current file being testing are successfully read from the SSD into RAM.
    Since there's way too much data on a SSD for a trick like RAPID to deal with, the only delay that could have been improved is the error correction processing time.  Still, the data has to pass checksum (or your computer would quickly become unbootable), so Samsung had to improve the actual decoding algorithm so that it produces fewer errors.

    edit: Oh, and by the way, I'm not receiving a single cent for posting these facts. wink.gif

You say not possible. shrug.

MS had investors believe in Windows 1.0 when it was just a video.

I believe Samsung has more at stake here to fudge these 'facts' with their team of programmers than you do with your slice of expertise.

And no, I am not belittling you. Just stating the obvious fact that you are greatly outclassed by the many programmers Samsung can afford and utilizes.
post #2896 of 3279
Quote:
Originally Posted by SATDK View Post

You say not possible. shrug.

MS had investors believe in Windows 1.0 when it was just a video.

I believe Samsung has more at stake here to fudge these 'facts' with their team of programmers than you do with your slice of expertise.

And no, I am not belittling you. Just stating the obvious fact that you are greatly outclassed by the many programmers Samsung can afford and utilizes.

    To me, this borders on fanaticism and demonstrates a complete lack of knowledge as to what is actually possible.  Samsung is already doing their best trick with RAPID.  This is not a matter of being outclassed, it is a matter of understanding how data transfers are handled between storage devices and software.  If Samsung's programmers were so great, we would not have had this issue in the first place, let alone a second time with the October fix.  I know the many stages the data goes through to get from the SSD to where it can be used by programs, and I will repeat: There is no way that the SSD can pretend to "read faster" than it really does.  You can insert caching mechanisms like RAPID in the middle, but the end of the matter is that the SSD will have to retrieve data eventually because everything doesn't fit in RAM, and at that point, the SSD's real performance will show.
    Once the SSD has fulfilled the data read request, there's no going back.  Either the request was fulfilled successfully (no error code) and in full (all the data that was requested), or it was not.  From a programs' standpoint, the fulfillment of the request comes with the data.  There's no pretending to a benchmark program (especially ones like SSD Read Speed Tester and File Bench that go through the filesystem) that the reads were fulfilled sooner than they were.  In other words, when the read request returns, it's returning with all the data, and the SSD can't say later "Oh, I've got more/revised data for you now."  Besides actually improving their algorithms or overclocking the SSD (limited by its already designed thermal capabilities), the only corner they can cut is error correction.  And if just a little corrupted data is returned—depending on when—your computer:
  • Will BSOD instead of booting
  • Won't be able to successfully boot to the desktop
  • Will crash programs on a regular basis, particularly when loading them
  • Will frequently report filesystem errors or missing files

    So for these reasons, they can't bypass error correction.  And error correction is rather black and white: Either the chunk just read (internally by the SSD) passes checksum, or it does not and needs to be read again.  That leaves one possibility: The new read algorithm has a lower error rate and/or a better way of reevaluating data to pass checksum quickly.

    While I'm fully with you guys that Samsung did a horrible job at customer service, I have the feeling from some of you that no matter what Samsung did to fix the 840 EVO, you would not be pacified.  BUT: economically, I believe that Samsung made the best decisions.  Coming clean publicly or giving more feedback to us about the issue—while appealing to technically inclined customers—would greatly spread word that there is something wrong with their SSDs.  As things stand now, most people are using the old, initial firmware blissfully unaware of the slower performance they are experiencing, and meanwhile, tons of positive reviews on the SSDs are pouring into places like Amazon daily.  Those of you who have been deeply offended are a very tiny part of their customer base.
My desktop PC
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-3770K Gigabyte P67A-D3-B3 NVIDIA GeForce 8400 GS  1x Corsair 8 GB 
Hard DriveHard DriveHard DriveOS
Kingston SV300S3 WesternDigital WD10EZEX Samsung HD154UI Windows 7 Ultimate SP1 x64 
MonitorMonitorKeyboardPower
Daewoo L947BK Gateway FPD1530 HTK-2001 Dynex DX-400WPS 
MouseAudio
Kensington K72400 Realtek ALC889 
  hide details  
Reply
My desktop PC
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-3770K Gigabyte P67A-D3-B3 NVIDIA GeForce 8400 GS  1x Corsair 8 GB 
Hard DriveHard DriveHard DriveOS
Kingston SV300S3 WesternDigital WD10EZEX Samsung HD154UI Windows 7 Ultimate SP1 x64 
MonitorMonitorKeyboardPower
Daewoo L947BK Gateway FPD1530 HTK-2001 Dynex DX-400WPS 
MouseAudio
Kensington K72400 Realtek ALC889 
  hide details  
Reply
post #2897 of 3279
rapid is a rather subpar version or primocache/supercache/forgettheothertool

LOL at ppl who think samsung can fake faster reads... there are several levels of checksums not to mention corrupted data breaks any encryption/signatures

in other news my dual evo raid0 is offline for the first time ever, have to figure out if it was the FW or other reason
gamebox
(13 items)
 
  
CPUMotherboard
e8200 evga 780i 
  hide details  
Reply
gamebox
(13 items)
 
  
CPUMotherboard
e8200 evga 780i 
  hide details  
Reply
post #2898 of 3279
Quote:
Originally Posted by Techie007 View Post

...The new read algorithm...

I generally agree, though not sure if it's the/a new read algorithm? I was under the assumption that it simply rewrites data in the background more aggressively.
Cute PC
(15 items)
 
  
CPUMotherboardGraphicsRAM
4930k@4200 Sabertooth x79 R9 290 Tri-X@950/1250 4x4GB@2133CL9 
Hard DriveCoolingOSMonitor
Crucial BX100 Mugen 4 Win7 Benq xl2411z 
MonitorKeyboardPowerCase
NEC EA231WMi QPad-MK50 (reds) Seasonic S12G 750 Define R4  
MouseMouse PadAudio
Deathadder 3.5G BE Razer Goliathus Speed Edition Large Onboard 
  hide details  
Reply
Cute PC
(15 items)
 
  
CPUMotherboardGraphicsRAM
4930k@4200 Sabertooth x79 R9 290 Tri-X@950/1250 4x4GB@2133CL9 
Hard DriveCoolingOSMonitor
Crucial BX100 Mugen 4 Win7 Benq xl2411z 
MonitorKeyboardPowerCase
NEC EA231WMi QPad-MK50 (reds) Seasonic S12G 750 Define R4  
MouseMouse PadAudio
Deathadder 3.5G BE Razer Goliathus Speed Edition Large Onboard 
  hide details  
Reply
post #2899 of 3279
I don't put it past Samsung to fudge things. I think that's exactly what they did with the first "fix." They may very well have hoped that the original fix worked, but by rewriting the data they made it impossible to know if it really did and they effectively kicked the can down the road. But I don't for one second believe they are faking reads to fool benchmarks. Even if doable (which it almost certainly isn't) that would be clear malfeasance and a huge mistake. This issue could be expensive, but it's not big enough for them to do something that stupid.

With that out of the way, I have a couple of questions.

1) Do the drives have an autonomous function which periodically rewrites old data or do I need to have Magician running for that to happen?

If it's the latter then I still consider the drive to be broken. The fact that the drive was much faster immediately after the firmware update isn't enough to convince me the drive is fixed (I'm keeping an open mind, but I'm still wary). It seems ok now, but what about a few months from now? I run a RAID0 so Magician isn't an option. I'm curious that that functionality would exist if it isn't needed.

2) Why can't Samsung's software see which drives I'm running in my RAID? Are their programmers just lazy?

My understanding is that other manufacturers don't have this problem with their software, and I can open up rapid storage and see my drives' Model and serial numbers and the firmware revision they're using, but even Samsung's data migration software which shouldn't have needed to do anything low-level refused to work because my drives were RAID'd and it didn't see them.
Edited by opcow - 5/18/15 at 1:11am
post #2900 of 3279
Quote:
Originally Posted by Tivan View Post

I generally agree, though not sure if it's the/a new read algorithm? I was under the assumption that it simply rewrites data in the background more aggressively.

    The last fix (in October) involved a Performance Restoration Tool that basically rewrote all the data on the SSD, refreshing it just like we could with MyDefrag or DiskFresh.  It also updated the firmware with a version that was supposed to keep degradation from happening in the future.  The entire "fix" would take 10-60 minutes to apply as the SSD was refreshed and the firmware updated.  When finished, the read speeds were back to normal.

    This new firmware is slightly different: Again, it is a two-prong solution, but this time, the main part is the firmware update and not the rewriting program, which is now optional (and part of Magician instead of being part of the firmware updater).  Many people chose to simply update the firmware and not refresh ("optimize") their SSD with Magician, just to see what the firmware update can do by itself.  After taking less than a minute to upgrade the firmware, the read speeds of slow files immediately increased to 300-400 MB/s—still slower than 500 MB/s—but much faster than 50-200 MB/s.  It does appear that the new firmware also slowly rewrites the drive, since people that have done repeated testing have seen an increase in performance over the period of just several days.

    An example of before/after fw/after optimizationAn example of before/after fw/after time.  I remember seeing a couple other interesting ones, but they're needles hidden in several haystacks (threads) now!  A test that I'd really like to see is a SSD that has a very slow, but large file on it, tested with a program like HD Tune over a period of time.  If the SSD is slowly rewriting itself, this could give us a good idea of the rewrite data rate (and thus a worst-case life expectancy scenario).

    So, given the immediate speed improvement after the update (with no time for data rewriting), I believe that the read algorithm has been improved in some way, be it fewer errors, faster CRC crunching, or better possibility guessing (fewer ECC attempts).  Plus slow data rewriting to keep things from aging significantly in the first place.  I'm definitely with you guys about wanting to know more details!  Oh, I just thought of another reason Samsung might not be saying very much: Patents and trade secrets.  This is new technology after all.  It would be quite the irony if part of the delay in releasing these fixes was Samsung rushing patent applications in!
My desktop PC
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-3770K Gigabyte P67A-D3-B3 NVIDIA GeForce 8400 GS  1x Corsair 8 GB 
Hard DriveHard DriveHard DriveOS
Kingston SV300S3 WesternDigital WD10EZEX Samsung HD154UI Windows 7 Ultimate SP1 x64 
MonitorMonitorKeyboardPower
Daewoo L947BK Gateway FPD1530 HTK-2001 Dynex DX-400WPS 
MouseAudio
Kensington K72400 Realtek ALC889 
  hide details  
Reply
My desktop PC
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-3770K Gigabyte P67A-D3-B3 NVIDIA GeForce 8400 GS  1x Corsair 8 GB 
Hard DriveHard DriveHard DriveOS
Kingston SV300S3 WesternDigital WD10EZEX Samsung HD154UI Windows 7 Ultimate SP1 x64 
MonitorMonitorKeyboardPower
Daewoo L947BK Gateway FPD1530 HTK-2001 Dynex DX-400WPS 
MouseAudio
Kensington K72400 Realtek ALC889 
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: SSD
Overclock.net › Forums › Components › Hard Drives & Storage › SSD › Samsung 840 EVO read speed drops on old-written data in the drive