Samsung 840 EVO read speed drops on old-written data in the drive - Page 327 - Overclock.net - An Overclocking Community

Forum Jump: 

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

Reply
 
Thread Tools
post #3261 of 3282 (permalink) Old 06-30-2016, 01:49 PM
New to Overclock.net
 
malventano's Avatar
 
Join Date: Sep 2013
Posts: 270
Rep: 50 (Unique: 28)
Quote:
Originally Posted by Techie007 View Post

If this is confirmed for sure, I hope @malventano picks up the story so that word gets around.

Ask and you shall receive.

One thing I noted though was that the data-filled 840 sample I had here actually sped up on sequential read passes, meaning it was not as badly affected as the 840 EVO was. The partial recovery reduced the speed gains seen from the firmware update, but they were still apparent. Advanced Performance Optimization capability also helps for extreme cases, or for those who are willing to sacrifice a write to freshen things up.
malventano is offline  
Sponsored Links
Advertisement
 
post #3262 of 3282 (permalink) Old 06-30-2016, 01:57 PM
New to Overclock.net
 
Yetyhunter's Avatar
 
Join Date: Sep 2010
Location: Belgium
Posts: 651
Rep: 24 (Unique: 19)
The firmware update does not show up.
And it seems I really need it

8700k @ 5Ghz, 1.33v // Asus Strix Z370-E Wifi // G-Skill Trident RGB 16GB 3200mhz // Asus GTX1080 STRIX
Samsung 500Gb 860Evo // Seasonic Focus+ Platinum 550W // Be Quiet! Dark Rock 4 // Meshify C + 3 additional phanteks 140mm
Yetyhunter is offline  
post #3263 of 3282 (permalink) Old 06-30-2016, 02:02 PM
Windows Wrangler
 
Techie007's Avatar
 
Join Date: Apr 2013
Location: Ohio
Posts: 2,217
Rep: 340 (Unique: 250)
Quote:
Originally Posted by Yetyhunter View Post

The firmware update does not show up.
And it seems I really need it

    Umm...that screenshot is a scan of a Seagate HDD? redface.gif    biggrin.gif

Techie007 is offline  
Sponsored Links
Advertisement
 
post #3264 of 3282 (permalink) Old 06-30-2016, 02:05 PM
New to Overclock.net
 
Join Date: Jan 2015
Posts: 731
Rep: 56 (Unique: 31)
Quote:
Originally Posted by Yetyhunter View Post

The firmware update does not show up.
And it seems I really need it


......it says your testing a ST3500410AS

Palorim12 is offline  
post #3265 of 3282 (permalink) Old 06-30-2016, 02:38 PM
New to Overclock.net
 
deepor's Avatar
 
Join Date: Feb 2013
Posts: 4,678
Rep: 470 (Unique: 317)
Quote:
Originally Posted by malventano View Post

Ask and you shall receive.

One thing I noted though was that the data-filled 840 sample I had here actually sped up on sequential read passes, meaning it was not as badly affected as the 840 EVO was. The partial recovery reduced the speed gains seen from the firmware update, but they were still apparent. Advanced Performance Optimization capability also helps for extreme cases, or for those who are willing to sacrifice a write to freshen things up.

What you've shown with those three graphs of running a test repeatedly, I saw a similar behavior with my SSD 840 that was tied to the temperature. While testing repeatedly, the drive heated up as seen in its SMART data temperature reading. The drive's performance increased the hotter it got. That's why running a test repeatedly improved the results in my tests.

After waiting for the drive to cool down, the results were again bad. Like, I ran the same test again on the next day, and the result was again bad the first time, then better the second time, etc.
deepor is offline  
post #3266 of 3282 (permalink) Old 06-30-2016, 02:51 PM
New to Overclock.net
 
malventano's Avatar
 
Join Date: Sep 2013
Posts: 270
Rep: 50 (Unique: 28)
I had a fan blowing across a high performance (unreleased) U.2 SSD what was sitting on the desk here. The 840 was in the same direct path of air flow. It was basically room temperature the entire time.
malventano is offline  
post #3267 of 3282 (permalink) Old 06-30-2016, 11:08 PM
New to Overclock.net
 
Yetyhunter's Avatar
 
Join Date: Sep 2010
Location: Belgium
Posts: 651
Rep: 24 (Unique: 19)
Quote:
Originally Posted by Techie007 View Post

    Umm...that screenshot is a scan of a Seagate HDD? redface.gif    biggrin.gif

Damn didn't see that last night LoL smile.gif) . Anyway is that normal for a normal hard drive ?
I was half a sleep when I posted this .

Still a bit slow.

8700k @ 5Ghz, 1.33v // Asus Strix Z370-E Wifi // G-Skill Trident RGB 16GB 3200mhz // Asus GTX1080 STRIX
Samsung 500Gb 860Evo // Seasonic Focus+ Platinum 550W // Be Quiet! Dark Rock 4 // Meshify C + 3 additional phanteks 140mm
Yetyhunter is offline  
post #3268 of 3282 (permalink) Old 07-01-2016, 04:16 AM
New to Overclock.net
 
deepor's Avatar
 
Join Date: Feb 2013
Posts: 4,678
Rep: 470 (Unique: 317)
Quote:
Originally Posted by Yetyhunter View Post

[...]

Still a bit slow.

Your motherboard probably has Intel SATA3 ports (two of them), and then some extra SATA3 ports provided by a different controller from for example Marvell or ASMedia. Those other controllers are often terrible compared to Intel or AMD controllers, and if you connected your drive to that extra controller, that could explain your results.
deepor is offline  
post #3269 of 3282 (permalink) Old 07-01-2016, 04:27 AM
New to Overclock.net
 
Yetyhunter's Avatar
 
Join Date: Sep 2010
Location: Belgium
Posts: 651
Rep: 24 (Unique: 19)
I checked and it's connected to the intel SATA3 port.

8700k @ 5Ghz, 1.33v // Asus Strix Z370-E Wifi // G-Skill Trident RGB 16GB 3200mhz // Asus GTX1080 STRIX
Samsung 500Gb 860Evo // Seasonic Focus+ Platinum 550W // Be Quiet! Dark Rock 4 // Meshify C + 3 additional phanteks 140mm
Yetyhunter is offline  
post #3270 of 3282 (permalink) Old 07-01-2016, 09:46 AM
Windows Wrangler
 
Techie007's Avatar
 
Join Date: Apr 2013
Location: Ohio
Posts: 2,217
Rep: 340 (Unique: 250)
Quote:
Originally Posted by Yetyhunter View Post

Damn didn't see that last night LoL smile.gif) . Anyway is that normal for a normal hard drive ?
I was half a sleep when I posted this .

Still a bit slow.

    Yes, the previous picture is normal for an older hard drive.  A newer HDD would start near 200 MB/s and drop off to about 100 MB/s at the end.

    On to the new picture.  Honestly, that graph looks perfectly fine to me, because:
  • You're using HD Tune, which is coded for HDDs and reads with tiny blocks, making I/O latency cause slightly slower speeds during the test.
  • HD Tune also calculates MB incorrectly using Base 2 math instead of the officially standardized, correct and logical Base 10 math, resulting in a 5% penalty on the reported speed.
  • You're probably not using the High Performance power profile for the test, and this allows the CPU to downclock (as it is mostly idle during the test), which causes slower I/O speeds.
  • You don't have a program running in the background maxing out a CPU core to keep the CPU from entering sleep states.

    All combined, these factors could easily shave off 50—150 MB/s off the benchmark.
 

Techie007 is offline  
Reply

Quick Reply
Message:
Options

Register Now

In order to be able to post messages on the Overclock.net - An Overclocking Community forums, you must first register.
Please enter your desired user name, your email address and other required details in the form below.
User Name:
If you do not want to register, fill this field only and the name will be used as user name for your post.
Password
Please enter a password for your user account. Note that passwords are case-sensitive.
Password:
Confirm Password:
Email Address
Please enter a valid email address for yourself.
Email Address:

Log-in



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may post new threads
You may post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off