Welcome to the MacNN Forums.

If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below.

You are here: MacNN Forums > News > Mac News > MacNN testing concludes on Samsung SSDs and Apple Trim implementation

MacNN testing concludes on Samsung SSDs and Apple Trim implementation
Thread Tools
NewsPoster
MacNN Staff
Join Date: Jul 2012
Status: Offline
Reply With Quote
Jul 24, 2015, 01:01 PM
 
When Apple released OS X 10.10.4, alongside the offering came an implementation of Trim technology to clean up and potentially speed SSD write speeds over time. Users choosing to activate the feature, previously only on Apple-provided SSDs were greeted with a dire warning about the potential for data loss should the feature go bad in any way. After a good first pass, MacNN has concluded its second round of testing on a drive series thought to be problematic with the command -- the Samsung 840 and 850 drives, both in pro and EVO lines.

History

We covered what the Trim function is in the previous article which launched this series. Up until the OS X 10.10.4 update, non-Apple drives had to rely on a sometimes dangerous hack to implement the cleanup feature. With 10.10.4 Apple has implemented a way to enable Trim for third-party SSDs, without resorting to the hacks. However, prior to executing the terminal command to turn the feature on, Apple issues a stern warning, making it perfectly clear that the risk of data loss falls squarely in the hands of the user.

There are two types of Trim -- queued, and sequential. We're testing sequential Trim, as implemented by the drive's firmware.

Testing Gear

We've got four SSDs from Samsung for this round of testing: either old retail stock, or original firmware and in-use for some time. On the testing block are the 840 EVO and Pro, and the 850 EVO and Pro drives, all 2.5-inch size, and 512GB capacity. All of the drives are pre-loaded with 200GB of data, which isn't modified in any way by the testing process.

The testing hardware is a 2012 i7 Mac mini running OS X 10.10.4. Connected to the Mac mini to support the drives initially were a RocketStor 5212 Thunderbolt SATA dock, and a dual-channel USB 3.0 RocketStor 5122B dock. Even though we've been assured that the USB dock was passing Trim, we've shifted to a second RocketStor 5212 for this, and every future round of testing. All of the AC adapters for the hardware are connected to an uninterruptible power supply, to prevent power outages or brownouts from effecting the testing process or inducing any SSD failure.

Protocol

Transferred files vary in size from 64KB through 6.3GB, adding up to 250GB per transfer. The drive copies were set up "round robin," progressing through drives one through four, one copy at a time. When a copy option off the drive was completed, the data was deleted through a normal Finder move to trash and empty trash routine.

Drives sat completely idle between transfer rounds other than OS indexing, giving each drive as much time idle as both reading and writing, and more than enough time for Trim collection to begin between operations. At the conclusion of the test, each drive has seen over 800TB of data copied to the drive, and just as much read.

Limitations of the test

We're aware that the test isn't perfect. It is an accelerated process, where we're artificially loading and unloading the SSDs to implement the idle Trim feature faster than normal use. Our use pattern on the drives is far heavier than normal OS drive usage, and less sporadic -- a SSD with an installed OS is "tickled" a lot, for virtual memory, OS file access, app loading, and the like. What we're doing is more akin to constant use of the drive for a Photoshop scratch disk.

What this test is not is a comprehensive test of Trim's reliability under OS X and with all SSDs ever manufactured. Results for this round specifically apply only to the Samsung 840 and 850 Pro and EVO series. This test could have been performed under Windows as well, as the real issue here is the drive series' firmware routines, and less about any implementation by Apple.

Conclusions

We've now moved 800TB of data on and off each drive, across two separate firmwares per drive. For "normal" installations, that's right around eight years of extremely heavy system and application drive use. We are seeing some fairly significant cell failure quantities, but as the drives are over-provisioned, or more flash cells than required in the drive to hit the advertised capacity, so we're still at 100 percent storage capacity. The drives are still usable, but given how hard we've hit the drives, in an abundance of caution, we aren't going to use them for anything mission-critical anymore

So, we're not seeing any problems, and we've put years of use on the entire line in just a few weeks. We theorize that most of the complaints about drive corruption on the Linux side of the fence is more about queued Trim, which is not implemented in OS X. This isn't a guarantee, as it is a heavily time-compressed test, but we here at MacNN feel safe about using the highly regarded Samsung offerings without qualm.

The Future

We're testing a few more drives round-robin right now. We've got a Crucial BX100 and a MX200, both in 512GB capacity on the rig. Additionally, an AMD Radeon 500GB and Patriot Blaze 480GB drive are running alongside the Crucial drives. We'll update this post in the future with the results of these four drives.
( Last edited by NewsPoster; Aug 7, 2015 at 09:23 AM. )
     
GaryDeezy
Fresh-Faced Recruit
Join Date: May 2013
Status: Offline
Reply With Quote
Jul 24, 2015, 01:29 PM
 
Thanks, good report! Curious: What tool did you use to measure the cell failure rate?
     
ekestler
Fresh-Faced Recruit
Join Date: Jul 2015
Status: Offline
Reply With Quote
Jul 24, 2015, 01:45 PM
 
Have you tested with the Transcend JetDrive 500 (a 480GB SSD for my mid-2011 MacBook Air)? Is TRIM safe to use with this drive?
     
ekestler
Fresh-Faced Recruit
Join Date: Jul 2015
Status: Offline
Reply With Quote
Jul 24, 2015, 01:54 PM
 
Further specifics on my question regarding the Transcend JetDrive 500:
Link Speed: 6 Gigabit
Negotiated Link Speed: 6 Gigabit
Physical Interconnect: SATA
Description: AHCI Version 1.30 Supported

TS480GJDM500:

Capacity: 480.1 GB (480,103,981,056 bytes)
Model: TS480GJDM500
Revision: 20140402
Serial Number: B406050028
Native Command Queuing: Yes
Queue Depth: 32
Removable Media: No
Detachable Drive: No
BSD Name: disk0
Medium Type: Solid State
TRIM Support: No
Partition Map Type: GPT (GUID Partition Table)
S.M.A.R.T. status: Verified
     
Mike Wuerthele
Managing Editor
Join Date: Jul 2012
Status: Offline
Reply With Quote
Jul 24, 2015, 02:53 PM
 
Gary, Techtool Pro does a pretty good job of interpreting the SMART extended drive status info, which parses all this. I've also got access to an Apple diagnostic tool which does the same.

ekestler - I've got a Mac SSD slot to m.2 drive adapter in my retina MacBook pro, so this is of interest. I'll have to work out a test suite for the "blade" SSDs, and coordinate with the manufacturers.
     
cashxx
Junior Member
Join Date: Apr 2009
Status: Offline
Reply With Quote
Jul 24, 2015, 04:27 PM
 
Good to hear! Thanks for the report and time in testing!
     
aroxnicadi
Junior Member
Join Date: Jun 2011
Location: Grande Prairie, Alberta
Status: Offline
Reply With Quote
Jul 24, 2015, 06:12 PM
 
Anyone know who makes the APPLE SSD SM1024F Media?
     
panjandrum
Dedicated MacNNer
Join Date: Dec 2004
Location: West Michigan
Status: Offline
Reply With Quote
Jul 24, 2015, 07:25 PM
 
That's great news and a very nicely done bit of reporting, thank you!
     
Mike Wuerthele
Managing Editor
Join Date: Jul 2012
Status: Offline
Reply With Quote
Jul 24, 2015, 08:53 PM
 
Originally Posted by aroxnicadi View Post
Anyone know who makes the APPLE SSD SM1024F Media?
Some are Samsung, some are SanDisk. SM1024F is Apple's part number for the drive, which could be from either manufacturer. SanDisk are the early ones, Samsung is the later.

The flash cells in the Samsung SM1024F aren't the same as those in the 840 or 850, nor is the controller.
     
frugalphone
Fresh-Faced Recruit
Join Date: Aug 2015
Status: Offline
Reply With Quote
Aug 11, 2015, 11:08 AM
 
Many thanks for thoroughness and testing! Newby here with what may be obvious:

Thunderbolt testing isn't quite the same as SATA, is it? I recall somewhere that problem(s) didn't exist via USB and Thunderbolt? Ie, Thunderbolt is direct vs cached; I don't know enough to understand Rocketstor test setup relative to an average older consumer system?

There's so many variables I'm finding it difficult to discern what to do to replace old hard drive.
I've other queries too ie summaries of data management for power surges / outages, ability of SSDs to recover from corruptions and will post on forum.
Thanks again!
     
hank
Fresh-Faced Recruit
Join Date: Dec 2010
Status: Offline
Reply With Quote
Oct 3, 2016, 02:18 PM
 
Any thoughts or warnings?

Newegg had these refurbished recently:

SAMSUNG Data Center Series SV843 2.5" 960GB SATA III V1 MLC VNAND Enterprise Solid State Drive?
     
   
Thread Tools
 
Forum Links
Forum Rules
You may not post new threads
You may not 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
Top
Privacy Policy
All times are GMT -4. The time now is 01:07 AM.
All contents of these forums © 1995-2017 MacNN. All rights reserved.
Branding + Design: www.gesamtbild.com
vBulletin v.3.8.8 © 2000-2017, Jelsoft Enterprises Ltd.,