• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Rumors about the Crucial MX100 "features"

I heard a rumor that the MX100 doesn't need "TRIM." Is this true? WHY is it true?

I also heard that it doesn't need any overprovisioning for practical purposes. Same questions.
 
Certainly in other Crucial drives they loose less performance without trim compared to other drives. The M550 for example manages to looses a lot less performance than an 840 pro.

All SSDs have a garbage system that doesn't rely on trim, its just some of them maintain more performance than others. Trim is just a performance improvement that helps the drive to know about deleted sectors earlier.
 
http://www.anandtech.com/show/8066/crucial-mx100-256gb-512gb-review/3
If I am reading the graphic correctly Over provisioning does help performance.
I have not read or heard about any SSD that does not need TRIM but then again I never heard of TRIM until 3 years ago.
Maybe if you use the SSD for storage only there would be no need to OP but this is conjecture.

I think some of us had expectations of these devices with a sci-fi flair: back in the '90s, there were speculations that non-volatile, non-mechanical storage media might be "little cubes" that you could hold in your hand or poise on your pinky.

So you wonder how many "mainstreamers" have upgraded desktop systems with them, oblivious to the garbage-collection, TRIM and other maintenance needs. Then there was the feverish rush to RAID0 a pair of SSDs, followed by the realization that it would slowly "go south" without some TRIM feature.

TRIM is implemented in both configurations I have which include the MX100 -- having bought a pair of 'em. Neither are over-provisioned -- at the moment. The desktop installation is only "mostly for reads with few writes" -- storing additional programs. For now, anyway. The other one is in this laptop, and MIGHT be overprovisioned as I add more programs and data.

I'm trying to remember how long I'd been using hard disks before I discovered "defragmentation." In other words -- an analog, first to the realization that "you need to assure certain things are being done" with your SSD, and ultimately -- a point where you don't need to think about it.
 
First SSD I had was a OCZ vertex...you had to manually run a dos based program to initiate the garbage collection until later a firmware introduced TRIM support. There must have been 8-9 FW upgrades and quite a few were destructive upgrades...meaning all data had to be erased.

Second drive was an OCZ Summit, based on the samsung controller. It didn't TRIM support for a long time. Oddly enough, only one or two FW upgrades...might have been just one and that was to introduce trim support.

The drives that seem to really benefit from OP are the samsung drives.

As far as defragmenting goes, took me some time to realize the benefits. Mainly because there were BIG differences in software out there. I was a huge fan of Disk Keeper products and beta tested them for a while. Now I rely on O&O defrag which is able to send the trim command to most drives with a click of a button and it seems to work just as good as the disk keeper products.
 
As far as I know there is no real performance benefit to defragging an SSD. The reason a hard drive benefits is that the physical time it takes the head to seek the right place on the disk. But with an SSD the block is actually logical, the SSD is already fragmenting the files underneath without the operating system knowing anything about it. The fragmentation picture that the OS sees isn't the actual placements of blocks at all so defragging at the OS level really has minimal impact on performance because the SSD is already dealing with fragmentation. The latency is due to the SATA interface and protocol and device time and not seek time like a HDD, that article seems to fundamentally misunderstand that point.

There must be some value to de-fragmenting at the OS level because it saves some space and avoids the OS having to request from different places on the drive, but because the SSD doesn't use the same placement that the OS does its not helping the SSD out at all. Trim is what helps the SSD by providing it with earlier information about which blocks are expired and can be deleted, it allows the drive to do something about when the file is deleted and not when a block is overwritten which will often be much later. That extra information improves the SSDs knowledge and improves garbage collection and hence write performance in the future.
 
Last edited:
Back
Top