AkG
Well-known member
- Joined
- Oct 24, 2007
- Messages
- 5,270
NON-TRIM Environment Testing
In order to replicate a non-TRIM environment we first modified our testbed so that it would not pass on the necessary cleaning commands. Meanwhile, to artificially induce a degrade state we ran eight hours of IOMeter set to 100% random, 100% write, 4k chunks of data at a 64 queue depth across the entire array’s capacity. At the end of this test, the IOMeter file is deleted and the drive was then tested. This will replicate drive performance after extended heavy usage prior to any self maintenance routines kicking in and is indicated by the “Dirty” results below.
In order to allow each drive’s self-maintenance routines to kick in, we then wait 30 minutes (Dirty + 30 results) with the system at idle and rerun the tests.
For a real world application we have opted for our standard Vista load time test.
Keeping an SSD's performance in top shape isn't an easy process. Some drives like Crucial's M4 and Corsair's Performance Pro have some aggressive background garbage collection routines that run during idle periods while SandForce-based products have a set amount of storage space reserved for wear leveling or implement a software solution (like Intel's Toolbox application). OCZ's Vertex 4 on the other hand takes a different path. The use a type of passive ITGC routine that runs in the background that does seem to work, but not all that well according to our results since performance was still lagging after some 30 minutes of idle time.
It is unfortunate that OCZ has still not taken a page from the original Vertex by giving their new drive a software solution – aka “wiper.exe” - to this age old problem. This is a missed opportunity, as Intel does offer a non-trim solution for their drives and the difference is noticeable. Simply put, even the best “Idle Time Garbage Collection” routines – which this drive does not appear to have – are a much slower solution than a software solution at getting a drive out of a degraded state. Luckily, there is one mitigating factor in the Vertex 4’s favor: “quantity has a quality all its own” and that extra large cache combined with a very powerful controller means that even when degraded the results are still very, very good.
It also bears mentioning that providing a software solution similar to Intel’s shouldn't be that difficult for OCZ to implement as they do “own” the controller and create its firmware in-house.
NON-TRIM Environment Testing
In order to replicate a non-TRIM environment we first modified our testbed so that it would not pass on the necessary cleaning commands. Meanwhile, to artificially induce a degrade state we ran eight hours of IOMeter set to 100% random, 100% write, 4k chunks of data at a 64 queue depth across the entire array’s capacity. At the end of this test, the IOMeter file is deleted and the drive was then tested. This will replicate drive performance after extended heavy usage prior to any self maintenance routines kicking in and is indicated by the “Dirty” results below.
In order to allow each drive’s self-maintenance routines to kick in, we then wait 30 minutes (Dirty + 30 results) with the system at idle and rerun the tests.
Real World Results
For a real world application we have opted for our standard Vista load time test.
Keeping an SSD's performance in top shape isn't an easy process. Some drives like Crucial's M4 and Corsair's Performance Pro have some aggressive background garbage collection routines that run during idle periods while SandForce-based products have a set amount of storage space reserved for wear leveling or implement a software solution (like Intel's Toolbox application). OCZ's Vertex 4 on the other hand takes a different path. The use a type of passive ITGC routine that runs in the background that does seem to work, but not all that well according to our results since performance was still lagging after some 30 minutes of idle time.
It is unfortunate that OCZ has still not taken a page from the original Vertex by giving their new drive a software solution – aka “wiper.exe” - to this age old problem. This is a missed opportunity, as Intel does offer a non-trim solution for their drives and the difference is noticeable. Simply put, even the best “Idle Time Garbage Collection” routines – which this drive does not appear to have – are a much slower solution than a software solution at getting a drive out of a degraded state. Luckily, there is one mitigating factor in the Vertex 4’s favor: “quantity has a quality all its own” and that extra large cache combined with a very powerful controller means that even when degraded the results are still very, very good.
It also bears mentioning that providing a software solution similar to Intel’s shouldn't be that difficult for OCZ to implement as they do “own” the controller and create its firmware in-house.
Last edited by a moderator: