What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

Corsair Performance 3 256GB SSD Review

Status
Not open for further replies.

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,270
Real World Data Transfers

Real World Data Transfers


No matter how good a synthetic benchmark like IOMeter or PCMark is, it can not really tell you how your hard drive will perform in “real world” situations. All of us here at Hardware Canucks strive to give you the best, most complete picture of a review item’s true capabilities and to this end we will be running timed data transfers to give you a general idea of how its performance relates to real life use. To help replicate worse case scenarios we will transfer a 10.00GB contiguous file and a folder containing 400 subfolders with a total 12,000 files varying in length from 200mb to 100kb (10.00 GB total).

Testing will include transfer to and transferring from the devices, using MS RichCopy (set to 1 file depth) and logging the performance of the drive. Here is what we found.


copy_lg.jpg%20


copy_sm.jpg%20



While the large file transfer performance is extremely good, the small file performance firmly sits in the middle of the pack. This comes as no surprise and we lay any reduction in performance solely at the feet of the garbage collection routines kicking in too aggressively.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,270
NON-TRIM Environment Testing

NON-TRIM Environment Testing


In many ways, Corsair’s Performance 3 should thrive in an environment that doesn’t support TRIM. To recreate this, 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 que depth across the entire drive’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.

To help give as both a detailed and practical overall picture of a given drive’s ability in this severe environment we have chosen two tests: one synthetic and the other more real world in nature.


Synthetic Results

Since reads are usually not greatly affected by a degraded state, for our synthetic non-trim test, we have chosen our standard sequential write test. By opting for this test and not one of our other shorter tests, the controller will not be able to compensate for being in a degraded state by using over-provisioning, caching or other similar buffers to hide the true state of the drive. To put it simply, by writing data across the entire drive, we will quickly see how big an impact this environment will have on them.

trim_write.jpg%20


Real World Results

For a real world application we have opted for our standard Vista load time test.

trim_boot.jpg%20


Without a doubt, this drive has extremely aggressive cleaning algorithms which in fact start working the moment they can, even if the system is not really in an idle state. On the positive side this meant a noticeable improvement after a mere 30 minutes of idle time. However, such an intense load upon the controller forces it to pick and choose between data reads / writes and cleaning. The unfortunate result is a decrease in the drive’s raw performance in order to ensure longevity.

One thing is for certain here: the Marvel 9174 controller running Corsair’s firmware makes the Performance 3 very hard to degrade. In other words, even with minimal idle time that occurs naturally throughout the course of the day we truly doubt you will notice a large hit in performance from not having TRIM. If you do notice and perceptible decrease in performance, simply let the system idle for awhile and it should be back to its old self.

In terms of our benchmark results, it seems that aggressive self maintenance routines lead to an impact upon small file performance. A controller only has so many cycles to go around and it is obvious that Marvel (and by extension Corsair) felt that some decreased synthetic benchmark numbers were a fair trade off for greater overall performance across a wide swath of scenarios, over a longer period of time.
 
Last edited by a moderator:

AkG

Well-known member
Joined
Oct 24, 2007
Messages
5,270
Conclusion

Conclusion


In a perfect world, every operating system and every conceivable combination of computer parts would be able to send and / or receive TRIM commands. Sadly, we don’t live in a perfect world. The almost dystopian PC landscape in fact bears very little resemblance to such a Utopia for all but the elite consumers with cutting edge systems. Sadly, this means anyone without the money to spend on a full system upgrade will likely be left out in the cold. Corsair and Marvell had other plans since the Performance 3 SSD caters to both ends of the market.

While the Performance 3 may not have wowed us with its extreme performance in our testbed’s normal configuration, this shouldn’t lead you to think it isn’t a cutting-edge drive. This drive has quite obviously been designed to meet the needs of a certain niche and the fit seems to be perfect. If you have been holding onto an antiquated installation of Windows XP / Vista or happen to be running certain Linux distros, the Performance 3 will likely be the best bet for long term endurance. In non-TRIM supporting systems, current SandForce-based SATA 6Gbps drives just can’t keep up. In short, the Performance 3 is a middle of the pack performer that has some flashes of brilliance.

This isn’t to say that Corsair’s Performance 3 isn’t without its fair share of minor issues. The cleaning algorithms going on behind the scenes can sure save its bacon but they tend to eat up valuable resources. The entire point of IDLE time garbage collection is to set things right when the drive isn’t being accessed but in this case it seems to be constantly running in the background. Certain aspects are therefore compromised in favor of long term performance endurance but real world boot times aren’t affected in an overly negative manner.

Even though anyone who is seriously looking at a near-$500 SATA 6Gbps SSD will likely have an environment which already supports TRIM, there are plenty of people out there who have been left high and dry. For these situations the Performance 3 offers a great upgrade route without the need for a full system overhaul. On the flip side, anyone with a newer TRIM-supporting setup will likely be better served with Corsair’s SandForce-based drives.


Pros:

- Increased write endurance thanks to 32nm NAND
- Amazingly aggressive self maintenance routines
- Great non-Trim environment performance
- Internal heat pads to help transfer heat from NAND to case


Cons:

- Aggressive Garbage collection comes at the expense of small file performance
- Less than optimal TRIM environment performance
 
Last edited by a moderator:
Status
Not open for further replies.
Top