Degradation and Steady-State Performance
Unfortunately, SSDs are not always as fast as in their “fresh” state. In most cases their performance goes down after some time and in real life we deal with completely different write speeds than what we see on the diagrams in the previous chapter of our review. The reason for this phenomenon is the following: as the SSD runs out of free pages in the flash memory, its controller has to clear memory page blocks before saving data into them, which causes substantial delays. Although, modern SSD controllers can alleviate the performance drop by erasing unused flash memory pages ahead of time, when idle. They use two techniques for that: idle-time garbage collection and TRIM.
Of course, users are more interested in the consistent performance of their SSDs over a long period of time rather than the peak speed they are going to see only during the initial short-term usage period, while the drive is still “fresh”. The SSD makers, however, declare the speed characteristics of “fresh” SSDs for marketing reasons. That’s why we decided to test the performance hit that occurs when a “fresh” SSD becomes a “steady” one.
To get a complete picture of SSD performance degradation we ran special tests based on the SNIA SSSI TWG PTS (Solid State Storage Performance Test Specification) methodology. The main idea of this approach is to measure write speed consecutively in four different cases. First we measure the “fresh” SSD speed. Then we measure the speed after the SSD has been fully filled with data twice. The third test occurs after a 30-minute break during which the controller can partially restore performance by running the idle-time garbage collection. And finally, we measure the speed after issuing a TRIM command.
We ran the tests in synthetic IOMeter 1.1.0 RC1 benchmark, where we measured random write speed when working with 4 KB data blocks aligned to flash memory pages at 32 requests queue depth. The test data were pseudo-random.
We had no complaints about the TRIM command implementation in the Vertex 4 series before and firmware 1.5 doesn’t change anything in this respect. The Vertex 4 SSDs can both use TRIM to bring their performance back to the original out-of-box state. The new firmware complements this with background garbage collection. Now, when idle, Vertex 4 series SSDs can partially restore their performance in OSes that lack TRIM support. However, only SSDs with Marvell 88S9174 can really be brought back to their original performance by means of that technique.
Since the characteristics of most SSDs do change once they transition from fresh out-of-the-box state into steady state, we measure their performance once again using CrystalDiskMark 3.0.1 benchmark. The diagrams below show the obtained results. We use random data writing and measure only performance during writes, because read speed remains constant.
The adequate TRIM implementation makes the Vertex 4 series even more attractive compared to SandForce-based SSDs which slow down after having been used for a while. They are going to enjoy a large advantage in steady-state performance when it comes to writing with a long request queue and to sequential writing.
Well, it remains to be seen if the Vertex 4 series can convert their high results in the synthetic benchmark into high performance in real-life applications. So, let’s run some tests that simulate this kind of load.