The SSD Review The Worlds Dedicated SSD Education and Review Resource | 
CRYSTAL DISK BENCHMARK VER. 3.0 X64
Crystal Disk Benchmark is used to measure read and write performance through sampling of raw (0/1 Fill/compressible) or random data which is, for the most part, incompressible. Many new SSD owners who cant wait to test the performance of their SSD often grab this program and run a quick test, not realizing that they are testing with incompressible data rather than compressible data used in testing by manufacturers. The following results will show Crystal results using both compressible and incompressible data samples. The Z-R4 is on the left with the io-D on the right:
OFILL (COMPRESSIBLE) DATA SAMPLE UTILIZED
RANDOM (INCOMPRESSIBLE) DATA SAMPLE UTILIZED
ANALYSIS
In comparing the tests using both compressible and incompressible data, we see that the results of the Z-R4 drop a bit while the io-D remains consistent for the most part. This is a perfect example of our earlier discussion relating to SSD compression and testing fluctuations. As impressive as these scores are, the extremely high 4K-QD32 scores of the Z-R4 definitely stand out and provide a great impression of what we should be in for when testing IOPS.
Up until recently, ATTO was the only benchmark created specifically for SSD testing and it uses incompressible data. AS SSD, for the most part, gives us the worst case scenario in SSD transfer speeds while using SandForce Driven SSDs as they use compression in storage as discussed earlier. Many enthusiasts like to AS SSD for their needs. Once again, the Z-R4 will be on the left with the io-D on the right. For these tests, however, we will display the results in bandwidth above with IOPS below.
ANALYSIS
Even mentioning a ‘worst case scenario’ seems a bit amusing when we speak of watching the Z-R4 pull off 2.3GB high sequential read disk access, 341, 094 IOPS read and 265,170IOPS write at 4k-64Thrd. Without even pushing the Z-R4 as we will do in our IOPS testing, its results are three times better than those put out by the io-D.
Would be more fair if you compared it to the 1.28 TiB variant of the Duo.
Brilliant article none the less…
I agree totally but we have to work with the hardware that we have access to. As for the compliment of it being a brilliant article, totally unexpected and thank you very much.
“we have to work with the hardware that we have access to”
OK, so you have access to the fastest OCZ hardware but not the fastest FIO hardware…and this makes for a subjective test? Seriously? When do you expect to have current hardware for live testing? Any chance we might get actual server-side testing to show off the true strength of FIO hardware and, more importantly, software? Oh wait, then we couldn’t have a test could we…you’d need a competitor other than OCZ….
WE would be pleased to hear suggestions as to other sources of competition for the card. Thanks ahead.
not sure why the harsh response or love affair with Fusion. Why do you care which company? I say Fusion should put up the hardware like OCZ and do real life tests within applications. Both companies can put there money where their mouth is.
Harsh response? Love affair? I guess I am a bit confused because, well, myself, when I read an article I want to know the reviewers opinion and feelings just as much as I do facts alone. This is what keeps my interest.
It is also an important factor to help the reader. Take for instance the stuttering 602 controller a few years back. Can you imagine a reviewer saying, ” The drive stalls and stutters a bit but is still a large step up from a hard drive” Say it like it is I believe and hope our fellow members feel the same.
Thank you for taking the time to respond and expressing your feelings.
This is subjective because the z-drive r4 is cheaper than the FIO drive.
You find it subjective because one performs alot better yet is alot cheaper? How so?
Please update using the ioDrive 2 they just released, also
Finally SSDs start approaching the RAM speeds. Not very useful yet for the regular users without deep pockets. So meantime we still get 2-5 times of these speeds with software based QSoft RAMDrive and, thanks to DRAM price drop, at the $5/GB. While many even never heard of that but we are enjoying such crazy RAMDrives’ speeds for our apps for almost a quarter of century since the DOS times.
Suggestion to authors – test it just for fun. The latest QSoft Enterprise edition or one of Romex Software have a lot of nice functions allowing to auto backup the RAMdrive and load it back when you switch on and off your computer. Yes it might be lost if PC crash if you do not autobackup things, but this typically never happen, It is not for servers or critically important files but in its turn it is soooooo much faster and is eternal (well, lifetime guarantee) and no wearing off, TRIM, problems with compressed or 4K files.
I do not know while similar board designs of RAMDrives as these two SSDs are not making its road to the world (with just the battery backups) – they are so much faster t yet
nice review. I like both of these companies, but I think you need to compare the iodrive II DUO if you really want to compare head to head what each manufacture would put against another. Another addition that would be nice is to see performance of actual work like indexed data using lucene. What is the performance gain on these working enviornments.
We have been in contact with FusionIO during CES and just may be able to appease your request soon enough.
OCZ Z-R5 is also coming
Sorry, but thinking this through HP should donate some equipment or Dell as well as updating the cards and also add tests of real applications to see performance gains. This was a great article none the less. Thank You
“Is there really a need for anything that fast?” with 4 dual GPUs being used for CUDA/OPenCl application you do need even more than what is being provided to keep the GPUs filled with data with bottleneck.