SanDisk Extreme Pro SSD (240GB, 480GB & 960GB) Review: The Fastest Just Got Faster
by Kristian Vättö on June 16, 2014 4:00 PM EST- Posted in
- Storage
- SSDs
- SanDisk
- Extreme Pro
Performance Consistency
Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal defragmentation. The reason we don’t have consistent IO latency with SSD is because inevitably all controllers have to do some amount of defragmentation or garbage collection in order to continue operating at high speeds. When and how an SSD decides to run its defrag or cleanup routines directly impacts the user experience as inconsistent performance results in application slowdowns.
To test IO consistency, we fill a secure erased SSD with sequential data to ensure that all user accessible LBAs have data associated with them. Next we kick off a 4KB random write workload across all LBAs at a queue depth of 32 using incompressible data. The test is run for just over half an hour and we record instantaneous IOPS every second.
We are also testing drives with added over-provisioning by limiting the LBA range. This gives us a look into the drive’s behavior with varying levels of empty space, which is frankly a more realistic approach for client workloads.
Each of the three graphs has its own purpose. The first one is of the whole duration of the test in log scale. The second and third one zoom into the beginning of steady-state operation (t=1400s) but on different scales: the second one uses log scale for easy comparison whereas the third one uses linear scale for better visualization of differences between drives. Click the buttons below each graph to switch the source data.
For more detailed description of the test and why performance consistency matters, read our original Intel SSD DC S3700 article.
 |
|||||||||
| SanDisk Extreme Pro | SanDisk Extreme II | Intel SSD 730 | Intel SSD 530 | OCZ Vector 150 | |||||
| Default | |||||||||
| 25% Spare Area | |||||||||
Similar to the Extreme II, the IO consistency is just awesome. SanDisk's firmware design is unique in the sense that instead of pushing high IOPS at the beginning, the performance drops close to 10K IOPS at first and then rises to over 50K and stays there for a period of time. The higher the capacity, the longer the high IOPS period: the 960GB Extreme Pro takes ~800 seconds before the IOPS drops to 10K (i.e. the drive reaches steady-state). I do not know why SanDisk's behavior is so different (maybe it has something to do with nCache?) but it definitely works well. Furthermore, SanDisk seems to be the only manufacturer that has really nailed IO consistency with a Marvell controller because Crucial/Micron and Plextor have had some difficulties and their performance is not even close to SanDisk.
However, I would not say that the Extreme Pro is unique. Both Intel SSD 730 and OCZ Vector 150 provide the same or even better performance at steady-state, and with added over-provisioning the difference is even more significant. That is not to say that the Extreme Pro is inconsistent, not at all, but for a pure 4KB random write workload there are drives that offer (slightly) better performance.
 |
|||||||||
| SanDisk Extreme Pro | SanDisk Extreme II | Intel SSD 730 | Intel SSD 530 | OCZ Vector 150 | |||||
| Default | |||||||||
| 25% Spare Area | |||||||||
 |
|||||||||
| SanDisk Extreme Pro | SanDisk Extreme II | Intel SSD 730 | Intel SSD 530 | OCZ Vector 150 | |||||
| Default | |||||||||
| 25% Spare Area | |||||||||
TRIM Validation
To test TRIM, I filled the drive with sequential data and proceeded with 60 minutes of 4KB random writes at queue depth of 32. I measured performance with HD Tach after issuing a single TRIM pass to the drive.
TRIM works for sure as the write speed is at steady 400MB/s.
.
Facebook
Twitter
RSS
85 Comments
View All Comments
Solid State Brain - Tuesday, June 17, 2014 - link
@Kristian VättöIf you still can, could you please post somewhere some screenshots (preferably) or write down the description/name for all SMART attributes for this drive from the SanDisk SSD Dashboard under the SMART tab?
SanDisk doesn't readily provide this information to the public, and if you could fulfill this request, it would get easier to make sense of those attributes with other popular third party drive SMART information tools such as CrystalDiskInfo.
This is what I got on my Extreme II SSD from that SanDisk SSD Dashboard. As far as I know the Extreme PRO has more/different SMART parameters, which is interesting since the controller should be the same:
5 / 05 - Retired Block Count
9 / 09 - Power On Hours
12 / 0C - Device Power Cycle Count
166 / A6 - Min W/E Cycle
167 / A7 - Min Bad Block/Die
168 / A8 - Maximum Erase Cycle
169 / A9 - Total Bad Block
171 / AB - Program Fail Count
172 / AC - Erase Fail Count
173 / AD - Average Erase Cycle
174 / AE - Unexpected Power Loss Count
187 / BB - Reported Uncorrectable Errors
194 / C2 - Current Temperature
212 / D4 - SATA PHY Error
230 / E6 - Percentage Total P/E Count XX.YY
232 / E8 - Spare Blocks Remaining
233 / E9 - Total GB Written to NAND
241 / F1 - Total GB Written
242 / F2 - Total GB Read
243 / F3 - [?]
Kristian Vättö - Tuesday, June 17, 2014 - link
My drives are currently at my friend's place as he does the photography for me (I don't have a DSLR), so I can't do this right now. However, I'll swing by his place next week at the latest, so feel free to remind me via email (kristian@anandtech.com) in a week or so if I forget :)Solid State Brain - Tuesday, June 17, 2014 - link
Ok, I will. FYI, I plan to submit that information to the CrystalDiskInfo author. After I sent him SMART attribute information for the Extreme II he promised to implement it in the next program version (so that they will not appear as "vendor specific" anymore).Seville Orange - Tuesday, June 17, 2014 - link
What happens to performance consistency if the drive has a few partitions?Say you have 50GB for Windows, 30GB for Linux, 10GB for Swap - if you use the remaining space as a partition will you then get max performance? or will the performance be reduced regardless because partitioning has the same effect as leaving spare area?
josquin - Thursday, July 10, 2014 - link
I also would like to get the answer to this question.croc123 - Tuesday, June 17, 2014 - link
Not to pick nits, but "SanDisk Extreme Pro SSD (240GB, 480GB & 960GB) Review: The Fastest Just Got Faster" seems to me to be a bit of hyperbole unsupported by the facts... A paid review, perhaps?Kristian Vättö - Tuesday, June 17, 2014 - link
The Extreme II was already the fastest SATA SSD, so in that sense "the fastest just got faster" because the Extreme Pro is essentially a tweaked Extreme II. I know we don't often use such headlines but I think in this case it's justified. Of course, feedback is always welcome -- do you prefer the general headlines instead?MrX8503 - Tuesday, June 17, 2014 - link
The tests show that it is the fastest. What kind of facts are you looking for?junky77 - Tuesday, June 17, 2014 - link
That's what I wanna get 4 years from now, with M.2 interfacejuhatus - Thursday, June 19, 2014 - link
That´s sarcasm right? M.2 PCI-E ssd are already 3x faster and with nvme, alot more.Comment on:
"All in all, the Extreme Pro is the only no compromise high-end SSD in the market." I would say high-end SATA SSD, this extreme pro is going to look like slow drive in 2015 with all the M.2 craze. So price is all that much more important factor, your going to pay hefty premium when there are multitudes faster products coming(and existing) and SATA/ACHI is capping your performance. Sata is dead, long live the new Sata :)
Im hoping my Z97 built this summer boots from M.2(or heck even pcie), any chance of getting article about that?