SanDisk X300s (512GB) Review
by Kristian Vättö on August 21, 2014 2:15 PM ESTPerformance Consistency
Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal defragmentation. The reason we do not have consistent IO latency with SSDs 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 dropdown selections 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.
 |
|||||||||
| Default | |||||||||
| 25% Over-Provisioning | |||||||||
The IO consistency is good but obviously not as good as the Extreme Pro due to lower over-provisioning (7% vs 12%). The architecture is still the same, though, as first the performance drops to around 10K IOPS, which is followed by a higher throughput burst. At steady-state the X300s averages about 5K IOPS, which is actually similar to the Crucial MX100 but with added over-provisioning the X300s gets close to the Extreme Pro level.
 |
|||||||||
| Default | |||||||||
| 25% Over-Provisioning | |||||||||
 |
|||||||||
| Default | |||||||||
| 25% Over-Provisioning | |||||||||
Facebook
Twitter
RSS
34 Comments
View All Comments
Kristian Vättö - Friday, August 22, 2014 - link
That is not true. Windows 7 is still the dominant OS in the enterprise space with Windows 8 only having a marginal share:http://www.sysaid.com/company/press/382-global-win...
Yes, that is one-year-old data but it shows that enterprises are not very keen on W8 and are adopting it very slowly. That in turn leaves a huge market for solutions like Wave ECS since the BitLocker in Windows 7 does not support Opal.
Besides, eDrive/BitLocker is the same for every drive. I don't see the need to revisit it with this drive because the process is not any different.
cbf - Friday, August 22, 2014 - link
Well, that market share article is from June 2013.While, I don't think Windows 8.1 is taking the market by storm, I think it is creeping in. I've deployed it due to things like improved startup/hibernation, BitLocker improvements, etc. The start menu just isn't that big a deal for my users.
In any event, it looks like we'll see Win 9 in the next six months, which I predict enterprises will deploy as fast as they've ever deployed any new Windows OS, so that should settle the issue.
jabber - Saturday, August 23, 2014 - link
Maybe not.Windows 9 is too soon. A lot of corps are only two years into their OS refresh, they aren't going to change till maybe 2017 at the earliest and then 10 is round the corner. A lot haven't moved to 7 till this year so they are going to hang around till 2020. Windows 10 will be the one that fits the schedule better.
9 will bomb probably. Plus anyone knows that 9 is purely a rushed damage limitation excercise.
devione - Thursday, August 21, 2014 - link
Hi Kristian,Really appreciate your efforts. However would it be possible to see future reviews involving Enterprise-grade SSDs? Thanks for your time.
Kristian Vättö - Friday, August 22, 2014 - link
Yeah, we have something in the works :)jay401 - Friday, August 22, 2014 - link
By the way, the Samsung 840 Evo in 256GB and 512GB sizes just dropped $20 and $50 in price on Amazon. $119 and $199 respectively, though the 500GB did just bump back up slightly to $212.7amood - Friday, August 22, 2014 - link
I appreciate the SEDs but I think these aren't open source and can't be audited like TC which is being audited right now. How to know for sure that the SED encryption is secure and doesn't have backdoor code for the spying?fk- - Saturday, August 23, 2014 - link
I'm still a bit confused about one thing - with all that security software listed in the table, what are the motherboard requirements to use the encryption on this drive? Do I still need a motherboard capable of setting ATA password if I want to password-protect the data on the drive?Or, to put it straight, is there any [software] way to use the option to password-protect the drive (and being prompted to enter the password on startup) on an older motherboard without UEFI, without ATA password capabilities and without Opal certification?
Kristian Vättö - Sunday, August 24, 2014 - link
Wave's ECS should do that as long as the drive is Opal certified. I tested without UEFI and it worked fine, and ATA password is just a BIOS feature whereas Opal is independent from the rest of the system (i.e. should work with any motherboard or system).mike8675309 - Sunday, August 24, 2014 - link
I assume that when you use the took to secure erase that when you enter the PSID that the drive is no deactivating the encryption, and then secure erasing the drive. Using that tool and that process must do something more complex so that avoids creating an attack vector.