A couple of weeks ago SNIA
just released a new version of their SSSI (SSD) performance test specification for public comment. Not sure if this is the first version out for public comment or not but I discussed a prior version in a presentation I did for SNW last October and I have blogged before about some of the mystery of measuring SSD performance. The current version looks a lot more polished than what I had to deal with last year but the essence of the performance testing remains the same:
- Purge test – using vendor approved process, purge (erase) all the data on the drive.
- Preconditioning test – Write 2X the capacity of the drive using 128KiB blocksizes and sequentially writing through the whole device’s usable address space.
- Steady state testing – varying blocksizes, varying read-write ratios, varying block number ranges, looped until steady state is achieved in device performance.
The steady state testing runs a random I/O mix for a minutes duration at whatever the current specified blocksize, RW ratio and block number range. Also, according to the specification the measurements for steady state are done once 4KiB block sizes and 100%
Read settles down. This steady state determinant testing must execute over a number of rounds (4?) then the other performance test runs are considered at “steady state”.
SNIA’s SSSI performance test benefits
Lets start by saying no performance test is perfect. I can always find fault in any performance test, even my own. Nevertheless, the SSSI new performance test goes a long way towards fixing some intrinsic problems with SSD performance measurement. Specifically,
- The need to discriminate between fresh out of the box (FOB) performance and ongoing drive performance. The preconditioning test is obviously a compromise in attempting to do this but writing double the full capacity of a drive will take a long time and should cause every NAND cell in the user space to be overwritten. Once is not enough to overwrite all the devices write buffers. However three times the device’s capacity may still show some variance in performance but it will take correspondingly longer.
- The need to show steady state SSD performance versus some peak value. SSDs are notorious for showing differing performance over time. Partially this is due to FOB performance (see above) but mostly this is due to the complexity of managing NAND erasure and programming overhead.
The steady state performance problem is not nearly as much an issue with hard disk drives but even here, with defect skipping, drive performance will degrade over time (but a much longer time than for SSDs). My main quibble with the test specification is how they elect to determine steady state – 4KiB with 100%
read seems a bit over simplified.
write IO needed to define SSD “steady state” performance? Most of my concern with how the test determines SSD steady state performance is that lack of write activity. My other worry with this approach is the blocksize seems a bit too small, however this is minor in comparison.
Let’s start with the fact that SSDs are by nature assymetrical devices. By that I mean their write performance differs substantially from their read performance due to the underlying nature of the NAND technology. But much of what distinguishes an enterprise SSD from a commercial drive is the sophistication of its write processing.
By using a 100% read rate we are undervaluing this sophistication.
But using 100% writes to test for steady state may be too much.
In addition, it’s It is hard for me to imagine any commercial or enterprise class device in service not having some portion of ongoing
write IO activity. I can easily be convinced that a normal R:W activity for an SSD device is somewhere between 90:10 and 50:50. But I have a difficult time seeing an SSD R:W ratio of 100:0 as realistic. And I feel any viable interpretation of device steady state performance needs to be based on realistic workloads.
In SNIA’s defense they had to pick some reproducible way to measure steady state. Some devices may have had difficulty reaching steady state with
any write activity. However, most other benchmarks have some sort of cut off that can be used to invalidate results. Reaching steady state is one current criteria for SNIA’s SSSI performance test. I just think adding some portion of write activity would be a better measure of SSD stability.
As for the 4KiB block size, it’s purely a question of what’s the most probable blocksize in the use of SSDs and may vary for enterprise or consumer applications. But 4KiB seems a bit behind the times especially with todays 128GB and higher drives…
What do you think should SSD steady state need some
portion of write activity or not?
5 thoughts on “SNIA’s new SSD performance test specification”
I do think it does need some portion of write activity. I good bet might around 10-20% to mirror a common use scenario (not covering all scenarios of course).
Also, the 4kb block size is a fairly common size for file system blocks, specifically on linux and unix systems. Now, I’m not saying it’s appropriate, I’m just saying that’s probably where the number came from.
First of all, thank you very much for taking the time to review the SNIA PTS in detail. Your comments focus on important aspects of the PTS that benefit from additional discussion. Some points below:
1. Steady State Determination
Steady state is defined in the PTS as the measurement window when 5 test loop rounds stay within a 20% excursion of the average round values and the slope of the linear curve fit of the round values does not exceed 10%.
The SS determination comes after standard pre conditioning: first writing 2X the user capacity in SEQ 128KiB W and then using the test loop of 56 points (R/W mixes of 100/0, 95/5, 65/35, 50/50, 35/65, 5/95, and 0/100 and Block sizes of 0.5KiB, 4KiB, 8KiB, 16KiB 32KiB, 64KiB, 128KiB and 1024KiB) at a specified queue depth and thread count.
So for the IOPS test, for example, the test loop does in fact include a wide matrix of R/W mixes and Block Sizes. The choice of determining SS using 4KiB block size at 100% W was made as somewhat of a practical consideration so that the test operator does not have to determine convergence for all R/W mixes and BSs.
2. 4KiB Block Sizes
4KiB is useful in many respects as Flash Management uses 4KB is the size of a page of virtual memory in most operating systems, and that most workloads will manage the SSD in 4KB blocks 100% of the time.
3. SS Convergence Plots and Measurement Window
A picture is worth a thousand words. If you take a look at Annex A: Sample Test Report, you can see how the dependent variable (test parameter) is plotted to determine convergence to steady state (plotting all block sizes but using the 4KiB as the determining BS), the calculation of the SS measurement window, and the plotting of results.
I hope this is helpful in clarifying the PTS. The SNIA SSS TWG appreciates all comments on the PTS and comments can be directly uploaded to the SSS TWG by going to the SNIA portal at http://www.snia.org/feedback/
Eden Kim, Chair
SNIA SSS TWG
Comments are closed.