Benchmark Your SSD
Like Maximum PC
1
INITIAL SETUP
To mimic our benchmarking, the target SSD should be a
secondary rather than primary OS drive. However, results
don’t vary hugely when testing an SSD as the main system drive.
>> We typically test box-fresh SSDs, so a critical part of our
regime is to first fill the drive to the brim and then delete all the
data and format the volume. It’s an easy way to make sure that a
drive’s basic garbage collection routines are functional. For an
SSD that’s already heavily used, this is probably redundant.
>> It doesn’t really matter what kind of data you use for the
pre-test fill. We favor large files like high-resolution video for
simplicity. While you’re filling the drive, keep an eye on the
W i n d o w s E x p l o r e r p r o g r e s s g r a p h — i t w i l l s h o w t h e t r a n s f e r r a t e.
Should the drive’s performance dip or stall due to exhausting any
cache [Image A] or the controller chipset overheating, you’ll get
a feel for how long that takes in terms of time or data quantity.2
PEAK SEQUENTIAL THROUGHPUT
To measure peak performance we use CrystalDiskMark 6.
It’s the tool we use for testing sequential read and write
performance. It’s worth noting that this type of benchmark
typically shows the drive off at its best. The quantity of data
transferred is limited and won’t exhaust features like high-
speed caches, which can mask the underlying performance of
the flash memory used in a drive.SURELY THE MOST MERCURIAL of PC components, solid-state drives have long presented a
moving target when it comes to benchmarking. Early SSDs were all about headline transfer
speeds. Then it became apparent that performance fell off rapidly as the drive’s capacity was
used. As solid-state technology matured, random access to small data sets emerged as a more
relevant measure of real-world performance. But even now, the best test regimes can’t fully
capture the character of an SSD. After all, there’s no substitute for hammering a drive with
day-to-day storage for years.
However, it is possible to capture a pretty good idea of the performance of a drive in relatively
short order using freely available software. Our approach involves testing both peak throughput
and arguably more relevant 4K per formance, along with an added real-world element in terms
of file transfers and prepping the drive for testing. The latter involves filling the drive entirely
before running benchmarks. That can be quite time-consuming with very large drives, in which
case you can opt to skip it. Where practical, and especially with a brand-new drive, however,
it can help to make benchmarking more realistic as well as shake out any serious flaws in
sustained performance. –JEREMY LAIRDYOU’LL NEED THIS
CRYSTALDISKMARK 6
https://crystalmark.info/en
ANVIL’S STORAGE
UTILITIES 1.1.0
https://anvils-storage-utilities.
en.lo4d.com/windows
Beyond that, around 30GB
of mixed files, ideally from a
game install, is required.>> CrystalDiskMark uses incompressible data in
default mode, so it won’t throw out overly optimistic
results as a consequence of the clever compression
algorithms that often can’t be used with real-world data
sets. Also, for SATA drives, sequential performance is
often limited by the interface. In practice, you won’t see
much more than 550MB/s in either direction.
>> Once downloaded, fire up CrystalDiskMark and
select the correct drive in the drop-down menu. Then hit
the “Seq Q32 T1” button [Image B] and let it rip. Results in
CrystalDiskMark should be close to the peak sequential
performance claimed by your drive manufacturer. If not,
you may have a faulty drive or a setup issue.3
RANDOM ACCESS PERFORMANCE
Peak sequential performance involves the biggest
numbers. But when it comes to that all-impor tant
subjective sense of snappiness and response, peak
throughput is largely irrelevant. Instead, measuring
random access performance provides more insight.
>> The standard test in this context is usually known as
4K random reads and writes. “4K” refers to the file size,
and “random” to the idea that the files will be written to
or read from multiple locations on the drive, in a process
that mimics typical OS and application drive traffic.BA©^ANVIL,^ C
RYST
ALDI
SKMARK650 MAXIMUM PC SEP 2020 maximumpc.com
R&D