Real ssd speed. Characteristics of SSD and HDD drives - what affects read and write speeds

Hi all! I think it’s no secret to anyone that one of the most important components inside your computer or laptop is the drive that contains the operating system. A completely logical consequence is the question - how to perform a speed test hard drive(or SSD, if the computer is newer).

If your operating system installed on a slow hard drive, it doesn't matter how powerful your CPU or RAM is - Windows itself and installed programs will be launched very reluctantly and you won’t be able to enjoy full multitasking.

In the age of the Internet, there are quite a lot of publications that will tell you about almost any drive model on sale. In addition, there are a huge number of programs for checking the speed of a hard drive, the result of which will be an understanding of what your drive is capable of.

There are many paid utilities kind of like PCMark or PassMark, which can test the entire system and can be found quite often in tests from well-known publications. We are taking a different path and I will tell you about four free ways Test the speed of your hard drive or solid state drive.

Real HDD or SSD performance Windows environment(and not only) is determined not only by the rotation speed of the magnetic disk or the memory of the drive chips, but also by many other important factors. The drive controller, the SATA version on the motherboard, the drivers of the controller itself, the operating mode (ACHI or IDE) - all this affects the performance of the disk subsystem (even the CPU or RAM can affect the performance)

Method 1: CrystalDiskMark is our main tool

Probably the most popular tool for testing hard drive speed is CrystalDiskMark. Almost no drive testing is complete without this utility - this situation will help you compare your results and draw the right conclusions. A big plus is the program’s ability to test not only HDD/SSD, but also flash drives and other storage media.

The application has both a distribution and a portable version that does not require installation. You can download it as usual on the official website (I, as always, recommend portable).

CrystalDiskMark is incredibly easy to use. We launch the utility, select the size of the test block (in the picture below we chose 1 GB), the number of test repetitions (I chose 5 - the more repetitions, the more accurate the result) and the drive itself. We press the “all” button and wait until the program runs all the tests (by the way, you can run a separate test for each mode).

In the screenshot on the left is the SSD speed test, and on the right is the HDD. Just so you know how big the difference is between them and what kind of performance gain you will get by replacing just one component in the system

Method 2. CrystalDiskInfo - detailed information about the HDD/SSD drive

At the very beginning of the note, I already wrote that the speed test of a hard drive or SSD will not be entirely correct if we do not find out the factors affecting the performance of the disk subsystem. The CrystalDiskInfo utility will tell you a lot of interesting things about your drive, but we are interested in just one nuance - download the application from the official website and run it.

Pay attention to the line “Transfer mode”, in the picture below I have it (SATA/600 | SATA/600). These parameters must match, i.e. By connecting the SSD drive to the SATA/300 port (this is the SATA II standard), we will get a maximum exchange speed with the disk of 300 MB, and if we look at the performance test in the first method, we see that the maximum read speed was far beyond 300...

By connecting such a high-speed drive to a SATA or SATA II port, its performance will simply be limited by the performance of the controller (with classic HDDs it is not so critical, since even SATA capabilities are abundant)

In general, CrystalDiskInfo can tell you about the temperature, operating time of the drive and many other useful indicators. For owners of classic HDDs, the Reallocate Sector item will be useful - thanks to it you can predict the failure of the device

Method 3. AS SSD Benchmark - a healthy competitor to CrystalDisk from the Germans

The Germans know how to make not only films for adults, but also excellent utilities for testing the speed of a hard drive or SSD. In this case, I want to introduce you to the AS SSD Benchmark application, the functionality of which is very similar to CrystalDiskMark, but unlike it, it also shows data access time (and in general there are still minor differences).

You can download it from the official website (it’s in German, the download link is at the end of the page), the application itself has English language(many bloggers have a version exclusively in German)

The utility is portable and does not require installation, just run the application, select the required tests and press START, just like in the first method. On the left is my home SSD, on the right is the classic HDD.

Please note that in the TOOLS menu there are a couple of interesting tests that can predict the performance of the drive when copying ISO files, programs or various toys - CrystalDiskMark does not have such functionality

Method 4. HD Tune is a good tool with a visual graph

HD Tune is most likely the most famous application for testing hard drive speed, but it is in last place in today's ranking for a reason. The fact is that free version HD Tune hasn't been updated since February 2008... but still works in 2k17 on latest Windows 10. As always, you can download from the official website (unfortunately there is no portable version)

After passing the test, we will have access to a visual reading graph (along with the maximum and minimum values, as well as the speed of data access). In general, the information is useful, but there is no way to test the disk writing speed, which is a little disappointing...

Due to its antiquities the application may not correctly detect modern drives, but this does not affect the test results in any way

Conclusion about hard drive speed testing programs

It's time to draw conclusions. We performed a HDD or SSD speed test using four different programs(or rather, there are only three applications for testing, and one more utility to make sure that the tests will be objective).

In reality, programs that allow you to check the speed of a hard drive are many times faster, but I decided to introduce you to the leaders of this niche... but if you have anything to add, I’m waiting for you in the comments.

Now more and more users are thinking about switching from HDD to SSD. This issue is especially acute for owners of mid-price gaming systems, since in the budget segment it still looks preferable HDD, and in the top-end, users can easily afford a capacious and fast solid state drive. In the mid-price market, you have to think about which part of the system to strengthen in a limited budget: take more powerful processor or a video card, install more RAM or buy an SSD.

Therefore, for testing we used a stand based on an overclocked 4-core processor. Don't go anywhere motherboard, 16 GB kit random access memory Patriot Viper 4 in DDR4-3200 mode and video card.

Test bench:

• AMD Ryzen 5 1400
• MSI X370 SLI PLUS
• be quiet! Silent Loop 240mm
• 2 x 8 GB DDR4-3400 Patriot Viper 4
• Colorful GTX 1060 SI-6G
• Kingston SSDNow KC400 (SKC400S37/256G)
• Seagate IronWolf ST2000VN004 2 TB
• be quiet! Dark Power Pro 11 850W
• be quiet! Pure Base 600 Window Orange
• AOC U2879VF

To begin with, we note that this SSD combines Toshiba A19 MLC memory chips, 1 GB of cache memory and a 4-core Phison S10 controller. It is opposed by a 2-terabyte HDD of the Seagate IronWolf series with a spindle speed of 5900 rpm and 64 MB of cache memory. Both use the SATA 3.0 interface.

In synthetic tests, the advantage of the GOODRAM Iridium Pro series model raises absolutely no questions. When working with incompressible data in CrystalDiskMark sequential read and write speeds were 564 and 530 MB/s, respectively. With a small-block load of 4 KiB files, the figures reach 34 and 110 MB/s. The competitor's sequential speeds are much lower - 137 and 121 MB/s, respectively. And with small files everything is very bad, like with all hard drives.

Working with compressible data in a test ATTO Disk Benchmark The solid-state drive also takes the lead: while the hard drive's read and write performance is in the region of 130-140 MB/s, the SSD reaches 530-560 MB/s.

In terms of data access time and other tests, the solid-state drive also looks much more interesting. You can watch the video below for more details. And we move on to gaming benchmarks.

Just to start, let’s clarify two points. First. Previously, we pre-launched almost all tests once or twice so that the necessary objects were loaded, and only then turned on recording and carried out control measurements. Now testing took place the first time, as if we launched the game and immediately rushed into battle.

Second. It's well known that SSDs make games load faster, but it's not always known by how much. We also decided to measure this point at the beginning of each test.

So let's start with Assassin's Creed Origins with a very high graphics preset. The waiting time for the benchmark to start was a little more than 4 seconds with an SSD, and with an HDD we had to wait more than 14 seconds. But the test itself was not particularly revealing, since both systems produced approximately the same results. And the Frame Time graph in the case of the hard drive was completely better.

When switching from HDD to SSD, benchmark loading time Ghost Recon Wildlands, decreases from 24 to 11 seconds or by 55%. During the test, the frame time graph in both cases was approximately the same, but still the system with an SSD produced 1 FPS more at the minimum frame rate.

Very interesting results were found in WATCH_DOGS 2 with a high graphics settings profile. Firstly, with an HDD it takes almost 4 times longer to load a game: 27 seconds versus 8. Secondly, on the first playthrough the system with hard drive noticeably slows down: freezes reach 6 FPS, so it’s unpleasant to play. But with an SSD there are no such problems, because the minimum figure was 56 frames/s, and the Frame Time graph was smoother.

After that, we turned around, reset the meters and drove along the same street again. And since all the main objects had already loaded, there was no big difference between the indicators: the minimum speed was 53 - 55 FPS, and the average was 61.

Online multiplayer Battlefield 1 with ultra settings, it loads onto the SSD almost twice as fast: 21 seconds versus 41. In terms of the minimum indicator, there is no difference, but the frame time graph is better in a system with an SSD, so the smoothness and comfort of gameplay should be higher. And in terms of average frequency it was ahead: 75 versus 69 FPS.

Developers Need for Speed ​​Payback They approached loading the level in a very original way: instead of a splash screen, they used an extended cutscene, so it was not possible to determine the loading time. We didn’t feel much of a difference in performance, although there is still a slight advantage when pairing with an SSD: 73 versus 70 fps at the minimum speed and 106 versus 104 at the average.

If you replace the hard drive with a solid-state drive, then the benchmark launch time GTA V is reduced from 31 to 14 seconds, or almost 55%. But we did not record any noticeable difference in the Frame Time graphs. Speed ​​indicators also turned out to be the same: 64 FPS with drawdowns of up to 45.

A more interesting picture is observed in The Third Witcher at maximum presets. Firstly, boot time is reduced from 37 to 14 seconds. Secondly, the Frame Time graph becomes smoother: even when we ran in the opposite direction, large differences were observed in the system with HDD, although the objects should have already loaded. As a result, we have a large advantage in terms of the minimum frequency: 45 versus 55 FPS in favor of the combination with the SSD.

The benchmark also turned out to be exemplary Rise of the Tomb Raider at very high settings. The reduction in startup time from 12 to 5 seconds is no longer particularly surprising, but the “Geothermal Valley” scene deserves close attention: when using the HDD, some objects are missing or are loaded as the camera moves, so the system is less loaded and produces a higher framerate. With an SSD, all objects are in place, so the speed is lower. As a result, we took the results of the “Syria” scene for the graph.

In the benchmark Middle-earth Shadow of War with a high profile, there was the highest gap in loading speed: 6 seconds versus 22. Interestingly, the test itself was faster on a system with an SSD, so I had to tinker a little with synchronization. The final results recorded parity in the average frequency and a 50% lead in the minimum frequency in favor of the combination with a solid-state disk.

Ends the test session PlayerUnknown's Battlegrounds at high settings. We stopped the loading timer only when all objects were completely loaded. The acceleration from using an SSD was 33%. And in terms of speed indicators, I was pleased with the 6% increase in the minimum frame rate. The average is fixed at parity.

Comparison of game loading times:

	Boot time from HDD, sec	Boot time from SSD, sec	Difference, %
WATCH_DOGS 2, High
GTA V, Very High
The Witcher 3, Max
Average

As a result, we see that replacing the hard drive with a solid-state drive leads to a reduction in game loading time by an average of 59%, in other words: loading is more than 2 times faster. In some cases, the frame time graph becomes smoother and the minimum FPS increases, that is, the comfort of the gameplay improves.

Comparison of minimum and average frame rates in games:

	SSD vs HDD, min FPS, %	SSD vs HDD, avg FPS, %
Assassin's Creed Origins, Very High
Tom Clancy's Ghost Recon Wildlands, High
WATCH_DOGS 2, High, Pass 1
WATCH_DOGS 2, High, Pass 2
Battlefield 1, Multiplayer, Ultra
Need for Speed ​​Payback, Ultra
GTA V, Very High
The Witcher 3, Max
Rise of the Tomb Raider, Syria, Very High
Middle-earth Shadow of War, High
PlayerUnknown's Battlegrounds, High
Average

The average increase in the minimum frequency was 88%, but all thanks to WATCH_DOGS 2. If we exclude this result, we get 12%. And here is the indicator average speed increased by less than 1.5%, which can be attributed to measurement error.

Results

Thus, does the comfort of the gaming process increase from HDD replacement on SSD? Our answer: Yes! Is such a replacement critically necessary and mandatory for the average gaming PC? It depends on who.

After all, you can still play with the HDD, although in some projects it may initially take time to load all the objects. Therefore, if it is the level of performance that is important, then it is better to direct free finances to a more powerful processor, a newer video card or more fast RAM. And if you are interested in the comfort of gaming and the operation of the computer as a whole, including loading the operating system, starting programs, deploying updates, etc., then an SSD will be a very useful purchase.

Article read 45301 times

Subscribe to our channels

In this article we will find out how and to what extent the SSD affects performance in real-life conditions of use.

If you have long wanted to see the real performance of SSDs in comparison with conventional HDDs, or if you were thinking about migrating your system to an SSD, but didn’t know if it was worth it, this article is for you!

There is little point in testing the disk under ideal conditions, because... This doesn’t happen in real life, so I deliberately consider tests using examples from real life, when the disk is filled with thousands of files, games, cache files of browsers and video processing programs, etc.

So, grab some popcorn, sit back, and let's get down to business.

What is the problem with HDD drives?

The problem is that ordinary HDD drive and, which we still use in computers, have not changed since the 1990x wiki, when it was first decided to ref make HDDs operating at 4300 rpm and 5400 rpm (revolutions per minute)

It was 2016 - 20-25 years later, we still have the same 5400 rpm drives running at 60-90 MB/s, but user needs have long since changed, we are now working with huge projects and big amount files in multitasking mode, requiring a lot of bandwidth and disk responsiveness, even if several other programs are already running in the background.
Since 2001, some manufacturers began to produce consumer segment disks operating at 7200 rpm, instead of 5400, but this did not change anything, the increase from 90 MB/s to 120 MB/s (33% - 5400-7200) is still does not give a significant effect.

Tests | synthetic (potential disk speeds)

Below is a synthetic test comparing the performance of the most important aspect - the disk's performance with small data blocks (specifically 4 KB):
During operations - reading (read)

• HDD is slower 94 times(0.68 MB/s vs. 63.6 MB/s), compared to SSD
• HDD is slower 53 times(0.36 MB/s vs. 19 MB/s), compared to SSD

During operations - recording (write)

• HDD is slower 178 times(0.78 MB/s vs. 139 MB/s), compared to SSD
• HDD is slower 86 times(0.64 MB/s vs. 55 MB/s), compared to SSD

Why are we mainly interested in the result of disk operation with small blocks of data?
The thing is, whether you open a browser, or import a project consisting of hundreds of files into a program like Unreal Engine, no matter what you do, in all such cases, the computer is processing a huge number of small blocks of data (mostly reading , so read speed is usually more important than write speed)
Sequential speed (“Seq Q32T1” and “Seq” in the screenshot above) is important when writing/reading large files (MB or GB), which happens less frequently and does not affect the responsiveness of the system to the same extent as working with thousands of small ones blocks.

Why are Apple computers so much more responsive than regular PCs and “never” slow down?

In the computer world, there is an opinion that the whole problem is in the operating system - Mac OSX on Apple computers“optimized”, “never slows down”, “no blue screens system failure"

Maybe it's because:
Apple computers (not counting the cheapest configurations): have all the same components, except one - m.2 SSD drive / proprietary analogues:
- Running at speeds (700 - 1100 MB/s) over NVMe, with the ability to handle 65,000 wait threads executing 65,000 commands each
- Having data loss prevention systems, overheating protection systems that help prevent errors and freezes when working with several GB of data consisting mainly of small blocks, in multitasking mode
- etc. and so on.
While, experience with Windows PC was formed while working with computers that have:
- Regular HDD 5400 rpm (noisy and vibrating during operation, due to the presence of moving parts) capable of processing 1 standby thread executing 32 commands
- Running at speed (60 - 110 MB/s)
- Constantly forcing all users to observe the “Not responding” state, observing the mockingly slow response when working in multitasking mode, not only with small, but also with relatively large blocks of data.

Leaving all the other components of the computer in place, swap the disks, putting the 5400 rpm HDD on the Apple, and the m.2 SSD on the Windows PC, and it turns out that the disk is really the most important (for speed and responsiveness) part of the computer, because a regular HDD drive is very slow, and forces the entire system to wait until it finishes processing all queues of tasks from programs and the OS, which slows down greatly when working in multitasking mode, having, in addition, applications doing work in the background, which can be quite a lot - from auto-updating project dependencies to tasks assigned for processing by the user himself.

Now, let's move on to the tests!

Test configuration | Real-life tests

All test results were obtained on a laptop with these components:
OS: Windows 10
CPU: i7 3610qm
RAM: 12 GB
Subjects:
HDD: Toshiba MQ01ABF050 | 465 GB (SATA)
SSD: Kingston HyperX Fury| 120 GB (SATA)

| Updating clean Windows 7 to Windows 10

SSD Total time: ~9 minutes - 188% faster (2.9 times)
HDD Total time: ~26 minutes

The first 4 lines are the process Windows updates 10
The last line is a test to make sure the update process is complete and the PC is ready to go.

| Windows 10 startup time

SSD Time Windows startup and programs in the tray: 0:16 | Total time: 0:23 - 217% faster (3.17 times)
HDD Windows startup time and tray programs: 0:48 | Total time: 1:13
PDF opened immediately after desktop appeared
The countdown ended after loading programs in the tray and fully opening PDF file

| Application launch time

SSD Application launch time | Total time: 1:44 - 274% faster (3.74 times)
HDD Application launch time | Total time: 6:29

| Application task execution time

SSD Performing tasks in applications | Total time: 2:29 - 175% faster (2.75 times)
HDD Performing tasks in applications | Total time: 6:50

results

Judging by the tests and sensations, our experimental HyperX Fury SSD outperformed the HDD in all respects in 100% of cases, solving the headache in all areas requiring high system responsiveness, such as game creation, video / audio processing, particle simulation, post-processing, work with hundreds of GB of data or thousands of OpenEXR.

After switching to SSD drive, there are no longer noticeable stuttering issues, whether this is a processing speed issue in AE, due to the fact that your sublime text downloads dependency updates, using 100% of the disk at this time, or stopping work due to the fact that you have BVH calculated in the background before rendering in blender, or while Maya, for several hours, creates alembic cache files , not allowing you to even access the Internet without freezing.
Not noticeably more and no waiting until Audacity hangs, after reducing the audio track, every 2 minutes and no waiting until all HDR or EXR in the folder are loaded each time for 1-3 minutes (!). You no longer have to stop one application in order to speed up the responsiveness of others, because... it loaded the disk at 100%. You don’t have to wait a few seconds after each action in Unreal Engine, for any aspect of the work, from importing files to applying and testing assets.
Not to mention the speed of rebooting the system after updates, which happens in seconds instead of minutes, and opening applications, which now happens “relatively” instantly.

Etc., etc., if you have encountered all this, you understand me well and there is no point in continuing to write resolved problems, but if you do not understand what we are talking about, most likely you will become bored reading a couple of hundred more problems resolved with using SSD, Anyway.

From personal experience, I noticed that while you are working on a computer with an HDD, you don’t notice how unproductive and irritating your work is due to constant expectations and the “not responding” status, especially if your work on the computer is not limited to surfing the Internet.

Bottom line - do you need an SSD?

If you need a disk:

• Operating absolutely silently (unlike HDD, which has moving parts that create noise and vibration)
• A disc that doesn't make you nervous because of endless expectations and slow work programs from the stage of opening the program - working in it - and until it closes, only because, unlike all other PC components and programs, the operating speed of consumer segment HDDs has not evolved over the past 20 years.
• If you need a disk that has a speed and responsiveness advantage over the HDD several times over in all types of tasks, from Internet browsing to multitasking typical for code / game development, working with 3D graphics, animation, particle simulation / video processing, audio / etc.

In this case, SSD is for you

The article is devoted to analyzing the performance of solid-state drives and hard drives. There is already an article on our website that describes in detail the pros and cons of SSDs. But this time I would like to dwell specifically on the comparison of the speed characteristics of these devices and tell in detail how great the advantage of solid-state drives is.

Quite often you hear that the superiority of SSDs in performance is not so significant - “only” 3-4 times. For example, the maximum speed of advanced hard drives is approximately 160-170 MB/s, while an SSD can show about 550 MB/s. A simple calculation gives a difference of almost 3.5 times. However, the processes that occur when reading information from a medium are much more complex, and it is incorrect to directly compare maximum speeds.

Test results for Vertex 3 SSD and Seagate 3 TB HDD
(clickable)

Take a look at the test results of the two devices obtained using popular program CrystalDiskMark. It will allow you to compare both types of drives when different modes work. The first drive is an OCZ SSD called Vertex 3, which has a very high performance. The second is a modern Seagate hard drive with a capacity of 3 TB, which has very high characteristics. We can say that some of the best representatives of each market segment are being compared.

The top number on the left is the linear read speed, when data is read sequentially. In this mode, almost all types of media show their maximum capabilities. The hard drive does not have to constantly move its heads, and most of the time is spent reading and transferring data. Solid State Drive in turn, transmits data in large blocks, using all channels. This behavior of devices is usually observed when copying huge files - movies, archives, DVD images. The difference in speed between the two devices is 3.27 times.

The second row of numbers is read in 512k blocks. The hard drive begins to spend more time moving the heads in search of each block, so the speed decreases. SSDs have to do more calculations to access different flash memory cells. Please note that the performance of an SSD is 92% of the maximum, while a regular HDD is only 37%. This behavior corresponds to copying a set of small photographs and illustrations or audio files.

The next row is reading in very small blocks of 4 KB. It is in this test that speeds drop the most. A classic hard drive spends the lion's share of time moving the heads in search of the necessary pieces of information, and the solid-state drive performs a huge number of calculations to find the necessary cells. As a result, the speed of the hard drive dropped by 220 times, and the speed of the SSD dropped by only 15 times. The speed difference between the two tested devices on 4K units is 52 times. This mode of operation corresponds to the process of loading the operating system, launching applications and copying text documents– that is, the most frequent operations on a PC.

Now it's time to talk about parallel execution of operations. While working on a computer, many processes are running in the system - programs and applications, system utilities, services that can access the drive at any time. It turns out that several read requests can arrive at one point in time. The hard drive is forced to process them one at a time - the heads can only read one file at a time. But an SSD has several memory chips in which information is stored. Therefore, you can process several requests at once, and they will all be executed in parallel.

The last line just shows the speed of work on 4K blocks with a request queue of 32. That is, the situation is simulated when you need to read 32 files of this size at once. As you can see, the hard drive has almost no differences in parallelization, since it can only receive one file at a time, while the SSD reads data in several threads, which allows for a 5.25-fold increase in performance. The slight difference in speed between a hard drive with and without a queue is explained by the presence of NCQ technology, which somehow organizes this very queue so as not to “run back and forth twice.”

For the sake of objectivity, it should be noted that such a deep queue almost never occurs in real conditions. For example, when the operating system boots, the queue value is approximately four.

In other words, if in theory (according to the documentation) the devices differ by a factor of 3.5, then in real operations during computer operation the difference can reach significantly greater values.

The right column in the program window is the results of the recording, for which all of the above is true.

Comparison of speed distribution of SSD (bottom) and HDD (top)

But that is not all. Take a look at the other graphs made by HD Tune. They show the distribution of speeds throughout the storage space (blue line). The left part corresponds to the beginning of the disk, the right – to the end. If the SSD issues same speed almost the entire volume, then the reading (and writing) of the hard drive seriously sags towards the middle of the space, and at the end it drops by more than 2 times. In practice, this means that if the operating system was installed on a full disk, or the last partition on the device, then the performance of the drive will be noticeably lower than stated. The same applies to access time (yellow dots), which increases as you move towards the end of the disk space.

It turns out, the initial superiority of 3.5 times in practice can result in 100 or 200 times. And this is compared to the best hard drives. There is nothing to say about ordinary discs with average characteristics. Therefore, buy an SSD as soon as possible.

Good day.

The speed of the disk determines the speed of the entire computer as a whole! Moreover, surprisingly, many users underestimate this point... But the loading speed of the Windows OS, the speed of copying files to/from a disk, the speed of launching (loading) programs, etc. - it all depends on the speed of the disk.

Nowadays there are two types of disks in PCs (laptops): HDD (hard disk drive - the usual hard disks) and SSD (solid-state drive - a newfangled solid-state drive). Sometimes their speed differs significantly (for example, Windows 8 on my computer with an SSD starts in 7-8 seconds, versus 40 seconds with an HDD - the difference is colossal!).

And now about what utilities and how you can check the speed of the disk.

One of best utilities for checking and testing disk speed (the utility supports both HDD and SSD disks). Works in all popular Windows OS: XP, 7, 8, 10 (32/64 bits). It supports the Russian language (although the utility is quite simple and easy to understand even without knowledge of English).

Rice. 1. CrystalDiskMark main window

To test your disk in CrystalDiskMark you need to:

• select the number of write and read cycles (in Fig. 2 this number is 5, the optimal option);
• 1 GiB - file size for testing (optimal option);
• “C:\” - drive letter for testing;
• To start the test, simply click the “All” button. By the way, in most cases they always focus on the line “SeqQ32T1” - i.e. sequential writing/reading - therefore, you can simply select a test specifically for this option (you need to press the button of the same name).

The first speed (Read column, from English “read”) is the speed of reading information from the disk, the second column is writing to the disk. By the way, in Fig. 2 SSD drive was tested ( Silicon Power Slim S70): read speed 242.5 Mb/s - not the best indicator. For modern SSD optimal speed is considered to be at least ~400 Mb/s, provided the connection is via SATA3* (although 250 Mb/s is more than the speed of a regular HDD and the increase in speed is visible to the naked eye).

* How to determine the operating mode SATA hard disk?

From the link above, in addition to CrystalDiskMark, you can also download another utility - CrystalDiskInfo. This utility will show you the SMART of the disk, its temperature, and other parameters (in general, an excellent utility for obtaining information about the device).

After starting it, pay attention to the line “Transfer mode” (see Fig. 3). If this line displays SATA/600 (up to 600 MB/s), then the drive is operating in SATA 3 mode (if the line displays SATA/300, i.e., the maximum throughput of 300 MB/s is SATA 2) .

AS SSD Benchmark

Author's website: http://www.alex-is.de/ (download link at the very bottom of the page)

Another very interesting utility. Allows you to easily and quickly test the hard drive of your computer (laptop): quickly find out the read and write speed. No installation required, use as standard (as with the previous utility).