Comparison of SSDs and HDDs in laptops in terms of usability.  Characteristics of SSD and HDD disks - what affects the read and write speed The speed of the ssd disk and hdd

Comparison of SSDs and HDDs in laptops in terms of usability. Characteristics of SSD and HDD disks - what affects the read and write speed The speed of the ssd disk and hdd

Of course, this is the main difference between the two, but not the only one.

Types of computer memory

Computer memory is where data is stored. The memory is divided into ephemeral(like random access memory or RAM), which only retains data as long as the computer is running, and permanent(non-volatile) that retains data even after power off.

It can also be divided by device, or rather, by type. Can be distinguished magnetic media(e.g. hard drives HDD, SSHD), optical, semiconductor and flash memory.

Differences between HDDs and SSDs

Media design

The main difference that first comes to mind is the internal structure.

Hard disk drives HDD are magnetic storage media. To read them, a special, movable head is used, which moves along the circular magnetic plates used for storing data, and thus searches for files.

SSD media are classified as flash memory built from NAND Flash cells only. This allows you to read and write files on the SSD much faster - all due to the fact that reading occurs without the participation of moving elements. Moving parts must arrive at the location of the file and cannot be present in multiple locations at the same time (which further slows down reading or writing multiple files).

Loudness during operation and resistance to damage

Moving elements are also responsible for the noise generated during the disc operation. Deprived of these moving parts, SSDs run silently. In addition, they are also more resistant to damage (again this is due to the lack of mechanical parts that can move, for example, in the event of a fall).

The AHCI protocol was created for HDDs at a time when faster media was never expected. Later SSDs had huge potential in terms of data flow, however, it was severely limited by the legacy protocol.

For new fast hard drives, a new NVMe protocol has been created. Its capabilities are shown in the table below:

Seagate HDD 1 TB
  • Read speed: 169 MB / s
  • Write speed: 186 MB / s

Uninterrupted and high-performance 7200 rpm HDD. Thanks to this, the launch and download of programs is much faster. The drive is also equipped with MTC (Multi-Tier Caching) technology, which optimizes data flow and speeds up writing and reading.

SSD ADATA 128GB
  • AHCI protocol
  • Read speed: 560 MB / sec
  • Write speed: 300 Mb / s

128 GB hard drive. Equipped with NAND Flash cells and SMI controller. DRAM cache and intelligent SLC caching further enhance its performance.

GOODRAM 240 GB solid state drive
  • Read speed: 550 MB / sec
  • Write speed: 320 Mb / s

One of the most durable and reliable solid state drives. Equipped with features such as SmartRefresh, SmartFlush and GuaranteedFlash to protect data in the event of power surges.

Samsung 250GB 960 EVO Solid State Drive
  • NVMe protocol
  • Read speed: 3200MB / sec
  • Write speed: 1500MB / sec

NVMe interface provides superior read and write speed. Reading speed is even faster thanks to Turbo Write technology. Dynamic thermal protection protects against overheating.

Comparison of HDDs and SSDs in terms of usability. Part 1

Introduction

Let's step aside for a moment from the reviews of the laptops themselves and turn to their components, namely, storage devices. Until the last moment, hard disk drives, aka "hard drives", reigned supreme here. However, relatively recently, they have a strong competitor - flash drives, SSD (Solid State Drive).

An SSD is a fundamentally different type of drive, it is built on the same technologies that are used in flash memory, and is similar to flash drives in terms of the organization of both cells and the drive as a whole.

Detailed information on speed and functional characteristics, as well as test results of modern drives can be found in the following materials site:

  • An overview of one of the first SSD drives,.
  • in which SSD Corsair is involved. This SSD was used in our tests as well.
  • Latest in time for testing fast SSDs and researching the impact of SSD capacity on performance.
  • You can read more about the performance of SSDs and hard drives on the site.

At the same time, most of the tests are aimed at savvy readers and are a comparison of the performance characteristics of selected drives. And although they contain a lot of interesting information about specific products, a large number of drive properties (especially those that are difficult to measure unambiguously) remain behind the scenes. Therefore, a potential buyer cannot always determine whether he needs a particular device.

In this series of materials, we will try to move away from the traditional method of testing drives (you can see its description on our website) and focus on subjective impressions of use. First of all, this study should answer the question: what does an ordinary user get from switching to SSDs, what are the advantages of a new type of drives in everyday work, is it worth switching to them, or is it better to stay with traditional hard drives for now? And in what cases are these or those drives more profitable.

Basic storage requirements

Any user has two basic requirements for a storage device: reliability(so that you can not be afraid for the safety of your data) and speed... Of course, there are other requirements, but they play a secondary role and are unlikely to be taken into account if the reliability or speed is not satisfactory.

Reliability- a key requirement, the importance of which cannot be overstated. Losing a laptop is not so scary: you can buy the same in the store. But if you lost your main laptop with all your personal archive or the hard drive on it failed, then everything is much sadder: you lose unique information that is often simply impossible to recover. It is obvious (and has long been emphasized in all presentations) that information in a corporate laptop can cost many times more than an entire laptop with giblets. However, the safety of information is important not only when it comes to business secrets: there is also the concept of subjective value. It is difficult to evaluate your photographs or documents in money, but for the author they mean a lot. Of course, there is backup, Internet storage, etc., but their use is not always possible and convenient.

At the same time, the reliability of storage systems for laptops is a very difficult and painful issue. Due to their design, hard drives are resistant to vibration and shock. During operation, the head hovers very close to the surface of the magnetic disk. Impact or jolting can cause it to touch the surface and either damage itself or scratch the surface - data at that location will be lost.

And with laptops, this happens all the time. Caught on the wire - and it flew off the table or sofa, worked "on your knees" and dropped, even a simple shake can damage the device. Very often, negligent or unskilled users themselves shorten the life of their disks. Take, for example, a typical example, when a user, holding a laptop on his lap, presses the "hibernation" button, the screen goes blank (for some reason, in new Windows systems, this happens, although XP showed on the screen that the hibernation process is still in progress) and the user is in full confident that the system has shut down, throws the laptop on the sofa - and at this time the system intensively writes the state of the operating system to disk.

Most manufacturers in corporate models (where the safety of information is the most important factor) began to introduce active protection of the hard disk, which should park the heads (take them away from the surface) if the laptop jerked or bumped. Manufacturers in the development of new models of mobile hard drives are trying to make them more resistant to external influences. However, this stock is not always enough.

The second most important requirement is speed drive operation. And here it should be noted that modern hard drives (especially mobile ones) are already close to the ceiling of their capabilities. There is no need to expect a radical increase in the operating speed, one can only hope for some evolutionary growth, and even then ... Besides, due to design features, a hard disk cannot always work at maximum speed. Firstly, the speed of reading and writing data strongly depends on whether it is the beginning of the disk or the end, and secondly, although with linear reading or writing (when a large amount of information is read and written in succession) the disk can provide a good speed, however, when working “ randomly "the speed drops to indecently small values, 1-2 MB / sec. And most often the main hard drive of a laptop works in this mode. Therefore, for example, laptops take a long time to boot: you need to read many small operating system files from different places.

An SSD is a fundamentally different type of device, so most of the disadvantages of an HDD are not typical for it. Let me briefly recall the main consumer advantages of SSD:

  • High speed read and write, the same anywhere in the drive.
  • Many times lower latency when working with data compared to hard drives.
  • No moving parts: The SSD is resilient to shock, vibration and shock, which means there is less chance of losing data.
  • SSD does not heat up, does not make noise, does not vibrate itself.
  • Less power consumption.
  • Large working temperature range.
  • Better weight and dimensions compared to a hard drive (the drive can be made smaller and lighter).

The main disadvantages of SSD:

  • Very high price.
  • Limited capacity.
  • Dependence of price on storage capacity, high cost of additional capacity.
  • Possibly limited life of memory cells.

Let's try to assess how these pros and cons of SSDs are weighty in and of themselves and in comparison with modern hard drives in constant operation.

Testing sections

The main goal of our testing is to understand the difference in performance between an SSD and a regular hard drive. First of all, this concerns speed characteristics: it is interesting to see how noticeable the difference in speed between a hard drive and an SSD is in the normal work of a laptop user. However, our testing is not limited to this.

All testing is divided into four major parts. In the first part, we talk about the test participants, methodology, etc.

In the second part, we will look at the performance of test participants in synthetic applications, and also evaluate, using the example of one of the participants, how the load of the operating system with data and third-party programs affects the work.

In the third part, we will compare the performance of test takers in real work. These are the main operations related to the operation of the operating system (boot, shutdown, entry and exit from hibernation), as well as the speed of copying files. Moreover, both on a clean system and on a system with installed applications. In addition, we will look at such an important parameter as the speed of file copying.

Finally, in the fourth part, we summarize the subjective feelings of using an SSD and HDD during normal work on a laptop. Plus, let's compare parameters such as heating and noise, as well as battery life.

However, even this is not the end of our testing. For I still have both drives, an operating system with a set of applications (this is my working system, so it is constantly in operation and gradually degrades), as well as cloning software. So it is possible to return to the tests at any time and at the same time see if the system performance deteriorates after a long work (there are persistent rumors about this). Therefore, we invite readers to actively participate in the discussion, ask questions, suggest their own tests and point out the moments where this or that type of drive differs for the better or, conversely, for the worse.

Test participants and methodology

It should be noted that fate has made some adjustments to the testing program. We originally planned to compare six drives: four hard drives and two SSDs. However, in the middle of testing, our test bench broke down, so only three drives, but the most interesting ones, took part in the testing core. If our readers are of great interest, you can try to test other drives using a similar method.

So, the following are involved in testing:

Seagate Momentus 5400.6 500 GB;
Seagate Momentus 7200.2 160 GB;
SSD CORSAIR CMFSSD-128GBG2D 128GB.

Let's take a closer look at the characteristics of the test participants.

Let's stop at this for now: we have a capacious disk, a fast disk, and an SSD with good performance: not top, but close to it.

Testing methodology

All tests were carried out on an ASUS K52Jr laptop. The laptop is relatively modern and fast, built on the new Intel HM55 Express chipset.

For testing, we took a standard configured Windows 7 system that comes with ASUS K52Jr with installed drivers. Only programs (such as Norton, etc.) were removed from the system. I would like to draw your attention to the following. In theory, SSD performance could improve with updated driver versions. However, we decided to take the drivers from the delivery kit (especially since the model is relatively fresh). This way you can "fix" the state of the system so that all drives work in more or less the same conditions. In addition, not all users (especially those who work on a laptop, and do not experiment) love games with drivers.

Synthetic tests

The programs HDD Tune 4.01 and Ashampoo HDD Control were installed on a clean system, with the help of which we evaluated the performance of drives in synthetic tests. It should be noted that the tests were done in order to understand what can be roughly expected from the drive. They were not decisive.

For HDD Tune, we did a basic test of reading from the disk surface. I would like to draw the attention of readers to the fact that these results cannot be completely objective, since the test was performed on the system disk on which the operating system is installed. The system and applications can also work with the disk right during the test, as a result of which the results may differ on different runs and will not be completely objective and repeatable. For the same reason, there is no write test. Full-scale tests can be viewed in other materials on our website, where they were carried out in accordance with an objective and comprehensive methodology.

In addition, we decided to remove additional tests in HD Tune: additional search and read tests, random read tests in the file system. Finally, we measured how long it takes for the program to scan the disk and display its structure (the number of folders and their size).

HDD Control was used more as a program to check the results obtained.

We also paid attention to the drive temperatures obtained during the test. Except, of course, the SSD, which doesn't heat up.

Real operating system tests

We decided to see how big the difference is in the use of different types of drives during normal operation with a laptop. For this, several groups of tests were carried out.

Operating system operation

First, we measured the speed at which the operating system performed the main actions: boot, go to hibernate, exit from hibernate and shutdown(in that order).

It feels like Windows 7 is much better optimized than its predecessor Vista. In particular, in everyday work you constantly feel that it "turns the disk" much less during work and in its absence. What does Vista do at the same time? the laptop can, standing in absolute idleness, thresh the disk for half an hour, which has a great effect on performance, and on the speed of application response, and on battery life. Plus, as it seemed to me, the new system "slows down" less when actively working with a hard disk, i.e. when the system is actively working with the hard disk, you can continue to work, the open application responds. Although sometimes there are situations that cause some irritation.

We tried to measure the time when the system was completely "loaded", ie. has stopped loading data from the hard drive. Windows 7 at startup completely turns on the desktop and with all its appearance shows that it is ready to perform tasks, but the hard drive continues to work with might and main, loading something. When measuring, we tried to take this time into account as well. Although at startup the situation is more or less decent, after the system is completely "ready" (the hourglass disappears next to the cursor) the disk spins for about half a minute, but after exiting the hibernate, this process continues for two or three minutes. You can work (I checked it on purpose), but, for example, new applications are difficult to launch.

Speaking about starting the system, one important point should be noted. When booting, the hard drive is constantly active, and it seems that the download speed depends only on it. However, on a system with an SSD, the disk access indicator goes out from time to time, i.e. data loading is not 100% of the operating system load time.

Data copying speed

Copying and transferring data is an important feature, and it depends a lot (if not all) on the drive.

For this part of testing, we have prepared four groups of files.

First, a 700 MB movie (folder size 734 486 528 bytes). Secondly, a set of zip files - a set of drivers for ASUS laptops. The folder size is 811 742 316 bytes, inside 53 files, ranging from 2 MB to 102 MB. Thirdly, and this is the most interesting thing - a set of documents. The folder size is 943 813 860 bytes. This includes MS Word documents and saved web pages (each includes a folder with graphic files used on the page). All files are very small, from 2KB to 40KB. As a rule, these are the most difficult files to copy, because they are "out of order" on the disk and copying takes a long time.

The fourth set is a folder with a size of 4 532 507 KB. Inside - 24 rar-files. We took a 4.5 GB archive and zipped it into a multivolume archive with a volume size of 200 MB. Apart from the copy tests, we used it in the unzip test.

For tests, the disk was divided into two partitions, approximately equal in capacity. Next, we copied files from drive C to drive D and vice versa. Those. files were copied within the same drive, and it worked simultaneously for reading and writing.

We also measured the time during which Total Commander erases files (a set of documents) from the C and D. It should be noted that large files are erased very quickly (which is understandable) and there is nothing to measure there, only erasing a folder with documents is of interest. I also want to note that the standard Conductor, which erases only information about the location of the file, almost instantly reports on the removal of anything.

In addition, we created a 1 GB virtual disk in RAM and tried to copy files to and from it. In this test, the drive is read-only or write-only, so in theory it should perform better.

Finally, we tried to see how much the unzipping process depends on the hard drive. To do this, we unzipped a large file from a multivolume archive on disk C.

Tests on a production system

After completing the tests on a clean system, we installed a large amount of software on the disk, which is usually used at work. This includes antivirus, office apps, mobile phone apps, organizer, and more. The applications are fairly standard, plus I tried to find several applications that have an "agent" that starts with the system and works with it all the time.

After installing the applications, we once again measured the time it took for basic operating system actions. We also measured the copy time again.

After that we tried to install two games (Crysis Warhead and H.A.W.K.) onto the disc. We also indexed the music collection using Helium Music Management and opened the photo collection using XnView.

Finally, we measured the startup time of some applications, for example MS Word.

And in the final we measured the time of the "parallel start". To do this, we turned on the antivirus check, started the process of copying files from D to C and launched MS Word to see how much more difficult it would be for him to start in this mode.

Note that OS tests (start, shutdown, etc.) were measured with a stopwatch, so there may be a slight error. The time was measured from the moment the laptop was started, i.e. including the time spent checking and starting the BIOS. Here I would like to note that the presence of a disc in the optical drive greatly increased the BIOS boot time (20 seconds instead of the usual 4), the tests were carried out without an optical disc in the drive.

Testing in the OS was carried out by recording actions from the screen, then we looked at how long the action took according to the timeline of the recording program and rounded up to whole seconds. Anticipating objections that this program could also work with a disk, I will answer: yes, it could. Just like any other TSR program. Since we are talking about a working system, and not synthetic testing, additional influences, which are more or less stable, help to better illustrate the work in real conditions.

Well, let's move on to the tests themselves!

Synthetic performance

Synthetic tests were needed primarily in order to arrange applicants, to see what to expect from them in greenhouse conditions. In addition, if there were something wrong with one of the drives, it would have been revealed already at this stage.

First, let's take a look at the simplest test - reading from the surface. First of all, we decided to quickly see how things stand with repetition, i.e. whether the test will produce similar numbers on multiple runs. The system rebooted between restarts, but not all of the resulting diagrams are presented in the article. So...

Now let's try to remove the data after some time, when the disk has worked thoroughly under load.

As you can see, the two tests give very similar results. However (just an example of why you can't test on the system disk) ...

With some launches, such failures appeared. Either these are accesses to the system disk, or disk problems due to overheating (look at the temperature, it is very high). Finally, we took the results the next day (but also at the end of testing):

Thus, the results are quite stable (only the reading from the buffer jumps a lot). However, in general, this drive did not show good speed even for notebook drives. It is also worth noting the very high temperature, which can even lead to bad consequences for the disk.

Let's look at the graphs of the second program:

As you can see, the second "run" is worse, especially the search time suffered. Is it due to heat? Let's see what the next day:

The graph is relatively flat, a failure appeared, apparently, the system was accessing the disk at the time of the test.

Thus, in general, the repeatability of HDTune 4.01 is good, while that of HDD Control is worse. In the future, we ran the test three times and chose a picture without failures. Except for 5400.6, where the second run failed.

What do we see? 5400.6 gives much higher linear performance figures compared to 7200.2. The access is worse (the average in tests was 18.5 ms), which is generally understandable. Hence the conclusion: in linear operations 5400.6 is noticeably faster, in random read and write operations (just small files) it can be slower ... Or maybe not. Let's see below how this is done in real life. For now, let's double-check the results in another program.

"Parallel counting" confirms the received data. Those. we will assume that 5400.6 is faster in linear speed. Moreover, it is also much more capacious, i.e. the probability that the entire system partition will be in the fastest part of the disk is higher. Although I should note that the scatter at random reading in the 7200 is smaller.

And finally, let's take a look at the star of today's testing: the Corsair SSD.

As the saying goes, "it has begun." Let me remind you that in the characteristics of this utility it was stated that the active mode was UDMA-5, the results of which we are observing. From this, at least, we can conclude that it is not always enough to buy an SSD and insert it into the place of a hard drive.

Let's check with the second program:

As you can see, here the speed is shown much higher - and closer to the stated figures.

It only remains to repeat the conclusions from almost any article. In benchmarks that show maximum performance, in greenhouse conditions, SSDs go very far ahead in terms of performance from traditional hard drives. At the same time, again, unlike hard drives, it can maintain the same high speed anywhere on the drive, without "failing" to the end. Third conclusion: SSDs have very short access times, i.e. the drive responds instantly to commands from the operating system. This parameter is almost an order of magnitude better than that of hard drives.

However, these conclusions have long been known. Let's see how things stand with more detailed tests.

Advanced Random Search and Linear Reading Tests

Let's start with 5400.6.

We have already seen the second four indicators, these are linear reads at the beginning, middle and end of the disk plus reads from the buffer. It is much more interesting to look at the beginning of the tablet. The first two numbers characterize a random search, and the picture is bleak. It is in this mode, when the disk constantly has to move the head and look for a small piece of information, and then move the head again, that performance suffers the most. This is evident from the huge drop: the read speed is less than a megabyte / sec. And the next two numbers show the difference between working with small and large blocks.

Let's compare the results with 7200.2.

As you can see, when searching, the positioning of the heads is a little faster, which gives a tiny advantage. As soon as a large block appeared in operation (that is, it was necessary to count at least a little in a row) 5400 instantly took the lead, and its advantage is quite significant. With sequential reading, everything is clear and so.

Now let's compare hard drives with SSDs.

In absolute terms, SSDs are far ahead. The access times are always the same (except for one case, but hard drives also had a hard time doing this test). During random reading, the speed also drops very much, although compared to hard drives it remains very high. We have already discussed linear reading, there are no surprises here and, in general, cannot be.

As you can see, SSDs are way ahead in terms of performance. However, there is a drop in performance when working with small blocks and volumes of information, and it is also very large. The SSD remains in the lead, but the absolute numbers are disappointing. By the way, note that when reading linearly, the results of the access times are not that different. There is nothing surprising here, but I will draw your attention to it anyway.

Random access operations

Since we started talking about access times, let's take a closer look at the corresponding test. Let's start as usual with 5400.6.

The test was taken when the hard drive was already warm enough (37 degrees Celsius, i.e. + 5 ° relative to the idle temperature). I would like to draw your attention to the fact that in this mode the number of sectors grows, access to which takes a long time, and this happens with both disks.

The chart looks different because here the division price is different, and on both scales. If you look at the numbers, then with small blocks 7200.2 is faster (just 14.5 milliseconds versus 18.5), but with a block size of 1 MB it already loses. What about SSD?

With such operations, hard drives are up to the SSD as up to the moon. What about the speed of reading, what about the access time. The difference is just at times. Since the SSD reads information in blocks, the larger the block, the more the gap grows. In terms of numbers, this drive is far ahead, but it does not like small blocks as well as ordinary hard drives. Those. it will work faster in relation to the disk, but in relation to its maximum results it shows an equally sad picture.

Working with the file system

Let's look at the work in the file system, i.e. a benchmark slightly closer to real life.

For comparison, let's see what result 7200.2 gives.

It can be seen that 5400.6 is faster everywhere. Let's see how the SSD is doing in this test.

For SSDs, the graph is smoother and you can see the characteristic features: dislike of small blocks and a stable lag of the write speed from the read speed. The overall speed is very high, well above the drives. I must also say that the benchmark results for SSDs are smoother, there is no such variation from run to run as in hard drives.

Preliminary findings

The obvious takeaway is that SSD speeds are much faster and access times are much better. However, these are not new conclusions at all; they have been repeated in one form or another for quite some time. Of course, SSD has its own characteristics, which, by the way, can be read about in objective testing, the link to which we have provided.

The mutual results of the hard drives surprised me: I did not expect such a lag of the 7200.2. Although it is clear that the model is older and the recording density is lower (this has a bad effect on the speed of working with the disc), nevertheless it seemed to me that it should outperform the 5400.6. In practice, the 7200.2 is almost everywhere inferior in speed in absolute numbers. In addition, and this is a very important operational fact: it heats up much more strongly, i.e. using it is not so pleasant. 5400.6 maintains moderate heat. SSD, by the way, does not heat up at all, but since there are no temperature sensors (and he does not need them), then this is subjectivity and we will leave it for the part with subjective measurements. Thus, when choosing a disk for a laptop, you need to be guided by the freshness of the model, but the rotational speed is not a very important indicator.

We will stop here. And in the next part, we are waiting for tests from real life - the time of system startup and shutdown, copying files, launching applications and much more.

Greetings!
The speed and performance of the entire personal computer as a whole depends on the performance of the disk (HDD, SSD)! However, to my surprise, quite a large number of users do not attach due importance to this aspect. And this despite the fact that the speed of loading the operating system, launching programs, copying files and data from disk and vice versa, directly depends on the data carrier. In other words, a fairly large number of typical operations on a PC are tied to the memory subsystem.

Now in computers and laptops, either traditional HDD (hard disk drive) or the recent trend - SSD (solid-state drive) are installed. Often, SSD drives significantly outperform classic HDDs in read / write speed. For example, Windows 10 starts up in 6..7 seconds, compared to 50 seconds of booting from a regular HDD - as you can see, the difference is quite significant!

This material will focus on ways to check the speed and performance of an installed HDD or SSD drive.

CrystalDiskMark Review

Quite a popular utility for measuring and testing the speed of an HDD or SSD disk. It works perfectly in Windows (XP, Vista, 7, 8.1, 10), is free and supports the Russian interface language. Official website of the program: http://crystalmark.info/

To test an HDD or SSD in CrystalDiskMark, you need to do the following:

1) Select write / read cycles. By default, this figure is 5 , which is the best option.

2) Then you need to select the size of the file to be recorded during the test. 1 GiB(1 Gigabyte) will be optimal.

3) Finally, you need to select a partition that will be used to test the disk. If you have several physical disks installed, then select the partition that is located on the disk you are interested in. In the example, the installed hard disk is one and the partition is selected accordingly C: \.

4) To start the test, click on the green button All... By the way, in the overwhelming majority of cases, the result is of interest, which is in the line SeqQ32T1- linear read / write speed. You can start testing only the linear read / write speed by clicking the corresponding button.

Test results will be displayed in columns:

Read- parameter showing the speed of data reading from the tested disk.

Write- a similar parameter, but showing the write speed to the tested hard disk.

On the Kingston UV300 SSD tested in the example, the linear read speed was 546 MB / s - which is a very decent result. In general, for the best representatives of SSD drives, this parameter varies around 500 .. 580 MB / s, taking into account the connection to the SATA3 connector on the motherboard.

If the speed of your SSD is significantly less than the speed declared by the manufacturer, then it makes sense to check if it is connected to SATA3.

How to determine the version and operating mode of the SATA port

The developer of CrystalDiskMark has prudently created another diagnostic utility - CrystalDiskInfo. Its task is to display S.M.A.R.T information about the state of the disk, its temperature and other parameters.

In general, it is a fairly convenient and intuitive utility that should be in service with users who need to monitor the state of the disk (its health) in order to avoid data loss due to its possible breakdown.

After starting the utility, look at the information that is displayed in the line “ Transmission mode»:

SATA / 600- means that the disk operates in SATA3 mode with a maximum bandwidth of 600 MB / s.

SATA / 300- this parameter means that the disk operates in SATA2 mode with a maximum bandwidth of 300 MB / s.

It can still be highlighted SATA / 150(150MB / s) - this is the first version of the SATA standard and it is considered very outdated and does not meet modern requirements for the bandwidth of connected media.

Whereas a classic HDD is enough SATA2(300MB / s), then the SSD must be connected to the port SATA3, otherwise he will not be able to reveal his full speed potential.

AS SSD Benchmark Review

I present to your attention another remarkable utility, the task of which is to test the speed of an HDD or SSD drive installed in a computer or laptop. With it, you can just as easily find out the speed characteristics of the connected disk.

The utility is free, does not need to be installed and works in Windows environment. Official website of the program: http://www.alex-is.de/

Management is carried out in a similar way to the CrystalDiskMark program. Linear reading speed is displayed here in the graph Seq.

HD Tune software overview

The HD Tune utility concludes this review. The capabilities of this program are not limited by testing the read / write speed. Among other things, it also allows you to check the health of the hard disk, its technical parameters and even scan the disk surface for errors.

If we focus on the capabilities of speed testing, then here we can note the following:

  • the ability to separately set testing for writing or reading
  • convenient visual graph of the write / read speed during testing
  • the ability to see the peak speed and access time

The program works in a Windows environment and provides convenient tools for monitoring and testing connected media.

Official website of the program: http://www.hdtune.com/

Brief summary

The speed of the connected media directly affects the overall performance of your computer or laptop. You should not neglect the control of speed characteristics, because the overall comfort of working with a computer depends on it.

Now you know how to check the speed of the connected media, as well as the possible nuances of its connection, on which the bandwidth of the connected HDD or SSD ultimately depends.

In this article, we will find out how and to what extent SSDs affect performance in real-world use.

If you have long wanted to see the real performance of SSDs in comparison with conventional HDDs, or if you were thinking of transferring the system to an SSD, but did not know if it was worth it, this article is for you!

It makes little sense to test the disc under ideal conditions, because this does not happen in life, so I intend to consider tests on examples from real life, when the disk is filled with thousands of files, games, cache files of browsers and video processing programs, etc.

In general, stock up on popcorn, sit back, and let's get down to business.

What is the problem with HDD drives?

The problem is that conventional HDD drives that we still use in computers have not changed since the 1990s wiki, when it was first decided to ref make HDDs running at 4300 rpm and 5400 rpm (revolutions per minute).

It was 2016 - 20-25 years later, we still have the same 5400 rpm disks running at 60-90 MB / s, but the needs of users have changed a long time ago, now we are working with huge projects and a large number of files in multitasking mode, requiring a lot of bandwidth and disk responsiveness, even if several other programs are already running in the background.
Beginning in 2001, some manufacturers began to release drives in the user segment 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 benchmark that compares the performance of the most important aspect - the work of a disk with small data blocks (in particular, 4 kb):
For operations - read (read)
  • HDD slower 94 times(0.68 MB / s vs 63.6 MB / s) vs. SSD
  • HDD slower 53 times(0.36 MB / s vs 19 MB / s) vs. SSD
During operations - write (write)
  • HDD slower 178 times(0.78 MB / s vs 139 MB / s) vs. SSD
  • HDD slower 86 times(0.64 MB / s vs.55 MB / s) vs. SSD

Why are we mainly interested in the result of a disk with small data blocks?
The fact is that whether you open a browser, or import a project consisting of hundreds of files into a program like Unreal Engine, it doesn't matter what you do, in all such cases, the computer processes a huge number of small data blocks (mainly reads , 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 often, and does not affect system responsiveness, 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 world of computers, there is an opinion that the whole trouble is in the operating system - Mac OSX on Apple computers is "optimized", "never slows down", "there are no blue screens of system failure"

Maybe it's because:
Apple computers (not counting the cheapest configurations): have all the same components, except for one - the m.2 SSD / proprietary counterparts:
- Runs at speeds (700 - 1100 MB / s) via NVMe, with the ability to handle 65,000 wait threads executing 65,000 commands each
- Having data loss prevention systems, overheating protection systems, helping to prevent errors and freezes when working with several GB of data consisting mainly of small blocks, in multitasking mode
- etc. etc.
While, experience with Windows pc formed when working with computers that have:
- Regular HDD 5400 rpm (noisy and vibrating during operation, due to the presence of moving parts), which has the ability to handle 1 waiting thread, executing 32 commands
- Running at speed (60 - 110 MB / s)
- Constantly forcing all users to observe the "Not responding" state, to observe 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 by installing 5400 rpm HDD on Apple, and m.2 SSD on Windows PC, and it turns out that the disk is really the most important (for performance and responsiveness) part of the computer. a regular HDD is very slow, and makes the whole system wait until it finishes processing all the task queues from programs and OS, which slows down a lot when working in multitasking mode, and, moreover, there are applications doing work in the background, which can be enough a lot - from auto-updating project dependencies to tasks set for processing by the user himself.

Now, let's move on to the tests!

Test configuration | Real-world 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)

| Upgrading clean Windows 7 to Windows 10

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

The first 4 lines are the Windows 10 update process
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 to start Windows and programs in the tray: 0:16 | Total time: 0:23 - 217% faster (3.17 times)
HDD Time to start Windows and programs in the tray: 0:48 | Total time: 1:13
PDF opened immediately after the desktop appeared
The countdown ended after loading the programs in the tray and fully opening the PDF file

| Application start time

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

| Time to complete tasks in applications

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 bypassed HDD in all parameters in 100% of cases, solving a 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 an SSD disk, you no longer notice any problems with freezes, whether it concerns the processing speed in AE, due to the fact that your sublime text downloads dependency updates using 100% of the disk at this time, or, if it stops working from -because BVH is being calculated in the background before rendering in blender, or while Maya, for several hours, creates alembic cache files, preventing you from even accessing the Internet without freezing.
Not much more and no waiting for Audacity to hang, after reducing the audio track, every 2 minutes, and no waiting for all HDR or EXR in the folder to load every time for 1-3 minutes (!). You no longer have to stop the work of one application in order to speed up the responsiveness of others. it loaded the disk at 100%. You don't even have to wait a few seconds after each action in Unreal Engine, for any aspect of 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.

And so on and so on. SSD anyway.

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

Bottom line - do you need an SSD?

If you need a disk:
  • Works absolutely silently (unlike HDD, which has moving parts that create noise and vibration)
  • A disk that does not make you nervous, because of endless expectations and slow operation of programs from the stage of opening a program - working in it - and before closing it, only because, unlike all other components of a pc and programs, the speed of HDD drives of a consumer segment has not evolved for the last 20 years.
  • If you need a disk that has several times the speed and responsiveness advantage over HDD in all types of tasks, from browsing the Internet to multitasking, typical of code / game development, working with 3D graphics, animation, particle simulation / video processing, audio / etc.
Then SSD is for you