SAS disks: purpose, description, technical characteristics of the device. How to choose the right SAS, SATA or SSD drive so as not to overpay and get maximum efficiency

Everyone knows the performance parameters of disk subsystems in theory. But what in practice? Many people ask this question, some build their own hypotheses. I decided to conduct a series of tests and determine “Who is who”. I started testing with all known utilities dd, hdparm, then moved on to fio, sysbench. A number of tests were also carried out using UnixBench and several other analogues. A number of graphs were generated, but with further testing it was discovered that most of the software was not suitable for adequately comparing different drives.
Using fio, it was possible to create a comparative table or graph for SAS, SATA, but when testing SSDs it turned out that the results obtained were completely unusable. Of course, I respect the developers of all this software, but at that moment it was decided to create a series of not synthetic tests, but ones closer to the real situation.

I’ll say right away that the test parameters and the machines themselves were selected in such a way that the test results were not distorted by the type of processor, its frequency or other parameters.

Test 1

Creating files

Over the course of eight cycles, the creation of small files with chaotic content and a gradual increase in the number of files per cycle was generated. The execution time was measured for each cycle.

The graph shows that SSD KINGSTON SV300S3 has a higher speed of file creation and is almost independent of their number. It is also worth noting that these particular discs have a more linear scale
Looking at SAS disks in Hardware RAID, it can be seen that the speed depends on the type of raid, but does not depend at all on the number of disks.
But more time is spent not on creating files, as it turned out, but on rewriting them. With this in mind, let's move on to the second test.

Test 2

Overwriting files

The same operations as in the first test were repeated, but new files were not created each time, but the same file was used, into which new information was written each time.


The terrible picture of the SATA 7,200 rpm MB2000GCVBR drives immediately catches your eye. Slow recording and 2x 300GB SAS SEAGATE. Therefore, I decided to remove them from the schedule for clarity on the rest.


The fastest subsystem turned out to be a single SSD KINGSTON. Second and third places went to 8x SEAGATE ST3300657SS and 4x SEAGATE ST3300657SS. We also see that as the number of SSDs in the array increases, the speed drops slightly.

Test 3

MySQL. Combining sql queries INSERT, SELECT, UPDATE, DELETE

An InnoDB table was created with the following structure:
CREATE TABLE `table` (
`id` int(10) unsigned NOT NULL AUTO_INCREMENT,
`time` int(11) NOT NULL,
`uid` int(11) NOT NULL,
`status` varchar(32) NOT NULL,
PRIMARY KEY (`id`),
FULLTEXT KEY `status` (`status`)
) ENGINE=InnoDB DEFAULT CHARSET=cp1251;

Several requests were generated simultaneously:
- INSERT;
- UPDATE with selection by PRIMARY KEY;
- UPDATE with selection by FULLTEXT (search by 4 characters out of 24): WHERE `status` LIKE "%(string)%";
- DELETE FROM with selection by PRIMARY KEY;
- DELETE FROM with selection without using a key: WHERE `time`>(int);
- SELECT with selection without using a key: WHERE `time`>(int);
- SELECT with selection by PRIMARY KEY;
- SELECT with selection by FULLTEXT (search by 4 characters out of 24): WHERE `status` LIKE "%(string)%";
- SELECT with selection without using a key: WHERE `uid`>(int).

And again we see the same picture as in the second test.

In the following tests I use the sysbench utility, which generates large files:
128 files, total sizes 10 GB, 30 GB and 50 GB.
Block size 4 KB.
I would like to immediately draw your attention to the fact that on some graphs, for some servers there is no data for 10 GB. This is due to the fact that these machines have more than 10 GB of RAM and data caching is performed. The lack of some results for 50 GB is due to lack of disk space, in the case of the KINGSTON SV300S3 SSD.

Test 4

Linear recording (file creation)

It can be seen that all variations with SSD KINGSTON SV300S3, as well as 8x SEAGATE ST3300657SS in RAID10, have the best performance. The increase in speed with an increase in the number of SAS disks is very clearly visible.
Here is the very moment where you can clearly see that SSDs are completely different. The difference is 4 times!

Test 5

Linear recording (file overwriting)

The leaders are still the same. If we compare 2x SSD from INTEL and 2x SAS there is practically no difference.

Test 6

Linear reading

Here we see a slightly different picture. The leaders are 4x SSD KINGSTON RAID10, with minimal changes in results as the file size increases, and 8x SEAGATE in RAID10, with a gradual decrease in speed, at speeds of 700 Mbit/s and 600 Mbit/s.
The lines for 1x SSD KINGSTON and 2x SSD KINGSTON RAID1 matched. Simply put, for linear reading it is better to take either RAID10 or a single disk. The use of RAID1 is not justified.
It is clearly seen that 2x SAS RAID1 and 4x SAS RAID10 showed very similarities. But when the number of disks is doubled, a huge increase in speed is visible.
2x SSD Intel RAID1 has a significant drop in speed in the range of 10 GB - 30 GB, and then they go at the same speed as SATA RAID1.

Test 7

Random reading

All SSDs are in the lead:
- 4x KINGSTON RAID10;
- 2x KINGSTON RAID1, 2x INTEL RAID1;
- 1 KINGSTON.

I copied everyone else onto the following graph for clarity.


The highest speed among these is naturally 8x SAS RAID10, but the speed drops sharply. But based on the data for 2x SAS and 4x SAS, I will assume that with further growth in volume the speed will stabilize.

Test 8

Random entry

2x 120GB SSD INTEL SSDSC2CT12 Hardware RAID1 SAS1068E with a stable speed of 30 Mbit/s has excellent performance. According to KINGSTON, as the number of disks increases, the speed, oddly enough, decreases. In fourth place is 8x SAS SEAGATE.

Test 9

Combined random read and write operations

We all know that no server is read-only or write-only. Both operations are always performed. And in most cases these are just random operations, not linear ones. So, let's see what we got.


Due to its excellent write speed, 2x SSD INTEL comes in far ahead, followed by SSD KINGSTON. Third place was shared by 2x SSD KINGSTON and 8x SAS SEAGATE.

Test 10

After carrying out all these tests, I decided that it would be convenient to derive the dependence of speed on the ratio of random read and random write operations.


Some have an increase in speed, some have a decrease, and 8x SAS RAID10 has a straight line.

Test 11

I also made a comparison of large arrays of SAS disks, which shows that it depends more on the speed of the disk than on their number.

It's time to take stock.
There were a lot of cars, but not enough. Unfortunately, I was not able to determine whether the indicators for the INTEL SSDSC2CT12 SSD are their feature or a feature of the raid controller. But I believe that it is the controller.

1. As the number of SAS disks in the array increases, all indicators only improve.
2. For MySQL, the slow subsystems are SATA RAID1 and SAS RAID1. For the rest there are differences, but they are not so significant.
3. For linear recording, both large arrays of SAS disks in RAID10 and SSDs are good. There is no point in using SSD arrays. The cost is rising, but the performance is stagnant.
4. Any large arrays are good for linear reading. But in practice lin. Reading without writing is almost unheard of here.
5. Random reading from single SSDs or Software RAID.
6. For random recording, it is better to use Hardware RAID from an SSD, although single SSDs do not sacrifice much.
7. Random read/write, that is, one of the most important indicators, has the best results on Hardware RAID from SSD.
8. Summarizing all of the above, for most tasks it is better to use large arrays (>=8) of SAS or Hardware RAID of SSD. But for some tasks it would be more correct to use single SSDs.
9. Based on the volumes of SSDs that are predominantly offered on our market, for VDS nodes it is worth using processors with maximum performance paired with large SAS arrays or mediocre processors and single SSDs. I think that using hw raid for two SSDs will be a bit expensive.
10. If you need a fast system and don't need a lot of disk space, 2x SSD in Hardware RAID will be the best choice. If you want to save a little at the expense of performance, then you can take a single SSD or two SSDs in a software raid.

Questions that remain unanswered:

1. What happens when you increase the number of SSDs in a Hardware RAID?
2. What is cheaper for virtual servers: expensive machines and one large SAS array or several mediocre servers with single SSDs? In this matter, you should also take into account the reliability/durability of SAS and SSD, since there are various rumors about the latter.

In addition to the listed tests and servers, there were many more, but they were not included in the results, since the tests were “calibrated” on them and many of them were found to be incorrect.
RAMDisk testing was also carried out. The results were pretty good, but not the best. Probably due to the fact that it was a virtual machine.

All tests, except the last one, were performed only on dedicated servers.

02Feb

Every day the volume of information is only growing, so a reliable storage system with high speed information processing is becoming a necessity.

The following types of disks are used to store data:

• HDD (hard disk drive) - magnetic disk drive with SATA and SAS interfaces
• SSD (solid-state drive) is a solid-state drive based on flash memory technology.

Both types of drives are widely used, have their own characteristics and solve different problems. So which drive suits your business needs? Let's figure it out.

What makes HDDs different?

Inside such a drive are several aluminum plates. Due to their rotation and the reading head, all operations of reading and writing information occur at speeds of up to 15 thousand revolutions per minute. Basically, of course, discs with 7200 rpm are used. Drives of this type are distinguished by a large amount of disk space - up to 10 TB on one disk and reliability when storing and recording information.

A modern drive is connected to a server using SATA or SAS interfaces.

In the professional environment, SATA and SAS, the names of the interfaces themselves are used to name the types of disks for corporate use. So what is the difference between SATA and SAS drives?

The use of one or another type of disk is determined by the type of problem being solved.

SATA– Serial Advanced Technology Attachment - hard drive for working with large amounts of data at relatively low speeds of up to 600 Mbit/s with a throughput of 6 Gbit/s. SATA drives are usually used for data storage or backup.

Via SATA you can connect an HDD to almost any Intel server. As for SSDs, the SATA interface on such drives is capable of transferring data at speeds of up to 6 Gbit/s.

SAS- Serial Attached SCSI - a hard drive connected via the SCSI command set, which operates at speeds of up to 1.2 GB/s, with a throughput of up to 24 Gbit/s. SAS is used for high-speed operations with multiple cycles of rewriting information, for example, for database management (DBMS), for high-load web servers and web applications and server systems. Moreover, SAS-based systems are easy to install and easily scalable.

The disadvantages of such a drive include its high price, which is partly justified by its high performance.

Technologies are developing, so SAS connectors are already compatible with SATA connectors, which is actively used on dedicated virtual servers to maintain speed while increasing storage capacity. That is, applications with varying degrees of performance can be combined in one subsystem.

Pros and cons of an SSD drive

SSD drives are based on memory chips. It processes files approximately 80 times faster than SATA.

But such high performance has its drawbacks - each new rewrite cycle “burns” the disk, significantly reducing its service life. And any malfunction of such a disk can cost the information recorded on it. Therefore, it is better not to use SSDs to organize backup storage.

SSD drives are necessary for projects where the speed of writing and reading processes is critical. With such disks, the speed of the site on any CMS significantly increases.

Which drive to choose for your business needs?

It is important to understand that these disks also have different applications, and you should not use them to solve the same problems - this is fraught with malfunction. For example, using an SSD to regularly generate streaming video quickly leads to its burnout and data loss. When choosing a SATA or SAS drive, you should also consider your business objectives:

How many requests will the disk process simultaneously? If there is a consistently large number of requests from many users, then you should choose the SAS interface.

How much storage is required for the server's disk subsystem? If the data volume exceeds 1 TB, you should pay attention to a SATA drive.

Are there plans to increase the volume of data and further scale the server? To increase server performance and increase fault tolerance, you should pay attention to a SAS disk.

Table 1 Selecting a disk for the task at hand

The optimal solution for business, where speed of loading and processing information, and reliability in data storage are equally important - a combination of disks. That is, in a company network, SATA drives are used for large archives and backups; a faster SAS drive type is recommended for efficient database management; and SSD is recommended for network portals and file sharing systems.

In some cases, a hybrid storage solution is used, SATA + SSD on different interfaces - this ensures stable data storage and high speed of information transfer and processing.

The SmileServer.ru dedicated server rental service offers all storage options that fully support the tasks of storing and accessing data for both small and large businesses.

Modern computer systems use SATA and SAS interfaces to connect main hard drives. As a rule, the first option suits home workstations, the second – server ones, so the technologies do not compete with each other, meeting different requirements. The significant difference in cost and memory capacity makes users wonder how SAS differs from SATA and look for compromise options. Let's see if this is worthwhile.

SAS(Serial Attached SCSI) is a serial interface for connecting storage devices, developed on the basis of parallel SCSI to execute the same set of commands. Used primarily in server systems.

SATA(Serial ATA) – serial data exchange interface based on parallel PATA (IDE). Used in home, office, multimedia PCs and laptops.

If we talk about HDDs, then, despite the differing technical characteristics and connectors, there are no fundamental differences between the devices. Backward one-way compatibility makes it possible to connect drives to the server board using both one and a second interface.

It is worth noting that both connection options are also possible for SSDs, but the significant difference between SAS and SATA in this case will be in the cost of the drive: the first can be tens of times more expensive for a comparable volume. Therefore, today such a solution, if not rare, is quite well-considered, and is intended for fast enterprise-level data processing centers.

Difference between SAS and SATA

As we already know, SAS is used in servers, SATA in home systems. In practice, this means that the former are accessed by many users at the same time and many tasks are solved, while the latter are dealt with by one person. Accordingly, the server load is much higher, so the disks must be sufficiently fault-tolerant and fast. SCSI protocols (SSP, SMP, STP) implemented in SAS allow more I/O operations to be processed simultaneously.

Directly for HDD, the circulation speed is determined primarily by the spindle rotation speed. For desktop systems and laptops, 5400 – 7200 RPM is necessary and sufficient. Accordingly, it is almost impossible to find a SATA drive with 10,000 RPM (unless you look at the WD VelociRaptor series, intended, again, for workstations), and anything higher is absolutely unattainable. SAS HDD spins up at least 7200 RPM, 10000 RPM can be considered the standard, and 15000 RPM is a sufficient maximum.

Serial SCSI drives are considered to be more reliable and have higher MTBF. In practice, stability is achieved more due to the checksum verification function. SATA drives, on the other hand, suffer from “silent errors” when data is partially written or damaged, which leads to the appearance of.

The main advantage of SAS also contributes to the fault tolerance of the system - two duplex ports, allowing you to connect one device via two channels. In this case, information exchange will be carried out simultaneously in both directions, and reliability is ensured by Multipath I/O technology (two controllers protect each other and share the load). The queue of marked commands is built up to a depth of 256. Most SATA drives have one half-duplex port, and the queue depth using NCQ technology is no more than 32.

The SAS interface requires the use of cables up to 10 m long. Up to 255 devices can be connected to one port via expanders. SATA is limited to 1 m (2 m for eSATA), and only supports one point-to-point connection.

Prospects for further development are where the difference between SAS and SATA is also felt quite acutely. The throughput of the SAS interface reaches 12 Gbit/s, and manufacturers are announcing support for data transfer rates of 24 Gbit/s. The latest revision of SATA stopped at 6 Gbit/s and will not evolve in this regard.

SATA drives, in terms of the cost of 1 GB, have a very attractive price tag. In systems where the speed of data access is not critical and the volume of stored information is large, it is advisable to use them.

comparison table

SAS	SATA
For server systems	Mainly for desktop and mobile systems
Uses the SCSI command set	Uses the ATA command set
Minimum HDD spindle speed 7200 RPM, maximum – 15000 RPM	Minimum 5400 RPM, maximum 7200 RPM
Supports technology for checking checksums when writing data	A large percentage of errors and bad sectors
Two full duplex ports	One half duplex port
Multipath I/O supported	Point-to-point connection
Command queue up to 256	Team queue up to 32
Cables up to 10 m can be used	Cable length no more than 1 m
Bus throughput up to 12 Gbit/s (in the future – 24 Gbit/s)	Bandwidth 6 Gbps (SATA III)
The cost of drives is higher, sometimes significantly	Cheaper in terms of price per 1 GB

Call or directly on the website! Our specialists will be happy to help you!

We are faced with a choice: what type of hard drive to install. The most popular types of hard drives are: SAS, SATA and NL-SAS. These three types are among the fastest storage media and store most of the world's data. Our article is devoted to the first type. We will look at what SAS disks are, what their parameters are, and what is the difference between the main types of devices mentioned.

Specifications

SAS disks have replaced the SCSI type. They have become the new standard in enterprise-class information storage. Of the three listed types, SAS disks are considered the most reliable, they are able to maintain performance in very difficult operating conditions. SAS hard drives perform much better than NL or SATA hard drives. An indicator of their reliability is the error rate. It determines how likely a single bit of error is to occur in media data. The error rate for SAS hard drives is usually one out of 10 16 bits. That is, this means that the probability of an error may occur in one in ten quadrillion bits. For example, you can compare this indicator with the error value in SATA hard drives, where it is one out of 10 15 (or one quadrillion). As you can see, the protection of SATA hard drives is also quite high, however, when the question arises of protecting stored information, the difference of one order of magnitude is quite significant.

SAS drives are produced to stricter standards than other types of hard drives. Thus, this technology is characterized by an average time between failures of 1.6 million hours, and SATA technology - 1.2 million. In addition to the listed parameters, controllers and disks of the type in question have many additional commands intended for diagnostics. These features make this technology more efficient than SATA. This is especially true in force majeure situations.

NL hard drives

This technology is a "new player" in the market. NL drives are a hybrid: a SATA hard drive with a SAS connector. That is, the speed, filling and head are taken from SATA technology, and the interface is fully compatible with SAS. NL technology is inferior to the disks in question in performance (due to the relatively low rotation speed). However, it fully complies with them in command queuing, as well as multi-threaded data transfer and support for multiple hosts.

Tagged order of sending commands and multi-threaded transmission

Simultaneous coordination of multiple sets of storage instructions, as well as information ordered by the storage controller, is transmitted most efficiently. SAS technology provides several full-duplex channels that provide quick access to stored information. One SAS-type hard drive can be controlled from several personal computers at once without the use of switches.

Conclusion

Essentially, SAS and SATA technologies are designed for different purposes: the former for fault tolerance and performance, and the latter for capacity. Therefore, they should not compete with each other.

SAS interface.

The SAS or Serial Attached SCSI interface provides connectivity over a physical interface, similar to SATA, devices, controlled by SCSI command set. Possessing backwards compatible with SATA, it makes it possible to connect any devices controlled by the SCSI command set via this interface - not only hard drives, but also scanners, printers, etc. Compared to SATA, SAS provides a more developed topology, allowing parallel connection of one device to two or more channels. Bus expanders are also supported, allowing you to connect multiple SAS devices to one port.

The SAS protocol is developed and maintained by the T10 committee. SAS was designed to communicate with devices such as hard drives, optical drives, and the like. SAS uses a serial interface to work with directly connected drives and is compatible with the SATA interface. Although SAS uses a serial interface as opposed to the parallel interface used by traditional SCSI, SCSI commands are still used to control SAS devices. Commands (Fig. 1) sent to the SCSI device are a sequence of bytes of a certain structure (command descriptor blocks).

Rice. 1.

Some commands are accompanied by an additional "parameter block", which follows the command descriptor block, but is passed as "data".

A typical SAS system consists of the following components:

1) Initiators. An initiator is a device that originates service requests for target devices and receives acknowledgments as requests are executed.

2) Target devices. The target device contains logical blocks and target ports that receive service requests and execute them; After processing of the request is completed, confirmation of the request is sent to the request initiator. The target device can be either a separate hard drive or an entire disk array.

3) Data delivery subsystem. It is part of the input/output system that transfers data between initiators and target devices. Typically, the data delivery subsystem consists of cables that connect the initiator and the target device. Additionally, in addition to cables, the data delivery subsystem may include SAS expanders.

3.1) Extenders. SAS extenders are devices that are part of the data delivery subsystem and allow facilitating data transfers between SAS devices, for example, allowing you to connect several target SAS devices to one initiator port. Connection via the extender is completely transparent to the target devices.

SAS supports connecting devices with SATA interface. SAS uses a serial protocol to transfer data between multiple devices, and thus uses fewer signal lines. SAS uses SCSI commands to control and communicate with target devices. The SAS interface uses point-to-point connections - each device is connected to the controller by a dedicated channel. Unlike SCSI, SAS does not require user termination of the bus. The SCSI interface uses a common bus - all devices are connected to one bus, and only one device can work with the controller at a time. In SCSI, the speed of information transfer along the different lines that make up the parallel interface may differ. The SAS interface does not have this drawback. SAS supports a very large number of devices, while SCSI supports 8, 16, or 32 devices per bus. SAS supports high data rates (1.5, 3.0 or 6.0 Gbps). This speed can be achieved by transferring information on each connection, while on the SCSI bus the bus bandwidth is divided among all devices connected to it.

SATA uses the ATA command set and supports hard drives and optical drives, while SAS supports a wider range of devices, including hard drives, scanners, and printers. SATA devices are identified by their SATA interface controller port number, while SAS devices are identified by their WWN (World Wide Name) identifiers. SATA devices (version 1) did not support command queues, while SAS devices support tagged command queues. SATA devices since version 2 support Native Command Queuing (NCQ).

SAS hardware communicates with target devices over several independent lines, which increases the fault tolerance of the system (the SATA interface does not have this capability). At the same time, SATA version 2 uses port duplicators to achieve a similar capability.

SATA is primarily used in non-critical applications such as home computers. The SAS interface, due to its reliability, can be used in mission-critical servers. Error detection and error handling are defined much better in SAS than in SATA. SAS is considered a superset of SATA, and does not compete with it.

SAS connectors are much smaller than traditional parallel SCSI connectors, allowing SAS connectors to be used to connect compact 2.5-inch drives. SAS supports information transfer at speeds from 3 Gbit/s to 10 Gbit/s. There are several options for SAS connectors:

SFF 8482 - option compatible with SATA interface connector;

SFF 8484 - internal connector with dense contact packing; allows you to connect up to 4 devices;

SFF 8470 - connector with tightly packed contacts for connecting external devices; allows you to connect up to 4 devices;

SFF 8087 - reduced Molex iPASS connector, contains a connector for connecting up to 4 internal devices; supports 10 Gbps speed;

SFF 8088 - reduced Molex iPASS connector, contains a connector for connecting up to 4 external devices; supports 10 Gbps speed.

The SFF 8482 connector allows you to connect SATA devices to SAS controllers, eliminating the need to install an additional SATA controller just because you need to connect a DVD burner, for example. Conversely, SAS devices cannot connect to the SATA interface and are equipped with a connector that prevents them from connecting to the SATA interface.