SAS vs SATA SSDs. What to choose? SAS disks: purpose, description, device specifications
Interface SAS (Serial Attached SCSI) - serial interface connecting hard disks, which replaced the parallel SCSI interface. Hard drives with a SAS interface are designed for use in server systems.
As the name implies, SAS is a relative of SCSI and is functionally a logical protocol of its predecessor, based on the electrical and mechanical part of the SATA serial interface.
Combined with the new addressing system, this allows up to 128 devices per port and up to 16,256 devices per controller.
Available in this moment SAS controllers and hard drives support data transfer speeds of 300 MB/s. SAS-2 version devices will transfer data at speeds of up to 600MB/s.
History of creation
In 2002, the T10 committee proposed a new SAS protocol that addressed the above-described shortcomings. The point-to-point connection provided dedicated bandwidth for each disk, the maximum cable length is up to 8 m per port (increased with the help of SAS expanders), the number of addressable devices in one domain increased to 16,256, instead of manually setting ID, unique numbers are used (WWN - World Wide Number), assigned to each of them at the production stage. Connectors for external SAS devices are designed to connect up to four drives and provide 1.2 Gbps bandwidth in one direction. Also, the SAS interface provided full support for hot plugging and command queue sorting.
SAS Standards
A set of SAS (Serial Attached SCSI) standards includes:
Application level: SCSI, ATA, SMP (Serial Management Protocol);
· transport level: SSP (Serial SCSI Protocol), STP (Serial ATA Tunneling Protocol, connecting SATA devices to SAS HBA via an expander), SMP (Serial Management Protocol, support for SAS expanders);
· SAS port layer;
· connection level: general part and SSP, STP, SMP;
· SAS phy: speed matching (slowing down by inserting fillers); encoding (8b10b as in FC and Ethernet); can be combined into a “wide” (2x, 3x, 4x) port in an HBA/RAID or expander; speed: SAS-1 - 3Gbit/s (300MB/s), SAS-2 - 6Gbit/s (600MB/s);
· physical layer: full duplex is provided; cables and connectors; a single internal connector is compatible with SATA devices, but not vice versa (SAS devices cannot be connected to a SATA controller); external and group connectors (wide port, several phy); SAS-2 introduced an adaptation period when connecting a device (training, which allows you to increase the cable length to 6m); SAS-2.1 introduces active cables (a built-in microcircuit allows you to reduce the cable thickness and increase the cable length to 30m); optical cable - up to 100m; miniSAS x4 connector provides power to the active cable; external miniSAS x4 cables have different connectors for input and output ports; SAS-2.1 added external miniSAS 8x and internal miniSAS 8x connectors.
Actually, the SAS data transfer protocol means three protocols at once:
1) serial SCSI protocol (Serial SCSI Protocol SSP), transmitting SCSI commands;
2) SCSI management protocol SMP, which transmits control information to expanders;
3) SATA Tunneled Protocol STP, establishes a connection that allows the transmission of SATA commands.
Thanks to the use of these three protocols, the SAS interface is fully compatible with existing SCSI applications, control software and SATA devices.
This multi-protocol architecture, combined with the physical compatibility of SAS and SATA connectors, makes SAS technology universal link between SAS and SATA devices.
SAS connectors
The SAS connector is universal and is compatible with SATA in form factor. This allows you to directly connect both SAS drives and SATA drives and thus use the system either for mission-critical applications that require high performance and fast access to data, or for more cost-effective applications with a lower cost per gigabyte.
The SATA command set is a subset of the SAS command set, allowing compatibility between SATA devices and SAS controllers. However, SAS drives cannot work with a SATA controller, so they are equipped with special keys on the connectors to eliminate the possibility of incorrect connection.
Connector SFF-8482 - internal connector for connecting a standard hard drive hot swap with SAS interface (you can also connect a drive with a SATA interface). In addition to data, the connector supplies power to the hard drive.
SFF-8484 connector is an adapter that allows you to connect a backplane or cage with an SFF-8484 connector to the controller. For 2 or 4 devices.
Connector SFF-8470 - external connector with high density contacts. Allows you to connect up to 4 devices. Infiniband type connector.
Connector SFF-8087 - internal mini-SAS connector for connecting up to 4 devices.
SFF-8088 connector - external mini-SAS connector for connecting up to 4 devices
Hard drive for a server, features of choice
The hard drive is the most valuable component in any computer. After all, it stores information that the computer and the user work with, if we are talking about personal computer. Every time a person sits down at a computer, he expects to run through the loading screen. operating system, and he will start working with his data, which the hard drive will release “to the mountain” from its depths. If we are talking about a hard drive, or even an array of them as part of a server, then there are tens, hundreds and thousands of users who expect to gain access to personal or work data. And all their quiet work or rest and entertainment depends on these devices, which constantly store data. Already from this comparison it is clear that requests to hard drives home and industrial classes are presented unequally - in the first case, one user works with it, in the second - thousands. It turns out that second hard The disk must be many times more reliable, faster, and more stable than the first, because many users work with it and rely on it. This article will look at the types of hard drives used in the corporate sector and the features of their design that allow them to achieve the highest reliability and performance.
SAS and SATA drives - so similar and so different
Until recently, the standards for industrial-class and consumer hard drives differed significantly and were incompatible - SCSI and IDE, but now the situation has changed - the overwhelming majority of them on the market are hard disks SATA and SAS (Serial Attached SCSI) standard. The SAS connector is universal in form factor and is compatible with SATA. This allows you to directly connect to a SAS system with both high-speed, but small capacity (at the time of writing - up to 300 GB) SAS drives, and less high-speed, but many times more capacious, SATA drives (at the time of writing, up to 2 TB). Thus, in one disk subsystem you can combine vital important applications applications that require high performance and fast access to data, and more cost-effective applications with a lower cost per gigabyte.
This design compatibility benefits both back panel manufacturers and end users by reducing hardware and engineering costs.
That is, you can connect to the SAS connectors as SAS devices, and SATA, and to SATA connectors Only SATA devices are connected.
SAS and SATA - high speed and large capacity. What to choose?
SAS drives, which replaced SCSI drives, completely inherited their main properties that characterize a hard drive: spindle speed (15,000 rpm) and volume standards (36,74,147 and 300 GB). However, SAS technology itself is significantly different from SCSI. Let's briefly look at the main differences and features: The SAS interface uses a point-to-point connection - each device is connected to the controller by a dedicated channel, in contrast, SCSI operates over a common bus.
SAS supports a large number of devices (>16384), while SCSI supports 8, 16, or 32 devices per bus.
The SAS interface supports data transfer rates between devices at speeds of 1.5; 3; 6 Gb/s, while for the SCSI interface the bus speed is not allocated to each device, but is divided between them.
SAS supports connecting slower SATA devices.
SAS configurations are much easier to install and install. Such a system is easier to scale. In addition, SAS hard drives inherited the reliability of SCSI hard drives.
When choosing a disk subsystem - SAS or SATA, you need to be guided by what functions will be performed by the server or workstation. To do this, you need to decide on the following questions:
1. How many simultaneous diverse requests will the disk process? If it's large, your clear choice is SAS disks. Also, if your system will serve a large number of users, choose SAS.
2. How much information will be stored on the disk subsystem of your server or workstation? If it is more than 1-1.5 TB, you should pay attention to a system based on SATA hard drives.
3. What is the budget allocated for the purchase of a server or workstation? It should be remembered that in addition to SAS disks, you will need a SAS controller, which also needs to be taken into account.
4. Do you plan to subsequently increase the volume of data, increase productivity, or increase system fault tolerance? If yes, then you will need a SAS-based disk subsystem; it is easier to scale and more reliable.
5. Your server will work with critical data and applications - Your choice is SAS drives designed for harsh operating conditions.
A reliable disk subsystem includes not only high-quality hard drives from a renowned manufacturer, but also an external disk controller. They will be discussed in one of next articles. Let's consider SATA drives, what types of these disks are there and which ones should be used when building server systems.
SATA drives: household and industrial sectors
SATA drives, used everywhere, from consumer electronics and home computers to high-performance workstations and servers, differ into subtypes, there are drives for use in household appliances, with low heat generation, power consumption, and, as a result, reduced performance, there are middle-class drives, for home computers, and there are drives for high-end systems. In this article we will look at the class of hard drives for high-performance systems and servers.
Performance characteristics
|
Server class HDD |
HDD desktop class |
|
|
Rotational speed |
7,200 rpm (nominal) |
7,200 rpm (nominal) |
|
Cache size |
||
|
Average delay time |
4.20 ms (nominal) |
6.35 ms (nominal) |
|
Data transfer rate |
||
|
Reading from drive cache (Serial ATA) |
maximum 3 Gb/s |
maximum 3 Gb/s |
|
physical characteristics |
||
|
Capacity after formatting |
1,000,204 MB |
1,000,204 MB |
|
Capacity |
||
|
Interface |
SATA 3 Gb/s |
SATA 3 Gb/s |
|
Number of sectors available to the user |
1 953 525 168 |
1 953 525 168 |
|
Dimensions |
||
|
Height |
25.4 mm |
25.4 mm |
|
Length |
147 mm |
147 mm |
|
Width |
101.6 mm |
101.6 mm |
|
0.69 kg |
0.69 kg |
|
|
Impact resistance |
||
|
Impact resistance in working condition |
65G, 2ms |
30G; 2 ms |
|
Impact resistance when not in use |
250G, 2ms |
250G, 2ms |
|
Temperature |
||
|
In working order |
-0°C to 60°C |
-0°C to 50°C |
|
Inoperative |
-40°C to 70°C |
-40°C to 70°C |
|
Humidity |
||
|
In working order |
relative humidity 5-95% |
|
|
Inoperative |
relative humidity 5-95% |
relative humidity 5-95% |
|
Vibration |
||
|
In working order |
||
|
Linear |
20-300 Hz, 0.75 g (0 to peak) |
22-330 Hz, 0.75 g (0 to peak) |
|
free |
0.004 g/Hz (10 - 300 Hz) |
0.005 g/Hz (10 - 300 Hz) |
|
Inoperative |
||
|
0.05 g/Hz (10 - 300 Hz) |
0.05 g/Hz (10 - 300 Hz) |
|
|
20-500 Hz, 4.0G (0 to peak) |
The table shows the characteristics of hard drives from one of the leading manufacturers; one column shows the data SATA hard drive server class, in another regular SATA hard drive.
From the table we see that disks differ not only in performance characteristics, but also in operational characteristics, which directly affect the life expectancy and successful operation of the hard drive. Please note that these hard drives differ only slightly in appearance. Let's look at what technologies and features allow us to do this:
The reinforced shaft (spindle) of the hard drive is fixed at both ends by some manufacturers, which reduces the influence of external vibration and facilitates precise positioning of the head unit during read and write operations.
The use of special intelligent technologies that take into account both linear and angular vibration, which reduces head positioning time and increases disk performance by up to 60%
Function for eliminating errors due to operating time in RAID arrays - prevents hard drives from falling out of RAID, which is a characteristic feature regular hard disks.
Adjustment of the flight height of the heads in combination with technology to prevent contact with the surface of the plates, which leads to significant increase disk lifespan.
A wide range of self-diagnosis functions that allow you to predict in advance the moment when HDD fails, and warn the user about this, which allows you to have time to save the information to a backup drive.
Features that reduce the rate of unrecoverable read errors, which increases the reliability of the server hard drive compared to conventional hard drives.
Speaking about the practical side of the issue, we can confidently say that specialized hard drives in servers “behave” much better. There are significantly fewer calls to the technical service regarding instability of RAID arrays and hard drive failures. Manufacturer support for the server segment of hard drives occurs much more quickly than conventional hard drives, due to the fact that the priority area of work for any manufacturer of data storage systems is the industrial sector. After all, it is here that the most advanced technologies are used to protect your information.
Analogue of SAS disks:
Hard drives from Western Digital VelociRaptor. These drives have a disk rotation speed of 10 thousand rpm, equipped with a SATA 6 Gb/s interface and 64 MB of cache memory. The time between failures of these drives is 1.4 million hours.
More details on the manufacturer's website www.wd.com
You can order the assembly of a server based on SAS or an analogue of SAS hard drives from our company "Status" in St. Petersburg; also, you can buy or order SAS hard drives in St. Petersburg:
- call +7-812-385-55-66 in St. Petersburg
- write to the address
- leave an application on our website on the "Online application" page
There are many myths in the IT field. “You can unsubscribe from spam”, “Two antiviruses are better than one”, “Server hard drives should only be branded.” When replacing and expanding the railway fleet, you need to take into account many nuances and subtleties, and this is also not without your prejudices. What types of hard drives are there for servers, how they differ, what you need to pay attention to, and whether they should have the logo of the server manufacturer - read about it under the cut.
If a disk is installed in a server, it must meet strict requirements for:
- Reliability. Unrecoverable data loss can result in multimillion-dollar losses and reputational damage.
- Productivity. Servers are a priori designed to process numerous requests.
- Response time. Users don't have to wait for the server disk to wake up and process their requests.
There are four main categories (we do not take into account SSD, SAS SSD, PCI-e SSD) hard drives:
- SATA (regular, “household” SATA) - spindle speed 5400 and 7200 rpm.
- SATA RAID Edition (SATA RE) - spindle speed 7200 rpm, support for RAID controller commands.
- SAS Near Line (SAS NL) - spindle speed 7200 rpm.
- SAS Enterprise - spindle speed 10,000 or 15,000 rpm.
SATA or SAS?
Initially, the SAS interface had higher bandwidth than SATA. But progress does not stand still, and the third generation of SATA III has a maximum throughput of 6 Gbit/s, like the second generation of SAS. However, servers with a third generation SAS controller with a throughput of up to 12 Gbit/s are already available on the market.
To connect SAS disks, the server must be equipped with an appropriate controller. At the same time, backward compatibility of the interfaces is ensured: SATA drives can be connected to the SAS controller, but vice versa - not.
Conclusion
When choosing hard drives, you must first consider the tasks that the server will perform:- If you do not need high access speed and reliability of data storage, and the number of disks will not exceed four, then we recommend installing SATA RAID Edition disks. This is an option for low-cost servers entry level servicing a small amount of users.
- If the server will serve databases, or the number of disks in the array will be 5 or more, then it is better to choose SAS NL. Most often, such disks are installed in servers operating in medium-sized companies: for accounting systems, CMS, corporate repositories, etc.
- And if you need maximum performance and/or reliability of data storage, for example, when processing financial transactions, then your choice is SAS Enterprise disks. These are media for highly loaded servers serving a large number of users, as well as for systems working with the most important data.
Tags: Add tags
Last time we looked at everything related to SCSI technology in a historical context: who invented it, how it developed, what varieties it has, and so on. We ended with the fact that the most modern and relevant standard is Serial Attached SCSI; it appeared relatively recently, but has undergone rapid development. The first implementation “in silicon” was shown by LSI in January 2004, and in November of the same year, SAS entered the top popular queries site storagesearch.com.
Let's start with the basics. How do devices using SCSI technology work? The SCSI standard is all about the client/server concept.
The client, called the initiator, sends various commands and waits for their results. Most often, of course, the SAS controller acts as the client. Today, SAS controllers are HBA and RAID controllers, as well as storage controllers located inside external systems data storage.
The server is called a target device, its task is to accept the initiator’s request, process it and return data or confirmation of the command back. The target device can also be separate disk, and a whole disk array. In this case, the SAS HBA inside the disk array (the so-called external storage system), designed to connect servers to it, operates in Target mode. Each target device is assigned a separate SCSI Target ID.
To connect clients with the server, a data delivery subsystem is used (English Service Delivery Subsystem), in most cases, this tricky name hides just cables. Cables are available for external connections, and for connections within servers. Cables change from generation to generation of SAS. Today there are three generations of SAS:
SAS-1 or 3Gbit SAS
- SAS-2 or 6Gbit SAS
- SAS-3 or 12 Gbit SAS – is being prepared for release in mid-2013
Internal and external SAS cables
Sometimes this subsystem may include SAS extenders or expanders. Expanders (English Expanders, expanders, but the word “expander” has taken root in Russian) are understood as devices that help deliver information from initiators to targets and back, but are transparent to target devices. One of the most typical examples is an expander that allows you to connect several target devices to one initiator port, for example, an expander chip in a disk shelf or on a server backplane. Thanks to this organization, servers can have more than 8 disks (controllers that are used today by leading server manufacturers are usually 8-port), and disk shelves can have any required amount.
The initiator connected to the target device by the data delivery system is called a domain. Any SCSI device contains at least one port, which can be an initiator port, a target port, or a combination of both. Ports can be assigned identifiers (PIDs).
Target devices consist of at least one Logical Unit Number or LUN. It is the LUN that identifies which of the disks or partitions of this target device the initiator will work with. The target is sometimes said to provide the initiator with a LUN. Thus, for complete addressing to the desired storage, the SCSI Target ID + LUN pair is used.
As in the well-known joke (“I don’t lend money, and First National Bank doesn’t sell seeds”), the target device usually does not act as the “sender of commands,” and the initiator does not provide a LUN. Although it is worth noting that the standard allows for the fact that one device can be both an initiator and a target, this is rarely used in practice.
For the “communication” of devices in SAS, there is a protocol, according to the “good tradition” and according to the OSI recommendation, divided into several layers (from top to bottom): Application, Transport, Link, PHY, Architecture and Physical.
SAS includes three transport protocol. Serial SCSI Protocol (SSP) - used to work with SCSI devices. Serial ATA Tunneling Protocol (STP) - for interaction with SATA drives. Serial Management Protocol (SMP) - for managing the SAS fabric. Thanks to STP, we can connect SATA drives to SAS controllers. Thanks to SMP, we can build large (up to 1000 disk/SSD devices in one domain) systems, and also use SAS zoning (more about this in the article about the SAS switch).
The link layer is used to manage connections and transfer frames. PHY layer - used for things like setting connection speed and encoding. At the architectural level there are issues of expanders and topology. The physical layer defines voltage, connection waveforms, etc.
All communication in SCSI is based on commands that the initiator sends to the target device and waits for their results. These commands are sent in the form of command description blocks (Command Description Block or CDB). A block consists of one byte of command code and its parameters. The first parameter is almost always LUN. A CDB can be anywhere from 6 to 32 bytes in length, although recent versions of SCSI allow variable-length CDBs.
After receiving the command, the target device returns a confirmation code. 00h means the command was received successfully, 02h means an error, 08h means the device is busy.
Teams are divided into 4 large categories. N, from English “non-data”, are intended for operations not directly related to data exchange. W, from “write” - recording the data received by the target device from the initiator. R, as you might guess from the word “read”, is used for reading. Finally B - for two-way data exchange.
There are quite a lot of SCSI commands, so we will list only the most frequently used ones.
Test unit ready (00h) - check if the device is ready, if there is a disk in it (if it is tape drive), whether the disk has spun up, and so on. It is worth noting that in in this case The device does not perform full self-diagnosis; there are other commands for this.
Inquiry (12h) - get the main characteristics of the device and its parameters
Send diagnostic (1Dh) - perform self-diagnosis of the device - the results of this command are returned after diagnostics with the Receive Diagnostic Results (1Ch) command
Request sense (03h) - the command allows you to get the execution status of the previous command - the result of this command can be either a message like “no error” or various failures, from the absence of a disk in the drive to serious problems.
Read capacity (25h) - allows you to find out the capacity of the target device
Format Unit (04h) - serves to destructively format the target device and prepare it for data storage.
Read (4 options) - reading data; exists in the form of 4 different commands, differing in CDB length
Write (4 options) - record. Same as for reading in 4 versions
Write and verify (3 options) - data recording and verification
Mode select (2 options) - installation various parameters devices
Mode sense (2 options) - returns current device parameters
Now let's look at a few typical examples of organizing data storage on SAS.
Example one, data storage server.
What is it and what is it eaten with? Large companies such as Amazon, Youtube, Facebook, Mail.ru and Yandex use servers of this type to store content. Content means video, audio information, pictures, results of indexing and information processing (for example, Hadoop, so popular recently in the USA), mail, etc. To understand the task and correctly select equipment for it, you need to additionally know a few introductory information, without which it is absolutely impossible. First and most importantly, the more disks, the better.
Data center of one of the Russian Web 2.0 companies
Processors and memory in such servers are not used much. Secondly, in the world of Web 2.0, information is stored geographically distributed, with several copies on different servers. 2-3 copies of information are stored. Sometimes, if it is requested frequently, more copies are stored to balance the load. Well, thirdly, based on the first and second, the cheaper the better. In most cases, all of the above leads to the use of high-capacity Nearline SAS or SATA drives. As a rule, Enterprise-level. This means that such drives are designed to operate 24x7 and are significantly more expensive than their counterparts used in desktop PCs. The case is usually chosen to be one that can accommodate more disks. If it is 3.5’’, then 12 disks in 2U.
Typical 2U storage server
Or 24 x 2.5’’ in 2U. Or other options in 3U, 4U, etc. Now, having the case, the number of disks and their type, we must select the connection type. Actually, the choice is not very large. And it comes down to using an expander or non-expander backplane. If we use an expander backplane, then the SAS controller can be 8-port. If expander-free, then the number of SAS controller ports must be equal to or exceed the number of disks. And finally, the choice of controller. We know the number of ports, 8, 16, 24, for example, and select a controller based on these conditions. There are 2 types of controllers, RAID and HBA. They differ in that RAID controllers support RAID levels 5,6,50,60 and have a fairly large amount of memory (512MB-2GB today) for caching. The HBA either has no memory at all or very little of it. In addition, HBAs either do not know how to do RAID at all, or they can only do simple levels that do not require a large amount of calculations. RAID 0/1/1E/10 is a typical set for HBA. Here we need an HBA, they are much cheaper, so we don’t need data protection at all and we strive to minimize the cost of the server.
16-port SAS HBA
Example two, Exchange mail server. As well as MDaemon, Notes and other similar servers.
Here everything is not as obvious as in the first example. Depending on how many users the server needs to serve, the recommendations will vary. In any case, we know that the Exchange database (the so-called Jet database) is best stored on RAID 5/6 and is cached well with using SSD. Depending on the number of users, we determine the required storage volumes “today” and “for growth.” We remember that the server lives for 3-5 years. Therefore, “for growth” can be limited to a 5-year perspective. Then it will be cheaper to completely change the server. Depending on the volume of the disks, we will choose the case. It’s easier with a backplane; it is recommended to use expanders, since the price requirements are not as stringent as in the previous case, and in general case, an increase in the price of a server by $50-$100, and sometimes more, we will quite endure for the sake of reliability and functionality. We will choose SAS or NL-SAS/Enterprise SATA disks depending on the volume. Next, data protection and caching. Let's choose a modern 4/8-port controller that supports RAID 5/6/50/60 and SSD caching. For LSI, this is any MegaRAID except 9240 with the CacheCade 2.0 caching function, or Nytro MegaRAID with an on-board SSD. For Adaptec, these are controllers that support MAX IQ. For caching in both cases (except for Nytro MegaRAID), you will need to take a pair of SSDs based on Enterprise-class e-MLC technology. Intel, Seagate, Toshiba, etc. have these. Prices and companies are your choice. If you don’t mind paying extra for the brand, then find similar products in the server lines of IBM, Dell, HP and go ahead!
Nytro MegaRAID SSD caching RAID controller
Example three, do-it-yourself external data storage system.
So, the most serious knowledge of SAS, of course, is required for those who produce data storage systems or want to make them themselves. We will focus on a fairly simple storage system, the software for which is produced by Open-E. Of course, you can make storage systems on Windows Storage Server, and on Nexenta, and on AVRORAID, and on Open NAS, and on any other software suitable for these purposes. I just outlined the main directions, and then the manufacturers’ websites will help you. So, if it's an external system, we almost never know how many disks the end user will need. We must be flexible. For this there are so-called JBODs - external disk shelves. They include one or two expanders, each of which has an input (4-port SAS connector), an output to the next expander, the remaining ports are routed to connectors intended for connecting disks. Moreover, in two-expander systems, the first port of the disk is routed to the first expander, the second port is routed to the second expander. This allows you to build fault-tolerant chains of JBODs. The head server may have internal drives in its composition, or not have them at all. In this case, “external” SAS controllers are used. That is, controllers with ports “outside”. The choice between a SAS RAID controller or a SAS HBA depends on the management software you choose. In the case of Open-E, this is a RAID controller. You can also take care of the caching option on SSD. If your storage system will have a lot of disks, then the Daisy Chain solution (when each subsequent JBOD connects to the previous one, or to the head server) is not suitable for many reasons. In this case, the head server is either equipped with several controllers, or a device called a SAS switch is used. It allows you to connect one or more servers to one or more JBODs. We will look at SAS switches in more detail in the following articles. For external data storage systems, it is strongly recommended to use only SAS disks (including NearLine) due to increased requirements for fault tolerance. The fact is that the SAS protocol includes much more features than SATA. For example, control of written-read data along the entire path using checksums (T.10 End-to-End protection). And the path, as we already know, can be very long.
Multi-disk JBOD
This concludes our excursion into the world of history and theory of SCSI in general and SAS in particular, and next time I will tell you in more detail about the use of SAS in real life.
Good afternoon, habrapeople!
The HGST company blog is back with you after a while. And today we would like to talk about the advantages of SAS solid-state drives over drives with a SATA interface.
The SAS device-to-device interface is designed for enterprise use and provides scalability, reliability, and high data availability, while SATA devices are optimized for lower-cost consumer applications.
Because drive manufacturers use the SAS interface for high-performance drives and the SATA interface for client drives and mass storage devices, solid-state drive (SSD) manufacturers largely continue to use the same partitioning. Enterprise-class SSDs with SATA interface are also now available in the market for high performance. However, by leveraging the SAS interface with more resilient flash devices, controllers, and firmware, we achieve a superior solution for workloads corporate level, such as online transaction processing (OLTP), high performance computing (HPC), database acceleration, data warehousing/data logging, virtualization and virtual desktop infrastructure, working with large volumes of data and hyperscale data, messaging and collaboration, interface with web servers, transmission of multimedia streams and provision of video on demand (VOD), cloud computing and data storage on a Tier-0 device for SAN and NAS networks.
With SAS interface features and industry-leading HGST technologies such as CellCare, PowerSafe and Data Path Protection, you benefit from:
Stable, high-performance SSD operation throughout its entire service life
Durability
Scalability
Operational reliability
High data availability
On-Device Data Manageability
Interaction with the system architecture being modernized
Workloads that enterprise-class SAS SSDs must support include:
Online processing transactions (OLTP)
High Performance Computing (HPC)
Database acceleration
Organization of data warehouses and storage of user data
Virtualization and virtual desktop infrastructure
Big Data and Hyperscale Data Analysis
Messaging programs and collaboration
Interface with web servers
Streaming media and video on demand (VOD)
Cloud computing
Tier-0 storage devices for SAN and NAS systems
SAS (Serial SCSI) and SATA (Serial ATA) - standard protocols transfer data between connected devices. They are designed to allow computers to communicate with peripheral devices such as controllers external memory and hard drives. Both interfaces (SAS and SATA) have a long history of development: they first appeared in the 1980s as parallel interfaces, and were converted to serial protocols about 10 years ago to further improve performance. When used with an external memory controller, the SAS or SATA interface can be used as an external interface to servers, as well as internal interface for connecting hard drives and SSDs. The controller can support many types of interfaces, but drives have only one type of interface - SAS or SATA. The interface does not depend on the storage medium (eg, flash memory, hard drive) or the quality of the components or firmware inside the disk. From this point of view, SAS and SATA interfaces behave the same.
Let's now look at the main parameters of drives
Performance
SCSI protocol. The SCSI protocol used by the SAS interface is faster and performs multiple, simultaneous I/O operations more efficiently than the Parallel ATA (SATA) command set.
Increase in data transfer speed - from 6 Gb/s to 12 Gb/s, and then up to 24 Gb/s. The SAS interface allows you to increase the data transfer speed from 6 Gb/s to 12 Gb/s; In addition, there is a clear roadmap for further increases in speed to 24 Gb/s. Currently, the SATA interface supports data transfer rates of up to 6 Gb/s, with no specific plans to increase the speed in the future.
Queues of tagged commands. Most SAS drives support a command queue depth of 128 (protocol limit is 65,536), which reduces latency and improves performance under high workloads. The hardware command queuing setting of the SATA interface only supports 32 commands.
Dual ports and multi-channel I/O. SAS drives have dual ports and support multiple initiators in the storage system; thus, multipath I/O and load balancing can improve performance. The SATA interface lacks support for multiple initiators, and most SATA drives do not have dual ports.
Full duplex data transmission. SAS drives support full-duplex mode (simultaneous data transfer in two directions), while SATA drives operate in half-duplex mode (data transfer in one direction).
Scalability
You can connect multiple drives to one port. The SAS interface supports a port expander of up to 255 devices (two-tier structure), so up to 65,635 drives can be connected to a single initiator port. SATA interface uses only point-to-point connection.
Use of extended cables. The use of SAS devices will provide a more convenient process for expanding the data center (data center), since they allow the use of passive copper cables up to 10 m long and optical cables up to 100 m long. SATA does not allow the use of cables longer than 2 meters.
Scalable performance. The performance of SAS SSDs in a RAID configuration is more scalable than SATA drives.
Compatible with SATA interface. SAS external memory controllers support SATA drives, allowing tiered storage using both SAS and SATA drives in a single array. However, SATA, in turn, does not support SAS drives.
High data availability
Dual ports for fault tolerance. SAS supports dual ports, while most SATA drives do not.
Several initiators. The SAS interface allows the connection of multiple controllers to a set of hard drives in a storage system, which ensures their rapid replacement and failover in case of failure. The SATA interface does not have such capabilities.
Hot connection. Disks with SAS and SATA interfaces can be connected in hot-swap mode.
Interaction with the system architecture being modernized
Roadmap for expansion functionality in future. Manufacturers of devices with a SAS interface plan to increase data transfer speeds to 24 Gb/s and probably even higher, while for SATA there is no such roadmap and the data transfer speed is limited to the current value of 6 Gb/s. By using SAS, enterprises can modernize their fleet of devices and move to more fast disks in the future while maintaining compatibility with previous versions, used in existing infrastructure.
SCSI. Because most enterprise drives use the SCSI command set, SAS remains compatible with multiple generations of storage systems.
HGST SSD drives are distinguished by high performance throughout the life of the disk. They use innovative technologies Advanced Flash Management and CellCare, providing exceptional high speed in sequential and random read/write mode. Solid-state drives are much faster than hard drives, although over time the flash memory cells wear out and their speed decreases, especially as the number of cycles of installing programs/removing files from the disk increases. HGST's Advanced Flash Management technology uses traditional wear-leveling algorithms, error detection and correction, bad block recovery, and data redundancy to improve service life, reliability, and SSD performance.
HGST CellCare is a patented flash memory controller technology that delivers enterprise-class durability, performance, and reliability in cost-effective, logic chips with high cell density for flash memory devices. CellCare technology dynamically monitors the parameters of memory cells as they wear out and uses predictive technologies to minimize wear on NAND flash memory chips by creating adaptive feedback between flash memory and controller. No less important aspect Cellcare technology is the ability to control the aging effect of flash memory and prevent the speed of SSD drives from decreasing as their service life increases. This feature of the unique Cellcare technology ensures trouble-free operation and high performance throughout the entire service life of the HGST SSD.
Now that the cost of data storage has increased significantly due to changes in exchange rates, the choice of IT infrastructure components requires creativity and compromise. In our opinion, repeatedly proven reliability and high performance throughout its service life should definitely be taken into account along with other factors. Indeed, in the medium and long term, such a decision will pay for itself in full.
In the next post we will continue talking about SSD drives and look at other benefits of HGST in this area.
