With the advent of a sufficiently large number of Serial Attached SCSI (SAS) peripherals, we can state the beginning of the transition of the corporate environment to the rails of the new technology. But SAS is not only a recognized successor to UltraSCSI technology, but also opens up new areas of use, raising the scalability of systems downright to unthinkable heights. We decided to demonstrate the potential of SAS by taking a closer look at the technology, host adapters, hard drives, and storage systems.

SAS is not a completely new technology: it takes the best of both worlds. The first part of SAS is about serial communication, which requires less physical wires and pins. The transition from parallel to serial transmission made it possible to get rid of the bus. Although the current SAS specifications define throughput at 300 MB/s per port, which is less than 320 MB/s for UltraSCSI, replacing a shared bus with a point-to-point connection is a significant advantage. The second part of SAS is the SCSI protocol, which remains powerful and popular.

SAS can also use a large set types of RAID. Giants such as Adaptec or LSI Logic offer an advanced set of features for expansion, migration, nesting, and other features in their products, including distributed RAID arrays across multiple controllers and drives.

Finally, most of the actions mentioned today are already performed "on the fly". Here we should note excellent products AMCC/3Ware , Areca And Broadcom/Raidcore, which allowed the transfer of enterprise-class features to SATA spaces.

Compared to SATA, the traditional SCSI implementation is losing ground on all fronts except in high-end enterprise solutions. SATA offers suitable hard drives, has a good price and a wide range of decisions. And let's not forget about another "smart" feature of SAS: it easily gets along with existing SATA infrastructures, since SAS host adapters easily work with SATA drives. But the SAS drive cannot be connected to the SATA adapter.

Source: Adaptec.

First, it seems to us, we should turn to the history of SAS. The SCSI standard (stands for "small computer system interface") has always been regarded as a professional bus for connecting drives and some other devices to computers. Hard drives for servers and workstations still use SCSI technology. Unlike the mass ATA standard, which allows only two drives to be connected to one port, SCSI allows up to 15 devices to be connected on one bus and offers a powerful command protocol. Devices must have a unique SCSI ID, which can be assigned either manually or through the SCAM (SCSI Configuration Automatically) protocol. Since the bus IDs of two or more SCSI adapters may not be unique, Logical Unit Numbers (LUNs) have been added to help identify devices in complex SCSI environments.

SCSI hardware is more flexible and reliable than ATA (this standard is also called IDE, Integrated Drive Electronics). Devices can be connected both inside the computer and outside, and the cable length can be up to 12 m, if it is properly terminated (in order to avoid signal reflections). As SCSI has evolved, numerous standards have emerged that specify different bus widths, clock speeds, connectors, and signal voltages (Fast, Wide, Ultra, Ultra Wide, Ultra2, Ultra2 Wide, Ultra3, Ultra320 SCSI). Luckily, they all use the same set of commands.

Any SCSI communication is established between the initiator (host adapter) sending commands and the target drive responding to them. Immediately after receiving a set of commands, the target drive sends a so-called sense code (status: busy, error or free), by which the initiator will know whether he will receive the desired response or not.

The SCSI protocol specifies almost 60 different commands. They are divided into four categories: non-data, bi-directional, read data, and write data.

The limitations of SCSI start to show up when you add drives to the bus. Today it is hardly possible to find a hard drive that can fully load the 320 MB / s throughput of Ultra320 SCSI. But five or more drives on the same bus is another matter entirely. An option would be to add a second host adapter for load balancing, but this comes at a cost. Cables are also a problem: twisted 80-wire cables are very expensive. If you also want to get a "hot swap" of drives, that is, an easy replacement of a failed drive, then special equipment (backplane) is required.

Of course, it's best to place the drives in separate fixtures or modules, which are usually hot swappable along with other nice control features. As a result, there are more professional SCSI solutions on the market. But they all cost a lot, which is why the SATA standard has developed so rapidly in recent years. And although SATA will never meet the needs of high-end enterprise systems, this standard perfectly complements SAS in creating new scalable solutions for next-generation network environments.

SAS does not use a common bus for multiple devices. Source: Adaptec.

SATA

On the left is the SATA connector for data transfer. On the right is the power connector. There are enough pins to supply 3.3V, 5V, and 12V voltages to each SATA drive.

The SATA standard has been on the market for several years, and today it has reached its second generation. SATA I featured 1.5 Gb/s throughput with two serial connections using low-voltage differential signaling. The physical layer uses 8/10 bit encoding (10 actual bits for 8 bits of data), which accounts for the maximum interface throughput of 150 MB/s. After the transition of SATA to a speed of 300 MB / s, many began to call the new standard SATA II, although during standardization SATA-IO(International Organization) planned to add more features first and then call it SATA II. Hence the latest specification is called SATA 2.5, it includes SATA extensions such as Native Command Queuing(NCQ) and eSATA (external SATA), port multipliers (up to four drives per port), etc. But additional SATA features are optional for both the controller and the hard drive itself.

Let's hope that in 2007 SATA III at 600 MB / s will still be released.

Where parallel ATA (UltraATA) cables were limited to 46cm, SATA cables can be up to 1m long, and for eSATA twice that. Instead of 40 or 80 wires, serial transmission requires only a few pins. Therefore, SATA cables are very narrow, easy to route inside a computer case, and don't obstruct airflow as much. A single device relies on a SATA port, making it a point-to-point interface.

SATA connectors for data and power provide separate plugs.

SAS

The signaling protocol here is the same as that of SATA. Source: Adaptec.

A nice feature of Serial Attached SCSI is that the technology supports both SCSI and SATA, as a result of which SAS or SATA drives (or both standards) can be connected to SAS controllers. However, SAS drives cannot work with SATA controllers due to the use of the Serial SCSI Protocol (SSP). Like SATA, SAS follows the point-to-point connection principle for drives (300 MB/s today), and thanks to SAS expanders (or expanders, expanders), more drives can be connected than are available SAS ports. SAS hard drives support two ports, each with its own unique SAS ID, so you can use two physical connections to provide redundancy - connect the drive to two different hosts. Thanks to STP (SATA Tunneling Protocol), SAS controllers can communicate with SATA drives connected to the expander.

Source: Adaptec.

Source: Adaptec.

Source: Adaptec.

Of course, the only physical connection of the SAS expander to the host controller can be considered a "bottleneck", so wide SAS ports are provided in the standard. A wide port groups multiple SAS connections into a single link between any two SAS devices (usually between a host controller and an extender/expander). The number of connections within the connection can be increased, it all depends on the requirements imposed. But redundant connections are not supported, nor are any loops or rings allowed.

Source: Adaptec.

Future implementations of SAS will add 600 and 1200 MB/s bandwidth per port. Of course, the performance of hard drives will not increase in the same proportion, but it will be more convenient to use expanders on a small number of ports.

Devices called "Fan Out" and "Edge" are expanders. But only the main Fan Out expander can work with the SAS domain (see 4x connection in the center of the diagram). Up to 128 physical connections are allowed per Edge expander, and you can use wide ports and/or connect other expanders/drives. The topology can be quite complex, but at the same time flexible and powerful. Source: Adaptec.

Source: Adaptec.

The backplane is the basic building block of any storage system that needs to be hot pluggable. Therefore, SAS expanders often involve powerful rigs (both in a single case and not). Typically, a single link is used to connect a simple snap-in to a host adapter. Expanders with built-in snap-ins, of course, rely on multi-channel connections.

Three types of cables and connectors have been developed for SAS. SFF-8484 is a multicore internal cable that connects the host adapter to the equipment. In principle, the same can be achieved by branching this cable at one end into several separate SAS connectors (see illustration below). SFF-8482 is a connector through which the drive is connected to a single SAS interface. Finally, the SFF-8470 is an external multicore cable, up to six meters long.

Source: Adaptec.

SFF-8470 cable for external multilink SAS connections.

Multicore cable SFF-8484. Four SAS channels/ports pass through one connector.

SFF-8484 cable that allows you to connect four SATA drives.

SAS as part of SAN solutions

Why do we need all this information? Most users will not come close to the SAS topology we discussed above. But SAS is more than a next-generation interface for professional hard drives, although it is ideal for building simple and complex RAID arrays based on one or more RAID controllers. SAS is capable of more. This is a point-to-point serial interface that scales easily as you add more links between any two SAS devices. SAS drives come with two ports, so you can connect one port through an expander to a host system and then create a backup path to another host system (or another expander).

Communication between SAS adapters and expanders (as well as between two expanders) can be as wide as there are available SAS ports. Expanders are usually rackmount systems that can accommodate a large number of drives, and the possible connection of SAS to a higher device in the hierarchy (for example, a host controller) is limited only by the capabilities of the expander.

With a rich and functional infrastructure, SAS allows you to create complex storage topologies, rather than dedicated hard drives or separate network storage. In this case, "complicated" should not mean that it is difficult to work with such a topology. SAS configurations consist of simple disk rigs or use expanders. Any SAS link can be scaled up or down depending on bandwidth requirements. You can use both powerful SAS hard drives and high-capacity SATA models. Together with powerful RAID controllers, you can easily set up, expand or reconfigure data arrays - both in terms of the RAID level and the hardware side.

All of this becomes even more important when you consider how fast corporate storage is growing. Today everyone is talking about SAN - storage area network. It implies a decentralized organization of a data storage subsystem with traditional servers using physically remote storages. A slightly modified SCSI protocol is launched over existing Gigabit Ethernet or Fiber Channel networks, encapsulated in Ethernet packets (iSCSI - Internet SCSI). A system that runs from a single hard drive to complex nested RAID arrays becomes a so-called target (target) and is tied to an initiator (host system, initiator), which treats the target as if it were just a physical element.

iSCSI, of course, allows you to create a strategy for the development of storage, data organization or access control. We get another level of flexibility by removing storage directly attached to servers, allowing any storage subsystem to become an iSCSI target. Moving to remote storage makes the system independent of storage servers (a dangerous point of failure) and improves the manageability of the hardware. From a programmatic point of view, the storage is still "inside" the server. The iSCSI target and initiator can be nearby, on different floors, in different rooms or buildings - it all depends on the quality and speed of the IP connection between them. From this point of view, it is important to note that the SAN is not well suited to the requirements of online applications such as databases.

2.5" SAS hard drives

2.5" hard drives for the professional sector are still perceived as a novelty. We have been reviewing the first such drive from Seagate for quite some time - 2.5" Ultra320 Savvio who left a good impression. All 2.5" SCSI drives use a 10,000 rpm spindle speed, but they fall short of the performance levels of 3.5" hard drives with the same spindle speed. The fact is that the outer tracks of 3.5 "models rotate at a higher linear speed, which provides a higher data transfer rate.

The advantage of small hard drives lies not in capacity: today the maximum for them is still 73 GB, while in 3.5 "enterprise-class hard drives we already get 300 GB. In many areas, the ratio of performance to physical volume occupied is very important or power efficiency. The more hard drives you use, the more performance you reap - paired with the appropriate infrastructure, of course. At the same time, 2.5" hard drives consume almost half as much energy as 3.5" competitors. If we consider the ratio performance per watt (I/O operations per watt), the 2.5" form factor gives very good results.

If you need capacity above all, then 3.5" 10,000 rpm drives are unlikely to be the best choice. The fact is that 3.5" SATA hard drives provide 66% more capacity (500 instead of 300 GB per hard drive), leaving the performance level acceptable. Many hard drive manufacturers offer SATA models for 24/7 operation, and the price of drives has been reduced to a minimum. Reliability problems can be solved by purchasing spare (spare) drives for immediate replacement in the array.

The MAY line represents Fujitsu's current generation of 2.5" drives for the professional sector. The rotation speed is 10,025 rpm, and the capacities are 36.7 and 73.5 GB. All drives come with 8 MB cache and give an average read seek time 4.0 ms and 4.5 ms writes As we already mentioned, a nice feature of 2.5" hard drives is reduced power consumption. Usually one 2.5" hard drive saves at least 60% of energy compared to a 3.5" drive.

3.5" SAS hard drives

The MAX is Fujitsu's current line of high performance 15,000 rpm hard drives. So the name fits perfectly. Unlike 2.5" drives, here we get a whopping 16MB of cache and a short average seek time of 3.3ms for reads and 3.8ms for writes. Fujitsu offers 36.7GB, 73.4GB, and 146GB models. GB (with one, two and four plates).

Fluid dynamic bearings have made their way to enterprise-class hard drives, so the new models are significantly quieter than the previous ones at 15,000 rpm. Of course, such hard drives should be properly cooled, and the equipment provides this too.

Hitachi Global Storage Technologies also offers its own line of high performance solutions. The UltraStar 15K147 runs at 15,000 rpm and has a 16 MB cache, just like the Fujitsu drives, but the platter configuration is different. The 36.7 GB model uses two platters instead of one, while the 73.4 GB model uses three platters instead of two. This indicates a lower data density, but such a design, in fact, allows you to not use the inner, slowest areas of the plates. As a result, the heads have to move less, which gives a better average access time.

Hitachi also offers 36.7GB, 73.4GB, and 147GB models with a claimed seek (read) time of 3.7ms.

Although Maxtor has already become part of Seagate, the company's product lines are still preserved. The manufacturer offers 36, 73 and 147 GB models, all of which feature a 15,000 rpm spindle speed and 16 MB cache. The company claims an average seek time of 3.4ms for reads and 3.8ms for writes.

The Cheetah has long been associated with high performance hard drives. Seagate was able to instill a similar association with the release of the Barracuda in the desktop segment, offering the first 7200 RPM desktop drive in 2000.

Available in 36.7 GB, 73.4 GB and 146.8 GB models. All of them are distinguished by a spindle speed of 15,000 rpm and an 8 MB cache. The average seek time for reading is 3.5 ms and for writing 4.0 ms.

Host adapters

Unlike SATA controllers, SAS components can only be found on server-grade motherboards or as expansion cards for PCI-X or PCI Express. If we take it a step further and look at RAID controllers (Redundant Array of Inexpensive Drives), they are sold, for the most part, as individual cards due to their complexity. RAID cards contain not only the controller itself, but also a redundancy information calculation acceleration chip (XOR engine), as well as cache memory. A small amount of memory is sometimes soldered onto the card (most often 128 MB), but some cards allow you to expand the amount using a DIMM or SO-DIMM.

When choosing a host adapter or RAID controller, you should clearly define what you need. The range of new devices is growing just before our eyes. Simple multiport host adapters will cost relatively little, while powerful RAID cards will cost a lot. Consider where you will place your drives: external storage requires at least one external slot. Rack servers typically require low profile cards.

If you need RAID, then decide whether you will use hardware acceleration. Some RAID cards take CPU resources for XOR calculations for RAID 5 or 6 arrays; others use their own XOR hardware engine. RAID acceleration is recommended for environments where the server does more than store data, such as databases or web servers.

All of the host adapter cards that we cited in our article support 300 MB/s per SAS port and allow for very flexible implementation of the storage infrastructure. Today, few people will be surprised by external ports, and take into account the support for both SAS and SATA hard drives. All three cards use the PCI-X interface, but PCI Express versions are already in development.

In our article, we paid attention to cards with eight ports, but the number of connected hard drives is not limited to this. With the help of a SAS expander (external), you can connect any storage. As long as a 4-lane connection is sufficient, you can increase the number of hard drives up to 122. Due to the performance cost of calculating the RAID 5 or RAID 6 parity information, typical external RAID storages will not be able to load the quad-lane bandwidth enough, even if a large number of drives are used.

48300 is a SAS host adapter designed for the PCI-X bus. The server market today continues to be dominated by PCI-X, although more and more motherboards are equipped with PCI Express interfaces.

The Adaptec SAS 48300 uses a PCI-X interface at 133 MHz, giving a throughput of 1.06 GB/s. Fast enough if the PCI-X bus is not loaded with other devices. If you include a lower speed device in the bus, then all other PCI-X cards will reduce their speed to the same. For this purpose, several PCI-X controllers are sometimes installed on the board.

Adaptec is positioning the SAS 4800 for midrange and low end servers and workstations. The suggested retail price is $360, which is quite reasonable. The Adaptec HostRAID feature is supported, allowing you to upgrade to the simplest RAID arrays. In this case, these are RAID levels 0, 1, and 10. The card supports an external four-channel SFF8470 connection, as well as an internal SFF8484 connector paired with a cable for four SAS devices, that is, we get eight ports in total.

The card fits into a 2U rack server when a low-profile slot cover is installed. The package also includes a CD with a driver, a quick installation guide, and an internal SAS cable through which up to four system drives can be connected to the card.

SAS player LSI Logic sent us a SAS3442X PCI-X host adapter, a direct competitor to the Adaptec SAS 48300. It comes with eight SAS ports that are split between two quad-lane interfaces. The "heart" of the card is the LSI SAS1068 chip. One of the interfaces is intended for internal devices, the second - for external DAS (Direct Attached Storage). The board uses the PCI-X 133 bus interface.

As usual, 300 MB/s interface is supported for SATA and SAS drives. There are 16 LEDs on the controller board. Eight of them are simple activity LEDs, and eight more are designed to report a system malfunction.

The LSI SAS3442X is a low profile card, so it fits easily into any 2U rack server.

Note driver support for Linux, Netware 5.1 and 6, Windows 2000 and Server 2003 (x64), Windows XP (x64) and Solaris up to 2.10. Unlike Adaptec, LSI chose not to add support for any RAID modes.

RAID adapters

SAS RAID4800SAS is Adaptec's solution for more complex SAS environments and can be used for application servers, streaming servers, and more. Before us, again, is an eight-port card, with one external four-lane SAS connection and two internal four-lane interfaces. But if an external connection is used, then only one four-channel interface remains from the internal ones.

The card is also designed for the PCI-X 133 bus, which provides sufficient bandwidth for even the most demanding RAID configurations.

As far as RAID modes are concerned, the SAS RAID 4800 easily overtakes its "younger brother": RAID levels 0, 1, 10, 5, 50 are supported by default if you have enough drives. Unlike the 48300, Adaptec has invested two SAS cables so you can connect eight hard drives to the controller right away. Unlike the 48300, the card requires a full-size PCI-X slot.

If you decide to upgrade your card to Adaptec Advanced Data Protection Suite, you'll be able to upgrade to double redundant RAID modes (6, 60), as well as a range of enterprise-class features: striped mirror drive (RAID 1E), hot spacing (RAID 5EE), and copyback hot spare. The Adaptec Storage Manager utility has a browser-like interface and can be used to manage all Adaptec adapters.

Adaptec provides drivers for Windows Server 2003 (and x64), Windows 2000 Server, Windows XP (x64), Novell Netware, Red Hat Enterprise Linux 3 and 4, SuSe Linux Enterprise Server 8 and 9, and FreeBSD.

SAS snap-ins

The 335SAS is a four-drive SAS or SATA drive accessory, but must be connected to a SAS controller. Thanks to the 120mm fan, the drives will be well cooled. You will also need to connect two Molex power plugs to the equipment.

Adaptec has included an I2C cable that can be used to control the rig via an appropriate controller. But with SAS drives, this will no longer work. An additional LED cable is designed to signal the activity of the drives, but, again, only for SATA drives. The package also includes an internal SAS cable for four drives, so an external four-channel cable will be enough to connect the drives. If you want to use SATA drives, you will have to use SAS to SATA adapters.

The retail price of $369 is not cheap. But you will get a solid and reliable solution.

SAS storage

SANbloc S50 is a 12-drive enterprise-class solution. You will receive a 2U rackmount enclosure that connects to SAS controllers. This is one of the best examples of scalable SAS solutions. The 12 drives can be either SAS or SATA. Or represent a mixture of both types. The built-in expander can use one or two quad-lane SAS interfaces to connect the S50 to a host adapter or RAID controller. Since we have a clearly professional solution, it is equipped with two power supplies (with redundancy).

If you have already purchased an Adaptec SAS host adapter, you can easily connect it to the S50 and manage drives using the Adaptec Storage Manager. If you install 500 GB SATA hard drives, then we get 6 TB of storage. If we take 300 GB SAS drives, then the capacity will be 3.6 TB. Since the expander is connected to the host controller by two four-lane interfaces, we will get a throughput of 2.4 GB / s, which will be more than enough for an array of any type. If you install 12 drives in a RAID0 array, then the maximum throughput will be only 1.1 GB / s. In the middle of this year, Adaptec promises to release a slightly modified version with two independent SAS I/O blocks.

SANbloc S50 contains the function of automatic monitoring and automatic control of fan speed. Yes, the device is too loud, so we were relieved to return it from the lab after the tests were completed. A drive failure message is sent to the controller via SES-2 (SCSI Enclosure Services) or via the physical I2C interface.

Operating temperatures for actuators are 5-55°C, and for accessories - from 0 to 40°C.

At the start of our tests, we got a peak throughput of just 610 MB/s. By changing the cable between the S50 and the Adaptec host controller, we were still able to reach 760 MB / s. We used seven hard drives to load the system in RAID 0 mode. Increasing the number of hard drives did not lead to an increase in throughput.

Test configuration

In this article, we'll look into the future of SCSI and look at some of the advantages and disadvantages of SCSI, SAS, and SATA interfaces.

In fact, the issue is a bit more complex than just replacing SCSI with SATA and SAS. Traditional parallel SCSI is a tried and tested interface that has been around for a long time. Currently, SCSI offers a very fast data transfer rate of 320 Megabytes per second (Mbps) using the modern Ultra320 SCSI interface. In addition, SCSI offers a wide range of features, including Command-Tag Queuing (a method of optimizing I/O commands to increase performance). SCSI hard drives are reliable; in a short distance, you can create a daisy chain of 15 devices connected to a SCSI link. These features make SCSI an excellent choice for high performance desktops and workstations, up to and including enterprise servers, to this day.

SAS hard drives use the SCSI command set and have the same reliability and performance as SCSI drives, but use a serial version of the SCSI interface at 300 Mbps. While slightly slower than 320 Mbps SCSI, the SAS interface is capable of supporting up to 128 devices over longer distances than the Ultra320 and can expand to 16,000 devices per channel. SAS hard drives offer the same reliability and rotation speeds (10000-15000) as SCSI drives.

SATA drives are a little different. Where SCSI and SAS drives focus on performance and reliability, SATA drives sacrifice them in favor of massive capacity increases and cost reductions. For example, a SATA drive has now reached a capacity of 1 terabyte (TB). SATA is used where maximum capacity is needed, such as data backup or archiving. SATA now offers point-to-point connections at speeds up to 300 Mbps, and easily outperforms the traditional parallel ATA interface at 150 Mbps.

So what will happen to SCSI? It works great. The problem with traditional SCSI is that it's just coming to the end of its useful life. Parallel SCSI at 320 Mb/s will not run much faster on current SCSI cable lengths. In comparison, SATA drives will reach 600 Mb/s in the near future, SAS have plans to reach 1200 Mb/s. SATA drives can also work with the SAS interface, so these drives can be used simultaneously in some storage systems. The potential for increased scalability and data transfer performance far exceeds that of SCSI. But SCSI isn't going away anytime soon. We will see SCSI in small and medium servers for a few more years. As hardware upgrades, SCSI will be systematically replaced by SAS/SATA drives to get faster and more convenient connections.

This article aims to explain the difference between hard drive types and help you make the right choice when buying a dedicated server.

SATA - Serial ATA

Currently, SATA drives are used on most personal computers in the world and on budget server hardware configurations. Compared to SAS and SSD drives, the read and write speed of SATA drives is noticeably lower, but they are chosen because of the large amount of information stored.

SATA drives are well suited for game servers that do not require frequent writing and reading information. It is also advisable to use SATA disks for the following purposes:

• streaming operations, such as video encoding;
• data warehouses;
• backup systems;
• voluminous, but not loaded file servers.

SAS - Serial Attached SCSI

SAS drives are designed from the ground up with enterprise and industrial workloads in mind, which has a positive effect on their performance. The rotation speed of SAS drives is twice as fast as that of SATA, so they should be chosen for tasks that are speed sensitive and require multi-threaded access. Also, SAS drives (unlike SSDs) can provide reliable and repeatable overwriting of data.

For hosting, SAS drives will be optimal, as they can provide high reliability of data storage. In addition, SAS hard drives are well suited for the following tasks:

• database management systems (DBMS);
• WEB servers with high load;
• distributed systems;
• systems that process a large number of requests - terminal servers, 1C servers.

The only drawback of SAS drives (like SSDs) is their small volume and high price.

SSD - Solid State Drive

Recently, SSDs have become more and more popular. An SSD does not use magnetic disks for recording, but contains only non-volatile memory chips, similar to those used in USB flash drives.

SSD drives have no moving parts, which ensures high mechanical strength, reduced power consumption and high speed. At the moment, SSD drives provide the highest possible read and write speed, which allows them to be used for any high-load projects.

The main disadvantage of SSD drives is that they are limited in the amount of information that can be rewritten to the drive. Accordingly, if your system overwrites more than 20 GB of data per day, be prepared to change the SSD drive after a while. By the way, the price of such disks is higher than that of both of the above types.

Many modern CMS when generating a page often require simultaneous access to several files on disk. It is for working with such systems that SSD drives are the ideal choice. Using SSD drives for busy sites is a guarantee that you will get the maximum data reading speed.

Why SAS?

The Serial Attached SCSI interface is not just a serial implementation of the SCSI protocol. It does a lot more than just porting SCSI features like TCQ (Tagged Command Queuing) over the new connector. If we wanted the most simplicity, then we would use the Serial ATA (SATA) interface, which is a simple point-to-point connection between a host and an end device such as a hard drive.

But SAS is based on an object model that defines a "SAS domain" - a data delivery system that can include optional expanders and SAS end devices, such as hard drives and host adapters (host bus adapters, HBA). In contrast From SATA, SAS devices can have multiple ports, each of which can use multiple physical connections to provide faster (wider) SAS connections, multiple initiators can access any given target, and cable lengths can be up to eight meters ( for the first generation of SAS) versus one meter for SATA. It is clear that this provides many opportunities for creating high-performance or redundant storage solutions. In addition, SAS supports the SATA Tunneling Protocol (STP), which allows you to connect SATA devices to the SAS controller.

The second generation SAS standard increases the connection speed from 3 to 6 Gb / s. This speed boost is very important for complex environments where high performance is required due to high-speed storage. The new version of SAS also aims to reduce the complexity of cabling as well as the number of connections per Gb/s throughput by increasing the possible length of cables and improving the performance of expanders (zoning and auto-discovery). Below we will talk about these changes in detail.

SAS Speed ​​Up to 6 Gb/s

To bring the benefits of SAS to a wider audience, the SCSI Trade Association (SCSI TA) presented a tutorial on SAS technology at the Storage Networking World Conference earlier this year in Orlando, Florida, USA. The so-called SAS Plugfest, which demonstrated 6Gb/s SAS operation, compatibility and features, took place even earlier in November 2008. LSI and Seagate were the first to introduce 6Gb/s SAS-capable hardware on the market, but other vendors should catch up soon as well. In our article, we'll take a look at the current state of SAS technology and some new devices.

Functions and basics of SAS

Fundamentals of SAS

Unlike SATA, the SAS interface operates on a full duplex basis, providing full bandwidth in both directions. As mentioned earlier, SAS connections are always established over physical connections using unique device addresses. In contrast, SATA can only address port numbers.

Each SAS address can contain multiple Physical Layer (PHY) interfaces, allowing for wider connections via InfiniBand (SFF-8470) or mini-SAS cables (SFF-8087 and -8088). Typically, four SAS interfaces with one PHY each are combined into one wide SAS interface that is already connected to the SAS device. Communication can also occur through expanders, which act more like switches than SAS devices.

Features such as zoning now allow administrators to associate specific SAS devices with initiators. This is where the increased throughput of 6Gb/s SAS will come in handy, as a quad-lane connection will now have twice the speed. Finally, SAS devices can even have multiple SAS addresses. Since SAS drives can use two ports, with one PHY on each, the drive can have two SAS addresses.

Connections and interfaces

Click on the picture to enlarge.

SAS connections are addressed through SAS ports using SSP (Serial SCSI Protocol), but communication at the bottom layer from PHY to PHY is done using one or more physical connections for bandwidth reasons. SAS uses 8/10 bit encoding to convert 8 bits of data into 10 character transmissions for the purposes of timing recovery, DC balance, and error detection. This results in an effective throughput of 300 MB/s for 3 Gb/s transfer mode and 600 MB/s for 6 Gb/s connections. Fiber Channel, Gigabit Ethernet, FireWire and others work in a similar coding scheme.

SAS and SATA power and data interfaces are very similar to each other. But if SAS has data and power interfaces combined into one physical interface (SFF-8482 on the device side), then SATA requires two separate cables. The gap between the power and data pins (see illustration above) is closed in the case of SAS, which does not allow connecting a SAS device to a SATA controller.

On the other hand, SATA devices can work fine on a SAS infrastructure thanks to STP, or in native mode if expanders are not used. STP adds additional latency to expanders as they need to establish a connection, which is slower than a direct SATA connection. However, the delays are still very small.

Domains, expanders

SAS domains can be represented as tree structures similar to complex Ethernet networks. SAS expanders can work with a large number of SAS devices, but they use the principle of circuit switching, rather than the more common packet switching. Some expanders contain SAS devices, others do not.

SAS 1.1 recognizes edge expanders, which allow a SAS initiator to communicate with up to 128 additional SAS addresses. In a SAS 1.1 domain, only two edge expanders can be used. However, a single fanout expander can connect up to 128 edge expanders, greatly increasing the infrastructure capacity of your SAS solution.

Click on the picture to enlarge.

Compared to SATA, the SAS interface can seem complicated: different initiators access the target devices through expanders, which involves laying the appropriate routes. SAS 2.0 simplifies and improves routing.

Keep in mind that SAS does not allow loops or multiple paths. All connections must be point-to-point and exclusive, but the connection architecture itself scales well.

New SAS 2.0 Features: Expanders, Performance

Expander zones and automatic configuration

Boundary (edge) and expanding (fanout) expanders practically remained in history. This is often attributed to updates in SAS 2.0, but the reason is actually the SAS zones introduced in 2.0, which remove the separation between edge and extension expanders. Of course, zones are usually implemented specifically for each manufacturer, and not as a single industry standard.

In fact, now several zones can be located on one information delivery infrastructure. This means that different initiators can access storage targets (storages) through the same SAS expander. Domain segmentation is done through zones, access is done in an exclusive way.

In modern computer systems, SATA and SAS interfaces are used to connect the 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 size makes users wonder how SAS differs from SATA and look for compromises. Let's see if this makes sense.

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) is a serial data exchange interface based on parallel PATA (IDE). It is used in home, office, multimedia PCs and laptops.

If we talk about HDD, then, despite the different technical characteristics and connectors, there are no cardinal differences between the devices. Backward one-way compatibility makes it possible to connect disks to the server board using both one and the second interface.

It is worth noting that both connection options are also real 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 dozens of times more expensive with a comparable volume. Therefore, today such a solution, if not rare, is sufficiently balanced, and is intended for fast corporate-level data centers.

Comparison

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

Directly for HDD, the speed of access is determined primarily by the speed of rotation of the spindle. 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 (except to look at the WD VelociRaptor series, again designed for workstations), and anything higher is absolutely unattainable. SAS HDD spins 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 corrupted, which leads to bad sectors.

The main advantage of SAS also works for the fault tolerance of the system - two duplex ports that allow 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 insure each other and share the load). The queue of tagged 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 assumes the use of cables up to 10 m long. Up to 255 devices can be connected to one port through expanders. SATA is limited to 1m (2m for eSATA), and only supports point-to-point connection of one device.

Prospects for further development - what is the difference between SAS and SATA is also felt quite sharply. The bandwidth of the SAS interface reaches 12 Gb / s, and manufacturers announce support for data transfer rates of 24 Gb / s. The latest revision of SATA stopped at 6 Gb / 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 access to data is not critical, and the amount of stored information is large, it is advisable to use them.

table