Network emulation tools in IP networks: test system infrastructure before deployment. (Connectivity).

Storage solutions based on Internet protocol (IP) network technology offer new options to solve the storage conundrum, but an undercurrent of concern exists around the impact of IP networks on system performance. How can if professionals be sure that these new technologies work in the real world before they deploy them into their infrastructures? How can the integrator and VAR community add value to end-user customers to lift the veil of fear, uncertainty, and doubt surrounding these new IP storage products and increase their adoption rate?

Understanding the drivers of storage performance and the limitations imposed by IP networks will help IT managers make smart decisions when designing their IF storage systems. But the only way to really assess the impacts of IP networks on storage performance is to test them using network emulation tools that allow users to recreate lifelike network conditions without the cost and hassle of procuring the network up-front.

IP Storage Applications

Internet Protocol (IP) storage is a reality. The wide acceptance of networked attached storage (NAS) demonstrates the viability of storage delivery over IP networks. Today, new protocols are enabling next-generation storage applications. For example, iFCP (Internet Fibre Channel protocol) and FCLP (Fibre Channel over LP) protocols are allowing companies with established Fibre Channel infrastructures to build bridges between their SAN islands using IP wide-area networks. These technologies have become increasingly important in today's environment as companies scramble to put reliable, affordable off-site backup and disaster recovery strategies in place. In addition, the imminent ratification of the iSCSI specification further broadens the horizon for IP storage to move beyond file-service and wide-area-networking applications into the core of networked storage systems with block-level storage services over

These new IP storage capabilities present if managers with a compelling business proposition: Leverage the TCP/IP skill sets of the current employee base and take advantage of the significant cost savings offered by mass-produced IP networking gear. Not only is there an order of magnitude difference in capital cost between Fibre Channel and IP technologies (I recently priced 1Gbit Fibre Channel HBAs in the $800 range while 1Ghit NIC cards cost less than $80 per unit) but the availability of management tools for IP networks far outstrip that of Fibre Channel, further enhancing the TCO of IP based storage networks.

Performance Drivers

Performance is a crucial issue for storage applications. Storage systems performance depends primarily on two system parameters: response time and throughput. Response time is the time between a host's data request and arrival of the first response bit to that host. Throughput is the steady rate of data flow between the storage system and the host.

Different applications have different performance requirements. For example, a database application performing numerous read/writes of small data blocks is more sensitive to response time, while less sensitive to throughput. Since the amount of data per request is relatively small, the server's maximum performance is limited by the amount of time it spends waiting for the data to return from the storage system.

Conversely, video-on-demand applications are less sensitive to response time, but more sensitive to throughput performance. For video-on-demand, the user may not care if it takes a second or two for the video to begin playing. However, once the video begins to play, any degradation of throughput would make the video jump and skip--severely reducing the viewers quality of experience.

Since requirements for different applications vary so widely, it's impossible to give a one-size-fits-all rule of thumb to help IT managers decide what route to take. Some applications have very stringent system performance requirements, while others can afford to use lower performance--and significantly lower cost systems.

Real-World IP Networks

IP networks can be nasty environments for storage applications. The structure of IP networks impact response time and throughput capabilities. IP is a best-effort delivery protocol; packets may be dropped, rerouted, reordered, duplicated, delayed, and even corrupted by bit errors. Other network effects, such as router congestion and bandwidth restriction further impact performance.

All of these network characteristics affect the response time and throughput of the system. Response time is dominated by latency, or delay in the network caused by distance (the speed of light), queuing delays, and dropped packets. The further apart the host and the server and the greater number of hops in the network, the more latency is introduced into the system, and the slower the system's response time.

Real-world network conditions also affect throughput. Throughput depends greatly on the transport protocol (layer 4) chosen to control traffic flow. The transmission control protocol (TCP) is a connection-oriented transport protocol. It establishes a connection dialogue between devices to insure that datagrams are received before continuing to transmit additional data. The dialogue consists of data packets flowing in one direction, and acknowledgement packets flowing back. As the TCP stack determines that the connection is good, it ratchets up the number of packets it sends before expecting an acknowledgement--thus increasing the throughput capability of the link. However, when the IP network drops packets, due to router congestion or other conditions, the receiving system doesn't send an acknowledgment. A time-out condition triggers the sender to retransmit the packet, the TCP stack slows down the rate at which it sends packets between acknowledgments and throughput falls off dramatically.

User datagram protocol (UDP) is another option for layer 4 transport. UDP is a connectionless transport protocol, which means that it does not establish a dialogue to insure that packets are being received before sending more data. UDP has significantly less overhead than TCP, and therefore can provide greater throughput than TCP. However, because it lacks the delivery guarantee, UDP relies on higher-level protocols to guarantee data integrity. It is best used on highly reliable LANs or for applications where some data loss minimally affects the system, such as streaming video applications.

How to Decide?

IT managers have many questions to answer regarding their IP storage solution. How far away can I put my disaster recovery site? What service level agreement do I need from my network provider? What transport protocol do I use? How many systems can I put on the same network? The list goes on and on.

With so many variables impacting storage system performance, it's very difficult to predict how systems will respond. Empirical testing is the best way to determine system performance, and how it changes under varying conditions.

Network emulation provides a mechanism to test IP storage infrastructure under real world conditions without the need to build out the actual network. Network emulators sit inline between storage devices and hosts to emulate all network conditions. The best make it easy for users to insert latency, packet jitter, packet loss, reorder, duplication, and corruption without affecting the wire-speed rate of the link. Other network impairments include simulating bandwidth restriction (simulating the effect of a gigabit line meeting a Fast Ethernet link) and reroute affects (the effect caused by a router link failure and TCP/IP resends packets over an alternate route).

While network emulators are useful in making decisions about how to configure local storage area networks, they are essential for pre-testing system performance across wide-area networks, where latency and network effects are multiplied.

Network Emulation in Action

The following example illustrates how a large system integrator used network emulation tools to alleviate customer concerns over IP storage and closed a large system sale. The customer, a large insurance company in the southwest, was investigating options for deploying a disaster recovery capability between two existing data centers, and a new, third disaster recovery location. The three locations were in different cities and thus required a wide area network implementation. The customer was very interested in Fibre Channel to IP bridging technology because of the relatively low cost of IP connectivity between the sites, but he was very concerned about the performance implications on his storage networks.

To alleviate customer concerns, the integrator deployed a set of network emulation gear to emulate the WAN. During the testing, the integrator and customer identified and eliminated several performance bottlenecks for the storage system--proving to the customer that the IP storage implementation would meet his requirements. Network emulation differentiated the integrator from his competition, made the customer comfortable with his solution and closed the sale.

Next-generation IP storage promises the benefits of Fibre Channel technology at the price point of P. While IP is widely accepted for NAS, some users are still concerned about the performance implications of P networks on their storage infrastructure.

Testing builds a customer's confidence that the solution will work as expected, and it avoids costly and embarrassing mistakes in sizing and provisioning the solution. By understanding key performance drivers and using network emulation tools to test their systems before deployment, the community will lift the veil of uncertainty and usher in the next wave in P--storage networks.

www.empirix.com

Garth Morrison is director of product marketing for IP storage at Empirix (Wilmington, Mass.)