The Emergence of Local Instance Networking (LIN)

Putting an end to the Centralized vs. Distributed Server Debate

BACKGROUND

As enterprises grow in size, and enterprise applications become more critical to business operations, CIOs are faced with a design dilemma: should branch offi ce infrastructure be centralized or distributed?

In a distributed implementation, email servers, fi le servers and databases are placed locally within each branch location. While this typically provides the best possible performance to end users, it results in “server sprawl”, which can be costly to implement and creates a variety of management, security, and compliance challenges.

The alternative is to consolidate server infrastructure into a select number of data centers, which enables all maintenance, troubleshooting, security policy enforcement, backups and auditing to be performed centrally. While this solves most of the challenges associated with server sprawl, it does not address one of the most important ones – performance. Most applications simply do not perform well over a wide area network (WAN) due to bandwidth and latency constraints.

Given the compelling arguments for server centralization, various solutions have emerged to try and improve application performance over enterprise WANs. “WAN optimization” products leverage compression and Quality of Service (QoS) techniques to maximize bandwidth utilization and prioritize enterprise traffi c; “application acceleration” products employ application-specifi c caching and latency mitigation tools to improve performance on an application-by-application basis. While both generations of products have benefi ts, neither addresses the full set of challenges facing enterprise IT staff – from cost and performance to security and management.

A breakthrough approach is required to solve existing performance and scale limitations, while preserving application transparency. This is accomplished with “Local Instance Networking,” the fi rst technology that provides all of the benefi ts of a centralized approach, without compromising performance. LIN is the fi rst network technology to improve application delivery while settling the centralized versus distributed debate.

1ST GENERATION: WAN OPTIMIZATION

WAN optimization products are most often deployed as bandwidth “band-aids”, providing short term benefi ts on congested WAN links where it is infeasible or too expensive to buy additional bandwidth. Although each vendor has their own proprietary implementations, WAN optimization solutions rely on two underlying technologies: compression and Quality of Service (QoS).

COMPRESSION
Compression is used to reduce the bandwidth consumed by traffi c traversing the WAN. “Payload” compression uses algorithms to identify relatively short byte sequences that are repeated frequently over time. These sequences are then replaced with shorter segments of code to reduce the size of transmitted data. Simple algorithms can fi nd repeated bytes within a single packet; more sophisticated algorithms can fi nd duplication across packets and even across fl ows. “Header” compression can provide additional bandwidth gains by reducing packet header information using specialized compression algorithms.

The gains realized by compression techniques vary depending on the mix of traffic traversing the WAN. Text and spreadsheets, for example, are easy to compress, so they typically yield 2-5x performance gains. On the other hand, pre-compressed content, like zip fi les, cannot be compressed much further. On average, most enterprises deploying compression technology will see around a 50% improvement in WAN utilization, which is the equivalent of doubling the effective WAN bandwidth. This is often not enough performance improvement to justify the additional hardware expenditure and operating costs.


QoS
In an effort to maximize WAN utilization, most enterprises will oversubscribe their network. When demand exceeds the capacity of a WAN link, and all traffi c is contending for the same limited resource, less important traffi c (such as web browsing ) may take bandwidth away from business-critical applications. To prevent this, most 1st generation WAN optimization solutions implement Quality of Service techniques to classify and prioritize traffi c based on applications, users, and other criteria.

By using a combination of compression and QoS techniques, 1st generation WAN optimization products enable enterprises to get more out of their congested WAN links. In some instances, this saves money by delaying the purchase of additional bandwidth. However, this is often a short term gain. It also does not address latency issues across the WAN, which has a signifi cant impact on application performance. In addition, even if a 512 Kbps WAN link or an E1/T1 is doubled, for example, this is still a far cry from the 100 Mbps that is available to when applications are access via a LAN. As a result, these techniques do not do much to mitigate or contain server sprawl.

It is important to note, however, that while compression and QoS are not suffi cient on their own for enterprise-wide application delivery, they are essential components of newer, more comprehensive application acceleration solutions, such as Local Instance Networking (described below). For instance, Silver Peak NX Series appliances include state of the art, cross-fl ow data compression and header compression as part of a broader Local Instance Networking solution. In addition, the Silver Peak solution maximizes WAN bandwidth utilization through advanced queuing and scheduling, as well as per application policy based decisions and application tagging.

2ND GENERATION:APPLICATION ACCELERATION

A second generation of products emerged to address some of the shortcomings of WAN optimization solutions. These “application acceleration” solutions can provide signifi cant improvements by optimizing the performance of specifi c applications. However, the tradeoff is ease of use, manageability, and long term interoperability. There are two broad techniques used for application acceleration: application proxies/ caches and latency compensation.

Application Proxies and Caches
Application proxies are used to locally simulate an application server, enabling specifi c content to be delivery locally with LAN-like performance. One example of a “proxy” type device is the web cache, which stores local copies of requested web pages so that subsequent requests for the same URL could be serviced from the local appliance disk rather than from the remote web server. This technique provides a reasonable boost for static content. However, it does not work well for dynamic content or applications that require up-todate information. Unfortunately, as most enterprise applications have been webifi ed, and web content is expected to be very dynamic in nature, web caches have reached a roadblock in terms of overall effectiveness.

More recently, similar proxy approaches have been extended to fi le services. Wide Area File Services (WAFS) emerged as a way of implementing proxy fi le servers in distributed offi ces. By confi guring clients to point to a WAFS share, the proxy fi le server can make remote content appear local. These devices terminate CIFS sessions, and then examine requests to see if the requested fi lename can be delivered locally. To achieve this, WAFS servers must replicate fi le locking semantics.

Although WAFS offers a number of specialized features, like the ability to authenticate users and read and write fi les even when the data center is unreachable (e.g., due to a network event), they create an enormous management burden. The branch offi ce, in effect, is supporting a full blown fi le server. This requires user and password updates and can lead to coherency issues when multiple versions of the “same” fi le exist in the network at the same time. In addition, they must be constantly updated to support the latest changes to fi le system protocols. As a result, rather than simplifying the branch offi ce, these approaches can actually make things more complicated by introducing another vendor’s implementation of a file system.

 If performance gains are to be achieved across all applications, WAFS and web caches have to be implemented in conjunction with other application-specifi c acceleration tools. In addition to being cost prohibitive, this is not scalable, as the applications themselves frequently undergo changes that require signifi cant modifi cation to those products that are used to accelerate them. This dynamic has already been witnessed in the email space, where a variety of MS Exchange acceleration products were rendered obsolete when Microsoft moved from Exchange 2000 to Exchange/Outlook 2003. Many enterprises are understandably wary of deploying application-specific acceleration solutions.

Latency Compensation
An alternative approach to application acceleration is to reduce the amount of latency created by underlying protocols, like TCP. Latency results when “chatty” protocols communicate frequently with a server, and are required to stop and wait for a response before the next step can proceed. The more steps, the longer the end user’s perceived response time.

Applications can be accelerated by eliminating or mitigating this chatty “stop and wait” behavior. In the case of TCP, standard techniques to achieve this have been around for years. “Window scaling”, for example, prevents bandwidth from being limited by TCP’s standard 64KB window size. “Selective acknowledgement” makes for effi cient recovery from sporadic loss events which can severely impact effi ciency on longer links. More recent TCP enhancements include optimizations for fi lling larger pipes, more aggressive behavior pertaining to window sizes, and improved Round Trip Time (RTT) monitoring. Fortunately, these techniques are well understood and are being incorporated into more and more networking devices, as well as clients and servers.

While these latency mitigation techniques are transparent at the application level, they still require termination and re-injection of TCP streams. Theoretically this should not be an issue. However, in practice, this can be problematic, because routing is often asymmetric - packets can take different inbound and outbound paths when communicating between different locations. In fact, in some load balancing scenarios, even traffi c fl owing in the same direction may not follow the same route. If both sides of a fl ow do not go through the same application acceleration device, TCP reassembly and re-injection will not work. This can make it complicated (and costly) to design and implement these type of solutions.

While 2nd generation application acceleration devices provide some very enticing performance gains for specifi c applications, deployment is often limited by several concerns:

• Lack of breadth – application proxies are focused on single, very specifi c applications.
• Lack of guaranteed compatibility – application acceleration solutions must keep pace with changes in the applications themselves.
• Lack of 100% coherency –caches often have diffi culty ensuring that only updated data is delivered; WAFS requires a duplication of fi le and record locking to ensure coherency.
• Diffi cult to deploy – these solutions require modifi cation to the applications, and often changes to the clients themselves.
Moreover, they do not always work in all enterprise environments, such as those deploying asymmetric routing.

Fortunately, some of the latency compensation techniques that operate at the protocol level can provide non-intrusive benefi ts. These are leveraged by the Silver Peak solution.

For example, Silver Peak NX Series appliances perform latency mitigation for TCP and CIFS in a “single sided” or “as-needed” basis. The Silver Peak NX Series appliance at a branch offi ce can terminate TCP fl ows and provide latency mitigation independent of the age and confi guration of the client stack. Silver Peak NX Series appliances can actively negotiate with application front ends (AFE) and data center servers to negotiate the most appropriate TCP options on behalf of the client. (If the data center cannot support advanced TCP options, the Silver Peak NX Series appliance in the data center appliance can implement these TCP extensions on its behalf.) The Silver Peak solution avoids unnecessary termination of TCP sessions on the data center side, reducing application latency, simplifying deployment, and increasing head-end scale.

3RD GENERATION:LOCAL INSTANCE NETWORKING

Local Instance Networking is the newest approach to application delivery. In addition to accelerating application performance, it addresses server sprawl by providing a viable mechanism for centralizing branch offi ce infrastructure while localizing information delivery.

Local Instance Networking inspects all WAN traffi c and stores a local instance of information in an application independent data store at each enterprise location. The local instance is transparently populated based on day-to-day usage, containing a subset of the enterprises working data set that is most relevant to each location. Each piece of information is stored only once per location, enabling an appropriately sized LIN appliance to hold weeks worth of data.

Local Instance Networking appliances examine outbound packets to see if a match exists in the local instance at the destination location. If a match exists, then the repetitive information is not sent across the WAN and instructions are sent to deliver the data locally. If the data has been modifi ed, only the delta is transmitted across the WAN, maximizing bandwidth utilization and application performance.

In a LIN implementation, all authentication, authorization, fi le and record locking is performed centrally by the native applications. This ensures 100% application coherency and future compatibility with new version of applications. By working at the network (or packet) level, a Local instance Network transparently supports all enterprise applications and transport methods, allowing for exceptionally simple deployments that provide immediate improvements to a wide variety of enterprise applications.

THE SILVER PEAK SOLUTION

Silver Peak is the fi rst vendor to leverage LIN technology to deliver an enterprisegrade solution for branch offi ce infrastructure centralization. The Silver Peak solution leverage the following innovative technology components:

Network memory™ – the cornerstone of the Silver Peak solution. Network Memory™ uses advanced fi ngerprinting technology to examine data prior to it being sent across a WAN. If these fi ngerprints match data that is stored in a local instance at the destination location, the information will not be sent across the WAN. Instead, instructions are sent to deliver the data locally.

Network Memory™ reduces the amount of information that is traversing a WAN by orders of magnitude and enables information to be delivered with LAN-like performance. As a result, it is an extremely effective tool when delivering an application across a distributed enterprise.

Compression: The Silver Peak solution supports advanced cross-fl ow payload and header compression. Cross-fl ow payload compression ensures that the transmission of data across the WAN is as effi cient as possible by eliminating redundant information. Header compression drastically reduces the overhead inherent to fl ows of small packets, as is the case with Voice over IP.

QoS: Silver Peak NX Series appliances supports a variety of QoS techniques, including advanced queuing and scheduling, as well as per application policy based decision–making and application tagging. Silver Peak’s advanced QoS capabilities enable enterprises to deploy and prioritize a wide variety of business critical applications, ensuring that each gets the network resources it needs.

Latency and loss mitigation –
The Silver Peak solution uses protocol acceleration techniques, such as window and transaction size adjustment to compensate for poor performance on high latency links. Moreover, the Silver Peak solution employs adaptive Forward Error Correction, which adds a small amount of redundant information to the payload so that errors can be easily corrected at the destination with minimal impact on performance. Silver Peak dynamically adjusts the FEC overhead in response to changing link conditions for maximum effectiveness in “lossy” environments.

Data security – Silver Peak NX Series appliances protect all locally-stored and transmitted information from physical and network-level security breaches using the 128-bit Advanced Encryption Standard (AES) and IPsec tunneling. Data encryption is done in hardware on the NX Series appliances.

Silver Peak offers the only networking solution to deliver the performance of distributed servers, without the cost and complexity. By operating at the network layer, it is completely transparent to all transport protocol (e.g., TCP, UDP, etc), and provides signifi cant benefi ts to all enterprise applications. By localizing information, yet centralizing management and control of branch offi ce infrastructure, Silver Peak is putting an end to server sprawl - and the management, security, cost, and compliance headaches that accompany it.

Bizi Arayın; Uzman kadromuz güvenlik taraması yapsın. Güvenlik konusunda risklerinizi belirlesin. Daha iyi bir güvenlik politikası için önerilerde bulunsun. Bize; +90 (216) 550 80 20 - 21 nolu telefondan arayarak yada, guvenlik@vedius.com adresine mail atarak ulaşabilirsiniz.

yada; Formu doldurun biz sizi arayalım Ad Soyad :   Firma/Görev :   Telefon :   E-posta :