Optimization & Acceleration
WAN optimization and next-generation QoS guarantee performance while using application acceleration to maximize responsiveness.
Ipanema's approach to WAN optimization combines the latest in application acceleration with deep application and network performance visibility and unique global and dynamic QoS. All are tightly coupled into the patented Autonomic Networking architecture of the Ipanema System. The result can be shown to be truly optimal – meaning the best application performance at the lowest cost. This is in contrast to competitors that tout their products as WAN Optimization Controllers (WOCs) but have not built-in any feedback loops to ensure that their products are actually benefitting end-users. There cannot be real WAN optimization without integrated measurement of results and automatically coordinated responses to constantly shifting user demand. It takes the Ipanema System's Autonomic Networking to realize true application performance improvement and guarantee it in this way – isolated controllers cannot manage it using only application acceleration.
This section explains how Ipanema's approach to WAN optimization, next-generation QoS and application acceleration:
Define application performance objectives per-user and enforces them globally over the WAN
The Ipanema System's unique ability to guarantee application performance comes from its application performance objective-based approach to WAN optimization, application acceleration and next-generation QoS. Unlike any other solution on the market, no local device configuration is required to manage the traffic. The objectives are defined in the central management software, which then communicates them to the ip|engines.
The ip|engines cooperate with each other to form a fully distributed system under the control of the global objectives. In this system there is no single point of failure; if the central management server goes down, the system continues to function correctly on the network. This differs from traditional approaches that try to manually configure how traffic should be managed device-by-device, hoping that good application performance will be the end result. With Ipanema, enterprises need only to define which applications matter the most for them by their relative criticalities to the business. A higher criticality is set for more important applications, for which the business needs guaranteed performance. A low criticality does not mean that the application does not matter for the business. It simply means that when demand for resources is high, the business can tolerate that the application receives fewer resources- Ipanema’s WAN optimization, application acceleration and next-generation QoS at work.
Applications are defined in the system using identification criteria from network layer 3 to 7, thanks to deep packet inspection (DPI). For example, Citrix and HTTP applications can be defined based on layer 7 published application names and URLs, respectively. Once defined, a per-user service level is configured for each application. This per-user service level defines what the WAN optimization, application acceleration and next-generation QoS should deliver in terms of network resources for each individual user of a given application. Resource requirements are defined using network attributes such as bandwidth, delay, jitter and loss thresholds. This service level information is contained in a dictionary in the central management software and can be customized to match each enterprise's unique application requirements.
Once the application performance objectives have been defined, the Ipanema System is able first to assess whether or not they are currently being delivered over the network. In the example below, site D has serious application performance problems, including poor performance of high criticality applications such as SAP. When Ipanema WAN optimization and next-generation QoS is activated, the system automatically reapplies the available resources to optimize end-user Quality of Experience (QoE) and productivity using the global objectives. In the example below, at site D, critical applications now receive the required network resources, resulting in these users being 100% satisfied across the entire network.
However this does not always fix all the performance problems in a network. Through application acceleration, Ipanema is able to mitigate the impact of delay and increase the bandwidth available for applications. This means that the business-critical application users are satisfied everywhere. For low criticality or recreational applications, enterprises can make the decision to explicitly limit their performance to discourage their use – in fact, an application performance objective with 0Kbits/s bandwidth will shut that application down, network wide.
Accelerate traffic while guaranteeing critical application performance
Application acceleration brings response time down, facilitating the QoE that users expect. A combination of techniques, including redundancy elimination (also referred to as compression, byte caching or deduplication), TCP acceleration and application acceleration (including specialized CIFS protocol optimization) mechanisms are dynamically applied under the control of Ipanema’s sophisticated, global and dynamic WAN optimization and next-generation QoS features.
Being part of an Autonomic Networking System, the WAN optimization, application acceleration and next-generation QoS mechanisms are triggered automatically depending on the nature of the applications. The system automatically adapts the application flows to emerging conditions in real-time based on a dynamic, global analysis of the traffic mix, user behavior and continuous tracking of WAN resource availability. Ipanema’s approach is:
- Controlled: Acceleration features are tightly integrated with Ipanema’s WAN optimization and next-generation QoS. Ipanema WAN optimization prevents application acceleration from creating congestion – even in meshed networks. In addition, the “virtual bandwidth” created by application acceleration and WAN optimization is allocated through next-generation QoS, i.e. according to business priorities.
- Transparent to the IT infrastructure: Ipanema’s WAN optimization, application acceleration and next-generation QoS does not require any change to the configuration of the IT infrastructure, and vice-versa.
- Transparent to the network: Ipanema’s WAN optimization, application acceleration and next-generation QoS modify the payload of the packets and preservers layer 3 and 4 information.
- Able to manage all applications: WAN optimization, application acceleration and next-generation QoS cover the three key application performance bottlenecks (bandwidth, TCP and the application protocol) and address all types of applications, including real-time, transactional and data transfer applications.
- A la carte/modular: Individual WAN optimization, application acceleration and next-generation QoS mechanisms can be deployed only where they are really required—a branch device is not always needed to get the benefit of the Ipanema System.
Globally manage meshed flows from the datacenters
In modern networks, competition for network resources occurs not only among applications but also among sites. In this example, a branch office accesses a critical SAP application over the WAN from the main data center. At the same time, the same user’s email application synchronizes data over the WAN from a regional data center. Then another user in the same branch also generates email traffic from the main data center. The resulting competition between application flows from the data centers creates congestion at the PE router at the branch, resulting in poor performance of SAP. Although such competition can be handled with a traffic management device located in the branch (as long as the traffic from data center does not contain non-TCP traffic), controlling it on the destination side is not optimal because it wastes WAN resources and/or jeopardize application performance.
Ipanema provides global management of network traffic, made possible by Cooperative Tele-Optimization among the devices located at the datacenters to avoid congestion in the PE router at the branch, even without installing a device there. The cooperating ip|engines in the datacenters exchange information in real-time about the flows they are controlling, and from that co-ordination they detect that they are both sending traffic to the branch. They dynamically compute the bandwidth that should be given to each user session going to the branch based on their shared knowledge of the traffic mix, its business-criticality and the resources available. This prevents any congestion from happening in the destination PE router by controlling the traffic at its source. Cooperative Tele-Optimization dramatically reduces the costs and the complexity of application traffic management over large distributed networks by removing the need for appliances in all branches.
Protect interactive applications and enable convergence
Ipanema's WAN optimization, application acceleration and next-generation QoS optimize more than just bandwidth – they also manage other characteristics of network resources, such as delay, loss and jitter. Smart Packet Forwarding technology allows application flows to be managed differently depending on their requirements and on individual user behavior. Packets belonging to real-time flows such as VoIP or video are forwarded in a manner that prevents the injection of unwanted delay, loss or jitter. Packets belonging to data-transfer flows, such as with FTP or email, are forwarded so that they receive the appropriate bandwidth resources without degrading other more delay-sensitive flows.
Packets belonging to interactive flows such as Citrix or Windows RDP typically require the lowest transit delay. These flows are analyzed by WAN optimization, application acceleration and next-generation QoS to detect the user behavior in real-time. This unique ability is required to deal with “hybrid” flows, such as such those where users load or save a local file inside a Citrix session, such as when editing documents. Ipanema is able to prevent the data-transfer phases of the interactive flow from freezing other users' interactive Citrix sessions
Combine multiple physical networks into a unified logical network
Smart Path Selection add next-generation network load balancing to WAN optimization, application acceleration and next-generation QoS. This next-generation network load balancing maximizes the value of multiple network-access implementations by unifying the different accesses at the global enterprise level and ensuring the optimum usage of each available path between sites. Ipanema’s next-generation network load balancing dynamically selects the best network access path for each session in order to guarantee the associated application SLA and maximize the application's performance and security.
Smart Path Selection provides enterprises with full business communication continuity through redundant networks while guaranteeing application performance and optimizing their network costs. Tightly integrated with the other visibility, WAN optimization, application acceleration and next-generation QoS features, Smart Path Selection automatically delivers benefits over redundant networks, with no extra operational workload. Smart Path Selection:
- Dynamically selects the best network access path for each session, maximizing application performance, security and network usage.
- Is built on the Ipanema System’s ability to enforce application-level SLAs guaranteeing the performance of all applications on the network (data, voice, video, interactive…).
- Makes all network accesses always available for use (vs. standard link failover) to enable enterprises to use all the network resources for which they are paying.
