Abstract: A system and method for dynamically identifying internal hosts in a heterogeneous computing environment with multiple subnetworks is disclosed. A plurality of packets are analyzed. Each such packet includes a source address of an originating host and a destination address of a receiving host. An unknown originating host located at the source address of an outbound packet is classified as an inside host with high confidence. An unknown receiving host located at the destination address of an inbound packet is classified as an inside host. The unknown receiving host is reclassified as an inside host with high confidence upon receiving a further outbound packet having a source address corresponding to the address of the unknown receiving host.

Abstract: Methods, apparatuses and systems that dynamically adjust the selection of differentiated network services for selected classes of traffic in response to changing network conditions or application performance levels. In one implementation, the present invention allows for a differentiated network services scheme that adapts to existing network conditions and, in one implementation, selects higher, generally more expensive classes of differentiated network service for certain data flows when the performance of selected applications degrades below a threshold level. The present invention, in one implementation, allows for bandwidth cost savings without sacrificing application performance.

Abstract: Methods, apparatuses and systems directed to a network traffic classification mechanism that probes hosts against one or more network application profiles to facilitate identification of network applications corresponding to data flows traversing a network.

Abstract: Methods, apparatuses, and systems directed to efficient compression processing in system architectures including a control plane and a data plane. Particular implementations feature integration of compression operations and mode selection with a beltway mechanism that takes advantage of atomic locking mechanisms supported by certain classes of hardware processors to handle the tasks that require atomic access to data structures while also reducing the overhead associated with these atomic locking mechanisms.

Abstract: Methods, apparatuses and systems directed to an adaptive partitioning mechanism responsive to observed latency conditions in a communications network. Embodiments of the present invention can be configured to adapt to changing network conditions and ensure that selected network applications meet desired QoS levels. In one implementation, the present invention provides a mechanism that adjusts the minimum bandwidth setting corresponding to a given partition in response to observed latency. According to one implementation, a latency threshold is configured relative to local queuing latency or a latency metric corresponding to the network itself. A process modulates the minimum bandwidth setting associated with one or more partitions in response to observed latency relative to the configured threshold.

Abstract: A method and apparatus for using an application layer demarcation point are described. In one embodiment, the method comprises monitoring end-to-end performance of a network application at an application demarcation point in a network, and mediating between provider infrastructure and customer infrastructure based on results of monitoring.

Abstract: Classification of network traffic based on conditions orthogonal to explicit attributes of packets in network traffic. In one implementation, classification of network traffic based on the behavior of one or more nodes associated with the network traffic. In one implementation, a mechanism is provided that allows for the creation of matching rule predicates that match to certain node behaviors of interest and cause the application of appropriate policies to the network traffic. In one implementation, the node behavior matching functionality can be combined to seamlessly operate in connection with other Layer 7 traffic classification mechanisms that operate on explicitly-presented attributes of the packets.

Abstract: Methods, apparatuses and systems directed to an automatic network traffic discovery and classification mechanism that includes dynamically adjusted traffic discovery thresholds. In one implementation, the dynamic discovery thresholds are adjusted based on analysis of one or more operational parameters associated with network traffic discovery, and/or network traffic characteristics. The present invention in one implementation can be configured to dynamically adjust one or more thresholds or range limits that affect the behavior of the automatic traffic classification mechanism, such as the rate at which new traffic classes are added to a traffic classification database. One implementation of the present invention minimizes the user intervention often required with the use of static traffic discovery thresholds.

Abstract: A beltway mechanism that takes advantage of atomic locking mechanisms supported by certain classes of hardware processors to handle the tasks that require atomic access to data structures while also reducing the overhead associated with these atomic locking mechanisms. The beltway mechanisms described herein can be used to control access to software and hardware facilities in an efficient manner.

Abstract: Methods, apparatuses and systems allowing for network link state mirroring in intermediate network devices. A variety of intermediate network devices disposed between two network devices are operationally transparent to the two network devices. For example, a bandwidth management device disposed between a gateway router and a LAN hub or switch, is operationally transparent, to both network devices since the bandwidth management device, pacing or otherwise controlling packet flows, does not alter the essential routing or switching functions of the devices. The present invention promotes or enhances this operational transparency by mirroring the link state detected at a first network interface on other network interfaces. This functionality is highly useful in today's network topologies where information regarding failure of a link can be used to re-route traffic, alert a network administrator, and the like.

Abstract: Methods, apparatuses and systems that dynamically adjust the selection of differentiated network services for selected classes of traffic in response to changing network conditions or application performance levels. In one implementation, the present invention allows for a differentiated network services scheme that adapts to existing network conditions and, in one implementation, selects higher, generally more expensive classes of differentiated network service for certain data flows when the performance of selected applications degrades below a threshold level. The present invention, in one implementation, allows for bandwidth cost savings without sacrificing application performance.

Abstract: A system and method for efficiently forwarding client requests from a proxy server in a TCP/IP computing environment is described. A plurality of transient requests are received from individual sending clients into a request queue. Each request is commonly addressed to an origin server. Time estimates of TCP overhead, slow start overhead, time-to-idle, and request transfer time for sending the requests over each of a plurality of managed connections to the origin server are dynamically calculated, concurrent to receiving and during processing of each request. The managed connection is chosen from, in order of preferred selection, a warm idle connection, an active connection with a time-to-idle less than a slow start overhead, a cold idle connection, an active connection with a time-to-idle less than a TCP overhead, a new managed connection, and an existing managed connection with a smallest time-to-idle. Each request is forwarded to the origin server over the selected managed connection.

Abstract: Methods and apparatuses allowing for dynamic partitioning of a network resource among a plurality of users. In one embodiment, the invention involves recognizing new users of a network resource; creating user partitions on demand for new users, wherein the user partition is operable to allocate a portion of a network resource; and, reclaiming inactive user partitions for subsequent new users.

Abstract: The present invention, in particular embodiments, is directed to methods, apparatuses and systems that provide an efficient compression technique for data streams transmitted to storage devices or over networks to remote hosts. Local storage as well as network transmission of streams is made more efficient by awareness and utilization of repeated sequences of data blocks. Such data blocks can be placed in a dictionary on persistent storage and shared across all streams. The dictionary is hierarchically indexed (two or more levels of indexing) to combine high efficiency search with efficient access to the stored data blocks. Additionally, data blocks, in particular implementations, are stored sequentially in order to improve overall performance.

Abstract: An example embodiment of the invention provides a process for lockless processing of hierarchical bandwidth partitions configurations in multiple processor architectures. In one embodiment, the process runs in an NPU's data plane and receives a packet for a partition from a child partition through a work queue. The process determines a suggested target bandwidth rate for the receiving partition's child partitions, based in part on a count of active child partitions, if a predefined time interval has passed. The process adopts a target bandwidth rate for the receiving partition suggested by the receiving partition's parent partition, if the receiving partition is not a root partition and the predefined time interval has passed. The process then transmits the packet to the receiving partition's parent partition through the work queue, if the receiving partition is not a root partition. Otherwise, the process transmits the packet to a port.

Abstract: A data and control plane architecture for network devices. An example system architecture includes a network processing unit implementing one or more data plane operations, and a network device operably coupled to the network processing unit that implements a control plane. In a particular implementation, the network processing unit is configured to process network traffic according to a data plane configuration, and sample selected packets to the network device. The network device processes the sampled packets and adjusts the data plane configuration responsive to the sampled packets. In particular implementations, the control plane and data plane implement, a server-side triggered policy caching mechanism that allows for previous classification policy decisions made for previous data flows to be applied to subsequent new flows.

Abstract: Methods, apparatuses and systems directed to improving the efficiency of bandwidth allocation schemes by adapting to slow-start mechanisms associated with network communications protocols, such as the TCP/IP protocol suite. In one implementation, the present invention scales down the initial target rate assigned to a data flow to a fraction of an initial estimate of the effective rate capacity of the communications path between two hosts. As packets are received, the target rate is gradually increased, eventually up to the detected rate capacity of the communications path. Implementations of the present invention improve the efficiency of bandwidth allocation by reducing the over-allocation of bandwidth to data flows during the slow-start phase, leaving more bandwidth available to other data flows.

Abstract: Methods, apparatuses and systems that facilitate the classification of web services network traffic. In one implementation, the present invention provides an automated mechanism that facilitates synchronization of a web services traffic classification database with the current or latest definitions of one to a plurality of web services of interest. In one implementation, the present invention processes interface definitions corresponding to a given Web service to construct a traffic classification configuration for the Web service, including one or more traffic classes and corresponding matching rules or attributes for each traffic class. In one implementation, the present invention automatically creates traffic classes and matching rules that allow for differentiation between the operations supported by a Web service.

Abstract: Methods, apparatuses and systems directed to an aggregate bandwidth utilization control scheme including fair share bandwidth allocation and dynamic allocation of bandwidth in response to detected traffic utilization. In one implementation, the present invention includes a weighted, fair share aggregate bandwidth allocation mechanism that dynamically responds to observed bandwidth utilization to provide unutilized or excess bandwidth to flows and partitions that require it. In another implementation, the present invention features a weighted fair share allocation scheme for hierarchical partition configurations. In other implementations, the present invention provides a per-flow target rate assignment mechanism that prevents spiraling decline of data flow rates.

Abstract: The present invention, in particular embodiments, is directed to methods, apparatuses and systems that provide an efficient compression technique for data streams transmitted to storage devices or over networks to remote hosts. Local storage as well as network transmission of streams is made more efficient by awareness and utilization of repeated sequences of data blocks. Such data blocks can be placed in a dictionary on persistent storage and shared across all streams. The dictionary is hierarchically indexed (two or more levels of indexing) to combine high efficiency search with efficient access to the stored data blocks. Additionally, data blocks, in particular implementations, are stored sequentially in order to improve overall performance.

Abstract: As many as three of the four heads spaced at 90.degree. intervals around the periphery of a head wheel may be in contact with the magnetic tape of a video recorder and reproducer at the same time. Oblique tracks are recorded on the tape record video date in blocks corresponding to sectors, each composed of the same numbers of lines, each track beginning with a video sector and ending with another video sector with small audio blocks inbetween. Four different sector designations succeed each other in turn. The video data of each block is preceded by an identification signal of which the two most significant bits designate the sector. The sector designations are separated from the outputs of each of the magnetic heads and control a PROM, the output of which controls a crosspoint switch to direct data blocks in accordance with the sector identification to four memories and the audio blocks to an audio memory.