Abstract: An intermediate network device performs service aware path selection. For example, the intermediate network device comprises a network interface that receives network traffic and a control unit that couples to the network interface. The control unit comprises a storage medium that stores a first set of cost factors for a first path from the intermediate network device to another intermediate network device. The first set of cost factors includes at least one optimization cost factor corresponding to intermediate optimization capabilities available to the intermediate network device that offset other cost factors of the first set. The storage medium also stores a second set of cost factors for a second path between the devices. The control unit selects either the first path or the second path over which to forward the network traffic based on the first and second sets of cost factors.

Abstract: A system includes a virtual machine (VM) server and a policy engine server. The VM server includes two or more guest operating systems and an agent. The agent is configured to collect information from the two or more guest operating systems. The policy engine server is configured to: receive the information from the agent; generate access control information for a first guest OS, of the two or more guest operating systems, based on the information; and configure an enforcer based on the access control information.

Abstract: A system includes a virtual machine (VM) server and a policy engine server. The VM server includes two or more guest operating systems and an agent. The agent is configured to collect information from the two or more guest operating systems. The policy engine server is configured to: receive the information from the agent; generate access control information for a first guest OS, of the two or more guest operating systems, based on the information; and configure an enforcer based on the access control information.

Abstract: A system discovers peer nodes in a failover system, establishes a secure channel between at least two of the peer nodes, and exchanges state information over the secure channel.

Abstract: A network device is configured to monitor a data size of data transmitted to a particular destination during a particular time period, determine, based on the monitored data size, an average data size for the particular destination and for the particular time period, establish a data connection toward the particular destination during the particular time period, set an initial data size for the data connection based on the average data size, and transmit data on the data connection in an amount equal to the initial data size.

Abstract: A system discovers peer nodes in a failover system, establishes a secure channel between at least two of the peer nodes, and exchanges state information over the secure channel.

Abstract: A system discovers peer nodes in a failover system, establishes a secure channel between at least two of the peer nodes, and exchanges state information over the secure channel.

Abstract: A network acceleration device includes a persistent, in-memory cache of network content. For example, the cache may store content in a manner that allows a software process to map virtual memory to specific, known regions of an underlying physical memory. Upon detecting a failure of a process executing within the network device, the network acceleration device may restart the software process and remap data structures of the cache to the known regions of the physical memory without necessarily requiring that the cache content be reloaded from a non-volatile memory, such as a hard drive. In this manner, the network acceleration device may accelerate download speeds by avoiding timely cache content restoration in the event of a software process failure.

Abstract: Techniques for centrally controlling client-side domain name resolution are described. A virtual private network (VPN) client installed on a client device may establish a VPN connection to a load-balancing server that balances load from client devices among a set of data centers that provide a resource. The VPN client may obtain and cache load-balancing information from the load-balancing server. The VPN client may then intercept a Domain Name System (DNS) request to resolve a hostname of a device in the data centers. The VPN client may use the load-balancing information to locally generate a DNS response to the DNS request. In addition, the load-balancing server may cause the VPN client to update its cached list of network addresses when one of the data centers fails.

Abstract: In general, techniques are described by which a path through a network may be selected based on service information. For example, a network device may include one or more interfaces, a control unit, and an integrated network acceleration device that provides a first set of services. The interfaces may receive service information that describes a second set of services provided by another network device. The control unit then determines, based on the service information, whether the other device shares any services in common with the integrated device. If so, the control unit selects a path through the network that includes the other device and causes the integrated device to apply the shared service to a portion of the traffic. The interfaces forward this portion along the determined path to the other device such that the other device applies the shared network acceleration services to the portion of the network traffic.

Abstract: A network acceleration device simultaneously caches and intelligently serves different historical versions of stored network content. For example, the network acceleration device may receive one or more requests for original content; however, subsequent updates to the content may create varying versions of the content, e.g., a pre-update version and one or more post-update versions. Client devices that requested the content prior to the update receive the pre-update version from the network acceleration device. Client devices that requested content after the update receive the post-update version from the network device. Moreover, the network acceleration device facilitates the simultaneous delivery of the pre-update version and the post-update version without waiting for delivery of the pre-update version to be complete. Thus, the network acceleration device may facilitate decreased download times by seamlessly and transparently providing both versions of the content simultaneously.

Abstract: An intermediate network device performs service aware path selection. For example, the intermediate network device comprises a network interface that receives network traffic and a control unit that couples to the network interface. The control unit comprises a storage medium that stores a first set of cost factors for a first path from the intermediate network device to another intermediate network device. The first set of cost factors includes at least one optimization cost factor corresponding to intermediate optimization capabilities available to the intermediate network device that offset other cost factors of the first set. The storage medium also stores a second set of cost factors for a second path between the devices. The control unit selects either the first path or the second path over which to forward the network traffic based on the first and second sets of cost factors.

Abstract: A network acceleration device provides application programming interface (API) that facilitates the sharing of cache resources among multiple network acceleration devices, thereby allowing the network acceleration devices to be clustered and share a common cache of network content. This clustered approach may advantageously allow clients serviced by one network acceleration device to benefit from previous network access requests issued by clients serviced by a different network acceleration device of the cluster.

Abstract: A device may receive a packet at a network device, and may retrieve from a table, by using information in a header of the packet as keys, records that include communication performance statistics associated with transport protocols. In addition, the device may select, based on the records, a transport protocol with an optimum communication performance statistics among the transport protocols and send the packet in accordance with the selected transport protocol from the network device.

Abstract: A device may receive a packet at a network device, and may retrieve from a table, by using information in a header of the packet as keys, records that include communication performance statistics associated with transport protocols. In addition, the device may select, based on the records, a transport protocol with an optimum communication performance statistics among the transport protocols and send the packet in accordance with the selected transport protocol from the network device.

Abstract: A network acceleration device includes a persistent, in-memory cache of network content. For example, the cache may store content in a manner that allows a software process to map virtual memory to specific, known regions of an underlying physical memory. Upon detecting a failure of a process executing within the network device, the network acceleration device may restart the software process and remap data structures of the cache to the known regions of the physical memory without necessarily requiring that the cache content be reloaded from a non-volatile memory, such as a hard drive. In this manner, the network acceleration device may accelerate download speeds by avoiding timely cache content restoration in the event of a software process failure.

Abstract: A network acceleration device simultaneously caches and intelligently serves different historical versions of stored network content. For example, the network acceleration device may receive one or more requests for original content; however, subsequent updates to the content may create varying versions of the content, e.g., a pre-update version and one or more post-update versions. Client devices that requested the content prior to the update receive the pre-update version from the network acceleration device. Client devices that requested content after the update receive the post-update version from the network device. Moreover, the network acceleration device facilitates the simultaneous delivery of the pre-update version and the post-update version without waiting for delivery of the pre-update version to be complete. Thus, the network acceleration device may facilitate decreased download times by seamlessly and transparently providing both versions of the content simultaneously.

Abstract: A method for configuring a server load balancer comprises receiving a user command defining a load balancing group capable of representing a plurality of target host servers within a network, and receiving user commands adding the target host servers to the load balancing group, wherein the user commands include configuration information for the target host servers. Upon receiving the user commands adding the target host servers to the load balancing group, the method includes updating a database of the server load balancer to include configuration information for the target host servers. After updating the database, the method includes receiving user commands assigning a label to a subset of the target host servers without creating a new load balancing group and without re-configuring information relating to the target host servers, wherein the label indicates the subset of the target host servers are capable of servicing a specific type of access request.