Juniper Networks, Inc.

Sairam Neelam

Amit Arora

Harmeet Singh

Prashant Singh

Erin C Macneil

Reji Thomas

Jimmy Jose

Amit Kumar Rao

Erin C MacNeil

Vivek Ramesh

Mani Kanta Kanaka Rayavarapu

Vinod Arumugham Chettiar

Shiva Kumar Yenigalla

A network device may execute a master application shared with another network device via a session, and may receive, by a backup application replication kernel, a replicated data object. The backup application replication kernel may provide the replicated data object to a backup application, and may calculate a time delta between when the replicated data object is received and when the replicated data object is consumed by the backup application. The backup application replication kernel may determine whether the time delta exceeds a first threshold or a second threshold, and may generate a session flag based on the time delta exceeding the first threshold or the second threshold. The backup application replication kernel may provide the session flag to a master application replication kernel and to the backup application, and the master application replication kernel may provide details of the session to the master application and the backup application.

Making transmission control protocol (TCP) sessions robust in a socket replication environment

A network device may establish, via a routing protocol daemon (RPD) of the network device, border gateway protocol (BGP) sockets with peer network devices and may establish a socket between the RPD and a periodic packet management daemon (PPMD) of the network device. The network device may provide file descriptors of the BGP sockets from the RPD to the PPMD, via the socket, and may provide, from the RPD and via the BGP sockets, non-keep alive protocol data units (PDUs) to the peer network devices. The network device may provide, from the PPMD and via the BGP sockets, keep alive PDUs to the peer network devices.

Increasing robustness of connections by offloading keep alive protocol data units

A network device may monitor a TCP session with another network device, and may identify ingress and/or egress packets, a TCP header, and a socket of the TCP session. The network device may inspect the ingress and/or egress packets, the TCP header, and the socket to identify a zero window advertisement, details of a last quantity of packets sent or received, synchronize, finish, or reset packets sent or received, negotiated TCP options, or buffer space utilization, and may temporarily record identified data based on the inspection. The network device may detect a TCP session flap when a finish packet or a reset packet is identified and recorded, and may store, in a dead TCP session list, the identified data based on the TCP session flap being detected.

Retaining key parameters after a transmission control protocol (TCP) session flap

A network device may execute a master application communicating with another network device via a session, and may receive, by a backup application replication layer, a replicated data object. The backup application replication layer may provide the replicated data object to a backup application, and may calculate a time delta between when the replicated data object is received and when the replicated data object arrives at the backup application. The backup application replication layer may determine whether the time delta exceeds a first threshold or a second threshold, and may generate a session flag based on the time delta exceeding the first threshold or the second threshold. The backup application replication layer may provide the session flag to a master application replication layer and to the backup application, and the master application replication layer may provide details of the session to the master application and the backup application.

A method and network device for detecting a TCP socket failure is described. A network device may be configured to detect a failure of a link between a first node and a second node, determine one or more transmission control protocol (TCP) sockets of a plurality of TCP sockets on the first node that are communicating over the link between the first node and the second node, write information to a TCP stack for the determined one or more TCP sockets, the information indicating that the determined one or more TCP sockets have an error, and remediate the determined one or more TCP sockets in response to the information.

Propagating node failure errors to TCP sockets

A disclosed method may include (1) identifying a packet that enters a start point of an encapsulation tunnel that spans at least a portion of a network, (2) discovering a maximum transmission unit of the encapsulation tunnel, (3) determining whether a size of the packet satisfies a size threshold that is based at least in part on the maximum transmission unit of the encapsulation tunnel, (4) detecting an encapsulation-triggering event in connection with the packet, and then in response to detecting the encapsulation-triggering event, (5) forwarding the packet via the start point of the encapsulation tunnel toward an end point of the encapsulation tunnel. Various other systems, methods, and computer-readable media are also disclosed.

Apparatus, system, and method for increasing bandwidth utilization in encapsulation tunnels

A disclosed method may include (1) identifying a memory buffer that is allocated to a packet on a computing device, (2) identifying one or more characteristics of the memory buffer allocated to the packet on the computing device, (3) determining, based at least in part on the characteristics of the memory buffer, that the memory buffer allocated to the packet has leaked, and then in response to determining that the memory buffer has leaked, (4) performing at least one action to remedy the leak of the memory buffer. Various other apparatuses, systems, and methods are also disclosed.

Apparatus, system, and method for detecting and remedying memory buffer leaks in network devices

A network device intercepts, from an application associated with a user space, a request message associated with obtaining information regarding a network state from a kernel. The network device directs the request message to a service daemon of the user space based on intercepting the request message, and determines, using the service daemon, network state information regarding the network state. The network device intercepts, from the service daemon, a response message associated with providing the network state information to the application, and directs an altered response message to the application based on intercepting the response message such that the altered response message identifies the kernel as a source of the response message and not the service daemon as the source of the response message.

Network state management

A network device may intercept, from an application associated with a user space of the network device, a request message to join a multicast group or to leave the multicast group. The request message may be addressed to a kernel of the network device. The network device may direct the request message to a service daemon associated with the user space of the network device. The network device may determine, using the service daemon, whether another application associated with the user space is a member of the multicast group. The network device may selectively generate, using the service daemon and based on whether the other application associated with the user space is the member of the multicast group, an advertisement message based on the request message, and transmit the advertisement message when the advertisement message is generated.

Multicast group membership management

A network device may determine a control plane session type associated with a control plane session. The control plane session may be associated with the network device. The network device may determine whether the control plane session type is associated with a forwarding information base (FIB) cache on the network device. The network device may obtain, based on determining that the control plane session type is associated with the FIB cache, forwarding information associated with the control plane session. The forwarding information may be stored in a FIB, associated with the FIB cache, on the network device. The network device may store the forwarding information in the FIB cache and process the control plane session using the forwarding information stored in the FIB cache.

Forwarding information base caching

The disclosed apparatus may include (1) forwarding, along a network path, a test packet that is (A) destined for an invalid port on a destination device and (B) fragmented by an intermediary device within the network path according to an MTU value of a network interface on the intermediary device, (2) receiving an error packet sent by the destination device in response to having determined that the test packet is destined for the invalid port, (3) determining a PMTU value of the network path by identifying, within the error packet, a size of the largest fragmented segment of the test packet received by the destination device, and then (4) forwarding, along the network path, at least one packet sized to comply with the PMTU value such that the packet remains unfragmented upon reaching the destination device. Various other apparatuses, systems, and methods are also disclosed.

Apparatus, system, and method for discovering network path maximum transmission units

Techniques are described to reduce false alarms in network devices utilizing keepalive messaging schemes. In order to potentially avoid false alarms, a transmitting network device adjusts quality of service QOS/TOS settings in keep-alive probe packets that are sent later in a current detection interval such that the keep-alive probe packets have escalating priorities. In addition, for keep-alive probe packets that are sent later in the current detection interval, the network device may also insert host-level preferential indicator within each of the packets to request preferential treatment at both itself and the peer network device.

Reducing false alarms when using network keep-alive messages

Techniques include quickly establishing a maximum transmission unit (MTU) for a network path, such as a network tunnel. In one example, data representative of the MTU is included in a header of a packet. If the MTU indicated in the packet is larger than a downstream network interface of a network device, the network device updates the data of the header to indicate the MTU of the downstream network interface, and an egress network device sends the packet back to an ingress network device. In another example, network devices fragment packets, if necessary, such that the fragments satisfy the MTU of the downstream network interface. The egress network device then determines the MTU for the path based on a largest received fragment, reassembles the fragments into a single packet, and returns the reassembled packet to the ingress network device. The packets may comprise echo packets of generic routing encapsulation (GRE).

Computing path maximum transmission unit size

Techniques are described for selectively triggering fast reroute of traffic by enhancing a protocol used for monitoring operational status of a forwarding plane of a router. The forwarding plane of the router outputs periodic messages that, when received by a peer router, provide an indication that the forwarding plane is operational and able to forward packets. In addition, when constructing the periodic messages, the forwarding plane embeds an indication of a status of internal communication between the forwarding plane and a control plane of the router. In this way, the forwarding plane of the transmitting router provides an indication to the peer router that, although operational, the forwarding plane may be operating according to stale forwarding information.

Growing community of inventors

Hyderabad Telangana, India

Sairam Neelam