NP4 Acceleration
NP4 network processors provide fastpath acceleration by offloading communication sessions from the FortiGate CPU. When the first packet of a new session is received by an interface connected to an NP4 processor, just like any session connecting with any FortiGate interface, the session is forwarded to the FortiGate CPU where it is matched with a security policy. If the session is accepted by a security policy and if the session can be offloaded its session key is copied to the NP4 processor that received the packet. All of the rest of the packets in the session are intercepted by the NP4 processor and fast-pathed out of the FortiGate unit to their destination without ever passing through the FortiGate CPU. The result is enhanced network performance provided by the NP4 processor plus the network processing load is removed from the CPU. In addition, the NP4 processor can handle some CPU intensive tasks, like IPsec VPN encryption/decryption.
Session keys (and IPsec SA keys) are stored in the memory of the NP4 processor that is connected to the interface that received the packet that started the session. All sessions are fast-pathed and accelerated, even if they exit the FortiGate unit through an interface connected to another NP4. The key to making this possible is the Integrated Switch Fabric (ISF) that connects the NP4s and the FortiGate unit interfaces together. The ISF allows any port connectivity. All ports and NP4s can communicate with each other over the ISF.
There are no special ingress and egress fast path requirements because traffic enters and exits on interfaces connected to the same ISF. Most FortiGate models with multiple NP4 processors connect all interfaces and NP4 processors to the same ISF (except management interfaces) so this should not ever be a problem.
There is one limitation to keep in mind; the capacity of each NP4 processor. An individual NP4 processor has a capacity of 20 Gbps (10 Gbps ingress and 10 Gbps egress). Once an NP4 processor hits its limit, sessions that are over the limit are sent to the CPU. You can avoid this problem by as much as possible distributing incoming sessions evenly among the NP4 processors. To be able to do this you need to be aware of which interfaces connect to which NP4 processors and distribute incoming traffic accordingly.
Some FortiGate units contain one NP4 processor with all interfaces connected to it and to the ISF. As a result, offloading is supported for traffic between any pair of interfaces.
Some FortiGate units include NP4Lite processors. These network processors have the same functionality and limitations as NP4 processors but with about half the performance. NP4lite processors can be found in mid-range FortiGate models such as the FortiGate-200D and 240D.