Abstract:
Techniques are described for supporting Fiber Channel over Ethernet (FCoE) link aggregation groups (LAGs) between a server and a data center switch in a data center. The techniques enable an access switch in the data center switch to assign class identifiers to each member link in an FCoE LAG between an FCoE node (Enode) of the server and the access switch. In this way, the access switch is able to redirect FCoE traffic from a Fiber Channel forwarder (FCF) of a storage area network (SAN) toward the Enode on the correct member link of the FCoE LAG. The techniques also enable scaling of FCoE initialization protocol (FIP) and FCoE sessions by installing FIP snooping filters that use on a source media access control (MAC) address hit determination in ingress filter processors (IFPs) of the access switch to avoid session limitations of virtual local area network (VLAN) filter processors (VFPs).
Abstract:
Techniques are described for supporting Fibre Channel over Ethernet (FCoE) link aggregation groups (LAGs) between a server and a data center switch in a data center. The techniques enable an access switch in the data center switch to assign class identifiers to each member link in an FCoE LAG between an FCoE node (Enode) of the server and the access switch. In this way, the access switch is able to redirect FCoE traffic from a Fibre Channel forwarder (FCF) of a storage area network (SAN) toward the Enode on the correct member link of the FCoE LAG. The techniques also enable scaling of FCoE initialization protocol (FIP) and FCoE sessions by installing FIP snooping filters that use on a source media access control (MAC) address hit determination in ingress filter processors (IFPs) of the access switch to avoid session limitations of virtual local area network (VLAN) filter processors (VFPs).
Abstract:
A firewall device may include a forwarding component that includes a filter block. The filter block may obtain a first hardware-implemented filter, where a hardware implementation limits the first hardware-implemented filter to a maximum quantity of rules; determine whether a last rule associated with the accessed hardware-implemented filter includes a split-filter action, where the split-filter action identifies a second hardware-implemented filter; and link the second hardware-implemented filter to the first hardware-implemented filter to make the second hardware-implemented filter a logical continuation of the first hardware-implemented filter, in response to determining that the last rule includes the split-filter action. The filter block may further determine whether a particular rule of the first hardware-implemented filter includes a next-filter action, where the next filter action identifies a third hardware-implemented filter; and process the third hardware-implemented filter independently of the sequence of hardware attachment points.