ouroboros/src/ipcpd/unicast, branch be

lib: Update FRCT loss recovery

2026-08-31T06:31:46+00:00

Some more stability fixes in FRCT. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Use capacity queue estimation for mb-ecn

2026-08-31T06:31:45+00:00

The mb-ecn algorithm was using rbuff queue depths in packets to mark, but sockets in the poa component report capacity in bytes. The tx rings are now adaptive to block on queuing delay instead of when full to prevent buffer bloat, controllable via fccntl (FLOWSTXQDLY and FLOWGTXQDLY). Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

lib: Replace shim IPCPs with points of attachment

2026-08-31T06:31:45+00:00

Removes the UDP and Ethernet shim IPCPs. The unicast and broadcast IPCPs can now directly attach to a "legacy" socket. We adopt Saltzer's Point-of-Attachment terminology, also advocated in Day's "Patterns in Network Architecture". The "poa" component manages these PoA's with one management thread, one link monitoring thread and one thread per attached point. For Ethernet PoA's the irm connect and enroll can resolve the destination IPCP or Layer name with a broadcast name query over the attached PoAs (first reply wins). UDP PoA's require a destination IP address or FQDN. attach to a local endpoint (required both server and client side): irm ipcp poa attach name a udp 10.0.0.1 irm ipcp poa attach name a udp 10.0.0.1:3435 irm ipcp poa attach name a udp [::1]:3435 irm ipcp poa attach name a eth dev eth0 irm ipcp poa attach name a eth dev eth0 ethertype 0xA000 release a PoA (refused while it carries a flow): irm ipcp poa detach name a udp 10.0.0.1:3435 irm ipcp poa detach name a eth eth0 list an IPCP's PoAs: irm ipcp poa list name a connect to a peer, by name or at an address: irm ipcp connect name b dst a irm ipcp connect name b dst a eth irm ipcp connect name b dst a eth dev eth0 irm ipcp connect name b dst a udp 10.0.0.1:3435 irm ipcp connect name b dst a udp peer.example.com:3435 disconnect by peer name, no address: irm ipcp disconnect name b dst a irm ipcp disconnect name b dst a component mgmt enroll has the same shape as connect: irm ipcp enroll name b layer lr autobind irm ipcp enroll name b layer lr autobind eth dev eth0 irm ipcp enroll name b layer lr autobind udp 10.0.0.1:3435 the IRMd config file attaches PoAs and names peers the same way: udp = [ "10.0.0.1", "10.0.0.1:3436" ] eth = [ "eth0", {dev="eth1", ethertype=0xA007} ] enrol={dst="LAN", eth={dev="eth0"}} conn=[{dst="lan3", eth={}}, {dst="lan4", udp="10.0.0.1:3435"}] Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Don't drop DT flows on -EAGAIN

2026-08-31T06:31:45+00:00

The scheduler was dropping DT flows when they were momentarily empty (-EAGAIN). Now it will continue to the next flow and only drop on hard errors. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Clean up pft on flow down

2026-08-31T06:31:45+00:00

The pft had stale DT entries after a flow goes down until the next lsdb update. The flow descriptors are now purged once the link is declared down. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Fix next value iteration in DHT

2026-08-31T06:31:45+00:00

There was a bug in the loop where only the last entry was checked. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Flush fd from pff after disconnect

2026-08-03T06:49:59+00:00

The flow descriptors were not immediately removed from the routing tables when they were disconnected, so forwarding paths could still use the fd after the IPCP has deallocated the flow. Refactors the tests and adds some for the del_fd function. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Add flow overshoot protection to mb-ecn

2026-07-22T07:04:47+00:00

The ECN marks were the only source of congestion information, and going into congestion collapse (dropping a lot of ECN packets and causing loss of signal) was unrecoverable. The sender's slow-start ramp clock now tracks a measured RTT to avoid overshooting into congestion collapse on the previously fixed (14ms) doubling on long-delay (e.g. 100ms) links. The flow allocator now carries a periodic heartbeat/ack to keep RTT estimates up-to-date. The heartbeat also serves as a congestion collapse detector: consecutive heartbeat losses will go into loss recovery, halving the window and pausing Additive Increase until the path is clear. The DT component now has a max_rtt config parameter that serves as a hint for the layer RTT to optimize slow-start for low-latency networks. These two mechanisms follow TCP, however only during slow start up to the first ECN signal and to recover from a total collapse until the ECN signal returns. MB-ECN is still fully RTT-independent in the AI/PD region. A shorter RTT path will just reach its equal fair share faster than a longer RTT path. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Process DT flows round-robin

2026-07-22T07:04:33+00:00

The deadline scheduler kept draining the same flow with fevent() until its queue was empty, so a single greedy flow monopolizes the link. Now it does a per-packet round-robin to ensure each flow is served. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders

ipcpd: Remove mutex on DT stats

2026-07-19T09:44:36+00:00

There was a bug where the flow's stat mutex was zero'd while held. Removed the mutex alltogether; use stamp != 0 as the validity guard of the flow stats while reading stats. Signed-off-by: Dimitri Staessens Signed-off-by: Sander Vrijders