ipcpd: Use capacity queue estimation for mb-ecn

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 <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>

1 files changed, 5 insertions, 1 deletions

diff --git a/src/ipcpd/unicast/ca.h b/src/ipcpd/unicast/ca.h
index fc6de445..188fb08a 100644
--- a/src/ipcpd/unicast/ca.h
+++ b/src/ipcpd/unicast/ca.h
@@ -67,10 +67,14 @@ void     ca_ctx_rtt(void *   ctx,
                     uint64_t now,
                     uint64_t rtt);
 
+/*
+ * Marks congestion from the egress queue. Both queued and mean are
+ * in bytes, so their ratio is the queue depth in packets.
+ */
 int      ca_calc_ecn(size_t    queued,
                      uint8_t * ecn,
                      qoscube_t qc,
-                     size_t    len);
+                     size_t    mean);
 
 bool     ca_marks_ecn(void);