SCTP sockets originated in a VRF can improve their performance if CRC32c
computation is delegated to underlying devices: update device features,
setting NETIF_F_SCTP_CRC. Iterating the following command in the topology
proposed with [1],
# ip vrf exec vrf-h2 netperf -H 192.0.2.1 -t SCTP_STREAM -- -m 10K
the measured throughput in Mbit/s improved from 2395 ± 1% to 2720 ± 1%.
[1] https://www.spinics.net/lists/netdev/msg486007.html
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
/* enable offload features */
dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM;
+ dev->features |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC;
dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
dev->hw_features = dev->features;