summaryrefslogtreecommitdiff
path: root/accel-pppd/net.c
AgeCommit message (Collapse)Author
2021-12-20T55: add netlink buffer size configuration parametersSergey V. Lobanov
Netlink buffers may overflow so it might be useful to increase send and receive netlink buffer sizes. Two parameters to [common] configuration section added: nl-rcv-buffer, nl-snd-buffer. It is required to set (sysctl) net.core.wmem_max>=nl-snd-buffer and net.core.rmem_max>=nl-rcv-buffer before running accel-pppd To check current netlink buffer size and related info use the following command: % ss -f netlink -m 0 0 rtnl:kernel * skmem:(r0,rb212992,t0,tb212992,f0,w0,o0,bl0,d0) 0 0 rtnl:-1140221812 * skmem:(r0,rb2048000,t0,tb80000,f0,w0,o0,bl0,d0) 0 0 rtnl:accel-pppd/14285 * skmem:(r0,rb2048000,t0,tb65536,f0,w0,o0,bl0,d0) ... (Please check man ss to get the meaning for r,rb,t,tb,f,w,o,bl and d params) In the ss output you will see the values doubled from configured. First accel-pppd netlink socket will use default values (rcv=1048576, snd=32768) regardless of configured nl-rcv-buffer and nl-snd-buffer values. Signed-off-by: Sergey V. Lobanov <sergey@lobanov.in>
2021-12-16vrf: T10: Add VRF supportDmitriyEshenko
Co-authored-by: Sergey V. Lobanov <svlobanov@users.noreply.github.com> Co-authored-by: Vladislav Grishenko <themiron@users.noreply.github.com>
2021-03-16Move debug print to proper place[anp/hsw]
2020-04-07T13: Fix build procedureDmitriyEshenko
2020-03-18net: new function get_ifindexSimon Chopin
The index of a given interface is an operation that highly depends on the network namespace we're in. This patch simply cuts out a function to get the index for a given interface name from the session initialization code, and expose it in the ap_net structure. This function can then be used to refresh the index when moving interfaces around. Signed-off-by: Simon Chopin <s.chopin@alphalink.fr>
2016-07-19check for setns availabilityDmitry Kozlov
2016-07-14net: code cleanupDmitry Kozlov
2016-07-14fix def_move_linkFrançois Cachereul
Do not know how this could work. It make more sense to move an interface from its original namespace not from its destination. Signed-off-by: François Cachereul <f.cachereul@alphalink.fr>
2016-07-11implemented support for network namespaceDmitry Kozlov
This is done using radius attribute NAS-Port-Id. The new format of this attribute is NAS-Port-Id=[ns/][name]. Namespaces must be created malually by "ip netns add ..." command
2016-04-15preparation for DPDK intergation (part 6)Dmitry Kozlov
2015-12-04preparation for DPDK intergation (part 5)Dmitry Kozlov
2015-12-04preparation for DPDK intergation (part 4)Dmitry Kozlov
2015-12-04preparation for DPDK intergation (part 3)Dmitry Kozlov
2015-12-04preparation for DPDK intergation (part 2)Dmitry Kozlov
2015-12-04preparation for DPDK intergationDmitry Kozlov