diff options
| author | Donald Sharp <sharpd@cumulusnetworks.com> | 2017-09-27 02:06:13 +0200 |
|---|---|---|
| committer | Donald Sharp <sharpd@cumulusnetworks.com> | 2017-09-27 02:06:13 +0200 |
| commit | 65d4e0c69b5cb6e7811784ef563e1b23ba162cff (patch) | |
| tree | f23648ad5e15b7050dd250a210baa5d550078fe8 /bgpd/bgp_nexthop.h | |
| parent | Merge pull request #1248 from vjardin6WIND/cleanup (diff) | |
| download | frr-65d4e0c69b5cb6e7811784ef563e1b23ba162cff.tar.xz frr-65d4e0c69b5cb6e7811784ef563e1b23ba162cff.zip | |
bgpd: Reduce multiaccess_check_v4 overhead for subgroups
Perf results at scale( >1k peers) showed a non-trivial
amount of time spent in bgp_multiaccess_check_v4. Upon
function examination we are looking up the nexthops
connected node in each call as well as having to unlock
it after each iteration. Rewrite to lookup the nexthop
node once.
This should reduce the node lookup by aproximately 1/2
which should yield some performance results. There are
probably better things to do here but would require
deeper thought.
Signed-off-by: Donald Sharp <sharpd@cumulusnetworks.com>
Diffstat (limited to 'bgpd/bgp_nexthop.h')
| -rw-r--r-- | bgpd/bgp_nexthop.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/bgpd/bgp_nexthop.h b/bgpd/bgp_nexthop.h index b482778fd..2c5b2ab11 100644 --- a/bgpd/bgp_nexthop.h +++ b/bgpd/bgp_nexthop.h @@ -82,6 +82,8 @@ extern int bgp_nexthop_lookup(afi_t, struct peer *peer, struct bgp_info *, int *, int *); extern void bgp_connected_add(struct bgp *bgp, struct connected *c); extern void bgp_connected_delete(struct bgp *bgp, struct connected *c); +extern int bgp_subgrp_multiaccess_check_v4(struct in_addr nexthop, + struct update_subgroup *subgrp); extern int bgp_multiaccess_check_v4(struct in_addr, struct peer *); extern int bgp_config_write_scan_time(struct vty *); extern int bgp_nexthop_self(struct bgp *, struct in_addr); |