gsadmin/spinifex
1
0
Fork 0
mirror of https://github.com/mulgadc/spinifex.git synced 2026-10-19 10:52:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(vpc): clear subnet drop gate when installing egress reroute

Browse Source 
A subnet with an attached IGW but no 0.0.0.0/0 route carries a
priority-1100 drop gate on the VPC router. When a route later lands
(NATGW reroute at 900, IGW reroute at 1000) the reroute is installed but
the drop gate was never removed, so the higher-priority gate wins and
black-holes the subnet's egress in lr_in_policy before it reaches routing
or SNAT. This left NAT-gateway private-subnet egress with 100% packet
loss: the SNAT stage saw zero packets and no conntrack was committed.

Remove the subnet's drop gate for the same prefix once a reroute is
installed. Idempotent and prefix-scoped, so a specific-prefix reroute is
a no-op and leaves the default gate intact.
This commit is contained in:
joshsiv-mulga
2026-07-21 08:48:05 +10:00
parent 31d71e0390
commit a795c2b204
1 changed files with 14 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
spinifex/network/external/igw.go
Vendored
+14 -2
View File
@@ -445,14 +445,26 @@ func (m *igwManager) ensureSubnetEgressAtPriority(ctx context.Context, vpcID, su
if nexthop == "" { if nexthop == "" {
return fmt.Errorf("%s: no gateway nexthop available for %s (IGW not attached?)", opName, vpcID) return fmt.Errorf("%s: no gateway nexthop available for %s (IGW not attached?)", opName, vpcID)
} }
return m.routes.AddSubnetEgress(ctx, vpcID, policy.SubnetEgressSpec{ if err := m.routes.AddSubnetEgress(ctx, vpcID, policy.SubnetEgressSpec{
SubnetID: subnetID, SubnetID: subnetID,
Prefix: prefix, Prefix: prefix,
Nexthop: nexthop, Nexthop: nexthop,
OutputPort: topology.GatewayRouterPort(vpcID), OutputPort: topology.GatewayRouterPort(vpcID),
Priority: priority, Priority: priority,
ExcludeCIDRs: m.rerouteExcludeCIDRs(ctx, vpcID), ExcludeCIDRs: m.rerouteExcludeCIDRs(ctx, vpcID),
}) }); err != nil {
return err
}
// The priority-1100 drop gate is installed while a subnet is routeless and
// outranks both reroutes (IGW 1000, NATGW 900), so a gate left in place once
// a route lands black-holes the subnet's egress before it reaches routing or
// SNAT. Clear it now that this prefix has a reroute. Idempotent and
// prefix-scoped: gates only exist for the default route, so a specific-prefix
// reroute is a no-op and leaves the default gate intact.
if err := m.RemoveSubnetEgressDrop(ctx, vpcID, subnetID, prefix); err != nil {
return fmt.Errorf("%s: clear drop gate for %s: %w", opName, subnetID, err)
}
return nil
} }
// EnsureSystemInstanceEgress installs a /32 reroute above the drop gate plus a plain // EnsureSystemInstanceEgress installs a /32 reroute above the drop gate plus a plain