sd-radv: do not stop on transient send errors
When the periodic RA timer fires, any error returned by sendmsg() currently propagates up through sd_radv_send() into radv_timeout(), which then calls sd_radv_stop(). The RA engine is never started again until the next carrier transition. On an 802.3ad bond there is a window right after carrier-up where the link is administratively up but no aggregator has been selected yet, so sendmsg() returns ENOBUFS. If the very first RA after a flap lands in that window, radv stops permanently and all clients lose their SLAAC addresses, on-link/PD prefixes, and default router once the previously advertised lifetimes expire, while IPv4 keeps working, leading to a very confusing situation with v4 up and v6 down. Handle this the same way solicited RAs already do (see radv_process_packet()): log the failure and reschedule the timer instead of giving up. ra_sent is left untouched on failure so we stay in the fast initial-advertisement regime until a send actually succeeds.
This commit is contained in:
@@ -254,9 +254,13 @@ int sd_radv_send(sd_radv *ra) {
|
||||
|
||||
r = radv_send_router(ra, NULL);
|
||||
if (r < 0)
|
||||
return log_radv_errno(ra, r, "Unable to send Router Advertisement: %m");
|
||||
|
||||
ra->ra_sent++;
|
||||
/* Do not treat transient send failures (e.g. ENOBUFS while a bond is still selecting an
|
||||
* aggregator after a carrier flap, or ENETDOWN/EADDRNOTAVAIL during a short link bounce) as
|
||||
* fatal: log and reschedule so we try again instead of stopping the RA engine for good.
|
||||
* Solicited RAs already behave this way, see radv_process_packet(). */
|
||||
log_radv_errno(ra, r, "Unable to send Router Advertisement, will retry later: %m");
|
||||
else
|
||||
ra->ra_sent++;
|
||||
|
||||
/* RFC 4861, Section 6.2.4, sending initial Router Advertisements */
|
||||
if (ra->ra_sent <= RADV_MAX_INITIAL_RTR_ADVERTISEMENTS)
|
||||
@@ -283,8 +287,12 @@ int sd_radv_send(sd_radv *ra) {
|
||||
assert(min_timeout <= max_timeout * 3 / 4);
|
||||
|
||||
timeout = min_timeout + random_u64_range(max_timeout - min_timeout);
|
||||
log_radv(ra, "Sent unsolicited Router Advertisement. Next advertisement will be in %s.",
|
||||
FORMAT_TIMESPAN(timeout, USEC_PER_SEC));
|
||||
if (r >= 0)
|
||||
log_radv(ra, "Sent unsolicited Router Advertisement. Next advertisement will be in %s.",
|
||||
FORMAT_TIMESPAN(timeout, USEC_PER_SEC));
|
||||
else
|
||||
log_radv(ra, "Next Router Advertisement attempt in %s.",
|
||||
FORMAT_TIMESPAN(timeout, USEC_PER_SEC));
|
||||
|
||||
return event_reset_time(
|
||||
ra->event, &ra->timeout_event_source,
|
||||
|
||||
Reference in New Issue
Block a user