mirror/freebsd
1
0
Fork 0
mirror of https://git.FreeBSD.org/src.git synced 2024-12-13 10:02:38 +00:00
Code Issues Releases Activity

lacp: short timeout erroneously declares link-flapping

Browse Source 
Panasas was seeing a higher-than-expected number of link-flap events.
After joint debugging with the switch vendor, we determined there were
problems on both sides; either of which might cause the occasional
event, but together caused lots of them.

On the switch side, an internal queuing issue was causing LACP PDUs --
which should be sent every second, in short-timeout mode -- to sometimes
be sent slightly later than they should have been. In some cases, two
successive PDUs were late, but we never saw three late PDUs in a row.

On the FreeBSD side, we saw a link-flap event every time there were two
late PDUs, while the spec says that it takes *three* seconds of downtime
to trigger that event. It turns out that if a PDU was received shortly
before the timer code was run, it would decrement less than a full
second after the PDU arrived. Then two delayed PDUs would cause two
additional decrements, causing it to reach zero less than three seconds
after the most-recent on-time PDU.

The solution is to note the time a PDU arrives, and only decrement if at
least a full second has elapsed since then.

Reported by:	Greg Foster <gfoster@panasas.com>
Reviewed by:	gallatin
Tested by:	Greg Foster <gfoster@panasas.com>
MFC after:	3 days
Sponsored by:	Panasas
Differential Revision:	https://reviews.freebsd.org/D35070
This commit is contained in:
Greg Foster 2022-04-25 23:38:23 -07:00 committed by Ravi Pokala
parent fa160738bd
commit 00a80538b4
2 changed files with 17 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
sys/net/ieee8023ad_lacp.c
View File

@ -49,6 +49,7 @@ __FBSDID("$FreeBSD$");
#include <sys/lock.h>
#include <sys/rwlock.h>
#include <sys/taskqueue.h>
#include <sys/time.h>
#include <net/if.h>
#include <net/if_var.h>
@ -1731,6 +1732,7 @@ lacp_sm_rx(struct lacp_port *lp, const struct lacpdu *du)
* EXPIRED, DEFAULTED, CURRENT -> CURRENT
*/
microuptime(&lp->lp_last_lacpdu_rx);
lacp_sm_rx_update_selected(lp, du);
lacp_sm_rx_update_ntt(lp, du);
lacp_sm_rx_record_pdu(lp, du);
@ -1940,14 +1942,26 @@ static void
lacp_run_timers(struct lacp_port *lp)
{
int i;
struct timeval time_diff;
for (i = 0; i < LACP_NTIMER; i++) {
KASSERT(lp->lp_timer[i] >= 0,
("invalid timer value %d", lp->lp_timer[i]));
if (lp->lp_timer[i] == 0) {
continue;
} else if (--lp->lp_timer[i] <= 0) {
if (lacp_timer_funcs[i]) {
} else {
if (i == LACP_TIMER_CURRENT_WHILE) {
microuptime(&time_diff);
timevalsub(&time_diff, &lp->lp_last_lacpdu_rx);
if (time_diff.tv_sec) {
/* At least one sec has elapsed since last LACP packet. */
--lp->lp_timer[i];
}
} else {
--lp->lp_timer[i];
}
if ((lp->lp_timer[i] <= 0) && (lacp_timer_funcs[i])) {
(*lacp_timer_funcs[i])(lp);
}
}

1
sys/net/ieee8023ad_lacp.h
View File

@ -222,6 +222,7 @@ struct lacp_port {
#define lp_key lp_actor.lip_key
#define lp_systemid lp_actor.lip_systemid
struct timeval lp_last_lacpdu;
struct timeval lp_last_lacpdu_rx;
int lp_lacpdu_sent;
enum lacp_mux_state lp_mux_state;
enum lacp_selected lp_selected;