On 2023/05/26 13:52, Stuart Henderson wrote:
> I think my main issues come around LS_REFRESH_TIME intervals, when
> there's loads of churn and "ospf6d: ospf engine" can be busy for
> minutes at a time (not always, but very often). Don't know if that rings
> any bells for anyone... (I am now reminded that RTM_DESYNC isn't handled
> by ospf6d which probably doesn't help matters).
Here's a first attempt at porting the fib reload/desync diffs from
ospfd to ospf6d ... Not sure if it's good yet, but it didn't immediately
crash and burn when I ran "ospf6ctl fib reload", at least.
Index: ospf6ctl/ospf6ctl.8
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6ctl/ospf6ctl.8,v
retrieving revision 1.13
diff -u -p -r1.13 ospf6ctl.8
--- ospf6ctl/ospf6ctl.8 2 Mar 2023 17:09:53 -0000 1.13
+++ ospf6ctl/ospf6ctl.8 26 May 2023 13:37:55 -0000
@@ -58,6 +58,9 @@ Remove the learned routes from the FIB.
Decoupling the FIB from an OSPF router may create routing loops and could cause
major routing issues in the complete OSPF cloud.
Only routers with just one link to the OSPF cloud can safely decouple the FIB.
+.It Cm fib reload
+Refetches and relearns the routes in the Forwarding Information Base
+a.k.a. the kernel routing table.
.It Cm log brief
Disable verbose debug logging.
.It Cm log verbose
Index: ospf6ctl/ospf6ctl.c
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6ctl/ospf6ctl.c,v
retrieving revision 1.53
diff -u -p -r1.53 ospf6ctl.c
--- ospf6ctl/ospf6ctl.c 27 Dec 2022 12:11:39 -0000 1.53
+++ ospf6ctl/ospf6ctl.c 26 May 2023 13:37:55 -0000
@@ -225,6 +225,11 @@ main(int argc, char *argv[])
printf("decouple request sent.\n");
done = 1;
break;
+ case FIB_RELOAD:
+ imsg_compose(ibuf, IMSG_CTL_FIB_RELOAD, 0, 0, -1, NULL, 0);
+ printf("reload request sent.\n");
+ done = 1;
+ break;
case LOG_VERBOSE:
verbose = 1;
/* FALLTHROUGH */
@@ -304,6 +309,7 @@ main(int argc, char *argv[])
case FIB:
case FIB_COUPLE:
case FIB_DECOUPLE:
+ case FIB_RELOAD:
case LOG_VERBOSE:
case LOG_BRIEF:
case RELOAD:
Index: ospf6ctl/parser.c
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6ctl/parser.c,v
retrieving revision 1.14
diff -u -p -r1.14 parser.c
--- ospf6ctl/parser.c 26 May 2019 09:27:09 -0000 1.14
+++ ospf6ctl/parser.c 26 May 2023 13:37:55 -0000
@@ -73,6 +73,7 @@ static const struct token t_main[] = {
static const struct token t_fib[] = {
{ KEYWORD, "couple", FIB_COUPLE, NULL},
{ KEYWORD, "decouple", FIB_DECOUPLE, NULL},
+ { KEYWORD, "reload", FIB_RELOAD, NULL},
{ ENDTOKEN, "", NONE, NULL}
};
Index: ospf6ctl/parser.h
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6ctl/parser.h,v
retrieving revision 1.9
diff -u -p -r1.9 parser.h
--- ospf6ctl/parser.h 26 May 2019 09:27:09 -0000 1.9
+++ ospf6ctl/parser.h 26 May 2023 13:37:55 -0000
@@ -29,6 +29,7 @@ enum actions {
FIB,
FIB_COUPLE,
FIB_DECOUPLE,
+ FIB_RELOAD,
LOG_VERBOSE,
LOG_BRIEF,
SHOW,
Index: ospf6d/control.c
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6d/control.c,v
retrieving revision 1.31
diff -u -p -r1.31 control.c
--- ospf6d/control.c 8 Mar 2023 04:43:14 -0000 1.31
+++ ospf6d/control.c 26 May 2023 13:37:55 -0000
@@ -279,6 +279,7 @@ control_dispatch_imsg(int fd, short even
case IMSG_CTL_FIB_DECOUPLE:
ospfe_fib_update(imsg.hdr.type);
/* FALLTHROUGH */
+ case IMSG_CTL_FIB_RELOAD:
case IMSG_CTL_RELOAD:
c->iev.ibuf.pid = imsg.hdr.pid;
ospfe_imsg_compose_parent(imsg.hdr.type, 0, NULL, 0);
Index: ospf6d/kroute.c
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6d/kroute.c,v
retrieving revision 1.67
diff -u -p -r1.67 kroute.c
--- ospf6d/kroute.c 8 Mar 2023 04:43:14 -0000 1.67
+++ ospf6d/kroute.c 26 May 2023 13:37:55 -0000
@@ -45,16 +45,22 @@ struct {
u_int32_t rtseq;
pid_t pid;
int fib_sync;
+ int fib_serial;
u_int8_t fib_prio;
int fd;
- struct event ev;
+ struct event ev, reload;
u_int rdomain;
+#define KR_RELOAD_IDLE 0
+#define KR_RELOAD_FETCH 1
+#define KR_RELOAD_HOLD 2
+ int reload_state;
} kr_state;
struct kroute_node {
RB_ENTRY(kroute_node) entry;
struct kroute_node *next;
struct kroute r;
+ int serial;
};
void kr_redist_remove(struct kroute_node *, struct kroute_node *);
@@ -90,7 +96,10 @@ void if_announce(void *);
int send_rtmsg(int, int, struct kroute *);
int dispatch_rtmsg(void);
int fetchtable(void);
-int rtmsg_process(char *, size_t);
+int refetchtable(void);
+int rtmsg_process(char *, size_t);
+void kr_fib_reload_timer(int, short, void *);
+void kr_fib_reload_arm_timer(int);
RB_HEAD(kroute_tree, kroute_node) krt;
RB_PROTOTYPE(kroute_tree, kroute_node, entry, kroute_compare)
@@ -165,6 +174,9 @@ kr_init(int fs, u_int rdomain, int redis
kr_dispatch_msg, NULL);
event_add(&kr_state.ev, NULL);
+ kr_state.reload_state = KR_RELOAD_IDLE;
+ evtimer_set(&kr_state.reload, kr_fib_reload_timer, NULL);
+
return (0);
}
@@ -374,6 +386,62 @@ kr_fib_decouple(void)
}
void
+kr_fib_reload_timer(int fd, short event, void *bula)
+{
+ if (kr_state.reload_state == KR_RELOAD_FETCH) {
+ kr_fib_reload();
+ kr_state.reload_state = KR_RELOAD_HOLD;
+ kr_fib_reload_arm_timer(KR_RELOAD_HOLD_TIMER);
+ } else {
+ kr_state.reload_state = KR_RELOAD_IDLE;
+ }
+}
+
+void
+kr_fib_reload_arm_timer(int delay)
+{
+ struct timeval tv;
+
+ timerclear(&tv);
+ tv.tv_sec = delay / 1000;
+ tv.tv_usec = (delay % 1000) * 1000;
+
+ if (evtimer_add(&kr_state.reload, &tv) == -1)
+ fatal("add_reload_timer");
+}
+
+void
+kr_fib_reload(void)
+{
+ struct kroute_node *krn, *kr, *kn;
+
+ kr_state.fib_serial++;
+
+ if (fetchifs(0) != 0 || fetchtable() != 0)
+ return;
+
+ for (kr = RB_MIN(kroute_tree, &krt); kr != NULL; kr = krn) {
+ krn = RB_NEXT(kroute_tree, &krt, kr);
+
+ do {
+ kn = kr->next;
+
+ if (kr->serial != kr_state.fib_serial) {
+
+ if (kr->r.priority == RTP_OSPF) {
+ kr->serial = kr_state.fib_serial;
+ if (send_rtmsg(kr_state.fd,
+ RTM_ADD, &kr->r) != 0)
+ break;
+ } else
+ kroute_remove(kr);
+ }
+
+ } while ((kr = kn) != NULL);
+ }
+}
+
+void
kr_fib_update_prio(u_int8_t fib_prio)
{
struct kroute_node *kr;
@@ -664,6 +732,8 @@ kroute_insert(struct kroute_node *kr)
{
struct kroute_node *krm, *krh;
+ kr->serial = kr_state.fib_serial;
+
if ((krh = RB_INSERT(kroute_tree, &krt, kr)) != NULL) {
/*
* Multipath route, add at end of list.
@@ -1279,7 +1349,7 @@ rtmsg_process(char *buf, size_t len)
int flags, mpath;
unsigned int scope;
u_short ifindex = 0;
- int rv;
+ int rv, delay;
size_t offset;
char *next;
@@ -1395,13 +1465,10 @@ rtmsg_process(char *buf, size_t len)
if ((okr = kroute_find(&prefix, prefixlen, prio))
!= NULL) {
- /* just add new multipath routes */
- if (mpath && rtm->rtm_type == RTM_ADD)
- goto add;
- /* get the correct route */
kr = okr;
- if (mpath && (kr = kroute_matchgw(okr,
- &nexthop, scope)) == NULL) {
+ if ((mpath || prio == kr_state.fib_prio) &&
+ (kr = kroute_matchgw(okr, &nexthop, scope))
==
+ NULL) {
log_warnx("rtmsg_process: mpath route"
" not found");
/* add routes we missed out earlier */
@@ -1432,13 +1499,15 @@ rtmsg_process(char *buf, size_t len)
kr->r.flags |= F_DOWN;
/* just readd, the RDE will care */
- kr_redistribute(okr);
+ okr->serial = kr_state.fib_serial;
+ kr_redistribute(kr);
} else {
add:
if ((kr = calloc(1,
sizeof(struct kroute_node))) == NULL) {
log_warn("rtmsg_process calloc");
- return (-1);
+ rv = -1;
+ break;
}
kr->r.prefix = prefix;
kr->r.prefixlen = prefixlen;
@@ -1517,6 +1586,23 @@ add:
break;
case RTM_IFANNOUNCE:
if_announce(next);
+ break;
+ case RTM_DESYNC:
+ /*
+ * We lost some routing packets. Schedule a reload
+ * of the kernel route/interface information.
+ */
+ if (kr_state.reload_state == KR_RELOAD_IDLE) {
+ delay = KR_RELOAD_TIMER;
+ log_info("desync; scheduling fib reload");
+ } else {
+ delay = KR_RELOAD_HOLD_TIMER;
+ log_debug("desync during KR_RELOAD_%s",
+ kr_state.reload_state ==
+ KR_RELOAD_FETCH ? "FETCH" : "HOLD");
+ }
+ kr_state.reload_state = KR_RELOAD_FETCH;
+ kr_fib_reload_arm_timer(delay);
break;
default:
/* ignore for now */
Index: ospf6d/ospf6.h
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6d/ospf6.h,v
retrieving revision 1.21
diff -u -p -r1.21 ospf6.h
--- ospf6d/ospf6.h 25 Mar 2013 14:29:35 -0000 1.21
+++ ospf6d/ospf6.h 26 May 2023 13:37:55 -0000
@@ -69,6 +69,10 @@
#define MIN_SPF_HOLDTIME 1
#define MAX_SPF_HOLDTIME 5
+/* msec */
+#define KR_RELOAD_TIMER 250
+#define KR_RELOAD_HOLD_TIMER 5000
+
#define MIN_MD_ID 0
#define MAX_MD_ID 255
Index: ospf6d/ospf6d.c
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6d/ospf6d.c,v
retrieving revision 1.53
diff -u -p -r1.53 ospf6d.c
--- ospf6d/ospf6d.c 8 Mar 2023 04:43:14 -0000 1.53
+++ ospf6d/ospf6d.c 26 May 2023 13:37:55 -0000
@@ -372,6 +372,9 @@ main_dispatch_ospfe(int fd, short event,
case IMSG_CTL_FIB_DECOUPLE:
kr_fib_decouple();
break;
+ case IMSG_CTL_FIB_RELOAD:
+ kr_fib_reload();
+ break;
case IMSG_CTL_KROUTE:
case IMSG_CTL_KROUTE_ADDR:
kr_show_route(&imsg);
Index: ospf6d/ospf6d.h
===================================================================
RCS file: /cvs/src/usr.sbin/ospf6d/ospf6d.h,v
retrieving revision 1.50
diff -u -p -r1.50 ospf6d.h
--- ospf6d/ospf6d.h 19 Jan 2021 09:46:51 -0000 1.50
+++ ospf6d/ospf6d.h 26 May 2023 13:37:55 -0000
@@ -93,6 +93,7 @@ enum imsg_type {
IMSG_CTL_SHOW_SUM_AREA,
IMSG_CTL_FIB_COUPLE,
IMSG_CTL_FIB_DECOUPLE,
+ IMSG_CTL_FIB_RELOAD,
IMSG_CTL_AREA,
IMSG_CTL_IFACE,
IMSG_CTL_KROUTE,
@@ -546,6 +547,7 @@ int kr_delete(struct kroute *);
void kr_shutdown(void);
void kr_fib_couple(void);
void kr_fib_decouple(void);
+void kr_fib_reload(void);
void kr_fib_update_prio(u_int8_t);
void kr_dispatch_msg(int, short, void *);
void kr_show_route(struct imsg *);
