@@ -358,6 +358,7 @@ int setup_map(struct multipath *mpp, char **params, struct vectors *vecs)
sysfs_set_scsi_tmo(conf, mpp);
marginal_pathgroups = conf->marginal_pathgroups;
+ mpp->sync_tick = conf->max_checkint;
pthread_cleanup_pop(1);
if (!mpp->features || !mpp->hwhandler || !mpp->selector) {
@@ -453,6 +453,8 @@ struct multipath {
int ghost_delay;
int ghost_delay_tick;
int queue_mode;
+ unsigned int sync_tick;
+ bool is_checked;
uid_t uid;
gid_t gid;
mode_t mode;
@@ -505,11 +505,16 @@ update_multipath_table (struct multipath *mpp, vector pathvec, int flags)
char __attribute__((cleanup(cleanup_charp))) *params = NULL;
char __attribute__((cleanup(cleanup_charp))) *status = NULL;
unsigned long long size;
+ struct config *conf;
if (!mpp)
return r;
size = mpp->size;
+ conf = get_multipath_config();
+ mpp->sync_tick = conf->max_checkint;
+ put_multipath_config(conf);
+
r = libmp_mapinfo(DM_MAP_BY_NAME | MAPINFO_MPATH_ONLY,
(mapid_t) { .str = mpp->alias },
(mapinfo_t) {
@@ -2342,6 +2342,37 @@ check_path_state(struct path *pp)
return newstate;
}
+static void
+do_sync_mpp(struct vectors * vecs, struct multipath *mpp)
+{
+ int i, ret;
+ struct path *pp;
+
+ mpp->is_checked = true;
+ ret = update_multipath_strings(mpp, vecs->pathvec);
+ if (ret != DMP_OK) {
+ condlog(1, "%s: %s", mpp->alias, ret == DMP_NOT_FOUND ?
+ "device not found" :
+ "couldn't synchronize with kernel state");
+ vector_foreach_slot (mpp->paths, pp, i)
+ pp->dmstate = PSTATE_UNDEF;
+ return;
+ }
+ set_no_path_retry(mpp);
+}
+
+static void
+sync_mpp(struct vectors * vecs, struct multipath *mpp, unsigned int ticks)
+{
+ if (mpp->sync_tick)
+ mpp->sync_tick -= (mpp->sync_tick > ticks) ? ticks :
+ mpp->sync_tick;
+ if (mpp->sync_tick)
+ return;
+
+ do_sync_mpp(vecs, mpp);
+}
+
/*
* Returns '1' if the path has been checked and '0' otherwise
*/
@@ -2356,7 +2387,6 @@ check_path (struct vectors * vecs, struct path * pp, unsigned int ticks)
unsigned int checkint, max_checkint;
struct config *conf;
int marginal_pathgroups, marginal_changed = 0;
- int ret;
bool need_reload;
if (pp->initialized == INIT_REMOVED)
@@ -2395,26 +2425,6 @@ check_path (struct vectors * vecs, struct path * pp, unsigned int ticks)
pp->tick = 1;
return 0;
}
- /*
- * Synchronize with kernel state
- */
- ret = update_multipath_strings(pp->mpp, vecs->pathvec);
- if (ret != DMP_OK) {
- if (ret == DMP_NOT_FOUND) {
- /* multipath device missing. Likely removed */
- condlog(1, "%s: multipath device '%s' not found",
- pp->dev, pp->mpp ? pp->mpp->alias : "");
- return 0;
- } else
- condlog(1, "%s: Couldn't synchronize with kernel state",
- pp->dev);
- pp->dmstate = PSTATE_UNDEF;
- }
- /* if update_multipath_strings orphaned the path, quit early */
- if (!pp->mpp)
- return 0;
- set_no_path_retry(pp->mpp);
-
if (pp->recheck_wwid == RECHECK_WWID_ON &&
(newstate == PATH_UP || newstate == PATH_GHOST) &&
((pp->state != PATH_UP && pp->state != PATH_GHOST) ||
@@ -2424,7 +2434,12 @@ check_path (struct vectors * vecs, struct path * pp, unsigned int ticks)
handle_path_wwid_change(pp, vecs);
return 0;
}
-
+ if (!pp->mpp->is_checked) {
+ do_sync_mpp(vecs, pp->mpp);
+ /* if update_multipath_strings orphaned the path, quit early */
+ if (!pp->mpp)
+ return 0;
+ }
if ((newstate != PATH_UP && newstate != PATH_GHOST &&
newstate != PATH_PENDING) && (pp->state == PATH_DELAYED)) {
/* If path state become failed again cancel path delay state */
@@ -2752,12 +2767,17 @@ checkerloop (void *ap)
while (checker_state != CHECKER_FINISHED) {
unsigned int paths_checked = 0, i;
struct timespec chk_start_time;
+ struct multipath *mpp;
pthread_cleanup_push(cleanup_lock, &vecs->lock);
lock(&vecs->lock);
pthread_testcancel();
+ vector_foreach_slot(vecs->mpvec, mpp, i)
+ mpp->is_checked = false;
get_monotonic_time(&chk_start_time);
if (checker_state == CHECKER_STARTING) {
+ vector_foreach_slot(vecs->mpvec, mpp, i)
+ sync_mpp(vecs, mpp, ticks);
vector_foreach_slot(vecs->pathvec, pp, i)
pp->is_checked = false;
checker_state = CHECKER_RUNNING;
Move the code to sync the mpp device state into a helper function and add a counter to to make sure that the device is synced at least once every max_checkint secs. This makes sure that multipath devices with no paths will still get synced with the kernel. Also, if multiple paths are checked in the same loop, the multipath device will only be synced with the kernel once, since every time the mpp is synced in any code path, mpp->sync_tick is reset. The code still syncs the mpp before updating the path state for two main reasons. 1. Sometimes multipathd leaves the mpp with a garbage state. Future patches will fix most of these cases, but the code intentially does not remove the mpp is resyncing fails while checking paths. But this does leave the mpp with a garbage state. 2. The kernel chages the multipath state independently of multipathd. If the kernel fails a path, a uevent will arrive shortly. But the kernel doesn't provide any notification when it switches the active path group or if it ends up picking a different one than multipathd selected. Multipathd needs to know the actual current pathgroup to know when it should be switching them. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> --- libmultipath/configure.c | 1 + libmultipath/structs.h | 2 ++ libmultipath/structs_vec.c | 5 +++ multipathd/main.c | 64 +++++++++++++++++++++++++------------- 4 files changed, 50 insertions(+), 22 deletions(-)