On Tue, Dec 10, 2024 at 02:02:32PM -0500, Benjamin Marzinski wrote:
> On Sat, Dec 07, 2024 at 12:36:07AM +0100, Martin Wilck wrote:
> > We previously didn't allow map removal inside the checker loop. But
> > with the late updates to the checkerloop code, it should be safe to orphan
> > paths and delete maps even in this situation. We remove such maps everywhere
> > else in the code already, whenever refresh_multipath() or setup_multipath()
> > is called.
>
> I don't think that this is safe. It's possible that the multipath device
> has paths in the INIT_REMOVED or INIT_PARTIAL state. These will get
> silently removed from the pathvec if we remove the map here. This will
> mess up our iteration through the pathvec in update_paths(). Perhaps a
> better idea would be to set mpp->sync_ticks to 0 if
> update_multipath_strings() fails in do_sync_mpp(). This would force a
> refresh by sync_mpp() at the start of the next loop in checkerloop(),
> where it can safely remove the multipath device.
If we go this route we should probably rename do_sync_map() to
sync_map() and rename sync_map() to something like check_refresh_map(),
since it would now be calling refresh_map() instead of do_sync_map().
>
> -Ben
>
> > Signed-off-by: Martin Wilck <mwilck@xxxxxxxx>
> > ---
> > multipathd/main.c | 43 ++++++++++++++++++++-----------------------
> > 1 file changed, 20 insertions(+), 23 deletions(-)
> >
> > diff --git a/multipathd/main.c b/multipathd/main.c
> > index 4a28fbb..131dab6 100644
> > --- a/multipathd/main.c
> > +++ b/multipathd/main.c
> > @@ -2446,34 +2446,30 @@ get_new_state(struct path *pp)
> > return newstate;
> > }
> >
> > -static void
> > -do_sync_mpp(struct vectors * vecs, struct multipath *mpp)
> > +/* Returns true if the mpp was deleted */
> > +static int
> > +do_sync_mpp(struct vectors *vecs, struct multipath *mpp)
> > {
> > - int i, ret;
> > - struct path *pp;
> > + int ret;
> > +
> > + ret = refresh_multipath(vecs, mpp);
> > + if (ret)
> > + return ret;
> >
> > - 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);
> > + return 0;
> > }
> >
> > -static void
> > +static int
> > 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;
> > + return 0;
> >
> > - do_sync_mpp(vecs, mpp);
> > + return do_sync_mpp(vecs, mpp);
> > }
> >
> > static int
> > @@ -2513,12 +2509,10 @@ update_path_state (struct vectors * vecs, struct path * pp)
> > return handle_path_wwid_change(pp, vecs)? CHECK_PATH_REMOVED :
> > CHECK_PATH_SKIPPED;
> > }
> > - if (pp->mpp->synced_count == 0) {
> > - do_sync_mpp(vecs, pp->mpp);
> > + if (pp->mpp->synced_count == 0 && do_sync_mpp(vecs, pp->mpp))
> > /* if update_multipath_strings orphaned the path, quit early */
> > - if (!pp->mpp)
> > - return CHECK_PATH_SKIPPED;
> > - }
> > + return CHECK_PATH_SKIPPED;
> > +
> > if ((newstate != PATH_UP && newstate != PATH_GHOST &&
> > newstate != PATH_PENDING) && (pp->state == PATH_DELAYED)) {
> > /* If path state become failed again cancel path delay state */
> > @@ -3018,8 +3012,11 @@ checkerloop (void *ap)
> > mpp->synced_count = 0;
> > if (checker_state == CHECKER_STARTING) {
> > vector_foreach_slot(vecs->mpvec, mpp, i) {
> > - sync_mpp(vecs, mpp, ticks);
> > - mpp->prio_update = PRIO_UPDATE_NONE;
> > + if (sync_mpp(vecs, mpp, ticks))
> > + /* map deleted */
> > + i--;
> > + else
> > + mpp->prio_update = PRIO_UPDATE_NONE;
> > }
> > vector_foreach_slot(vecs->pathvec, pp, i)
> > pp->is_checked = CHECK_PATH_UNCHECKED;
> > --
> > 2.47.0
