> Aha, okay. That's not the right fix, but points the way to the real > problem. Basically, the rdcache_gen/rdcache_revoking behavior is based on > how things worked before we looked at i_data.nrpages. We should never > clear rdcache_gen (unless, perhaps, we're sure we don't hold the cap, but > there's no point), and it being zero no longer has any special meaning. > > Can you try the below patch? I've done some light testing, but nothing > serious yet. >
Tried this patch. It's working well! Thanks, Henry -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
