osd: fix map advance limit to handle map gaps

The recent change in cf25bdf6b0090379903981fe8cee5ea75efd7ba0 would stop
advancing after some number of epochs, but did not take into consideration
the possibilty that there are missing maps.  In that case, it is impossible
to advance past the gap.

Fix this by increasing the max epoch as we go so that we can always get
beyond the gap.

Signed-off-by: Sage Weil <sage@inktank.com>

diff --git a/src/osd/OSD.cc b/src/osd/OSD.cc
index ebd85e7da6e254c2cc2fbb174995f96d2497ed8c..b297bf50149c13b5aa14d1bc8507cc68048d455b 100644 (file)
--- a/src/osd/OSD.cc
+++ b/src/osd/OSD.cc
@@ -6031,8 +6031,13 @@ bool OSD::advance_pg(
        next_epoch <= osd_epoch && next_epoch <= max;
        ++next_epoch) {
     OSDMapRef nextmap = service.try_get_map(next_epoch);
-    if (!nextmap)
+    if (!nextmap) {
+      dout(20) << __func__ << " missing map " << next_epoch << dendl;
+      // make sure max is bumped up so that we can get past any
+      // gap in maps
+      max = MAX(max, next_epoch + g_conf->osd_map_max_advance);
       continue;
+    }
 
     vector<int> newup, newacting;
     int up_primary, acting_primary;
@@ -6063,7 +6068,7 @@ bool OSD::advance_pg(
   service.pg_update_epoch(pg->info.pgid, lastmap->get_epoch());
   pg->handle_activate_map(rctx);
   if (next_epoch <= osd_epoch) {
-    dout(10) << __func__ << " advanced by max " << g_conf->osd_map_max_advance
+    dout(10) << __func__ << " advanced to max " << max
             << " past min epoch " << min_epoch
             << " ... will requeue " << *pg << dendl;
     return false;