mon/OSDMonitor: set POOL_CREATING flag until initial pool pgs are created

Set the flag when the pool is created, and clear it when the initial set
of PGs have been created by the mon.  Move the update_creating_pgs()
block so that we can process the pgid removal from the creating list and
the pool flag removal in the same epoch; otherwise we might remove the
pgid but have no cluster activity to roll over another osdmap epoch to
allow the pool flag to be removed.

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

diff --git a/src/mon/CreatingPGs.h b/src/mon/CreatingPGs.h
index cc2d4f0da001e01064477a515c1a97f5e5e7bd3a..51bc9902c5cf4409c0623b669f82ed9b5ee35a1e 100644 (file)
--- a/src/mon/CreatingPGs.h
+++ b/src/mon/CreatingPGs.h
@@ -47,6 +47,17 @@ struct creating_pgs_t {
   /// pools that exist in the osdmap for which at least one pg has been created
   std::set<int64_t> created_pools;
 
+  bool still_creating_pool(int64_t poolid) {
+    for (auto& i : pgs) {
+      if (i.first.pool() == poolid) {
+       return true;
+      }
+    }
+    if (queue.count(poolid)) {
+      return true;
+    }
+    return false;
+  }
   bool create_pool(int64_t poolid, uint32_t pg_num,
                   epoch_t created, utime_t modified) {
     if (created_pools.count(poolid) == 0) {

diff --git a/src/mon/OSDMonitor.cc b/src/mon/OSDMonitor.cc
index 3a816024fa32ef0245096e61ca135af427ff4f60..ea84caeab7930bdd86c3d9582ba0b37cb5157bd6 100644 (file)
--- a/src/mon/OSDMonitor.cc
+++ b/src/mon/OSDMonitor.cc
@@ -1069,6 +1069,26 @@ void OSDMonitor::encode_pending(MonitorDBStore::TransactionRef t)
     tmp.deepish_copy_from(osdmap);
     tmp.apply_incremental(pending_inc);
 
+    // update creating pgs first so that we can remove the created pgid and
+    // process the pool flag removal below in the same osdmap epoch.
+    auto pending_creatings = update_pending_pgs(pending_inc, tmp);
+    bufferlist creatings_bl;
+    encode(pending_creatings, creatings_bl);
+    t->put(OSD_PG_CREATING_PREFIX, "creating", creatings_bl);
+
+    // remove any old POOL_CREATING flags
+    for (auto& i : tmp.get_pools()) {
+      if (i.second.has_flag(pg_pool_t::FLAG_CREATING) &&
+         !pending_creatings.still_creating_pool(i.first)) {
+       dout(10) << __func__ << " done creating pool " << i.first
+                << ", clearing CREATING flag" << dendl;
+       if (pending_inc.new_pools.count(i.first) == 0) {
+         pending_inc.new_pools[i.first] = i.second;
+       }
+       pending_inc.new_pools[i.first].flags &= ~pg_pool_t::FLAG_CREATING;
+      }
+    }
+
     // remove any legacy osdmap nearfull/full flags
     {
       if (tmp.test_flag(CEPH_OSDMAP_FULL | CEPH_OSDMAP_NEARFULL)) {
@@ -1417,12 +1437,6 @@ void OSDMonitor::encode_pending(MonitorDBStore::TransactionRef t)
   pending_metadata.clear();
   pending_metadata_rm.clear();
 
-  // and pg creating, also!
-  auto pending_creatings = update_pending_pgs(pending_inc, tmp);
-  bufferlist creatings_bl;
-  encode(pending_creatings, creatings_bl);
-  t->put(OSD_PG_CREATING_PREFIX, "creating", creatings_bl);
-
   // removed_snaps
   if (tmp.require_osd_release >= CEPH_RELEASE_MIMIC) {
     for (auto& i : pending_inc.new_removed_snaps) {
@@ -6651,6 +6665,7 @@ int OSDMonitor::prepare_new_pool(string& name,
     pi->set_flag(pg_pool_t::FLAG_NOPGCHANGE);
   if (g_conf()->osd_pool_default_flag_nosizechange)
     pi->set_flag(pg_pool_t::FLAG_NOSIZECHANGE);
+  pi->set_flag(pg_pool_t::FLAG_CREATING);
   if (g_conf()->osd_pool_use_gmt_hitset)
     pi->use_gmt_hitset = true;
   else