ReplicatedPG: clean out completed trimmed objects as we go

Also, explicitely maintain a max number of concurrently trimming
objects.

Fixes: 9113
Backport: dumpling, firefly, giant
Signed-off-by: Samuel Just <sam.just@inktank.com>

diff --git a/src/common/config_opts.h b/src/common/config_opts.h
index a065a772f9b13021ca87ba64fa99e95ac940ca82..f9a4a5929e59d5b722cfeace798d0816c2122e5f 100644 (file)
--- a/src/common/config_opts.h
+++ b/src/common/config_opts.h
@@ -480,6 +480,9 @@ OPTION(osd_heartbeat_interval, OPT_INT, 6)       // (seconds) how often we ping
 OPTION(osd_heartbeat_grace, OPT_INT, 20)         // (seconds) how long before we decide a peer has failed
 OPTION(osd_heartbeat_min_peers, OPT_INT, 10)     // minimum number of peers
 
+// max number of parallel snap trims/pg
+OPTION(osd_pg_max_concurrent_snap_trims, OPT_U64, 2)
+
 // minimum number of peers tha tmust be reachable to mark ourselves
 // back up after being wrongly marked down.
 OPTION(osd_heartbeat_min_healthy_ratio, OPT_FLOAT, .33)

diff --git a/src/osd/ReplicatedPG.cc b/src/osd/ReplicatedPG.cc
index 95b61a3112246da131e2b8981090659cd230f069..de58ebefc58a1e804d72efa469245f60e91c8810 100644 (file)
--- a/src/osd/ReplicatedPG.cc
+++ b/src/osd/ReplicatedPG.cc
@@ -11889,32 +11889,45 @@ boost::statechart::result ReplicatedPG::TrimmingObjects::react(const SnapTrim&)
 
   dout(10) << "TrimmingObjects: trimming snap " << snap_to_trim << dendl;
 
-  // Get next
-  hobject_t old_pos = pos;
-  int r = pg->snap_mapper.get_next_object_to_trim(snap_to_trim, &pos);
-  if (r != 0 && r != -ENOENT) {
-    derr << __func__ << ": get_next returned " << cpp_strerror(r) << dendl;
-    assert(0);
-  } else if (r == -ENOENT) {
-    // Done!
-    dout(10) << "TrimmingObjects: got ENOENT" << dendl;
-    post_event(SnapTrim());
-    return transit< WaitingOnReplicas >();
+  for (set<RepGather *>::iterator i = repops.begin();
+       i != repops.end(); 
+       ) {
+    if ((*i)->all_applied && (*i)->all_committed) {
+      (*i)->put();
+      repops.erase(i++);
+    } else {
+      ++i;
+    }
   }
 
-  dout(10) << "TrimmingObjects react trimming " << pos << dendl;
-  RepGather *repop = pg->trim_object(pos);
-  if (!repop) {
-    dout(10) << __func__ << " could not get write lock on obj "
-            << pos << dendl;
-    pos = old_pos;
-    return discard_event();
-  }
-  assert(repop);
-  repop->queue_snap_trimmer = true;
+  while (repops.size() < g_conf->osd_pg_max_concurrent_snap_trims) {
+    // Get next
+    hobject_t old_pos = pos;
+    int r = pg->snap_mapper.get_next_object_to_trim(snap_to_trim, &pos);
+    if (r != 0 && r != -ENOENT) {
+      derr << __func__ << ": get_next returned " << cpp_strerror(r) << dendl;
+      assert(0);
+    } else if (r == -ENOENT) {
+      // Done!
+      dout(10) << "TrimmingObjects: got ENOENT" << dendl;
+      post_event(SnapTrim());
+      return transit< WaitingOnReplicas >();
+    }
+
+    dout(10) << "TrimmingObjects react trimming " << pos << dendl;
+    RepGather *repop = pg->trim_object(pos);
+    if (!repop) {
+      dout(10) << __func__ << " could not get write lock on obj "
+              << pos << dendl;
+      pos = old_pos;
+      return discard_event();
+    }
+    assert(repop);
+    repop->queue_snap_trimmer = true;
 
-  repops.insert(repop->get());
-  pg->simple_repop_submit(repop);
+    repops.insert(repop->get());
+    pg->simple_repop_submit(repop);
+  }
   return discard_event();
 }
 /* WaitingOnReplicasObjects */
@@ -11948,7 +11961,7 @@ boost::statechart::result ReplicatedPG::WaitingOnReplicas::react(const SnapTrim&
   for (set<RepGather *>::iterator i = repops.begin();
        i != repops.end();
        repops.erase(i++)) {
-    if (!(*i)->all_applied) {
+    if (!(*i)->all_applied || !(*i)->all_committed) {
       return discard_event();
     } else {
       (*i)->put();