OSD: verify that client ops are targeted correctly in the current epoch

We were previously only looking at the epoch the op was sent in, which meant
that if we had dropped responsibility somewhere between send_epoch and our
current epoch, we would queue up the op until a new osdmap came along. If it
never did, we could block all client IO against us...

Fixes: #8338
Signed-off-by: Greg Farnum <greg@inktank.com>

diff --git a/src/osd/OSD.cc b/src/osd/OSD.cc
index 220eac652723e8ee5e3968b27b6cfe41257afa59..143d992048d1715b9f2bbba1dd32bdc61adf342b 100644 (file)
--- a/src/osd/OSD.cc
+++ b/src/osd/OSD.cc
@@ -7857,6 +7857,13 @@ void OSD::handle_op(OpRequestRef op, OSDMapRef osdmap)
     return;
   }
 
+  // check against current map too
+  if (!osdmap->have_pg_pool(pgid.pool()) ||
+      osdmap->get_pg_acting_role(pgid.pgid, whoami) < 0) {
+    dout(7) << "dropping; no longer have PG (or pool); client will retarget" << dendl;
+    return;
+  }
+
   PG *pg = get_pg_or_queue_for_pg(pgid, op);
   if (pg) {
     op->send_map_update = share_map.should_send;