Fix a bug in LSM where updates with overwrite could be skipped.

References JIRA BF-829

The issue was that we were not looking in all chunks of an LSM
tree before deciding whether to apply an update (insert or remove).

2 files changed, 96 insertions, 4 deletions

diff --git a/src/lsm/lsm_cursor.c b/src/lsm/lsm_cursor.c
index a18269baa28..4508c54b6ff 100644
--- a/src/lsm/lsm_cursor.c
+++ b/src/lsm/lsm_cursor.c
@@ -394,10 +394,18 @@ __clsm_open_cursors(
 	lsm_tree = clsm->lsm_tree;
 	chunk = NULL;
 
-	if (update) {
-		if (txn->isolation == TXN_ISO_SNAPSHOT)
-			F_SET(clsm, WT_CLSM_OPEN_SNAPSHOT);
-	} else
+	/*
+	 * Ensure that any snapshot update has cursors on the right set of
+	 * chunks to guarantee visibility is correct.
+	 */
+	if (update && txn->isolation == TXN_ISO_SNAPSHOT)
+		F_SET(clsm, WT_CLSM_OPEN_SNAPSHOT);
+
+	/*
+	 * Query operations need a full set of cursors. Overwrite cursors
+	 * do queries in service of updates.
+	 */
+	if (!update || !F_ISSET(c, WT_CURSTD_OVERWRITE))
 		F_SET(clsm, WT_CLSM_OPEN_READ);
 
 	if (lsm_tree->nchunks == 0)
diff --git a/test/suite/test_bug013.py b/test/suite/test_bug013.py
new file mode 100644
index 00000000000..2993385dba1
--- /dev/null
+++ b/test/suite/test_bug013.py
@@ -0,0 +1,84 @@
+#!/usr/bin/env python
+#
+# Public Domain 2014-2015 MongoDB, Inc.
+# Public Domain 2008-2014 WiredTiger, Inc.
+#
+# This is free and unencumbered software released into the public domain.
+#
+# Anyone is free to copy, modify, publish, use, compile, sell, or
+# distribute this software, either in source code form or as a compiled
+# binary, for any purpose, commercial or non-commercial, and by any
+# means.
+#
+# In jurisdictions that recognize copyright laws, the author or authors
+# of this software dedicate any and all copyright interest in the
+# software to the public domain. We make this dedication for the benefit
+# of the public at large and to the detriment of our heirs and
+# successors. We intend this dedication to be an overt act of
+# relinquishment in perpetuity of all present and future rights to this
+# software under copyright law.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+
+import wiredtiger, wttest
+
+# test_bug013.py
+#    Test data consistency in LSM with updates. Ensure that overwrite
+#    cursors see all entries in the tree (i.e: they open cursors on all
+#    chunks in the LSM tree).
+#    See JIRA BF-829
+class test_bug013(wttest.WiredTigerTestCase):
+    """
+    Test LSM data consistency.
+    """
+    uri = 'table:test_bug013'
+
+    def check_entries(self, keys):
+        # Test by iterating.
+        cursor = self.session.open_cursor(self.uri, None, None)
+        i = 0
+        for i1, i2, i3, v1 in cursor:
+            self.assertEqual( keys[i], [i1, i2, i3])
+            i += 1
+        cursor.close()
+        self.assertEqual(i, len(keys))
+
+    def test_lsm_consistency(self):
+        self.session.reconfigure("isolation=snapshot")
+        self.session.create(self.uri, 'key_format=iii,value_format=i,type=lsm')
+        cursor = self.session.open_cursor(self.uri, None, None)
+        cursor[(2, 6, 1)] = 0
+        cursor.close()
+        # Ensure the first chunk is flushed to disk, so the tree will have
+        # at least two chunks. Wrapped in a try, since it sometimes gets
+        # an EBUSY return
+        try:
+            self.session.verify(self.uri, None)
+        except wiredtiger.WiredTigerError:
+            pass
+
+        # Add a key
+        cursor = self.session.open_cursor(self.uri, None, 'overwrite=false')
+        cursor[(1, 5, 1)] = 0
+        cursor.close()
+
+        # Remove the key we just added. If the LSM code is broken, the
+        # search for the key we just inserted returns not found - so the
+        # key isn't actually removed.
+        cursor = self.session.open_cursor(self.uri, None, 'overwrite=false')
+        cursor.set_key((1, 5, 1))
+        cursor.remove()
+        cursor.close()
+
+        # Verify that the data is as we expect
+        self.check_entries([[2, 6, 1]])
+
+if __name__ == '__main__':
+    wttest.run()
+