Implement blacklist/whitelist

Change from the all/whitelist ebhavior to the blacklist/whitelist
behaviour documented in the write-up

docs/ANTI_ENTROPY.md

@@ -2,7 +2,7 @@
 
 ## Background
 
-In the initial releases of Riak, there were three levels of protection against loss of data, where loss is caused by either a backend store not receiving data (because it was unavailable), or losing writes (due to a crash, or corruption of previously written data):
+In the early history of Riak, there were three levels of protection against loss of data, where loss is caused by either a backend store not receiving data (because it was unavailable), or losing writes (due to a crash, or corruption of previously written data):
 
 - [Read repair](http://docs.basho.com/riak/kv/2.2.3/learn/concepts/replication/#read-repair), whenever an object was read, if as part of that read it was discovered that a vnode that should have the an update but instead has an older version of an object; then post the completion of the read the finite-state-machine managing the get would update the out-of-date vnode with the latest version.
 
@@ -36,7 +36,7 @@ Although this represented an improvement in terms of entropy management, there w
 
 - The hash of the object was *not* based on a canonicalised version of the object, so could be inconsistent between trees (https://github.com/basho/riak_kv/issues/1189).
 
-- Converting the object from_binary and sending it to another process has a potentially non-trivial cost for larger objects with significant amounts of metadata (e.g. 2i terms).
+- Converting the object from_binary and sending it to another process (to pass from the `riak_kv_vnode` to the `riak_kv_index_hashtree` has a potentially non-trivial cost for larger objects with significant amounts of metadata (e.g. 2i terms).
 
 - Hashtrees may become mysteriously inconsistent following rebuilds, if the rebuild followed a cluster change operation (e.g. adding/removing a node) - and there would be storms of read actions prompted that would not lead to repairs.
 

include/leveled.hrl

@@ -67,9 +67,17 @@
                         waste_retention_period :: integer(),
                         reload_strategy = [] :: list()}).
 
--record(recent_aae, {buckets :: list()|all,
-                        % whitelist of buckets to support recent recent AAE
-                        % or all to support all buckets
+-record(recent_aae, {filter :: whitelist|blacklist,
+                        % the buckets list should either be a
+                        % - whitelist - specific buckets are included, and
+                        % entries are indexed by bucket name
+                        % - blacklist - specific buckets are excluded, and
+                        % all other entries are indexes using the special
+                        % $all bucket
+                        
+                        buckets :: list(),
+                        % whitelist or blacklist of buckets to support recent
+                        % AAE
                         
                         limit_minutes :: integer(),
                         % how long to retain entries the temporary index for

src/leveled_bookie.erl

@@ -393,8 +393,9 @@ init([Opts]) ->
                 case get_opt(recent_aae, Opts, ?RECENT_AAE) of
                     false ->
                         false;
-                    {BucketList, LimitMinutes, UnitMinutes} ->
-                        #recent_aae{buckets = BucketList,
+                    {FilterType, BucketList, LimitMinutes, UnitMinutes} ->
+                        #recent_aae{filter = FilterType,
+                                    buckets = BucketList,
                                     limit_minutes = LimitMinutes,
                                     unit_minutes = UnitMinutes}
                 end,

src/leveled_codec.erl

@@ -430,12 +430,18 @@ aae_indexspecs(false, _Bucket, _Key, _SQN, _H, _LastMods) ->
 aae_indexspecs(_AAE, _Bucket, _Key, _SQN, _H, []) ->
     [];
 aae_indexspecs(AAE, Bucket, Key, SQN, H, LastMods) ->
+    InList = lists:member(Bucket, AAE#recent_aae.buckets),
     Bucket0 =
-        case AAE#recent_aae.buckets of
-            all ->
-                {all, Bucket};
-            ListB ->
-                case lists:member(Bucket, ListB) of
+        case AAE#recent_aae.filter of
+            blacklist ->
+                case InList of
+                    true ->
+                        false;
+                    false ->
+                        {all, Bucket}
+                end;
+            whitelist ->
+                case InList of
                     true ->
                         Bucket;
                     false ->
@@ -811,7 +817,10 @@ parseolddate_test() ->
     ?assertMatch(no_index, PD).
 
 genaaeidx_test() ->
-    AAE = #recent_aae{buckets=all, limit_minutes=60, unit_minutes=5},
+    AAE = #recent_aae{filter=blacklist,
+                        buckets=[],
+                        limit_minutes=60,
+                        unit_minutes=5},
     Bucket = <<"Bucket1">>,
     Key = <<"Key1">>,
     SQN = 1,
@@ -832,16 +841,22 @@ genaaeidx_test() ->
     AAESpecs0 = aae_indexspecs(AAE, Bucket, Key, SQN, H, LastMods0),
     ?assertMatch(0, length(AAESpecs0)),
     
-    AAE0 = AAE#recent_aae{buckets=[<<"Bucket0">>]},
+    AAE0 = AAE#recent_aae{filter=whitelist,
+                            buckets=[<<"Bucket0">>]},
     AAESpecsB0 = aae_indexspecs(AAE0, Bucket, Key, SQN, H, LastMods1),
     ?assertMatch(0, length(AAESpecsB0)),
-    AAESpecsB1 = aae_indexspecs(AAE0, <<"Bucket0">>, Key, SQN, H, LastMods1),
     
+    AAESpecsB1 = aae_indexspecs(AAE0, <<"Bucket0">>, Key, SQN, H, LastMods1),
     ?assertMatch(1, length(AAESpecsB1)),
     [{{?IDX_TAG, <<"Bucket0">>, {Fld, Term}, <<"Key1">>},
         {SQN, {active, TS}, no_lookup, null}}] = AAESpecsB1,
     ?assertMatch(true, is_integer(TS)),
     ?assertMatch(17, length(binary_to_list(Term))),
-    ?assertMatch("$aae.", lists:sublist(binary_to_list(Fld), 5)).
+    ?assertMatch("$aae.", lists:sublist(binary_to_list(Fld), 5)),
+    
+    AAE1 = AAE#recent_aae{filter=blacklist,
+                            buckets=[<<"Bucket0">>]},
+    AAESpecsB2 = aae_indexspecs(AAE1, <<"Bucket0">>, Key, SQN, H, LastMods1),
+    ?assertMatch(0, length(AAESpecsB2)).
 
 -endif.

test/end_to_end/tictac_SUITE.erl

@@ -507,7 +507,7 @@ recent_aae_allaae(_Config) ->
     TreeSize = small,
     % SegmentCount = 256 * 256,
     UnitMins = 2,
-    AAE = {all, 60, UnitMins},
+    AAE = {blacklist, [], 60, UnitMins},
     
     % Test requires multiple different databases, so want to mount them all
     % on individual file paths
@@ -658,7 +658,7 @@ recent_aae_bucketaae(_Config) ->
     TreeSize = small,
     % SegmentCount = 256 * 256,
     UnitMins = 2,
-    AAE = {[<<"Bucket">>], 60, UnitMins},
+    AAE = {whitelist, [<<"Bucket">>], 60, UnitMins},
     
     % Test requires multiple different databases, so want to mount them all
     % on individual file paths
@@ -825,7 +825,7 @@ recent_aae_expiry(_Config) ->
     % SegmentCount = 256 * 256,
     UnitMins = 1,
     TotalMins = 2,
-    AAE = {all, TotalMins, UnitMins},
+    AAE = {backlist, [], TotalMins, UnitMins},
     
     % Test requires multiple different databases, so want to mount them all
     % on individual file paths