From f8b3101a3af2c03aadbdfdb98b0fdbecf366bfa9 Mon Sep 17 00:00:00 2001
From: Martin Sumner <martin.sumner@adaptip.co.uk>
Date: Mon, 15 Jul 2019 13:44:39 +0100
Subject: [PATCH] Two memory management helpers

Two helpers for memory management:

1 - a scan over the cdb file may lead to a lot of binary references being made.  So force a GC fater the scan.

2 - the penciller files contain slots that will be frequently read - so advice the page cache to pre-load them on startup.

This is in response to unexpected memory mangement issues in a potentially non-conventional setup - where the erlang VM held a lot of memory (that could be GC'd , in preference to the page cache - and consequently disk I/O and request latency were higher than expected.
---
 src/leveled_cdb.erl            |  3 ++
 src/leveled_sst.erl            |  1 +
 test/end_to_end/riak_SUITE.erl | 57 +++++++++++++++++++++++++++++++---
 3 files changed, 57 insertions(+), 4 deletions(-)

diff --git a/src/leveled_cdb.erl b/src/leveled_cdb.erl
index 586f85a..ae1412a 100644
--- a/src/leveled_cdb.erl
+++ b/src/leveled_cdb.erl
@@ -1301,6 +1301,7 @@ scan_over_file(Handle, Position, FilterFun, Output, LastKey) ->
             end,
             % Bring file back to that position
             {ok, Position} = file:position(Handle, {bof, Position}),
+            garbage_collect(),
             {eof, Output};
         {Key, ValueAsBin, KeyLength, ValueLength} ->
             NewPosition = case Key of
@@ -1316,10 +1317,12 @@ scan_over_file(Handle, Position, FilterFun, Output, LastKey) ->
                             Output,
                             fun extract_valueandsize/1) of
                 {stop, UpdOutput} ->
+                    garbage_collect(),
                     {Position, UpdOutput};
                 {loop, UpdOutput} ->
                     case NewPosition of
                         eof ->
+                            garbage_collect(),
                             {eof, UpdOutput};
                         _ ->
                             scan_over_file(Handle,
diff --git a/src/leveled_sst.erl b/src/leveled_sst.erl
index 6d98103..c5768cf 100644
--- a/src/leveled_sst.erl
+++ b/src/leveled_sst.erl
@@ -1277,6 +1277,7 @@ open_reader(Filename) ->
     <<FileVersion:8/integer, 
         SlotsLength:32/integer, 
         SummaryLength:32/integer>> = Lengths,
+    ok = file:advise(Handle, 9, SlotsLength, will_need),
     {ok, SummaryBin} = file:pread(Handle, SlotsLength + 9, SummaryLength),
     {Handle, FileVersion, SummaryBin}.
 
diff --git a/test/end_to_end/riak_SUITE.erl b/test/end_to_end/riak_SUITE.erl
index 7d0d70f..5e82ce7 100644
--- a/test/end_to_end/riak_SUITE.erl
+++ b/test/end_to_end/riak_SUITE.erl
@@ -1214,8 +1214,8 @@ dollar_bucket_index(_Config) ->
 bigobject_memorycheck(_Config) ->
     RootPath = testutil:reset_filestructure(),
     {ok, Bookie} = leveled_bookie:book_start(RootPath,
-                                              100,
-                                              100000000,
+                                              200,
+                                              1000000000,
                                               testutil:sync_strategy()),
     Bucket = <<"B">>,
     IndexGen = fun() -> [] end,
@@ -1227,7 +1227,7 @@ bigobject_memorycheck(_Config) ->
             {Obj, Spc} = testutil:set_object(Bucket, Key, Value, IndexGen, []),
             testutil:book_riakput(Bookie, Obj, Spc)
         end,
-    lists:foreach(ObjPutFun, lists:seq(1, 600)),
+    lists:foreach(ObjPutFun, lists:seq(1, 700)),
     {ok, _Ink, Pcl} = leveled_bookie:book_returnactors(Bookie),
     {binary, BL} = process_info(Pcl, binary),
     {memory, M0} = process_info(Pcl, memory),
@@ -1235,5 +1235,54 @@ bigobject_memorycheck(_Config) ->
     io:format("Pcl binary memory ~w ~w memory ~w~n", [B0, length(BL), M0]),
     true = B0 < 500 * 4000,
     true = M0 < 500 * 4000,
+    % All processes
+    {_TotalCDBBinMem, _TotalCDBProcesses} = cdb_memory_check(),
     ok = leveled_bookie:book_close(Bookie),
-    testutil:reset_filestructure(). 
\ No newline at end of file
+    {ok, BookieR} = leveled_bookie:book_start(RootPath,
+                                              2000,
+                                              1000000000,
+                                              testutil:sync_strategy()),
+    {RS_TotalCDBBinMem, _RS_TotalCDBProcesses} = cdb_memory_check(),
+    true = RS_TotalCDBBinMem < 1024 * 1024,
+        % No binary object references exist after startup
+    ok = leveled_bookie:book_close(BookieR),
+    testutil:reset_filestructure(). 
+
+
+cdb_memory_check() ->
+    TotalCDBProcesses =
+        lists:filter(fun(P) ->
+                        {dictionary, PD} = 
+                            process_info(P, dictionary),
+                        case lists:keyfind('$initial_call', 1, PD) of
+                            {'$initial_call',{leveled_cdb,init,1}} ->
+                                true;
+                            _ ->
+                                false
+                        end
+                        end,
+                        processes()),
+    TotalCDBBinMem =
+        lists:foldl(fun(P, Acc) ->
+                        BinMem = calc_total_binary_memory(P),
+                        io:format("Memory for pid ~w is ~w~n", [P, BinMem]),
+                        BinMem + Acc
+                    end,
+                        0,
+                        TotalCDBProcesses),
+    io:format("Total binary memory ~w in ~w CDB processes~n",
+                [TotalCDBBinMem, length(TotalCDBProcesses)]),
+    {TotalCDBBinMem, TotalCDBProcesses}.
+
+calc_total_binary_memory(Pid) ->
+    {binary, BL} = process_info(Pid, binary),
+    TBM = lists:foldl(fun({_R, Sz, _C}, Acc) -> Acc + Sz end, 0, BL),
+    case TBM > 1000000 of
+        true ->
+            FilteredBL =
+                lists:filter(fun(BMD) -> element(2, BMD) > 1024 end, BL),
+            io:format("Big-ref details for ~w ~w~n", [Pid, FilteredBL]);
+        false ->
+            ok
+    end,
+    TBM.
\ No newline at end of file