[erlang-questions] QLC doesn't use lookup joins on bare values

[Sam Bobroff]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hi Erlangers,

I've discovered that when performing a QLC query, QLC is unable to use
a fast join unless the values being returned by both generators are
wrapped as tuples.

Does anyone know if this is caused just because that pattern isn't
recognised by QLC? Would it be worth adding this as a pattern?

Here's an example (notice that "one" is done by traversal and is slow,
while "two" is done by a merge join and is fast):

- -module(question).
- -export([start/0]).

- -include_lib("stdlib/include/qlc.hrl").

- -define(N, 1000).

start() ->
        TA = ets:new(ta, []),
        TB = ets:new(tb, []),
        [ ets:insert(TA, {X}) || X <- lists:seq(1, ?N) ],
        [ ets:insert(TB, {X, $a - 1 + (X rem 26)}) || X <- lists:seq(1, ?N) ],
        one(TA, TB),
        two(TA, TB),
        init:stop().

one(TA, TB) ->
        TMP = qlc:q([A || {A} <- ets:table(TA)]),
        QLC = qlc:q([element(2, B) || A <- TMP, B <- ets:table(TB), A =:= element(2, B)]),
        do("one", QLC).

two(TA, TB) ->
        TMP = qlc:q([A || A <- ets:table(TA)]),
        QLC = qlc:q([element(2, B) || {A} <- TMP, B <- ets:table(TB), A =:= element(2, B)]),
        do("two", QLC).

do(Name, QLC) ->
        io:fwrite("Query Info for query ~p: ~s\n", [Name, qlc:info(QLC)]),
        ST = now(),
        Result = qlc:e(QLC),
        ET = now(),
        io:fwrite("Query time: ~ps\nResults: ~p\n", [timer:now_diff(ET, ST) / 1000000, length(Result)]).

Running this on my machine (running Erlang R12B):

$ erlc question.erl && erl -noshell -run question
Query Info for query "one": qlc:q([element(2, B) ||                          
           A <-                                                              
               ets:table(8204,                                               
                         [{traverse,{select,[{{'$1'},[true],['$1']}]}}]),    
           B <- ets:table(12301),                                            
           A =:= element(2, B)])                                             
Query time: 0.908338s                                                        
Results: 1000
Query Info for query "two": begin
    V1 =
        qlc:q([P0 ||
                   P0 = {A} <- qlc:keysort(1, ets:table(8204), [])]),
    V2 =
        qlc:q([[G1|B] ||
                   G1 <- V1,
                   B <- qlc:keysort(2, ets:table(12301), []),
                   element(1, G1) == element(2, B)],
              [{join,merge}]),
    qlc:q([element(2, B) ||
               [{A}|B] <- V2,
               A =:= element(2, B)])
end
Query time: 0.010174s
Results: 1000

Cheers,
Sam.
- -- 
Sam Bobroff | sam@REDACTED | M5 Networks
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (GNU/Linux)

iEYEARECAAYFAknn4sMACgkQm97/UHSa/AQJ1wCfa5OxpvF+RngKfFniuXQxWZ8i
BxMAnifufDoqp0ZrRYdd4oHILmPyBCez
=250i
-----END PGP SIGNATURE-----