Yaron,

I use a slightly modified version of the CSV library's load_rows . Here is the main code which is highly imperative style. I might transform it in purely functional style ?

The main program is :

open Printf;;
open Sys;;
let timed_exec start_message f =
print_string start_message;
let st1 = time () in
let r = f () in
print_endline ("done in " ^ (string_of_float ((time ()) -. st1)) );
r;;

(* This line enabled makes the program really slow ! *)
let run_threaded f = Thread.create (fun () -> f (); Thread.exit ()) ()

let () = timed_exec "Reading data " (fun () ->
load_rows (fun _ -> ()) (open_in "file1.csv");
load_rows (fun _ -> ()) (open_in "file2.csv");
()
)

The load_rows :
let load_rows ?(separator = ',') ?(nread = -1) f chan =
let nr = ref 0 in
let row = ref [] in            (* Current row. *)
let field = ref [] in            (* Current field. *)
let state = ref StartField in        (* Current state. *)
let end_of_field () =
    let field_list = List.rev !field in
    let field_len = List.length field_list in
    let field_str = String.create field_len in
    let rec loop i = function
    [] -> ()
      | x :: xs ->
    field_str.[i] <- x;
    loop (i+1) xs
    in
    loop 0 field_list;
    row := (Some field_str) :: !row;
    field := [];
    state := StartField
in
let empty_field () =
    row := None :: !row;
    field := [];
    state := StartField
in
let end_of_row () =
    let row_list = List.rev !row in
    f row_list;
    row := [];
    state := StartField;
    nr := !nr + 1;
in
let rec loop () =
    let c = input_char chan in
    if c != '\r' then (            (* Always ignore \r characters. *)
      match !state with
    StartField ->            (* Expecting quote or other char. *)
        if c = '"' then (
          state := InQuotedField;
          field := []
        ) else if c = separator then (* Empty field. *)
          empty_field ()
        else if c = '\n' then (    (* Empty field, end of row. *)
          empty_field ();
          end_of_row ()
        ) else (
          state := InUnquotedField;
          field := [c]
        )
    | InUnquotedField ->        (* Reading chars to end of field. *)
        if c = separator then    (* End of field. *)
          end_of_field ()
        else if c = '\n' then (    (* End of field and end of row. *)
          end_of_field ();
          end_of_row ()
        ) else
          field := c :: !field
    | InQuotedField ->        (* Reading chars to end of field. *)
        if c = '"' then
          state := InQuotedFieldAfterQuote
        else
          field := c :: !field
    | InQuotedFieldAfterQuote ->
        if c = '"' then (        (* Doubled quote. *)
          field := c :: !field;
          state := InQuotedField
        ) else if c = '0' then (    (* Quote-0 is ASCII NUL. *)
          field := '\000' :: !field;
          state := InQuotedField
        ) else if c = separator then (* End of field. *)
          end_of_field ()
        else if c = '\n' then (    (* End of field and end of row. *)
          end_of_field ();
          end_of_row ()
        ) else (            (* Bad single quote in field. *)
          field := c :: '"' :: !field;
          state := InQuotedField
        )
    ); (* end of match *)
if( nread < 0 or !nr < nread) then loop () else ()
in
try
    loop ()
with
      End_of_file ->
    (* Any part left to write out? *)
    (match !state with
         StartField ->
           if !row <> [] then
        ( empty_field (); end_of_row () )
       | InUnquotedField | InQuotedFieldAfterQuote ->
           end_of_field (); end_of_row ()
       | InQuotedField ->
           raise (Bad_CSV_file "Missing end quote after quoted field.")
    )

Thanks,
Rémi

On Mon, Feb 16, 2009 at 17:47, Yaron Minsky <yminsky@gmail.com> wrote:

2009/2/16 Rémi Dewitte <remi@gide.net>
Hello,

I would like to read two files in two different threads.

I have made a first version reading the first then the second and it takes 2.8s (native).

I decided to make a threaded version and before any use of thread I realized that just linking no even using it to the threads library makes my first version of the program to run in 12s !

Do you have a short benchmark you can post? The idea that the thread-overhead would make a difference like that, particularly for IO-bound code (which I'm guessing this is) is pretty surprising.

y

I use pcre, extlib, csv libraries as well.

I guess it might come from GC slowing down thinks here, doesn't it ? Where can it come from otherwise ? Is there a workaround or something I should know ?

Can ocaml use multiple cores ?

Do you have few pointers on libraries to make parallel I/Os ?

Thanks,
Rémi

_______________________________________________
Caml-list mailing list. Subscription management:
http://yquem.inria.fr/cgi-bin/mailman/listinfo/caml-list
Archives: http://caml.inria.fr
Beginner's list: http://groups.yahoo.com/group/ocaml_beginners
Bug reports: http://caml.inria.fr/bin/caml-bugs