我在HP
Proliant服务器上运行了高度并发的应用程序。该应用程序是我用erlang编码的文件系统索引器。它在文件系统上找到的每个文件夹中产生一个进程，并将所有文件路径记录在碎片化的Mnesia数据库中。（数据库由disc_only_copies表的类型组成，其文件系统的屏幕快照可在
此处 查看。）

下面显示了完成文件系统的高强度工作的代码片段：

%%% -------- COPYRIGHT NOTICE --------------------------------------------------------------------
%% @author Muzaaya Joshua, <joshmuza@gmail.com> [http://joshanderlang.blogspot.com]
%% @version 1.0 free software, but modification prohibited
%% @copyright Muzaaya Joshua (file_scavenger-1.0) 2011 - 2012 . All rights reserved
%% @reference <a href="http://www.erlang.org">OpenSource Erlang WebSite</a>
%% 
%%% ---------------- EDOC INTRODUCTION TO THE MODULE ----------------------------------------------
%% @doc This module provides the low level APIs for reading, writing,
%% searching, joining and moving within directories.The module implementation
%% took place on @date at @time.
%% @end

-module(file_scavenger_utilities).

%%% ------- EXPORTS -------------------------------------------------------------------------------
-compile(export_all).

%%% ------- INCLUDES -----------------------------------------------------------------------------

%%% -------- MACROS ------------------------------------------------------------------------------
-define(IS_FOLDER(X),filelib:is_dir(X)).
-define(IS_FILE(X),filelib:is_file(X)).
-define(FAILED_TO_LIST_DIR(X),error_logger:error_report(["*** File Scavenger Utilities Error ***** ",{error,"Failed to List Directory"},{directory,X}])).
-define(NOT_DIR(X),error_logger:error_report(["*** File Scavenger Utilities Error ***** ",{error,"Not a Directory"},{alleged,X}])).
-define(NOT_FILE(X),error_logger:error_report(["*** File Scavenger Utilities Error ***** ",{error,"Not a File"},{alleged,X}])).
%%%--------- TYPES -------------------------------------------------------------------------------

%% @type dir() = string(). 
%%  Must be containing forward slashes, not back slashes. Must not end with a slash
%%  after the exact directory.e.g this is wrong: "C:/Program Files/SomeDirectory/"
%%  but this is right: "C:/Program Files/SomeDirectory"
%% @type file_path() = string(). 
%%  Must be containing forward slashes, not back slashes.
%%  Should include the file extension as well e.g "C:/Program Files/SomeFile.pdf"

%% -----------------------------------------------------------------------------------------------
%% @doc Enters a directory and executes the fun ForEachFileFound/2 for each file it finds
%% If it finds a directory, it executes the fun %% ForEachDirFound/2. 
%% Both funs above take the parent Dir as the first Argument. Then, it will spawn an 
%% erlang process that will spread the found Directory too in the same way as the parent directory 
%% was spread. The process of spreading goes on and on until every File (wether its in a nested 
%% Directory) is registered by its full path.
%% @end
%%
%% @spec spread_directory(dir(),dir(),funtion(),function())-> ok.

spread_directory(Dir,Top_Directory,ForEachFileFound,ForEachDirFound) when is_function(ForEachFileFound),is_function(ForEachDirFound) ->
    case ?IS_FOLDER(Dir) of
        false -> ?NOT_DIR(Dir); 
        true -> 
            F = fun(X)->
                    FileOrDir = filename:absname_join(Dir,X),
                    case ?IS_FOLDER(FileOrDir) of
                        true -> 
                            (catch ForEachDirFound(Top_Directory,FileOrDir)),
                            spawn(fun() -> ?MODULE:spread_directory(FileOrDir,Top_Directory,ForEachFileFound,ForEachDirFound) end);
                        false -> 
                            case ?IS_FILE(FileOrDir) of
                                false -> {error,not_a_file,FileOrDir};
                                true -> (catch ForEachFileFound(Top_Directory,FileOrDir))
                            end
                    end
                end,
            case file:list_dir(Dir) of      
                {error,_} -> ?FAILED_TO_LIST_DIR(Dir);
                {ok,List} -> lists:foreach(F,List)
            end
    end.    

该函数spread_directory/4是通用的，它需要两个funs。一个乐趣：ForEachFileFound/2与最热门目录一起使用，找到的文件并对其执行任何操作，另一个乐趣：ForEachDirFound/2与最热门目录一起使用，它以所需的任何方式查找和使用该文件夹。

我用于此应用程序的启动脚本可确保erlang能够生成尽可能多的进程。进程完成对文件夹的索引编制后，将退出。

#!/usr/bin/env sh
echo "Starting File Scavenger System. Layer 1 on the P2P File Sharing System....."
erl \
    -name file_scavenger@127.0.0.1 \
    +P 13421779 \
    -pa ./ebin ./lib/*/ebin ./include \
    -mnesia dir '"./database"' \
    -mnesia dump_log_write_threshold 10000 \
    -eval "application:load(file_scavenger)" \
    -eval "application:start(file_scavenger)"

有一个gen_server将密集模块与数据库连接，在其中记录所有路径。下面显示了开始spread_directory工作的位置的片段：

handle_cast(index_dirs,#scavenger{directory_paths = Dirs} = State)->
{File,Folder} = case {State#scavenger.verbose,State#scavenger.verbose_to} of
{true,tty} ->
{
fun(TopDir,Fl)->
io:format(” File: ~p~n”,[Fl]),
file_scavenger_database:insert_file(filename:basename(Fl),file,Fl,TopDir,filename:extension(Fl))
end,
fun(TopDir,Fd) ->
io:format(” Folder: ~p~n”,[Fd]),
file_scavenger_database:insert_file(Fd,folder,Fd,TopDir,undefined)
end
};
{true,SomeFile}->
{
fun(TopDir,Fl)->
os:cmd(“echo File: ” Fl ” >> ” SomeFile),
file_scavenger_database:insert_file(filename:basename(Fl),file,Fl,TopDir,filename:extension(Fl))
end,
fun(TopDir,Fd)->
os:cmd(“echo Folder: ” Fd ” >> ” SomeFile),
file_scavenger_database:insert_file(Fd,folder,Fd,TopDir,undefined)
end
}
end,
Main = fun(Dir) ->
error_logger:info_msg(“*** File scavenger Server indexing directory: ~p~n”,[Dir]),
spawn(fun() -> file_scavenger_utilities:spread_directory(Dir,Dir,File,Folder) end)
end,
lists:foreach(Main,Dirs),
{noreply,State};
handle_cast(stop, State) -> {stop, normal, State}.

可以在整个应用程序中找到更多源详细信息。您可以在以下位置找到应用程序的完整源代码和构建文件：
File_scavenger-1.0.zip
。

现在，我在服务器（HP Proliant G6，包含Intel处理器（2个处理器，每个4个核，每个核2.4 GHz速度，8 MB高速缓存大小），20 GB
RAM大小，1.5 TB磁盘空间）上启动应用程序。这些高功率机器已经可以使用了。应该在这两个机器之间复制系统数据库。每个服务器都运行Solaris
10（64位），其终端现在如下所示：

bash-3.00# sh file_scavenger.sh
Starting File Scavenger System. Layer 1 on the P2P File Sharing System.....
Erlang R14B03 (erts-5.8.4) [source] [smp:8:8] [rq:8] [async-threads:0] [hipe] [kernel-poll:false]

Eshell V5.8.4  (abort with ^G)
(file_scavenger@127.0.0.1)1>
=INFO REPORT==== 18-Aug-2011::09:36:04 ===
Starting File Scavenger Database......
=INFO REPORT==== 18-Aug-2011::09:36:04 ===
Database Successfully Started....

=INFO REPORT==== 18-Aug-2011::09:36:04 ===
Starting File Scavenger Database......
=INFO REPORT==== 18-Aug-2011::09:36:04 ===
Database Successfully Started....

=INFO REPORT==== 18-Aug-2011::09:36:04 ===
File Scavenger Server starting with default verbose settings....

(file_scavenger@127.0.0.1)1> file_scavenger_server:index_dirs().

服务器开始运行，并向终端详细说明其找到的所有文件和文件夹。服务器配备了过多的RAM（20 GB）和交换空间（交换为16
GB）。但是，它运行了大约18个小时，最后，erlang虚拟机报告了这一点：

File: "/proc/4324/root/opt/csw/gcc4/share/locale/ja/LC_MESSAGES/gcc.mo"
 Folder: "/proc/4324/root/opt/csw/gcc4/share/locale/da"
 Folder: "/proc/4324/root/opt/csw/gcc4/share/locale/es/LC_MESSAGES"
 File: "/proc/4324/root/proc/4984/root/.thumbnails/normal/dc259e3897e8af4b379c6d956b6c1393.png"
 File: "/proc/4324/root/proc/4984/root/.thumbnails/fail/gnome-thumbnail-factory/223c19786421b7101d14075bdec46f61.png"
 File: "/proc/4324/root/opt/csw/gcc4/libexec/gcc/i386-pc-solaris2.10/4.5.1/install-tools/mkheaders"
 File: "/proc/4324/root/opt/csw/gcc4/libexec/gcc/i386-pc-solaris2.10/4.5.1/cc1plus"
 File: "/proc/4324/root/opt/csw/gcc4/lib/libsupc++.la"

Crash dump was written to: erl_crash.dump
eheap_alloc: Cannot allocate 153052320 bytes of memory (of type "heap").
Abort - core dumped
bash-3.00#

问题1. 使用如此强大的服务器，为什么操作系统无法为应用程序提供这种内存（这是唯一运行的应用程序）？

问题2. 指示我启动的Erlang仿真器能够生成所需数量的进程。价值+P 13421779。Erlang
VM是否无法访问此内存或未能将其分配给进程？

问题3.
对于Solaris，它看到一个过程：epmd，可能包含并启动数千个微线程。我可以对Solaris进行哪些配置以使其永不停止我的应用程序，无论它可能有多少“内存不足”？可用的交换空间为16
GB，RAM为20 GB，说实话，一定有问题。

问题4.
我可以对Erlang仿真器进行哪些配置，以避免这些堆内存崩溃转储，尤其是当服务器上可能需要的所有内存都可用时？如果Erlang仍然无法将此类内存分配给简单的文件系统索引器（严重并发），我将如何在该服务器上运行更多消耗内存的应用程序？

最后，欢迎进行其他所有为避免在此类功能强大的硬件上出现堆内存问题而进行的调整。提前致谢