.\" Automatically generated by Pod::Man 2.28 (Pod::Simple 3.28) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' . ds C` . ds C' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is turned on, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .\" .\" Avoid warning from groff about undefined register 'F'. .de IX .. .nr rF 0 .if \n(.g .if rF .nr rF 1 .if (\n(rF:(\n(.g==0)) \{ . if \nF \{ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . if !\nF==2 \{ . nr % 0 . nr F 2 . \} . \} .\} .rr rF .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. . \" fudge factors for nroff and troff .if n \{\ . ds #H 0 . ds #V .8m . ds #F .3m . ds #[ \f1 . ds #] \fP .\} .if t \{\ . ds #H ((1u-(\\\\n(.fu%2u))*.13m) . ds #V .6m . ds #F 0 . ds #[ \& . ds #] \& .\} . \" simple accents for nroff and troff .if n \{\ . ds ' \& . ds ` \& . ds ^ \& . ds , \& . ds ~ ~ . ds / .\} .if t \{\ . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' .\} . \" troff and (daisy-wheel) nroff accents .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' .ds 8 \h'\*(#H'\(*b\h'-\*(#H' .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] .ds ae a\h'-(\w'a'u*4/10)'e .ds Ae A\h'-(\w'A'u*4/10)'E . \" corrections for vroff .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' . \" for low resolution devices (crt and lpr) .if \n(.H>23 .if \n(.V>19 \ \{\ . ds : e . ds 8 ss . ds o a . ds d- d\h'-1'\(ga . ds D- D\h'-1'\(hy . ds th \o'bp' . ds Th \o'LP' . ds ae ae . ds Ae AE .\} .rm #[ #] #H #V #F C .\" ======================================================================== .\" .IX Title "MCE::Stream 3pm" .TH MCE::Stream 3pm "2014-10-24" "perl v5.20.1" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" MCE::Stream \- Parallel stream model for chaining multiple maps and greps .SH "VERSION" .IX Header "VERSION" This document describes MCE::Stream version 1.517 .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 2 \& ## Exports mce_stream, mce_stream_f, mce_stream_s \& use MCE::Stream; \& \& my (@m1, @m2, @m3); \& \& ## Default mode is map and processed from right\-to\-left \& @m1 = mce_stream sub { $_ * 3 }, sub { $_ * 2 }, 1..10000; \& mce_stream \e@m2, sub { $_ * 3 }, sub { $_ * 2 }, 1..10000; \& \& ## Native Perl \& @m3 = map { $_ * $_ } grep { $_ % 5 == 0 } 1..10000; \& \& ## Streaming grep and map in parallel \& mce_stream \e@m3, \& { mode => \*(Aqmap\*(Aq, code => sub { $_ * $_ } }, \& { mode => \*(Aqgrep\*(Aq, code => sub { $_ % 5 == 0 } }, 1..10000; \& \& ## Array or array_ref \& my @a = mce_stream sub { $_ * $_ }, 1..10000; \& my @b = mce_stream sub { $_ * $_ }, [ 1..10000 ]; \& \& ## File_path, glob_ref, or scalar_ref \& my @c = mce_stream_f sub { chomp; $_ }, "/path/to/file"; \& my @d = mce_stream_f sub { chomp; $_ }, $file_handle; \& my @e = mce_stream_f sub { chomp; $_ }, \e$scalar; \& \& ## Sequence of numbers (begin, end [, step, format]) \& my @f = mce_stream_s sub { $_ * $_ }, 1, 10000, 5; \& my @g = mce_stream_s sub { $_ * $_ }, [ 1, 10000, 5 ]; \& \& my @h = mce_stream_s sub { $_ * $_ }, { \& begin => 1, end => 10000, step => 5, format => undef \& }; .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" This module allows one to stream multiple map and/or grep operations in parallel. Code blocks run simultaneously from right-to-left. Chunk data are sent immediately to the next code block during processing. The results are appended immediately as well when passing the reference to the array. .PP .Vb 3 \& ## Appends are serialized, even out\-of\-order ok, but immediately. \& ## Out\-of\-order chunks are held temporarily until ordered chunks \& ## arrive before appending. \& \& mce_stream \e@a, sub { $_ }, sub { $_ }, sub { $_ }, 1..10000; \& \& ## input \& ## chunk1 input \& ## chunk3 chunk2 input \& ## chunk2 chunk2 chunk3 input \& ## append1 chunk3 chunk1 chunk4 input \& ## append2 chunk1 chunk5 chunk5 input \& ## append3 chunk5 chunk4 chunk6 ... \& ## append4 chunk4 chunk6 ... \& ## append5 chunk6 ... \& ## append6 ... \& ## ... \& ## .Ve .PP \&\s-1MCE\s0 incurs a small overhead due to passing of data. Therefore, a fast code block will likely run faster when chaining multiple map functions natively in Perl. However, the overhead quickly diminishes as the complexity of the code increases. .PP .Vb 2 \& ## 0.542 secs \-\- baseline using the native map function \& my @m1 = map { $_ * 4 } map { $_ * 3 } map { $_ * 2 } 1..1000000; \& \& ## 0.765 secs \-\- this is quite amazing considering data passing \& my @m2 = mce_stream \& sub { $_ * 4 }, sub { $_ * 3 }, sub { $_ * 2 }, 1..1000000; \& \& ## 0.592 secs \-\- appends to @m3 are immediate \& my @m3; mce_stream \e@m3, \& sub { $_ * 4 }, sub { $_ * 3 }, sub { $_ * 2 }, 1..1000000; .Ve .PP The mce_stream_s function will provide better times, useful when the input data is simply a range of numbers. Workers generate sequences mathematically among themselves without any interaction from the manager process. Two arguments are required for mce_stream_s (begin, end). Step defaults to 1 if begin is smaller than end, otherwise \-1. .PP .Vb 3 \& ## 0.447 secs \-\- numbers are generated mathematically via sequence \& my @m4; mce_stream_s \e@m4, \& sub { $_ * 4 }, sub { $_ * 3 }, sub { $_ * 2 }, 1, 1000000; .Ve .SH "OVERRIDING DEFAULTS" .IX Header "OVERRIDING DEFAULTS" The following list 6 options which may be overridden when loading the module. .PP .Vb 1 \& use Sereal qw(encode_sereal decode_sereal); \& \& use MCE::Stream \& default_mode => \*(Aqgrep\*(Aq, ## Default \*(Aqmap\*(Aq \& max_workers => 8, ## Default \*(Aqauto\*(Aq \& chunk_size => 500, ## Default \*(Aqauto\*(Aq \& tmp_dir => "/path/to/app/tmp", ## $MCE::Signal::tmp_dir \& freeze => \e&encode_sereal, ## \e&Storable::freeze \& thaw => \e&decode_sereal ## \e&Storable::thaw \& ; .Ve .PP There is a simpler way to enable Sereal with \s-1MCE 1.5.\s0 The following will attempt to use Sereal if available, otherwise will default back to using Storable for serialization. .PP .Vb 1 \& use MCE::Stream Sereal => 1; \& \& ## Serialization is through Sereal if available. \& my @m2 = mce_stream sub { $_ * $_ }, 1..10000; .Ve .SH "CUSTOMIZING MCE" .IX Header "CUSTOMIZING MCE" .IP "init" 3 .IX Item "init" The init function accepts a hash of \s-1MCE\s0 options. The gather and bounds_only options, if specified, will be ignored due to being used internally by the module (not shown below). .Sp .Vb 1 \& use MCE::Stream; \& \& MCE::Stream::init { \& chunk_size => 1, max_workers => 4, \& \& user_begin => sub { \& print "## ", MCE\->wid, " started\en"; \& }, \& \& user_end => sub { \& print "## ", MCE\->wid, " completed\en"; \& } \& }; \& \& my @a = mce_stream sub { $_ * $_ }, 1..100; \& \& print "\en", "@a", "\en"; \& \& \-\- Output \& \& ## 1 started \& ## 2 started \& ## 3 started \& ## 4 started \& ## 3 completed \& ## 1 completed \& ## 2 completed \& ## 4 completed \& \& 1 4 9 16 25 36 49 64 81 100 121 144 169 196 225 256 289 324 361 \& 400 441 484 529 576 625 676 729 784 841 900 961 1024 1089 1156 \& 1225 1296 1369 1444 1521 1600 1681 1764 1849 1936 2025 2116 2209 \& 2304 2401 2500 2601 2704 2809 2916 3025 3136 3249 3364 3481 3600 \& 3721 3844 3969 4096 4225 4356 4489 4624 4761 4900 5041 5184 5329 \& 5476 5625 5776 5929 6084 6241 6400 6561 6724 6889 7056 7225 7396 \& 7569 7744 7921 8100 8281 8464 8649 8836 9025 9216 9409 9604 9801 \& 10000 .Ve .PP Like with MCE::Stream::init above, \s-1MCE\s0 options may be specified using an anonymous hash for the first argument. Notice how both max_workers and task_name can take an anonymous array for setting values individually for each code block. Remember that MCE::Stream processes from right-to-left when setting the individual values. .PP .Vb 1 \& use MCE::Stream; \& \& my @a = mce_stream { \& max_workers => [ 2, 4, 3, ], task_name => [ \*(Aqc\*(Aq, \*(Aqb\*(Aq, \*(Aqa\*(Aq ], \& \& user_end => sub { \& my ($task_id, $task_name) = (MCE\->task_id, MCE\->task_name); \& print "$task_id \- $task_name completed\en"; \& }, \& \& task_end => sub { \& my ($mce, $task_id, $task_name) = @_; \& MCE\->print("$task_id \- $task_name ended\en"); \& } \& }, \& sub { $_ * 4 }, ## 2 workers, named c \& sub { $_ * 3 }, ## 4 workers, named b \& sub { $_ * 2 }, 1..10000; ## 3 workers, named a \& \& \-\- Output \& \& 0 \- a completed \& 0 \- a completed \& 0 \- a completed \& 0 \- a ended \& 1 \- b completed \& 1 \- b completed \& 1 \- b completed \& 1 \- b completed \& 1 \- b ended \& 2 \- c completed \& 2 \- c completed \& 2 \- c ended .Ve .PP Note that the anonymous hash, for specifying options, also comes first when passing the array reference. .PP .Vb 3 \& my @a; mce_stream { \& ... \& }, \e@a, sub { ... }, sub { ... }, 1..10000; .Ve .SH "API DOCUMENTATION" .IX Header "API DOCUMENTATION" Scripts using MCE::Stream can be written using the long or short form. The long form becomes relavant when mixing modes. Processing occurs from right-to-left. .PP .Vb 3 \& my @m3 = mce_stream \& { mode => \*(Aqmap\*(Aq, code => sub { $_ * $_ } }, \& { mode => \*(Aqgrep\*(Aq, code => sub { $_ % 5 == 0 } }, 1..10000; \& \& my @m4; mce_stream \e@m4, \& { mode => \*(Aqmap\*(Aq, code => sub { $_ * $_ } }, \& { mode => \*(Aqgrep\*(Aq, code => sub { $_ % 5 == 0 } }, 1..10000; .Ve .PP For multiple grep blocks, the short form can be used. Simply specify the default mode for the module. The two valid values for default_mode is 'grep' and 'map'. .PP .Vb 1 \& use MCE::Stream default_mode => \*(Aqgrep\*(Aq; \& \& my @f = mce_stream_f sub { /ending$/ }, sub { /^starting/ }, $file; .Ve .PP The following assumes 'map' for default_mode in order to demonstrate all the possibilities of passing input data into the code block. .IP "mce_stream sub { code }, list" 3 .IX Item "mce_stream sub { code }, list" Input data can be defined using a list or passing a reference to an array. .Sp .Vb 2 \& my @a = mce_stream sub { $_ * 2 }, 1..1000; \& my @b = mce_stream sub { $_ * 2 }, [ 1..1000 ]; .Ve .IP "mce_stream_f sub { code }, file" 3 .IX Item "mce_stream_f sub { code }, file" The fastest of these is the /path/to/file. Workers communicate the next offset position among themselves without any interaction from the manager process. .Sp .Vb 3 \& my @c = mce_stream_f sub { chomp; $_ . "\er\en" }, "/path/to/file"; \& my @d = mce_stream_f sub { chomp; $_ . "\er\en" }, $file_handle; \& my @e = mce_stream_f sub { chomp; $_ . "\er\en" }, \e$scalar; .Ve .IP "mce_stream_s sub { code }, sequence" 3 .IX Item "mce_stream_s sub { code }, sequence" Sequence can be defined as a list, an array reference, or a hash reference. The functions require both begin and end values to run. Step and format are optional. The format is passed to sprintf (% may be omitted below). .Sp .Vb 1 \& my ($beg, $end, $step, $fmt) = (10, 20, 0.1, "%4.1f"); \& \& my @f = mce_stream_s sub { $_ }, $beg, $end, $step, $fmt; \& my @g = mce_stream_s sub { $_ }, [ $beg, $end, $step, $fmt ]; \& \& my @h = mce_stream_s sub { $_ }, { \& begin => $beg, end => $end, step => $step, format => $fmt \& }; .Ve .IP "mce_stream { input_data => iterator }, sub { code }" 3 .IX Item "mce_stream { input_data => iterator }, sub { code }" An iterator reference can by specified for input data. Notice the anonymous hash as the first argument to mce_stream. The only other way is to specify input_data via MCE::Stream::init. This prevents MCE::Stream from configuring the iterator reference as another user task which will not work. .Sp Iterators are described under \*(L"\s-1SYNTAX\s0 for \s-1INPUT_DATA\*(R"\s0 at MCE::Core. .Sp .Vb 3 \& MCE::Stream::init { \& input_data => iterator \& }; \& \& my @a = mce_stream sub { $_ * 3 }, sub { $_ * 2 }; .Ve .SH "MANUAL SHUTDOWN" .IX Header "MANUAL SHUTDOWN" .IP "finish" 3 .IX Item "finish" \&\s-1MCE\s0 workers remain persistent as much as possible after running. Shutdown occurs when the script exits. One can manually shutdown \s-1MCE\s0 by simply calling finish after running. This resets the \s-1MCE\s0 instance. .Sp .Vb 1 \& use MCE::Stream; \& \& MCE::Stream::init { \& chunk_size => 20, max_workers => \*(Aqauto\*(Aq \& }; \& \& my @a = mce_stream { ... } 1..100; \& \& MCE::Stream::finish; .Ve .SH "INDEX" .IX Header "INDEX" \&\s-1MCE\s0 .SH "AUTHOR" .IX Header "AUTHOR" Mario E. Roy, .SH "LICENSE" .IX Header "LICENSE" This program is free software; you can redistribute it and/or modify it under the terms of either: the \s-1GNU\s0 General Public License as published by the Free Software Foundation; or the Artistic License. .PP See for more information.