Algorithm-Classifier-IsolationForest
view release on metacpan or search on metacpan
benchmarking/bench-streamd.pl view on Meta::CPAN
#!/usr/bin/perl
# benchmarking/bench-streamd.pl
#
# Benchmarks `iforest streamd` end to end: the script spawns its own
# daemon on a temp Unix socket and pumps rows through the JSON-lines
# protocol, measuring points/second wall-clock at the client.
#
# Sections:
# 1. in-process baseline -- score_learn on an identical model in this
# process; the ceiling everything else is measured against. The
# gap between it and the socket numbers is protocol + JSON + IPC
# overhead, not model work.
# 2. batch-size sweep -- prequential rows per {"rows": [...]}
# message; directly informs streamc's --batch choice.
# 3. modes -- prequential vs score vs learn at a fixed
# batch size.
# 4. row forms -- positional arrays vs tagged objects (the
# tagged form pays hashref building + tagged_row_to_array).
# 5. concurrent clients -- total throughput with 1/2/4 connections
# pumping at once. The daemon is a single select loop sharing one
# model, so this should stay ~flat: it measures fairness overhead,
# not parallel speedup.
# 6. command latency -- ping round trips (pure protocol floor)
# and the wall cost of an on-demand save.
#
# Reference numbers (2026-07-08, 8-core dev box, C backend,
# Cpanel::JSON::XS, 100 trees, window 2048, eta 32, 5 features):
# in-process score_learn ~2,770 pts/s; over the socket ~2,700 pts/s at
# any batch >= 16 (~2% overhead) and ~2,500 pts/s even at batch 1;
# score mode ~29,000 pts/s (no learning -- the tree walk is cheap, the
# learn is what costs); tagged objects ~21,000 vs positional ~30,000 in
# score mode; throughput is flat across 1/2/4 concurrent clients (one
# shared model, one loop -- by design); ping ~29,000 round trips/s;
# save ~140 ms. The wire is nowhere near the bottleneck -- the model
# is.
#
# Run with:
# perl -Ilib benchmarking/bench-streamd.pl
use strict;
use warnings;
use FindBin;
use lib "$FindBin::Bin/../lib";
use lib "$FindBin::Bin";
use BenchAccel qw(wall_rate wall_time_median);
use Time::HiRes qw(time);
use File::Temp qw(tempdir);
use IO::Select ();
use IO::Socket::UNIX ();
use POSIX ();
use Algorithm::Classifier::IsolationForest::Online ();
eval { require JSON::MaybeXS; 1 }
or die "this benchmark needs JSON::MaybeXS (streamd's wire protocol): $@";
my $JSON = JSON::MaybeXS->new( utf8 => 1 );
use constant PI => 3.14159265358979;
sub gaussian {
my ( $mu, $sigma ) = @_;
return $mu + $sigma * sqrt( -2 * log( rand() || 1e-12 ) ) * cos( 2 * PI * rand() );
}
sub make_data {
my ( $n, $nf ) = @_;
return [
map {
[ map { gaussian( 0, 1 ) } 1 .. $nf ]
} 1 .. $n
];
}
# --- model shape (matches bench-online-score-accel.pl) -------------------
my $N_TREES = 100;
my $WINDOW = 2048;
my $ETA = 32;
my $NF = 5;
my @TAGS = map { "f$_" } 0 .. $NF - 1;
# --- spawn the daemon -----------------------------------------------------
my $bin = "$FindBin::Bin/../src_bin/iforest";
die "cannot find $bin\n" unless -f $bin;
my $tmp = tempdir( CLEANUP => 1 );
my $sock = "$tmp/b.sock";
die "temp socket path too long for a Unix socket ($sock)\n" if length($sock) > 100;
my $daemon = fork();
die "fork failed: $!" unless defined $daemon;
if ( !$daemon ) {
open( STDOUT, '>>', "$tmp/streamd.log" ) or die $!;
open( STDERR, '>>', "$tmp/streamd.log" ) or die $!;
exec(
$^X, "-I$FindBin::Bin/../lib", $bin, 'streamd', '-f',
'--socket' => $sock,
'--pid' => "$tmp/b.pid",
'--model-dir' => "$tmp/models",
'--save-interval' => 3600, # no interval saves mid-benchmark
'-n' => $N_TREES,
'--window' => $WINDOW,
'--eta' => $ETA,
'-s' => 42,
( map { ( '-t' => $_ ) } @TAGS ),
) or die "exec failed: $!";
} ## end if ( !$daemon )
for ( 1 .. 100 ) {
last if -S $sock;
select( undef, undef, undef, 0.1 ); ## no critic (ProhibitSleepViaSelect)
}
die "daemon never came up; see $tmp/streamd.log\n" unless -S $sock;
END {
kill( 'TERM', $daemon ) if $daemon && kill( 0, $daemon );
}
( run in 4.782 seconds using v1.01-cache-2.11-cpan-600a1bdf6e4 )