From 53c45c621b1087443b613304a7008b91b91085aa Mon Sep 17 00:00:00 2001
From: Yorick Peterse <yorickpeterse@gmail.com>
Date: Tue, 29 Apr 2014 13:38:56 +0200
Subject: [PATCH] Basic memory profiling setup.

This makes it a bit easier to profile memory usage of certain components and
plot them using Gnuplot. In the past I would write one-off scripts for this and
throw them away, only to figure out I needed them again later on.

Profiling samples are written to profile/samples and can be plotted using
corresponding Gnuplot scripts found in profile/plot. The latter requires
Gnuplot to be installed.
---
 .gitignore                         |  3 +++
 profile/lexer/big_xml.rb           |  8 ++++++
 profile/plot/lexer/big_xml.gnuplot | 20 +++++++++++++++
 profile/profile_helper.rb          | 41 ++++++++++++++++++++++++++++++
 profile/samples/.gitkeep           |  0
 profile/samples/lexer/.gitkeep     |  0
 6 files changed, 72 insertions(+)
 create mode 100644 profile/lexer/big_xml.rb
 create mode 100755 profile/plot/lexer/big_xml.gnuplot
 create mode 100644 profile/profile_helper.rb
 create mode 100644 profile/samples/.gitkeep
 create mode 100644 profile/samples/lexer/.gitkeep

diff --git a/.gitignore b/.gitignore
index 3359fde..92805d5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -7,3 +7,6 @@ lib/oga/xml/lexer.rb
 lib/oga/xml/parser.rb
 
 benchmark/fixtures/big.xml
+
+profile/samples/*.txt
+profile/samples/lexer/*.txt
diff --git a/profile/lexer/big_xml.rb b/profile/lexer/big_xml.rb
new file mode 100644
index 0000000..20db5bf
--- /dev/null
+++ b/profile/lexer/big_xml.rb
@@ -0,0 +1,8 @@
+require_relative '../profile_helper'
+
+xml   = read_big_xml
+lexer = Oga::XML::Lexer.new(xml)
+
+profile_memory('lexer/big_xml')
+
+lexer.advance { |tok| }
diff --git a/profile/plot/lexer/big_xml.gnuplot b/profile/plot/lexer/big_xml.gnuplot
new file mode 100755
index 0000000..8dc2129
--- /dev/null
+++ b/profile/plot/lexer/big_xml.gnuplot
@@ -0,0 +1,20 @@
+#!/usr/bin/env gnuplot
+
+set title "Lexing 10MB of XML"
+
+set xlabel "Sample"
+set ylabel "Memory (MB)"
+
+set yrange [0:*]
+
+set term qt persist
+set grid
+
+set style line 1 lc rgb "#0060ad" lt 1 lw 2 pt 7 ps 1
+
+plot "profile/samples/lexer/big_xml.txt" \
+    using 0:($1 / 1024 ** 2) \
+    with linespoints ls 1 \
+    title "Memory"
+
+# vim: set ft=gnuplot:
diff --git a/profile/profile_helper.rb b/profile/profile_helper.rb
new file mode 100644
index 0000000..d021579
--- /dev/null
+++ b/profile/profile_helper.rb
@@ -0,0 +1,41 @@
+require_relative '../lib/oga'
+
+##
+# Returns memory usage in bytes. This relies on the /proc filesystem, it won't
+# work without it.
+#
+# @return [Fixnum]
+#
+def memory_usage
+  return File.read('/proc/self/status').match(/VmRSS:\s+(\d+)/)[1].to_i * 1024
+end
+
+##
+# Reads a big XML file and returns it as a String.
+#
+# @return [String]
+#
+def read_big_xml
+  return File.read(File.expand_path('../../benchmark/fixtures/big.xml', __FILE__))
+end
+
+##
+# Writes memory samples to a file until the thread is killed.
+#
+# @param [String] name The name of the samples file.
+# @param [Fixnum] interval The sample interval. The default is 200 ms.
+# @return [Thread]
+#
+def profile_memory(name, interval = 0.2)
+  return Thread.new do
+    path        = File.expand_path("../samples/#{name}.txt", __FILE__)
+    handle      = File.open(path, 'w')
+    handle.sync = true
+
+    loop do
+      handle.write("#{memory_usage}\n")
+
+      sleep(interval)
+    end
+  end
+end
diff --git a/profile/samples/.gitkeep b/profile/samples/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/profile/samples/lexer/.gitkeep b/profile/samples/lexer/.gitkeep
new file mode 100644
index 0000000..e69de29