Merge branch 'bp/fsmonitor'

We learned to talk to watchman to speed up "git status" and other
operations that need to see which paths have been modified.

* bp/fsmonitor:
  fsmonitor: preserve utf8 filenames in fsmonitor-watchman log
  fsmonitor: read entirety of watchman output
  fsmonitor: MINGW support for watchman integration
  fsmonitor: add a performance test
  fsmonitor: add a sample integration script for Watchman
  fsmonitor: add test cases for fsmonitor extension
  split-index: disable the fsmonitor extension when running the split index test
  fsmonitor: add a test tool to dump the index extension
  update-index: add fsmonitor support to update-index
  ls-files: Add support in ls-files to display the fsmonitor valid bit
  fsmonitor: add documentation for the fsmonitor extension.
  fsmonitor: teach git to optionally utilize a file system monitor to speed up detecting new or changed files.
  update-index: add a new --force-write-index option
  preload-index: add override to enable testing preload-index
  bswap: add 64 bit endianness helper get_be64

1 files changed, 120 insertions, 0 deletions

diff --git a/templates/hooks--fsmonitor-watchman.sample b/templates/hooks--fsmonitor-watchman.sample
new file mode 100755
index 0000000000..9eba8a7409
--- /dev/null
+++ b/templates/hooks--fsmonitor-watchman.sample
@@ -0,0 +1,120 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use IPC::Open2;
+
+# An example hook script to integrate Watchman
+# (https://facebook.github.io/watchman/) with git to speed up detecting
+# new and modified files.
+#
+# The hook is passed a version (currently 1) and a time in nanoseconds
+# formatted as a string and outputs to stdout all files that have been
+# modified since the given time. Paths must be relative to the root of
+# the working tree and separated by a single NUL.
+#
+# To enable this hook, rename this file to "query-watchman" and set
+# 'git config core.fsmonitor .git/hooks/query-watchman'
+#
+my ($version, $time) = @ARGV;
+
+# Check the hook interface version
+
+if ($version == 1) {
+	# convert nanoseconds to seconds
+	$time = int $time / 1000000000;
+} else {
+	die "Unsupported query-fsmonitor hook version '$version'.\n" .
+	    "Falling back to scanning...\n";
+}
+
+# Convert unix style paths to escaped Windows style paths when running
+# in Windows command prompt
+
+my $system = `uname -s`;
+$system =~ s/[\r\n]+//g;
+my $git_work_tree;
+
+if ($system =~ m/^MSYS_NT/ || $system =~ m/^MINGW/) {
+	$git_work_tree = `cygpath -aw "\$PWD"`;
+	$git_work_tree =~ s/[\r\n]+//g;
+	$git_work_tree =~ s,\\,/,g;
+} else {
+	$git_work_tree = $ENV{'PWD'};
+}
+
+my $retry = 1;
+
+launch_watchman();
+
+sub launch_watchman {
+
+	my $pid = open2(\*CHLD_OUT, \*CHLD_IN, 'watchman -j')
+	    or die "open2() failed: $!\n" .
+	    "Falling back to scanning...\n";
+
+	# In the query expression below we're asking for names of files that
+	# changed since $time but were not transient (ie created after
+	# $time but no longer exist).
+	#
+	# To accomplish this, we're using the "since" generator to use the
+	# recency index to select candidate nodes and "fields" to limit the
+	# output to file names only. Then we're using the "expression" term to
+	# further constrain the results.
+	#
+	# The category of transient files that we want to ignore will have a
+	# creation clock (cclock) newer than $time_t value and will also not
+	# currently exist.
+
+	my $query = <<"	END";
+		["query", "$git_work_tree", {
+			"since": $time,
+			"fields": ["name"],
+			"expression": ["not", ["allof", ["since", $time, "cclock"], ["not", "exists"]]]
+		}]
+	END
+
+	print CHLD_IN $query;
+	close CHLD_IN;
+	my $response = do {local $/; <CHLD_OUT>};
+
+	die "Watchman: command returned no output.\n" .
+	    "Falling back to scanning...\n" if $response eq "";
+	die "Watchman: command returned invalid output: $response\n" .
+	    "Falling back to scanning...\n" unless $response =~ /^\{/;
+
+	my $json_pkg;
+	eval {
+		require JSON::XS;
+		$json_pkg = "JSON::XS";
+		1;
+	} or do {
+		require JSON::PP;
+		$json_pkg = "JSON::PP";
+	};
+
+	my $o = $json_pkg->new->utf8->decode($response);
+
+	if ($retry > 0 and $o->{error} and $o->{error} =~ m/unable to resolve root .* directory (.*) is not watched/) {
+		print STDERR "Adding '$git_work_tree' to watchman's watch list.\n";
+		$retry--;
+		qx/watchman watch "$git_work_tree"/;
+		die "Failed to make watchman watch '$git_work_tree'.\n" .
+		    "Falling back to scanning...\n" if $? != 0;
+
+		# Watchman will always return all files on the first query so
+		# return the fast "everything is dirty" flag to git and do the
+		# Watchman query just to get it over with now so we won't pay
+		# the cost in git to look up each individual file.
+		print "/\0";
+		eval { launch_watchman() };
+		exit 0;
+	}
+
+	die "Watchman: $o->{error}.\n" .
+	    "Falling back to scanning...\n" if $o->{error};
+
+	binmode STDOUT, ":utf8";
+	local $, = "\0";
+	print @{$o->{files}};
+}