fsmonitor: add test cases for fsmonitor extension

Test the ability to add/remove the fsmonitor index extension via
update-index.

Test that dirty files returned from the integration script are properly
represented in the index extension and verify that ls-files correctly
reports their state.

Test that ensure status results are correct when using the new fsmonitor
extension.  Test untracked, modified, and new files by ensuring the
results are identical to when not using the extension.

Test that if the fsmonitor extension doesn't tell git about a change, it
doesn't discover it on its own.  This ensures git is honoring the
extension and that we get the performance benefits desired.

Three test integration scripts are provided:

fsmonitor-all - marks all files as dirty
fsmonitor-none - marks no files as dirty
fsmonitor-watchman - integrates with Watchman with debug logging

To run tests in the test suite while utilizing fsmonitor:

First copy t/t7519/fsmonitor-all to a location in your path and then set
GIT_FORCE_PRELOAD_TEST=true and GIT_FSMONITOR_TEST=fsmonitor-all and run
your tests.

Note: currently when using the test script fsmonitor-watchman on
Windows, many tests fail due to a reported but not yet fixed bug in
Watchman where it holds on to handles for directories and files which
prevents the test directory from being cleaned up properly.

Signed-off-by: Ben Peart <benpeart@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 186 insertions, 0 deletions

diff --git a/t/t7519/fsmonitor-all b/t/t7519/fsmonitor-all
new file mode 100755
index 0000000000..691bc94dc2
--- /dev/null
+++ b/t/t7519/fsmonitor-all
@@ -0,0 +1,24 @@
+#!/bin/sh
+#
+# An test hook script to integrate with git to test fsmonitor.
+#
+# 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.
+#
+#echo "$0 $*" >&2
+
+if test "$#" -ne 2
+then
+	echo "$0: exactly 2 arguments expected" >&2
+	exit 2
+fi
+
+if test "$1" != 1
+then
+	echo "Unsupported core.fsmonitor hook version." >&2
+	exit 1
+fi
+
+echo "/"
diff --git a/t/t7519/fsmonitor-none b/t/t7519/fsmonitor-none
new file mode 100755
index 0000000000..ed9cf5a6a9
--- /dev/null
+++ b/t/t7519/fsmonitor-none
@@ -0,0 +1,22 @@
+#!/bin/sh
+#
+# An test hook script to integrate with git to test fsmonitor.
+#
+# 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.
+#
+#echo "$0 $*" >&2
+
+if test "$#" -ne 2
+then
+	echo "$0: exactly 2 arguments expected" >&2
+	exit 2
+fi
+
+if test "$1" != 1
+then
+	echo "Unsupported core.fsmonitor hook version." >&2
+	exit 1
+fi
diff --git a/t/t7519/fsmonitor-watchman b/t/t7519/fsmonitor-watchman
new file mode 100755
index 0000000000..7ceb32dc18
--- /dev/null
+++ b/t/t7519/fsmonitor-watchman
@@ -0,0 +1,140 @@
+#!/usr/bin/perl
+
+use strict;
+use warnings;
+use IPC::Open2;
+
+# An example hook script to integrate Watchman
+# (https://facebook.github.io/watchman/) with git to speed up detecting
+# new and modified files.
+#
+# The hook is passed a version (currently 1) and a time in nanoseconds
+# formatted as a string and outputs to stdout all files that have been
+# modified since the given time. Paths must be relative to the root of
+# the working tree and separated by a single NUL.
+#
+# To enable this hook, rename this file to "query-watchman" and set
+# 'git config core.fsmonitor .git/hooks/query-watchman'
+#
+my ($version, $time) = @ARGV;
+#print STDERR "$0 $version $time\n";
+
+# Check the hook interface version
+
+if ($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/) {
+	$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 {
+
+	# Set input record separator
+	local $/ = 0666;
+
+	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
+	
+	open (my $fh, ">", ".git/watchman-query.json");
+	print $fh $query;
+	close $fh;
+
+	print CHLD_IN $query;
+	my $response = <CHLD_OUT>;
+
+	open ($fh, ">", ".git/watchman-response.json");
+	print $fh $response;
+	close $fh;
+
+	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 $? != 0;
+
+		# Watchman will always return all files on the first query so
+		# return the fast "everything is dirty" flag to git and do the
+		# Watchman query just to get it over with now so we won't pay
+		# the cost in git to look up each individual file.
+
+		open ($fh, ">", ".git/watchman-output.out");
+		print "/\0";
+		close $fh;
+
+		print "/\0";
+		eval { launch_watchman() };
+		exit 0;
+	}
+
+	die "Watchman: $o->{error}.\n" .
+	    "Falling back to scanning...\n" if $o->{error};
+
+	open ($fh, ">", ".git/watchman-output.out");
+	print $fh @{$o->{files}};
+	close $fh;
+
+	binmode STDOUT, ":utf8";
+	local $, = "\0";
+	print @{$o->{files}};
+}