Merge branch 'jh/gitweb-caching' (early part)

* 'jh/gitweb-caching' (early part):
  gitweb: Add optional extra parameter to die_error, for extended explanation
  gitweb: add a "string" variant of print_sort_th
  gitweb: add a "string" variant of print_local_time
  gitweb: Check that $site_header etc. are defined before using them
  gitweb: Makefile improvements
  gitweb: Load checking
  gitweb: Make running t9501 test with '--debug' reliable and usable

6 files changed, 248 insertions, 76 deletions

diff --git a/Makefile b/Makefile
index 83383c38f1..7bf2fca407 100644
--- a/Makefile
+++ b/Makefile
@@ -275,29 +275,6 @@ pathsep = :
 # JavaScript minifier invocation that can function as filter
 JSMIN =
 
-# default configuration for gitweb
-GITWEB_CONFIG = gitweb_config.perl
-GITWEB_CONFIG_SYSTEM = /etc/gitweb.conf
-GITWEB_HOME_LINK_STR = projects
-GITWEB_SITENAME =
-GITWEB_PROJECTROOT = /pub/git
-GITWEB_PROJECT_MAXDEPTH = 2007
-GITWEB_EXPORT_OK =
-GITWEB_STRICT_EXPORT =
-GITWEB_BASE_URL =
-GITWEB_LIST =
-GITWEB_HOMETEXT = indextext.html
-GITWEB_CSS = gitweb.css
-GITWEB_LOGO = git-logo.png
-GITWEB_FAVICON = git-favicon.png
-ifdef JSMIN
-GITWEB_JS = gitweb.min.js
-else
-GITWEB_JS = gitweb.js
-endif
-GITWEB_SITE_HEADER =
-GITWEB_SITE_FOOTER =
-
 export prefix bindir sharedir sysconfdir
 
 CC = gcc
@@ -1518,6 +1495,11 @@ $(patsubst %.perl,%,$(SCRIPT_PERL)): % : %.perl
 	chmod +x $@+ && \
 	mv $@+ $@
 
+
+.PHONY: gitweb
+gitweb:
+	$(QUIET_SUBDIR0)gitweb $(QUIET_SUBDIR1) all
+
 ifdef JSMIN
 OTHER_PROGRAMS += gitweb/gitweb.cgi   gitweb/gitweb.min.js
 gitweb/gitweb.cgi: gitweb/gitweb.perl gitweb/gitweb.min.js
@@ -1525,30 +1507,13 @@ else
 OTHER_PROGRAMS += gitweb/gitweb.cgi
 gitweb/gitweb.cgi: gitweb/gitweb.perl
 endif
-	$(QUIET_GEN)$(RM) $@ $@+ && \
-	sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \
-	    -e 's|++GIT_VERSION++|$(GIT_VERSION)|g' \
-	    -e 's|++GIT_BINDIR++|$(bindir)|g' \
-	    -e 's|++GITWEB_CONFIG++|$(GITWEB_CONFIG)|g' \
-	    -e 's|++GITWEB_CONFIG_SYSTEM++|$(GITWEB_CONFIG_SYSTEM)|g' \
-	    -e 's|++GITWEB_HOME_LINK_STR++|$(GITWEB_HOME_LINK_STR)|g' \
-	    -e 's|++GITWEB_SITENAME++|$(GITWEB_SITENAME)|g' \
-	    -e 's|++GITWEB_PROJECTROOT++|$(GITWEB_PROJECTROOT)|g' \
-	    -e 's|"++GITWEB_PROJECT_MAXDEPTH++"|$(GITWEB_PROJECT_MAXDEPTH)|g' \
-	    -e 's|++GITWEB_EXPORT_OK++|$(GITWEB_EXPORT_OK)|g' \
-	    -e 's|++GITWEB_STRICT_EXPORT++|$(GITWEB_STRICT_EXPORT)|g' \
-	    -e 's|++GITWEB_BASE_URL++|$(GITWEB_BASE_URL)|g' \
-	    -e 's|++GITWEB_LIST++|$(GITWEB_LIST)|g' \
-	    -e 's|++GITWEB_HOMETEXT++|$(GITWEB_HOMETEXT)|g' \
-	    -e 's|++GITWEB_CSS++|$(GITWEB_CSS)|g' \
-	    -e 's|++GITWEB_LOGO++|$(GITWEB_LOGO)|g' \
-	    -e 's|++GITWEB_FAVICON++|$(GITWEB_FAVICON)|g' \
-	    -e 's|++GITWEB_JS++|$(GITWEB_JS)|g' \
-	    -e 's|++GITWEB_SITE_HEADER++|$(GITWEB_SITE_HEADER)|g' \
-	    -e 's|++GITWEB_SITE_FOOTER++|$(GITWEB_SITE_FOOTER)|g' \
-	    $< >$@+ && \
-	chmod +x $@+ && \
-	mv $@+ $@
+	$(QUIET_SUBDIR0)gitweb $(QUIET_SUBDIR1) $(patsubst gitweb/%,%,$@)
+
+ifdef JSMIN
+gitweb/gitweb.min.js: gitweb/gitweb.js
+	$(QUIET_SUBDIR0)gitweb $(QUIET_SUBDIR1) $(patsubst gitweb/%,%,$@)
+endif # JSMIN
+
 
 git-instaweb: git-instaweb.sh gitweb/gitweb.cgi gitweb/gitweb.css gitweb/gitweb.js
 	$(QUIET_GEN)$(RM) $@ $@+ && \
@@ -1575,12 +1540,6 @@ $(patsubst %.perl,%,$(SCRIPT_PERL)) git-instaweb: % : unimplemented.sh
 	mv $@+ $@
 endif # NO_PERL
 
-
-ifdef JSMIN
-gitweb/gitweb.min.js: gitweb/gitweb.js
-	$(QUIET_GEN)$(JSMIN) <$< >$@
-endif # JSMIN
-
 ifndef NO_PYTHON
 $(patsubst %.py,%,$(SCRIPT_PYTHON)): GIT-CFLAGS
 $(patsubst %.py,%,$(SCRIPT_PYTHON)): % : %.py
diff --git a/gitweb/Makefile b/gitweb/Makefile
new file mode 100644
index 0000000000..c9eb1ee667
--- /dev/null
+++ b/gitweb/Makefile
@@ -0,0 +1,129 @@
+# The default target of this Makefile is...
+all::
+
+# Define V=1 to have a more verbose compile.
+#
+# Define JSMIN to point to JavaScript minifier that functions as
+# a filter to have gitweb.js minified.
+#
+
+prefix ?= $(HOME)
+bindir ?= $(prefix)/bin
+RM ?= rm -f
+
+# JavaScript minifier invocation that can function as filter
+JSMIN ?=
+
+# default configuration for gitweb
+GITWEB_CONFIG = gitweb_config.perl
+GITWEB_CONFIG_SYSTEM = /etc/gitweb.conf
+GITWEB_HOME_LINK_STR = projects
+GITWEB_SITENAME =
+GITWEB_PROJECTROOT = /pub/git
+GITWEB_PROJECT_MAXDEPTH = 2007
+GITWEB_EXPORT_OK =
+GITWEB_STRICT_EXPORT =
+GITWEB_BASE_URL =
+GITWEB_LIST =
+GITWEB_HOMETEXT = indextext.html
+GITWEB_CSS = gitweb.css
+GITWEB_LOGO = git-logo.png
+GITWEB_FAVICON = git-favicon.png
+ifdef JSMIN
+GITWEB_JS = gitweb.min.js
+else
+GITWEB_JS = gitweb.js
+endif
+GITWEB_SITE_HEADER =
+GITWEB_SITE_FOOTER =
+
+# include user config
+-include ../config.mak.autogen
+-include ../config.mak
+
+# determine version
+../GIT-VERSION-FILE: .FORCE-GIT-VERSION-FILE
+	$(QUIET_SUBDIR0)../ $(QUIET_SUBDIR1) GIT-VERSION-FILE
+
+-include ../GIT-VERSION-FILE
+
+### Build rules
+
+SHELL_PATH ?= $(SHELL)
+PERL_PATH  ?= /usr/bin/perl
+
+# Shell quote;
+bindir_SQ = $(subst ','\'',$(bindir))         #'
+SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH)) #'
+PERL_PATH_SQ  = $(subst ','\'',$(PERL_PATH))  #'
+
+# Quiet generation (unless V=1)
+QUIET_SUBDIR0  = +$(MAKE) -C # space to separate -C and subdir
+QUIET_SUBDIR1  =
+
+ifneq ($(findstring $(MAKEFLAGS),w),w)
+PRINT_DIR = --no-print-directory
+else # "make -w"
+NO_SUBDIR = :
+endif
+
+ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifndef V
+	QUIET          = @
+	QUIET_GEN      = $(QUIET)echo '   ' GEN $@;
+	QUIET_SUBDIR0  = +@subdir=
+	QUIET_SUBDIR1  = ;$(NO_SUBDIR) echo '   ' SUBDIR $$subdir; \
+	                 $(MAKE) $(PRINT_DIR) -C $$subdir
+	export V
+	export QUIET
+	export QUIET_GEN
+	export QUIET_SUBDIR0
+	export QUIET_SUBDIR1
+endif
+endif
+
+all:: gitweb.cgi
+
+ifdef JSMIN
+FILES=gitweb.cgi gitweb.min.js
+gitweb.cgi: gitweb.perl gitweb.min.js
+else # !JSMIN
+FILES=gitweb.cgi
+gitweb.cgi: gitweb.perl
+endif # JSMIN
+
+gitweb.cgi:
+	$(QUIET_GEN)$(RM) $@ $@+ && \
+	sed -e '1s|#!.*perl|#!$(PERL_PATH_SQ)|' \
+	    -e 's|++GIT_VERSION++|$(GIT_VERSION)|g' \
+	    -e 's|++GIT_BINDIR++|$(bindir)|g' \
+	    -e 's|++GITWEB_CONFIG++|$(GITWEB_CONFIG)|g' \
+	    -e 's|++GITWEB_CONFIG_SYSTEM++|$(GITWEB_CONFIG_SYSTEM)|g' \
+	    -e 's|++GITWEB_HOME_LINK_STR++|$(GITWEB_HOME_LINK_STR)|g' \
+	    -e 's|++GITWEB_SITENAME++|$(GITWEB_SITENAME)|g' \
+	    -e 's|++GITWEB_PROJECTROOT++|$(GITWEB_PROJECTROOT)|g' \
+	    -e 's|"++GITWEB_PROJECT_MAXDEPTH++"|$(GITWEB_PROJECT_MAXDEPTH)|g' \
+	    -e 's|++GITWEB_EXPORT_OK++|$(GITWEB_EXPORT_OK)|g' \
+	    -e 's|++GITWEB_STRICT_EXPORT++|$(GITWEB_STRICT_EXPORT)|g' \
+	    -e 's|++GITWEB_BASE_URL++|$(GITWEB_BASE_URL)|g' \
+	    -e 's|++GITWEB_LIST++|$(GITWEB_LIST)|g' \
+	    -e 's|++GITWEB_HOMETEXT++|$(GITWEB_HOMETEXT)|g' \
+	    -e 's|++GITWEB_CSS++|$(GITWEB_CSS)|g' \
+	    -e 's|++GITWEB_LOGO++|$(GITWEB_LOGO)|g' \
+	    -e 's|++GITWEB_FAVICON++|$(GITWEB_FAVICON)|g' \
+	    -e 's|++GITWEB_JS++|$(GITWEB_JS)|g' \
+	    -e 's|++GITWEB_SITE_HEADER++|$(GITWEB_SITE_HEADER)|g' \
+	    -e 's|++GITWEB_SITE_FOOTER++|$(GITWEB_SITE_FOOTER)|g' \
+	    $< >$@+ && \
+	chmod +x $@+ && \
+	mv $@+ $@
+
+ifdef JSMIN
+gitweb.min.js: gitweb.js
+	$(QUIET_GEN)$(JSMIN) <$< >$@
+endif # JSMIN
+
+clean:
+	$(RM) $(FILES)
+
+.PHONY: all clean .FORCE-GIT-VERSION-FILE
diff --git a/gitweb/README b/gitweb/README
index e34ee793ef..6c2c8e1259 100644
--- a/gitweb/README
+++ b/gitweb/README
@@ -174,7 +174,7 @@ not include variables usually directly set during build):
    Base URL for relative URLs in pages generated by gitweb,
    (e.g. $logo, $favicon, @stylesheets if they are relative URLs),
    needed and used only for URLs with nonempty PATH_INFO via
-   <base href="$base_url>.  Usually gitweb sets its value correctly,
+   <base href="$base_url">.  Usually gitweb sets its value correctly,
    and there is no need to set this variable, e.g. to $my_uri or "/".
  * $home_link
    Target of the home link on top of all pages (the first part of view
@@ -228,6 +228,11 @@ not include variables usually directly set during build):
    repositories from launching cross-site scripting (XSS) attacks.  Set this
    to true if you don't trust the content of your repositories. The default
    is false.
+ * $maxload
+   Used to set the maximum load that we will still respond to gitweb queries.
+   If server load exceed this value then return "503 Service Unavaliable" error.
+   Server load is taken to be 0 if gitweb cannot determine its value.  Set it to
+   undefined value to turn it off.  The default is 300.
 
 
 Projects list file format
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl
index 7e477af956..d0c3ff258d 100755
--- a/gitweb/gitweb.perl
+++ b/gitweb/gitweb.perl
@@ -221,6 +221,12 @@ our %avatar_size = (
 	'double'  => 32
 );
 
+# Used to set the maximum load that we will still respond to gitweb queries.
+# If server load exceed this value then return "503 server busy" error.
+# If gitweb cannot determined server load, it is taken to be 0.
+# Leave it undefined (or set to 'undef') to turn off load checking.
+our $maxload = 300;
+
 # You define site-wide feature defaults here; override them with
 # $GITWEB_CONFIG as necessary.
 our %feature = (
@@ -551,12 +557,38 @@ if (-e $GITWEB_CONFIG) {
 	do $GITWEB_CONFIG_SYSTEM if -e $GITWEB_CONFIG_SYSTEM;
 }
 
+# Get loadavg of system, to compare against $maxload.
+# Currently it requires '/proc/loadavg' present to get loadavg;
+# if it is not present it returns 0, which means no load checking.
+sub get_loadavg {
+	if( -e '/proc/loadavg' ){
+		open my $fd, '<', '/proc/loadavg'
+			or return 0;
+		my @load = split(/\s+/, scalar <$fd>);
+		close $fd;
+
+		# The first three columns measure CPU and IO utilization of the last one,
+		# five, and 10 minute periods.  The fourth column shows the number of
+		# currently running processes and the total number of processes in the m/n
+		# format.  The last column displays the last process ID used.
+		return $load[0] || 0;
+	}
+	# additional checks for load average should go here for things that don't export
+	# /proc/loadavg
+
+	return 0;
+}
+
 # version of the core git binary
 our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown";
 $number_of_git_cmds++;
 
 $projects_list ||= $projectroot;
 
+if (defined $maxload && get_loadavg() > $maxload) {
+	die_error(503, "The load average on the server is too high");
+}
+
 # ======================================================================
 # input validation and dispatch
 
@@ -3222,7 +3254,7 @@ EOF
 	print "</head>\n" .
 	      "<body>\n";
 
-	if (-f $site_header) {
+	if (defined $site_header && -f $site_header) {
 		insert_file($site_header);
 	}
 
@@ -3323,12 +3355,13 @@ sub git_footer_html {
 		print "</div>\n"; # class="page_footer"
 	}
 
-	if (-f $site_footer) {
+	if (defined $site_footer && -f $site_footer) {
 		insert_file($site_footer);
 	}
 
 	print qq!<script type="text/javascript" src="$javascript"></script>\n!;
-	if ($action eq 'blame_incremental') {
+	if (defined $action &&
+	    $action eq 'blame_incremental') {
 		print qq!<script type="text/javascript">\n!.
 		      qq!startBlame("!. href(action=>"blame_data", -replay=>1) .qq!",\n!.
 		      qq!           "!. href() .qq!");\n!.
@@ -3354,22 +3387,33 @@ sub git_footer_html {
 # 500: The server isn't configured properly, or
 #      an internal error occurred (e.g. failed assertions caused by bugs), or
 #      an unknown error occurred (e.g. the git binary died unexpectedly).
+# 503: The server is currently unavailable (because it is overloaded,
+#      or down for maintenance).  Generally, this is a temporary state.
 sub die_error {
 	my $status = shift || 500;
 	my $error = shift || "Internal server error";
-
-	my %http_responses = (400 => '400 Bad Request',
-			      403 => '403 Forbidden',
-			      404 => '404 Not Found',
-			      500 => '500 Internal Server Error');
+	my $extra = shift;
+
+	my %http_responses = (
+		400 => '400 Bad Request',
+		403 => '403 Forbidden',
+		404 => '404 Not Found',
+		500 => '500 Internal Server Error',
+		503 => '503 Service Unavailable',
+	);
 	git_header_html($http_responses{$status});
 	print <<EOF;
 <div class="page_body">
 <br /><br />
 $status - $error
 <br />
-</div>
 EOF
+	if (defined $extra) {
+		print "<hr />\n" .
+		      "$extra\n";
+	}
+	print "</div>\n";
+
 	git_footer_html();
 	exit;
 }
@@ -3471,14 +3515,21 @@ sub git_print_header_div {
 }
 
 sub print_local_time {
+	print format_local_time(@_);
+}
+
+sub format_local_time {
+	my $localtime = '';
 	my %date = @_;
 	if ($date{'hour_local'} < 6) {
-		printf(" (<span class=\"atnight\">%02d:%02d</span> %s)",
+		$localtime .= sprintf(" (<span class=\"atnight\">%02d:%02d</span> %s)",
 			$date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'});
 	} else {
-		printf(" (%02d:%02d %s)",
+		$localtime .= sprintf(" (%02d:%02d %s)",
 			$date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'});
 	}
+
+	return $localtime;
 }
 
 # Outputs the author name and date in long form
@@ -4302,17 +4353,24 @@ sub fill_project_list_info {
 # print 'sort by' <th> element, generating 'sort by $name' replay link
 # if that order is not selected
 sub print_sort_th {
+	print format_sort_th(@_);
+}
+
+sub format_sort_th {
 	my ($name, $order, $header) = @_;
+	my $sort_th = "";
 	$header ||= ucfirst($name);
 
 	if ($order eq $name) {
-		print "<th>$header</th>\n";
+		$sort_th .= "<th>$header</th>\n";
 	} else {
-		print "<th>" .
-		      $cgi->a({-href => href(-replay=>1, order=>$name),
-		               -class => "header"}, $header) .
-		      "</th>\n";
+		$sort_th .= "<th>" .
+		            $cgi->a({-href => href(-replay=>1, order=>$name),
+		                     -class => "header"}, $header) .
+		            "</th>\n";
 	}
+
+	return $sort_th;
 }
 
 sub git_project_list_body {
@@ -4743,7 +4801,7 @@ sub git_project_list {
 	}
 
 	git_header_html();
-	if (-f $home_text) {
+	if (defined $home_text && -f $home_text) {
 		print "<div class=\"index_include\">\n";
 		insert_file($home_text);
 		print "</div>\n";
diff --git a/t/gitweb-lib.sh b/t/gitweb-lib.sh
index 76d8b7b803..5a734b1b7b 100644
--- a/t/gitweb-lib.sh
+++ b/t/gitweb-lib.sh
@@ -25,6 +25,7 @@ our \$favicon = 'file:///$TEST_DIRECTORY/../gitweb/git-favicon.png';
 our \$projects_list = '';
 our \$export_ok = '';
 our \$strict_export = '';
+our \$maxload = undef;
 
 EOF
 
diff --git a/t/t9501-gitweb-standalone-http-status.sh b/t/t9501-gitweb-standalone-http-status.sh
index 0688a57e1d..7590f10b66 100755
--- a/t/t9501-gitweb-standalone-http-status.sh
+++ b/t/t9501-gitweb-standalone-http-status.sh
@@ -33,7 +33,6 @@ test_expect_success \
     grep "403 - Snapshot format not allowed" gitweb.output &&
     gitweb_run "p=.git;a=snapshot;h=HEAD;sf=zip" &&
     grep "403 - Unsupported snapshot format" gitweb.output'
-test_debug 'cat gitweb.output'
 
 
 cat >>gitweb_config.perl <<\EOF
@@ -50,7 +49,6 @@ test_expect_success \
     grep "403 - Snapshot format not allowed" gitweb.output &&
     gitweb_run "p=.git;a=snapshot;h=HEAD;sf=zip" &&
     grep "Status: 200 OK" gitweb.output'
-test_debug 'cat gitweb.output'
 
 
 cat >>gitweb_config.perl <<\EOF
@@ -72,7 +70,7 @@ test_expect_success \
     'snapshots: tgz explicitly enabled' \
     'gitweb_run "p=.git;a=snapshot;h=HEAD;sf=tgz" &&
     grep "Status: 200 OK" gitweb.output'
-test_debug 'cat gitweb.output'
+test_debug 'cat gitweb.headers'
 
 
 # ----------------------------------------------------------------------
@@ -82,7 +80,7 @@ test_expect_success 'snapshots: good tree-ish id' '
 	gitweb_run "p=.git;a=snapshot;h=master;sf=tgz" &&
 	grep "Status: 200 OK" gitweb.output
 '
-test_debug 'cat gitweb.output'
+test_debug 'cat gitweb.headers'
 
 test_expect_success 'snapshots: bad tree-ish id' '
 	gitweb_run "p=.git;a=snapshot;h=frizzumFrazzum;sf=tgz" &&
@@ -105,7 +103,7 @@ test_expect_success 'snapshots: good object id' '
 	gitweb_run "p=.git;a=snapshot;h=$ID;sf=tgz" &&
 	grep "Status: 200 OK" gitweb.output
 '
-test_debug 'cat gitweb.output'
+test_debug 'cat gitweb.headers'
 
 test_expect_success 'snapshots: bad object id' '
 	gitweb_run "p=.git;a=snapshot;h=abcdef01234;sf=tgz" &&
@@ -114,4 +112,26 @@ test_expect_success 'snapshots: bad object id' '
 test_debug 'cat gitweb.output'
 
 
+# ----------------------------------------------------------------------
+# load checking
+
+# always hit the load limit
+cat >>gitweb_config.perl <<\EOF
+our $maxload = 0;
+EOF
+
+test_expect_success 'load checking: load too high (default action)' '
+	gitweb_run "p=.git" &&
+	grep "Status: 503 Service Unavailable" gitweb.headers &&
+	grep "503 - The load average on the server is too high" gitweb.body
+'
+test_debug 'cat gitweb.log' # just in case
+test_debug 'cat gitweb.headers'
+
+# turn off load checking
+cat >>gitweb_config.perl <<\EOF
+our $maxload = undef;
+EOF
+
+
 test_done