check: add -L <n> parameter to rerun failed tests

If check is run with -L <n>, then a failed test will be rerun <n> times
before proceeding to the next test. Following completion of the rerun
loop, aggregate pass/fail statistics are printed.

Rerun tests will be tracked as a single failure in overall pass/fail
metrics (via @try and @bad), with .out.bad, .dmesg, .core, .hints,
.notrun and .full saved using a .rerun# suffix.

Suggested-by: Theodore Ts'o <tytso@mit.edu>
Link: https://lwn.net/Articles/897061/
Signed-off-by: David Disseldorp <ddiss@suse.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Zorro Lang <zlang@kernel.org>

1 files changed, 54 insertions, 3 deletions

diff --git a/check b/check
index 6dbdb2a8..5f6d86b4 100755
--- a/check
+++ b/check
@@ -26,6 +26,7 @@ do_report=false
 DUMP_OUTPUT=false
 iterations=1
 istop=false
+loop_on_fail=0
 
 # This is a global variable used to pass test failure text to reporting gunk
 _err_msg=""
@@ -78,6 +79,7 @@ check options
     --large-fs		optimise scratch device for large filesystems
     -s section		run only specified section from config file
     -S section		exclude the specified section from the config file
+    -L <n>		loop tests <n> times following a failure, measuring aggregate pass/fail metrics
 
 testlist options
     -g group[,group...]	include tests from these groups
@@ -336,6 +338,9 @@ while [ $# -gt 0 ]; do
 		;;
 	--large-fs) export LARGE_SCRATCH_DEV=yes ;;
 	--extra-space=*) export SCRATCH_DEV_EMPTY_SPACE=${r#*=} ;;
+	-L)	[[ $2 =~ ^[0-9]+$ ]] || usage
+		loop_on_fail=$2; shift
+		;;
 
 	-*)	usage ;;
 	*)	# not an argument, we've got tests now.
@@ -553,6 +558,19 @@ _expunge_test()
 	return 0
 }
 
+# retain files which would be overwritten in subsequent reruns of the same test
+_stash_fail_loop_files() {
+	local seq_prefix="${REPORT_DIR}/${1}"
+	local cp_suffix="$2"
+
+	for i in ".full" ".dmesg" ".out.bad" ".notrun" ".core" ".hints"; do
+		rm -f "${seq_prefix}${i}${cp_suffix}"
+		if [ -f "${seq_prefix}${i}" ]; then
+			cp "${seq_prefix}${i}" "${seq_prefix}${i}${cp_suffix}"
+		fi
+	done
+}
+
 # Retain in @bad / @notrun the result of the just-run @test_seq. @try array
 # entries are added prior to execution.
 _stash_test_status() {
@@ -564,8 +582,35 @@ _stash_test_status() {
 				      "$test_status" "$((stop - start))"
 	fi
 
+	if ((${#loop_status[*]} > 0)); then
+		# continuing or completing rerun-on-failure loop
+		_stash_fail_loop_files "$test_seq" ".rerun${#loop_status[*]}"
+		loop_status+=("$test_status")
+		if ((${#loop_status[*]} > loop_on_fail)); then
+			printf "%s aggregate results across %d runs: " \
+				"$test_seq" "${#loop_status[*]}"
+			awk "BEGIN {
+				n=split(\"${loop_status[*]}\", arr);"'
+				for (i = 1; i <= n; i++)
+					stats[arr[i]]++;
+				for (x in stats)
+					printf("%s=%d (%.1f%%)",
+					       (i-- > n ? x : ", " x),
+					       stats[x], 100 * stats[x] / n);
+				}'
+			echo
+			loop_status=()
+		fi
+		return	# only stash @bad result for initial failure in loop
+	fi
+
 	case "$test_status" in
 	fail)
+		if ((loop_on_fail > 0)); then
+			# initial failure, start rerun-on-failure loop
+			_stash_fail_loop_files "$test_seq" ".rerun0"
+			loop_status+=("$test_status")
+		fi
 		bad+=("$test_seq")
 		;;
 	list|notrun)
@@ -758,8 +803,12 @@ function run_section()
 	seqres="$check"
 	_check_test_fs
 
-	local tc_status
-	for seq in $list ; do
+	loop_status=()	# track rerun-on-failure state
+	local tc_status ix
+	local -a _list=( $list )
+	for ((ix = 0; ix < ${#_list[*]}; !${#loop_status[*]} && ix++)); do
+		seq="${_list[$ix]}"
+
 		if [ ! -f $seq ]; then
 			# Try to get full name in case the user supplied only
 			# seq id and the test has a name. A bit of hassle to
@@ -829,7 +878,9 @@ function run_section()
 		fi
 
 		# record that we really tried to run this test.
-		try+=("$seqnum")
+		if ((!${#loop_status[*]})); then
+			try+=("$seqnum")
+		fi
 
 		awk 'BEGIN {lasttime="       "} \
 		     $1 == "'$seqnum'" {lasttime=" " $2 "s ... "; exit} \