fsmonitor: add tests for Linux

Add a smoke test that verifies the filesystem actually delivers
inotify events to the daemon.  On some configurations (e.g.,
overlayfs with older kernels), inotify watches succeed but events
are never delivered.  The daemon cookie wait will time out, but
every subsequent test would fail.  Skip the entire test file early
when this is detected.

Add a test that exercises rapid nested directory creation to verify
the daemon correctly handles the EEXIST race between recursive scan
and queued inotify events.  When IN_MASK_CREATE is available and a
directory watch is added during recursive registration, the kernel
may also deliver a queued IN_CREATE event for the same directory.
The second inotify_add_watch() returns EEXIST, which must be treated
as harmless.  An earlier version of the listener crashed in this
scenario.

Reduce --start-timeout from the default 60 seconds to 10 seconds so
that tests fail promptly when the daemon cannot start.

Harden the test helpers to work in environments without procps
(e.g., Fedora CI): fall back to reading /proc/$pid/stat for the
process group ID when ps is unavailable, guard stop_git() against
an empty pgid, and redirect stderr from kill to /dev/null to avoid
noise when processes have already exited.

Use set -m to enable job control in the submodule-pull test so that
the background git pull gets its own process group, preventing the
shell wait from blocking on the daemon.  setsid() in the previous
commit detaches the daemon itself, but the intermediate git pull
process still needs its own process group for the test shell to
manage it correctly.

Signed-off-by: Paul Tarjan <github@paulisageek.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/t/t7527-builtin-fsmonitor.sh b/t/t7527-builtin-fsmonitor.sh
index 409cd0cd121695ed6f90761df75eadf621611de5..774da5ac60924d0923fea1f96abcae4cc7227f15 100755 (executable)
--- a/t/t7527-builtin-fsmonitor.sh
+++ b/t/t7527-builtin-fsmonitor.sh
@@ -10,9 +10,58 @@ then
        test_done
 fi
 
+# Verify that the filesystem delivers events to the daemon.
+# On some configurations (e.g., overlayfs with older kernels),
+# inotify watches succeed but events are never delivered.  The
+# cookie wait will time out and the daemon logs a trace message.
+#
+# Use "timeout" (if available) to guard each step against hangs.
+maybe_timeout () {
+       if type timeout >/dev/null 2>&1
+       then
+               timeout "$@"
+       else
+               shift
+               "$@"
+       fi
+}
+verify_fsmonitor_works () {
+       git init test_fsmonitor_smoke || return 1
+
+       GIT_TRACE_FSMONITOR="$PWD/smoke.trace" &&
+       export GIT_TRACE_FSMONITOR &&
+       maybe_timeout 30 \
+               git -C test_fsmonitor_smoke fsmonitor--daemon start \
+                       --start-timeout=10
+       ret=$?
+       unset GIT_TRACE_FSMONITOR
+       if test $ret -ne 0
+       then
+               rm -rf test_fsmonitor_smoke smoke.trace
+               return 1
+       fi
+
+       maybe_timeout 10 \
+               test-tool -C test_fsmonitor_smoke fsmonitor-client query \
+                       --token 0 >/dev/null 2>&1
+       maybe_timeout 5 \
+               git -C test_fsmonitor_smoke fsmonitor--daemon stop 2>/dev/null
+       ! grep -q "cookie_wait timed out" "$PWD/smoke.trace" 2>/dev/null
+       ret=$?
+       rm -rf test_fsmonitor_smoke smoke.trace
+       return $ret
+}
+
+if ! verify_fsmonitor_works
+then
+       skip_all="filesystem does not deliver fsmonitor events (container/overlayfs?)"
+       test_done
+fi
+
 stop_daemon_delete_repo () {
        r=$1 &&
-       test_might_fail git -C $r fsmonitor--daemon stop &&
+       test_might_fail maybe_timeout 30 \
+               git -C $r fsmonitor--daemon stop 2>/dev/null
        rm -rf $1
 }
 
@@ -67,7 +116,7 @@ start_daemon () {
                        export GIT_TEST_FSMONITOR_TOKEN
                fi &&
 
-               git $r fsmonitor--daemon start &&
+               git $r fsmonitor--daemon start --start-timeout=10 &&
                git $r fsmonitor--daemon status
        )
 }
@@ -520,6 +569,28 @@ test_expect_success 'directory changes to a file' '
        grep "^event: dir1$" .git/trace
 '
 
+test_expect_success 'rapid nested directory creation' '
+       test_when_finished "git fsmonitor--daemon stop; rm -rf rapid" &&
+
+       start_daemon --tf "$PWD/.git/trace" &&
+
+       # Rapidly create nested directories to exercise race conditions
+       # where directory watches may be added concurrently during
+       # event processing and recursive scanning.
+       for i in $(test_seq 1 20)
+       do
+               mkdir -p "rapid/nested/dir$i/subdir/deep" || return 1
+       done &&
+
+       # Give the daemon time to process all events
+       sleep 1 &&
+
+       test-tool fsmonitor-client query --token 0 &&
+
+       # Verify daemon is still running (did not crash)
+       git fsmonitor--daemon status
+'
+
 # The next few test cases exercise the token-resync code.  When filesystem
 # drops events (because of filesystem velocity or because the daemon isn't
 # polling fast enough), we need to discard the cached data (relative to the
@@ -910,7 +981,10 @@ test_expect_success "submodule absorbgitdirs implicitly starts daemon" '
 start_git_in_background () {
        git "$@" &
        git_pid=$!
-       git_pgid=$(ps -o pgid= -p $git_pid)
+       git_pgid=$(ps -o pgid= -p $git_pid 2>/dev/null ||
+               awk '{print $5}' /proc/$git_pid/stat 2>/dev/null) &&
+       git_pgid="${git_pgid## }" &&
+       git_pgid="${git_pgid%% }"
        nr_tries_left=10
        while true
        do
@@ -921,15 +995,16 @@ start_git_in_background () {
                fi
                sleep 1
                nr_tries_left=$(($nr_tries_left - 1))
-       done >/dev/null 2>&1 &
+       done >/dev/null 2>&1 3>&- 4>&- 5>&- 6>&- 7>&- &
        watchdog_pid=$!
        wait $git_pid
 }
 
 stop_git () {
-       while kill -0 -- -$git_pgid
+       test -n "$git_pgid" || return 0
+       while kill -0 -- -$git_pgid 2>/dev/null
        do
-               kill -- -$git_pgid
+               kill -- -$git_pgid 2>/dev/null
                sleep 1
        done
 }
@@ -944,7 +1019,7 @@ stop_watchdog () {
 
 test_expect_success !MINGW "submodule implicitly starts daemon by pull" '
        test_atexit "stop_watchdog" &&
-       test_when_finished "stop_git; rm -rf cloned super sub" &&
+       test_when_finished "set +m; stop_git; rm -rf cloned super sub" &&
 
        create_super super &&
        create_sub sub &&