fuzzy: abort scrub stress testing if the scratch fs went down

There's no point in continuing a stress test of online fsck if the
filesystem goes down.  We can't query that kind of state directly, so as
a proxy we try to stat the mountpoint and interpret any error return as
a sign that the fs is down.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Zorro Lang <zlang@redhat.com>
Signed-off-by: Zorro Lang <zlang@kernel.org>

diff --git a/common/fuzzy b/common/fuzzy
index 6519d5c1e28c9d942bf8488f42953849a1f10627..f1bc2dc75640350cb7d77cf54feca214800c83a9 100644 (file)
--- a/common/fuzzy
+++ b/common/fuzzy
@@ -338,10 +338,17 @@ __stress_scrub_filter_output() {
                    -e '/No space left on device/d'
 }
 
+# Decide if the scratch filesystem is still alive.
+__stress_scrub_scratch_alive() {
+       # If we can't stat the scratch filesystem, there's a reasonably good
+       # chance that the fs shut down, which is not good.
+       stat "$SCRATCH_MNT" &>/dev/null
+}
+
 # Decide if we want to keep running stress tests.  The first argument is the
 # stop time, and second argument is the path to the sentinel file.
 __stress_scrub_running() {
-       test -e "$2" && test "$(date +%s)" -lt "$1"
+       test -e "$2" && test "$(date +%s)" -lt "$1" && __stress_scrub_scratch_alive
 }
 
 # Run fs freeze and thaw in a tight loop.
@@ -486,6 +493,10 @@ _scratch_xfs_stress_scrub() {
        done
        _scratch_xfs_stress_scrub_cleanup
 
+       # Warn the user if we think the scratch filesystem went down.
+       __stress_scrub_scratch_alive || \
+               echo "Did the scratch filesystem die?"
+
        echo "Loop finished at $(date)" >> $seqres.full
 }