[PATCH 2/6] common: capture metadump output if xfs filesystem check fails

["Darrick J. Wong" <djwong@kernel.org>]

From: Darrick J. Wong <djwong@djwong.org>

Capture metadump output when various userspace repair and checker tools
fail or indicate corruption, to aid in debugging.  We don't bother to
annotate xfs_check because it's bitrotting.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
---
 README     |    2 ++
 common/xfs |   26 ++++++++++++++++++++++++++
 2 files changed, 28 insertions(+)


diff --git a/README b/README
index 43bb0cee..36f72088 100644
--- a/README
+++ b/README
@@ -109,6 +109,8 @@ Preparing system for tests:
              - Set TEST_FS_MODULE_RELOAD=1 to unload the module and reload
                it between test invocations.  This assumes that the name of
                the module is the same as FSTYP.
+	     - Set SNAPSHOT_CORRUPT_XFS=1 to record compressed metadumps of XFS
+	       filesystems if the various stages of _check_xfs_filesystem fail.
 
         - or add a case to the switch in common/config assigning
           these variables based on the hostname of your test
diff --git a/common/xfs b/common/xfs
index 2156749d..ad1eb6ee 100644
--- a/common/xfs
+++ b/common/xfs
@@ -432,6 +432,21 @@ _supports_xfs_scrub()
 	return 0
 }
 
+# Save a compressed snapshot of a corrupt xfs filesystem for later debugging.
+_snapshot_xfs() {
+	local metadump="$1"
+	local device="$2"
+	local logdev="$3"
+	local options="-a -o"
+
+	if [ "$logdev" != "none" ]; then
+		options="$options -l $logdev"
+	fi
+
+	$XFS_METADUMP_PROG $options "$device" "$metadump" >> "$seqres.full" 2>&1
+	gzip -f "$metadump" >> "$seqres.full" 2>&1 &
+}
+
 # run xfs_check and friends on a FS.
 _check_xfs_filesystem()
 {
@@ -482,6 +497,9 @@ _check_xfs_filesystem()
 		# mounted ...
 		mountpoint=`_umount_or_remount_ro $device`
 	fi
+	if [ "$ok" -ne 1 ] && [ "$SNAPSHOT_CORRUPT_XFS" = "1" ]; then
+		_snapshot_xfs "$seqres.scrub.md" "$device" "$2"
+	fi
 
 	$XFS_LOGPRINT_PROG -t $extra_log_options $device 2>&1 \
 		| tee $tmp.logprint | grep -q "<CLEAN>"
@@ -491,6 +509,8 @@ _check_xfs_filesystem()
 		cat $tmp.logprint			>>$seqres.full
 		echo "*** end xfs_logprint output"	>>$seqres.full
 
+		test "$SNAPSHOT_CORRUPT_XFS" = "1" && \
+			_snapshot_xfs "$seqres.logprint.md" "$device" "$2"
 		ok=0
 	fi
 
@@ -516,6 +536,8 @@ _check_xfs_filesystem()
 		cat $tmp.repair				>>$seqres.full
 		echo "*** end xfs_repair output"	>>$seqres.full
 
+		test "$SNAPSHOT_CORRUPT_XFS" = "1" && \
+			_snapshot_xfs "$seqres.repair.md" "$device" "$2"
 		ok=0
 	fi
 	rm -f $tmp.fs_check $tmp.logprint $tmp.repair
@@ -529,6 +551,8 @@ _check_xfs_filesystem()
 			cat $tmp.repair				>>$seqres.full
 			echo "*** end xfs_repair output"	>>$seqres.full
 
+			test "$SNAPSHOT_CORRUPT_XFS" = "1" && \
+				_snapshot_xfs "$seqres.rebuild.md" "$device" "$2"
 			ok=0
 		fi
 		rm -f $tmp.repair
@@ -540,6 +564,8 @@ _check_xfs_filesystem()
 			cat $tmp.repair				>>$seqres.full
 			echo "*** end xfs_repair output"	>>$seqres.full
 
+			test "$SNAPSHOT_CORRUPT_XFS" = "1" && \
+				_snapshot_xfs "$seqres.rebuildrepair.md" "$device" "$2"
 			ok=0
 		fi
 		rm -f $tmp.repair