From: Lai Siyao <lai.siyao@whamcloud.com>
Date: Mon, 10 Jul 2023 04:30:28 +0000 (-0400)
Subject: LU-11036 test: race in sanity-lfsck test_8
X-Git-Url: https://git.whamcloud.com/?a=commitdiff_plain;h=6b13323c4334ae347bfce5df6a6e8adf89b6113a;p=fs%2Flustre-release.git

LU-11036 test: race in sanity-lfsck test_8

In sanity-lfsck test_8, "sleep 1" is run after START_NAMESPACE,
but it still has chance that LFSCK status is complete but LFSCK
thread not quit yet, therefore the following START_NAMESPACE may fail
with -EALREADY. Just check the first lfsck started scanning.

And similarly use wait_update to check flags for DELAY3.

Lustre-change: https://review.whamcloud.com/51720
Lustre-commit: f1ddb4093ed623c1382f75e47807e4081962cc3d

Test-Parameters: trivial MDSCOUNT=2 MDTCOUNT=4 testlist=sanity-lfsck env=ONLY=8,ONLY_REPEAT=10
Signed-off-by: Lai Siyao <lai.siyao@whamcloud.com>
Change-Id: Ie1f612bebb52c4755e5b4e13d58ab8bf2aeb2832
Reviewed-on: https://review.whamcloud.com/c/ex/lustre-release/+/51927
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
---

diff --git a/lustre/tests/sanity-lfsck.sh b/lustre/tests/sanity-lfsck.sh
old mode 100644
new mode 100755
index e97298c..5bec755
--- a/lustre/tests/sanity-lfsck.sh
+++ b/lustre/tests/sanity-lfsck.sh
@@ -969,16 +969,12 @@ test_8()
 	#define OBD_FAIL_LFSCK_DELAY2		0x1601
 	do_facet $SINGLEMDS $LCTL set_param fail_loc=0x1601
 	$START_NAMESPACE || error "(16) Fail to start LFSCK for namespace!"
-	sleep 1
-	[ -n "$($SHOW_NAMESPACE |
-		grep -E "status: init|status: completed")" ] && {
-		$START_NAMESPACE ||
-		namespace_error "(16) Fail to start LFSCK for namespace!"
-	} || echo "lfsck for namespace has been started"
-
-	STATUS=$($SHOW_NAMESPACE | awk '/^status/ { print $2 }')
-	[ "$STATUS" == "scanning-phase1" ] ||
-		error "(17) Expect 'scanning-phase1', but got '$STATUS'"
+	wait_update_facet $SINGLEMDS "$LCTL get_param -n \
+		mdd.${MDT_DEV}.lfsck_namespace |
+		awk '/^status/ { print \\\$2 }'" "scanning-phase1" 32 || {
+		$SHOW_NAMESPACE
+		error "(17) unexpected status"
+	}
 
 	echo "stop $SINGLEMDS"
 	stop $SINGLEMDS > /dev/null || error "(18) Fail to stop MDS!"
@@ -1043,11 +1039,12 @@ test_8()
 	}
 
 	# wait to process one inode at least (OBD_FAIL_LFSCK_DELAY3)
-	sleep 3
-
-	local FLAGS=$($SHOW_NAMESPACE | awk '/^flags/ { print $2 }')
-	[ "$FLAGS" == "scanned-once,inconsistent" ] ||
-		error "(23) Expect 'scanned-once,inconsistent',but got '$FLAGS'"
+	wait_update_facet $SINGLEMDS "$LCTL get_param -n \
+		mdd.${MDT_DEV}.lfsck_namespace |
+		awk '/^flags/ { print \\\$2 }'" "scanned-once,inconsistent" 32 || {
+		$SHOW_NAMESPACE
+		error "(23) Expect 'scanned-once,inconsistent'"
+	}
 
 	do_facet $SINGLEMDS $LCTL set_param fail_loc=0 fail_val=0
 	wait_update_facet $SINGLEMDS "$LCTL get_param -n \