LU-15791 tests: Get health before removing drop rules

lnet_health_post() can race with recovery pings, so we should
wait to delete the drop rules until after we've gathered the
health and resend values.

Test-Parameters: trivial testlist=sanity-lnet
Fixes: 79ab053562 ("LU-13569 lnet: Deprecate lnet_recovery_interval")
Signed-off-by: Chris Horn <chris.horn@hpe.com>
Change-Id: Ia7595e015809f796cafcc40382d98ab66a708a49
Reviewed-on: https://review.whamcloud.com/47998
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Cyril Bordage <cbordage@whamcloud.com>
Reviewed-by: Frank Sehr <fsehr@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lustre/tests/sanity-lnet.sh b/lustre/tests/sanity-lnet.sh
index 28afdfd..5ef45ef 100755 (executable)
--- a/lustre/tests/sanity-lnet.sh
+++ b/lustre/tests/sanity-lnet.sh
@@ -1346,6 +1346,8 @@ function lnet_health_post() {
 
        restore_lnet_params
 
+       $LCTL net_drop_del -a
+
        do_lnetctl peer set --health 1000 --all
        do_lnetctl net set --health 1000 --all
 
@@ -1549,7 +1551,6 @@ test_204() {
                add_health_test_drop_rules ${hstatus}
                do_lnetctl discover ${RNIDS[0]} &&
                        error "Should have failed"
-               $LCTL net_drop_del -a
 
                lnet_health_post
 
@@ -1574,7 +1575,6 @@ test_205() {
                add_health_test_drop_rules ${hstatus}
                do_lnetctl discover ${RNIDS[0]} &&
                        error "Should have failed"
-               $LCTL net_drop_del -a
 
                lnet_health_post
 
@@ -1589,7 +1589,6 @@ test_205() {
                add_health_test_drop_rules ${hstatus}
                do_lnetctl discover ${RNIDS[0]} &&
                        error "Should have failed"
-               $LCTL net_drop_del -a
 
                lnet_health_post
 
@@ -1618,7 +1617,6 @@ test_206() {
                add_health_test_drop_rules ${hstatus}
                do_lnetctl discover ${RNIDS[0]} &&
                        error "Should have failed"
-               $LCTL net_drop_del -a
 
                lnet_health_post
 
@@ -1648,8 +1646,6 @@ test_207() {
 
                lnet_health_post
 
-               $LCTL net_drop_del -a
-
                check_resends || return $?
                check_no_local_health || return $?
                check_remote_health || return $?
@@ -1667,8 +1663,6 @@ test_207() {
 
                lnet_health_post
 
-               $LCTL net_drop_del -a
-
                check_no_resends || return $?
                check_no_local_health || return $?
                check_remote_health || return $?
@@ -1775,7 +1769,6 @@ test_209() {
 
        do_lnetctl discover ${RNIDS[0]} &&
                error "Should have failed"
-       $LCTL net_drop_del -a
 
        lnet_health_post
 
@@ -1795,7 +1788,6 @@ test_209() {
 
        do_lnetctl discover ${RNIDS[0]} &&
                error "Should have failed"
-       $LCTL net_drop_del -a
 
        lnet_health_post