From fb19103b08d413c228a755e639daadba427d25e6 Mon Sep 17 00:00:00 2001 From: Elena Gryaznova Date: Mon, 25 Jan 2010 14:42:11 +0300 Subject: [PATCH 1/1] b=20918 improve log warning i=Brian --- lustre/tests/recovery-mds-scale.sh | 5 ++++- lustre/tests/recovery-random-scale.sh | 8 +++++--- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/lustre/tests/recovery-mds-scale.sh b/lustre/tests/recovery-mds-scale.sh index 59c368e..0ab9999 100644 --- a/lustre/tests/recovery-mds-scale.sh +++ b/lustre/tests/recovery-mds-scale.sh @@ -262,7 +262,10 @@ while [ $ELAPSED -lt $DURATION -a ! -e $END_RUN_FILE ]; do if [ $sleep -lt $MINSLEEP ]; then reqfail=$((reqfail +1)) log "WARNING: failover and two check_client_loads time exceeded SERVER_FAILOVER_PERIOD - MINSLEEP ! -Failed to meet interval $reqfail times ( REQFAIL=$REQFAIL ); have sleep=$sleep" +Failed to load the filesystem with I/O for a minimum period of $MINSLEEP $reqfail times ( REQFAIL=$REQFAIL ). +This iteration, the load was only applied for sleep=$sleep seconds. +Probably the hardware is taking excessively long to boot. +Try to increase SERVER_FAILOVER_PERIOD (current is $SERVER_FAILOVER_PERIOD), bug 20918" [ $reqfail -gt $REQFAIL ] && exit 6 fi diff --git a/lustre/tests/recovery-random-scale.sh b/lustre/tests/recovery-random-scale.sh index 65de6c1..f0a7601 100644 --- a/lustre/tests/recovery-random-scale.sh +++ b/lustre/tests/recovery-random-scale.sh @@ -292,9 +292,11 @@ while [ $ELAPSED -lt $DURATION -a ! -e $END_RUN_FILE ]; do # the value ( SERVER_FAILOVER_PERIOD - MINSLEEP ) if [ $sleep -lt $MINSLEEP ]; then reqfail=$((reqfail +1)) - log "WARNING: failover, client reintegration and check_client_loads time -exceeded SERVER_FAILOVER_PERIOD - MINSLEEP ! -Failed to meet interval $reqfail times ( REQFAIL=$REQFAIL ); have sleep=$sleep" + log "WARNING: failover, client reintegration and check_client_loads time exceeded SERVER_FAILOVER_PERIOD - MINSLEEP ! +Failed to load the filesystem with I/O for a minimum period of $MINSLEEP $reqfail times ( REQFAIL=$REQFAIL ). +This iteration, the load was only applied for sleep=$sleep seconds. +Probably the hardware is taking excessively long to boot. +Try to increase SERVER_FAILOVER_PERIOD (current is $SERVER_FAILOVER_PERIOD), bug 20918" [ $reqfail -gt $REQFAIL ] && exit 6 fi -- 1.8.3.1