From: Elena Gryaznova Date: Wed, 26 May 2010 06:36:35 +0000 (+0400) Subject: b=20918 report max recovery time estimated X-Git-Tag: v1_10_0_43~13 X-Git-Url: https://git.whamcloud.com/?p=fs%2Flustre-release.git;a=commitdiff_plain;h=ad0acd4cbf64dbc362490b7a51a99ffea1d602b1 b=20918 report max recovery time estimated i=Andrew.Perepechko --- diff --git a/lustre/tests/recovery-random-scale.sh b/lustre/tests/recovery-random-scale.sh index b36c410..4f8e879 100644 --- a/lustre/tests/recovery-random-scale.sh +++ b/lustre/tests/recovery-random-scale.sh @@ -48,6 +48,8 @@ build_test_filter check_and_setup_lustre rm -rf $DIR/[df][0-9]* +max_recov_time=$(max_recovery_time) + # the test node needs to be insulated from a lustre failure as much as possible, # so not even loading the lustre modules is ideal. # -- umount lustre @@ -291,6 +293,7 @@ while [ $ELAPSED -lt $DURATION -a ! -e $END_RUN_FILE ]; do 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. +Estimated max recovery time : $max_recov_time 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