From 5b61148576fd9e96c4296314a6418d8d77e53baa Mon Sep 17 00:00:00 2001 From: Jian Yu Date: Mon, 5 Apr 2021 09:27:08 -0700 Subject: [PATCH] EX-2745 tests: limit debug log entries for hot-pools.sh This patch adds --since "$duration seconds ago" option to journalctl to gather lamigo and lpurge service debug logs for the exact runs. Test-Parameters: trivial testlist=hot-pools,hot-pools Test-Parameters: trivial testgroup=review-dne-part-2 Change-Id: Idbb81bc4dc7fc669074c1e8f8c156627abe6c610 Signed-off-by: Jian Yu Reviewed-on: https://review.whamcloud.com/43208 Tested-by: jenkins Tested-by: Maloo Reviewed-by: John L. Hammond Reviewed-by: Alex Zhuravlev Reviewed-by: Li Xi --- lustre/tests/hot-pools.sh | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/lustre/tests/hot-pools.sh b/lustre/tests/hot-pools.sh index b47e502..24c9756 100644 --- a/lustre/tests/hot-pools.sh +++ b/lustre/tests/hot-pools.sh @@ -64,6 +64,7 @@ declare -a LAMIGO_SRVFILE declare -a LAMIGO_USERFILE declare -a LAMIGO_DUMPFILE declare -a LAMIGO_PIDFILE +declare -a LAMIGO_START_TIME # lpurge configuration options LPURGE_MOUNT=${LPURGE_MOUNT:-"$MOUNT"} @@ -88,6 +89,7 @@ declare -a LPURGE_SRVFILE declare -a LPURGE_DUMPFILE declare -a LPURGE_FIDS_DUMPFILE declare -a LPURGE_PIDFILE +declare -a LPURGE_START_TIME # create OST pools create_ost_pools() { @@ -120,6 +122,7 @@ init_lamigo_vars() { LAMIGO_USERFILE+=("/var/lib/lamigo-$mdt.chlg") LAMIGO_DUMPFILE+=("/var/run/lamigo-$mdt.stats") LAMIGO_PIDFILE+=("/var/run/lamigo-$mdt.pid") + LAMIGO_START_TIME+=(0) done } @@ -140,6 +143,7 @@ init_lpurge_vars() { LPURGE_DUMPFILE+=("/var/run/lpurge-$ost.stats") LPURGE_FIDS_DUMPFILE+=("/var/run/lpurge-$ost.fids") LPURGE_PIDFILE+=("/var/run/lpurge-$ost.pid") + LPURGE_START_TIME+=(0) done for i in $(seq $MDSCOUNT); do @@ -168,11 +172,12 @@ hot_pools_logfile() { local facet="$1" local tool="${2:-hot_pools}" local host="$(facet_active_host $facet)" + local service="$(facet_svc $facet)" local prefix=$TESTLOG_PREFIX [[ -z "$TESTNAME" ]] || prefix+=".$TESTNAME" - printf "${prefix}.${tool}_log.${host}.log" + printf "${prefix}.${tool}-${service}_log.${host}.log" } lamigo_logfile() { @@ -427,6 +432,7 @@ start_one_lamigo_service() { create_one_lamigo_service $i echo "Start lamigo on MDS $(facet_active_host $facet): $start_cmd" + LAMIGO_START_TIME[i]=$SECONDS do_facet $facet "$start_cmd" || error "failed to start lamigo service" sleep 2 do_facet $facet "$status_cmd" @@ -446,8 +452,10 @@ stop_one_lamigo_service() { local srv_file=${LAMIGO_SRVFILE[i]} local pid_file=${LAMIGO_PIDFILE[i]} local pid=$(do_facet $facet "cat $pid_file") + local duration=$((SECONDS - LAMIGO_START_TIME[i] + 10)) - local jctl_cmd="journalctl -u lamigo-$mdt &> $(lamigo_logfile $facet)" + local jctl_cmd="journalctl --since \\\"$duration seconds ago\\\"" + jctl_cmd+=" -u lamigo-$mdt &> $(lamigo_logfile $facet)" local stop_cmd="systemctl stop lamigo-$mdt" [[ -n "$pid" ]] || { echo "cannot find lamigo PID"; return 0; } @@ -792,6 +800,7 @@ start_one_lpurge_service() { create_one_lpurge_service $i echo "Start lpurge on OSS $(facet_active_host $facet): $start_cmd" + LPURGE_START_TIME[i]=$SECONDS do_facet $facet "$start_cmd" || error "failed to start lpurge service" sleep 2 do_facet $facet "$status_cmd" @@ -811,8 +820,10 @@ stop_one_lpurge_service() { local srv_file=${LPURGE_SRVFILE[i]} local pid_file=${LPURGE_PIDFILE[i]} local pid=$(do_facet $facet "cat $pid_file") + local duration=$((SECONDS - LPURGE_START_TIME[i] + 10)) - local jctl_cmd="journalctl -u lpurge-$dev &> $(lpurge_logfile $facet)" + local jctl_cmd="journalctl --since \\\"$duration seconds ago\\\"" + jctl_cmd+=" -u lpurge-$dev &> $(lpurge_logfile $facet)" local stop_cmd="systemctl stop lpurge-$dev" [[ -n "$pid" ]] || { echo "cannot find lpurge PID"; return 0; } -- 1.8.3.1