init-ceph: do not stop start on first failure

When starting we often loop over many daemon instances.  Currently we stop
on the first error and do not try to start other daemons.

Instead, try them all, but return a failure if anything did not start.

Fixes: #2545
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
(cherry picked from commit d395aa521e8a4b295ed2b08dd7cfb7d9f995fcf7)

Conflicts:

	src/init-ceph.in

diff --git a/src/ceph_common.sh b/src/ceph_common.sh
index b66b1de3a53d5e041891b25ba735155033eaad7a..f20628bfa225d90377480a04aa8bc0c4b946aef4 100644 (file)
--- a/src/ceph_common.sh
+++ b/src/ceph_common.sh
@@ -87,6 +87,24 @@ do_cmd() {
     fi
 }
 
+do_cmd_okfail() {
+    ERR=0
+    if [ -z "$ssh" ]; then
+       [ $verbose -eq 1 ] && echo "--- $host# $1"
+       ulimit -c unlimited
+       whoami=`whoami`
+       if [ "$whoami" = "$user" ] || [ -z "$user" ]; then
+           bash -c "$1" || { [ -z "$3" ] && echo "failed: '$1'" && ERR=1 && return 1; }
+       else
+           sudo su $user -c "$1" || { [ -z "$3" ] && echo "failed: '$1'" && ERR=1 && return 1; }
+       fi
+    else
+       [ $verbose -eq 1 ] && echo "--- $ssh $2 \"if [ ! -d $sshdir ]; then mkdir -p $sshdir; fi; cd $sshdir ; ulimit -c unlimited ; $1\""
+       $ssh $2 "if [ ! -d $sshdir ]; then mkdir -p $sshdir; fi; cd $sshdir ; ulimit -c unlimited ; $1" || { [ -z "$3" ] && echo "failed: '$ssh $1'" && ERR=1 && return 1; }
+    fi
+    return 0
+}
+
 do_root_cmd() {
     if [ -z "$ssh" ]; then
        [ $verbose -eq 1 ] && echo "--- $host# $1"

diff --git a/src/init-ceph.in b/src/init-ceph.in
index 8c1855a6aa0e7b10602a2c623ef488aef947ea9d..41fe4f4f4c82d1903ac1212447308b5c2443d80d 100644 (file)
--- a/src/init-ceph.in
+++ b/src/init-ceph.in
@@ -314,7 +314,10 @@ for name in $what; do
            get_conf pre_start "" "pre start command"
            get_conf post_start "" "post start command"
            [ -n "$pre_start" ] && do_cmd "$pre_start"
-           do_cmd "$cmd" $runarg
+           do_cmd_okfail "$cmd" $runarg
+           if [ "$ERR" != "0" ]; then
+               EXIT_STATUS=$ERR
+           fi
            [ -n "$post_start" ] && do_cmd "$post_start"
            [ -n "$lockfile" ] && [ "$?" -eq 0 ] && touch $lockfile
            ;;