Currently, a transient network error can kill a run if it happens while
downloading the tarball to one of the target systems. This commit
therefore does a 60-second wait and then a retry. If further experience
indicates, a more elaborate mechanism might be used later.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
ret=$?
if test "$ret" -ne 0
then
- echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
- exit 10 | tee -a "$oldrun/remote-log"
+ echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. | tee -a "$oldrun/remote-log"
+ sleep 60
+ cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
+ ret=$?
+ if test "$ret" -ne 0
+ then
+ echo Unable to download $T/binres.tgz to system $i, giving up. | tee -a "$oldrun/remote-log"
+ exit 10
+ fi
fi
done