torture: Use elapsed time to detect hangs

The kvm-test-1-run.sh currently counts "sleep 1" commands to detect
hangs.  This can fail spectacularly on busy systems, where "sleep 1"
might take far longer than one second to complete.  This commit
therefore changes hang detection to use elapsed time measurements.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>

1 files changed, 12 insertions, 6 deletions

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 2bfdb48cd920..27e544e29510 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -167,14 +167,18 @@ fi
 qemu_pid=$!
 commandcompleted=0
 echo Monitoring qemu job at pid $qemu_pid
-for ((i=0;i<$seconds;i++))
+while :
 do
+        kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
         if kill -0 $qemu_pid > /dev/null 2>&1
         then
+                if test $kruntime -ge $seconds
+                then
+                        break;
+                fi
                 sleep 1
         else
                 commandcompleted=1
-                kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
                 if test $kruntime -lt $seconds
                 then
                         echo Completed in $kruntime vs. $seconds >> $resdir/Warnings 2>&1
@@ -194,20 +198,22 @@ done
 if test $commandcompleted -eq 0
 then
         echo Grace period for qemu job at pid $qemu_pid
-        for ((i=0;i<=$grace;i++))
+        while :
         do
+                kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
                 if kill -0 $qemu_pid > /dev/null 2>&1
                 then
-                        sleep 1
+                        :
                 else
                         break
                 fi
-                if test $i -eq $grace
+                if test $kruntime -ge $((seconds + grace))
                 then
-                        kruntime=`awk 'BEGIN { print systime() - '"$kstarttime"' }'`
                         echo "!!! Hang at $kruntime vs. $seconds seconds" >> $resdir/Warnings 2>&1
                         kill -KILL $qemu_pid
+                        break
                 fi
+                sleep 1
         done
 fi