From 6a64a4a9d20a7a43eee6181c7bab738329844eba Mon Sep 17 00:00:00 2001
From: Oliver Walsh <owalsh@redhat.com>
Date: Fri, 30 Jun 2017 11:51:06 +0100
Subject: Tolerate network errors in pingtest retry logic

We use ping -w <deadline> -c <count>. This will ping every second until
<count> replies are received, or <deadline> is reached, or a network error occurs.

With the current retry logic a network error will result in a short tight loop
instead of waiting for the network to come up.

This change reduces the deadline to 10s, but sleeps 60s between retries.

Change-Id: Ib00cff6f843c04a00737b40e3ef3d1560d6e6d2d
Related-bug: #1680167
---
 validation-scripts/all-nodes.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'validation-scripts/all-nodes.sh')

diff --git a/validation-scripts/all-nodes.sh b/validation-scripts/all-nodes.sh
index ed7fefb7..296dcd36 100644
--- a/validation-scripts/all-nodes.sh
+++ b/validation-scripts/all-nodes.sh
@@ -10,12 +10,13 @@ function ping_retry() {
     PING_CMD=ping6
   fi
   until [ $COUNT -ge $TIMES ]; do
-    if $PING_CMD -w 300 -c 1 $IP_ADDR &> /dev/null; then
+    if $PING_CMD -w 10 -c 1 $IP_ADDR &> /dev/null; then
       echo "Ping to $IP_ADDR succeeded."
       return 0
     fi
     echo "Ping to $IP_ADDR failed. Retrying..."
     COUNT=$(($COUNT + 1))
+    sleep 60
   done
   return 1
 }
-- 
cgit 1.2.3-korg