From f1ce462da088bba87d891014c5d8b5c9eeaca238 Mon Sep 17 00:00:00 2001 From: Alan Conway Date: Mon, 10 Aug 2009 21:10:53 +0000 Subject: Watchdog feature to remove unresponsive cluster nodes. In some intstances (e.g. while resolving an error) it's possible for a hung process to hang the entire cluster as they wait for its response. The cluster can handle terminated processes but hung processes present a problem. If the watchdog plugin is loaded and --watchdog-interval is set then the broker forks a child process that runs a very simple watchdog program, and starts a timer in the broker process to signal the watchdog every interval/2 seconds. The watchdog kills its parent if it does not receive a signal for interval seconds. This allows a stuck broker to be removed from the cluster so other cluster members can continue. git-svn-id: https://svn.apache.org/repos/asf/qpid/trunk@802927 13f79535-47bb-0310-9956-ffa450edef68 --- qpid/cpp/src/tests/test_watchdog | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100755 qpid/cpp/src/tests/test_watchdog (limited to 'qpid/cpp/src/tests/test_watchdog') diff --git a/qpid/cpp/src/tests/test_watchdog b/qpid/cpp/src/tests/test_watchdog new file mode 100755 index 0000000000..c2f33501b8 --- /dev/null +++ b/qpid/cpp/src/tests/test_watchdog @@ -0,0 +1,16 @@ +#!/bin/sh +# Tests for the watchdog plug-in + +# Start a broker with watchdog, freeze it with kill -STOP, verify that it is killed. +export QPID_WATCHDOG_EXE=$PWD/../qpidd_watchdog +PORT=`../qpidd -dp0 --no-data-dir --auth=no --no-module-dir --load-module $PWD/../.libs/watchdog.so --log-to-file=qpidd_watchdog.log --watchdog-interval 1` +PID=`../qpidd -cp $PORT` +kill -STOP $PID +sleep 2 + +if kill -0 $PID 2>/dev/null; then + echo "Hung process did not die." + kill $PID +else + true +fi -- cgit v1.2.1