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

1 files changed, 9 insertions, 0 deletions

diff --git a/qpid/cpp/src/cluster.mk b/qpid/cpp/src/cluster.mk
index c4907a1b04..d90a06e1e2 100644
--- a/qpid/cpp/src/cluster.mk
+++ b/qpid/cpp/src/cluster.mk
@@ -89,4 +89,13 @@ cluster_la_LIBADD=  -lcpg $(libcman) libqpidbroker.la libqpidclient.la
 cluster_la_CXXFLAGS = $(AM_CXXFLAGS) -fno-strict-aliasing
 cluster_la_LDFLAGS = $(PLUGINLDFLAGS)
 
+# The watchdog plugin and helper executable
+dmodule_LTLIBRARIES += watchdog.la
+watchdog_la_SOURCES = qpid/cluster/WatchDogPlugin.cpp
+watchdog_la_LIBADD = libqpidbroker.la
+watchdog_la_LDFLAGS = $(PLUGINLDFLAGS)
+
+qpidexec_PROGRAMS += qpidd_watchdog
+qpidd_watchdog_SOURCES = qpid/cluster/qpidd_watchdog.cpp
+
 endif				# HAVE_LIBCPG